Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment. Prior virtual try-on works face two major challenges in achieving this goal: a) the paired (human, garment) training data has limited availability; b) generating textures on the human that perfectly match that of the prompted garment is difficult, often resulting in distorted text and faded textures. Our work explores ways to tackle these issues through both synthetic data as well as model refinement. We introduce a garment extraction model that generates (human, synthetic garment) pairs from a single image of a clothed individual. The synthetic pairs can then be used to augment the training of virtual try-on. We also propose an Error-Aware Refinement-based Schrödinger Bridge (EARSB) that surgically targets localized generation errors for correcting the output of a base virtual try-on model. To identify likely errors, we propose a weakly-supervised error classifier that localizes regions for refinement, subsequently augmenting the Schrödinger Bridge’s noise schedule with its confidence heatmap. Experiments on VITON-HD and DressCode-Upper demonstrate that our synthetic data augmentation enhances the performance of prior work, while EARSB improves the overall image quality. In user studies, our model is preferred by the users in an average of 59% of cases. Code is available at this link.

Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time.Prior work often addresses this by predicting future model weights.However, full model prediction is prohibitively expensive for even reasonably sized models.Thus, recent methods only predict the classifier layer, limiting generalization by failing to adjust other model components.To address this, we propose Temporal Experts Averaging (TEA), a novel and scalable TDG framework that updates the entire model using weight averaging to maximize generalization potential while minimizing computational costs.Our theoretical analysis guides us to two steps that enhance generalization to future domains.First, we create expert models with functional diversity yet parameter similarity by fine-tuning a domain-agnostic base model on individual temporal domains while constraining weight changes.Second, we optimize the bias-variance tradeoff through adaptive averaging coefficients derived from modeling temporal weight trajectories in a principal component subspace.Expert's contributions are based on their projected proximity to future domains.Extensive experiments across 7 TDG benchmarks, 5 models, and 2 TDG settings shows TEA outperforms prior TDG methods by up to 69% while being up to 60x more efficient 1 .

Large models achieve strong performance on Vision-and-Language Navigation (VLN) tasks, but are costly to run in resource-limited environments.Token pruning offers appealing tradeoffs for efficiency with minimal performance loss by reducing model input size, but prior work overlooks VLN-specific challenges.For example, information loss from pruning can effectively increase computational cost due to longer walks.Thus, the inability to identify uninformative tokens undermines the supposed efficiency gains from pruning.To address this, we propose Navigation-Aware Pruning (NAP), which uses navigation-specific traits to simplify the pruning process by pre-filtering tokens into foreground and background.For example, image views are filtered based on whether the agent can navigate in that direction.We also extract navigation-relevant instructions using a Large Language Model.After filtering, we focus pruning on background tokens, minimizing information loss.To further help avoid increases in navigation length, we discourage backtracking by removing low-importance navigation nodes.Experiments on standard VLN benchmarks show NAP significantly outperforms prior work, preserving higher success rates while saving more than 50% FLOPS 1 .

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to capture relevant information without affecting predictions on any previously learned categories. While these adaptors are generally more efficient than finetuning the entire network, they still can require tens to hundreds of thousands task-specific trainable parameters even for relatively small networks. This makes it challenging to operate in resource-constrained environments with high communication costs, such as edge devices or mobile phones. Thus, we propose Reparameterized, Compact weight Adaptation for Sequential Tasks (RECAST), a novel method that dramatically reduces the number of task-specific trainable parameters to fewer than 50 – several orders of magnitude less than competing methods like LoRA. RECAST accomplishes this efficiency by learning to decompose layer weights into a soft parameter-sharing framework consisting of a set of shared weight templates and very few module-specific scaling factors or coefficients. This soft parameter-sharing framework allows for effective task-wise reparameterization by tuning only these coefficients while keeping templates frozen. A key innovation of RECAST is the novel weight reconstruction pipeline called Neural Mimicry, which eliminates the need for pretraining from scratch. This allows for high-fidelity emulation of existing pretrained weights within our framework and provides quick adaptability to any model scale and architecture. Extensive experiments across six diverse datasets demonstrate RECAST outperforms the state-of-the-art by up to ∼ 1.5% and improves baselines by > 3% across various scales, architectures, and parameter spaces. Moreover, we show that RECAST’s architecture-agnostic nature allows for seamless integration with existing methods, further boosting performance.

Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods combine robust features from web-scale pretrained backbones with new features learned from source data, and this has dramatically improved benchmark results. However, it remains unclear if DG finetuning methods are becoming better over time, or if improved benchmark performance is simply an artifact of stronger pre-training. Prior studies have shown that perceptual similarity to pre-training data correlates with zero-shot performance, but we find the effect limited in the DG setting. Instead, we posit that having perceptually similar data in pretraining is not enough; and that it is how well these data were learned that determines performance. This leads us to introduce the Alignment Hypothesis, which states that the final DG performance will be high if and only if alignment of image and class label text embeddings is high. Our experiments confirm the Alignment Hypothesis is true, and we use it as an analysis tool of existing DG methods evaluated on DomainBed datasets by splitting evaluation data into In-pretraining (IP) and Out-of-pretraining (OOP). We show that all evaluated DG methods struggle on DomainBed-OOP, while recent methods excel on DomainBed-IP. Put together, our findings highlight the need for DG methods which can generalize beyond pretraining alignment. We release DomainBed-OOP at https://huggingface.co/datasets/PTeterwak/DomainBed_OOP.

Prior work using Masked Autoencoders (MAEs) typically relies on random patch masking based on the assumption that images have significant redundancies across different channels, allowing for the reconstruction of masked content using cross-channel correlations. However, this assumption does not hold in Multi-Channel Imaging (MCI), where channels may provide complementary information with minimal feature overlap. Thus, these MAEs primarily learn local structures within individual channels from patch reconstruction, failing to fully leverage cross-channel interactions and limiting their MCI effectiveness. In this paper, we present ChA-MAEViT, an MAE-based method that enhances feature learning across MCI channels via four key strategies: (1) dynamic channel-patch masking, which compels the model to reconstruct missing channels in addition to masked patches, thereby enhancing cross-channel dependencies and improving robustness to varying channel configurations; (2) memory tokens, which serve as long-term memory aids to promote information sharing across channels, addressing the challenges of reconstructing structurally diverse channels; (3) hybrid token fusion module, which merges fine-grained patch tokens with a global class token to capture richer representations; and (4) Channel-Aware Decoder, a lightweight decoder utilizes channel tokens to effectively reconstruct image patches. Experiments on satellite and microscopy datasets, CHAMMI, JUMP-CP, and So2Sat, show that ChA-MAEViT significantly outperforms state-of-the-art MCI-ViTs by 3.0-21.5%, highlighting the importance of cross-channel interactions in MCI. Our code is publicly available at https://github.com/chaudatascience/cha_mae_vit.

Domain Generalization (DG) aims to develop classifiers that can generalize to new, unseen data distributions, a critical capability when collecting new domain-specific data is impractical. A common DG baseline minimizes the empirical risk on the source domains. Recent studies have shown that this approach, known as Empirical Risk Minimization (ERM), can outperform most more complex DG methods when properly tuned. However, these studies have primarily focused on a narrow set of hyperparameters, neglecting other factors that can enhance robustness and prevent overfitting and catastrophic forgetting, properties which are critical for strong DG performance. In our investigation of training data utilization (i.e., duration and setting validation splits), initialization, and additional regularizers, we find that tuning these previously overlooked factors significantly improves model generalization across diverse datasets without adding much complexity. We call this improved, yet simple baseline ERM++. Despite its ease of implementation, ERM++ improves DG performance by over 5% compared to prior ERM baselines on a standard benchmark of 5 datasets with a ResNet-50 and over 15% with a ViT-B/16. It also outperforms all state-of-the-art methods on DomainBed datasets with both architectures. Importantly, ERM++ is easy to integrate into existing frameworks like DomainBed, making it a practical and powerful tool for researchers and practitioners. Overall, ERM++ challenges the need for more complex DG methods by providing a stronger, more reliable baseline that maintains simplicity and ease of use. Code is available at https://github.com/piotr-teterwak/erm_plusplus

Human image editing includes tasks like changing a person's pose, their clothing, or editing the image according to a text prompt. However, prior work often tackles these tasks separately, overlooking the benefit of mutual reinforcement from learning them jointly. In this paper, we propose UniHuman, a unified model that addresses multiple facets of human image editing in real-world settings. To enhance the model's generation quality and generalization capacity, we leverage guidance from human visual encoders and introduce a lightweight pose-warping module that can exploit different pose representations, accommodating unseen textures and patterns. Furthermore, to bridge the disparity between existing human editing benchmarks with real-world data, we curated 400K high-quality human image-text pairs for training and collected 2K human images for out-of-domain testing, both encompassing diverse clothing styles, backgrounds, and age groups. Experiments on both in-domain and out-of-domain test sets demonstrate that UniHuman outperforms task-specific models by a significant margin. In user studies, UniHuman is preferred by the users in an average of 77% of cases. Our project is available at this link.

Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Large Language Models (vLLMs) hold promise as a viable solution due to their demonstrated emergent capabilities on new tasks. However, despite being trained on millions of short seconds-long videos, vLLMs are unable to understand minutes-long videos and accurately answer questions about them. To address this limitation, we propose a lightweight and self-supervised approach, Key frame-conditioned long video-LLM (Koala), that introduces learnable spatiotemporal queries to adapt pretrained vLLMs for generalizing to longer videos. Our approach introduces two new tokenizers that condition on visual tokens computed from sparse video key frames for understanding short and long video moments. We train our proposed approach on HowTo100M and demonstrate its effectiveness on zero-shot long video understanding benchmarks, where it outperforms state-of-the-art large models by 3 - 6% in absolute accuracy across all tasks. Surprisingly, we also empirically show that our approach not only helps a pretrained vLLM to understand long videos but also improves its accuracy on short-term action recognition.

Discussion and debate among Large Language Models (LLMs) have gained considerable attention due to their potential to enhance the reasoning ability of LLMs. Although natural language is an obvious choice for communication due to LLM's language understanding capability, the token sampling step needed when generating natural language poses a potential risk of information loss, as it uses only one token to represent the model's belief across the entire vocabulary. In this paper, we introduce a communication regime named CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. Specifically, we remove the token sampling step from LLMs and let them communicate their beliefs across the vocabulary through the expectation of the raw transformer output embeddings. Remarkably, by deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights, outperforming the state-of-the-art LLM debate methods using natural language by 0.5-5.0% across five reasoning tasks and multiple open-source LLMs of varying sizes. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs. We anticipate that CIPHER will inspire further exploration for the design of interactions within LLM agent systems, offering a new direction that could significantly influence future developments in the field.

Multi-Channel Imaging (MCI) contains an array of challenges for encoding useful feature representations not present in traditional images. For example, images from two different satellites may both contain RGB channels, but the remaining channels can be different for each imaging source. Thus, MCI models must support a variety of channel configurations at test time. Recent work has extended traditional visual encoders for MCI, such as Vision Transformers (ViT), by supplementing pixel information with an encoding representing the channel configuration. However, these methods treat each channel equally, i.e., they do not consider the unique properties of each channel type, which can result in needless and potentially harmful redundancies in the learned features. For example, if RGB channels are always present, the other channels can focus on extracting information that cannot be captured by the RGB channels. To this end, we propose DiChaViT, which aims to enhance the diversity in the learned features of MCI-ViT models. This is achieved through a novel channel sampling strategy that encourages the selection of more distinct channel sets for training. Additionally, we employ regularization and initialization techniques to increase the likelihood that new information is learned from each channel. Many of our improvements are architecture agnostic and can be incorporated into new architectures as they are developed. Experiments on both satellite and cell microscopy datasets, CHAMMI, JUMP-CP, and So2Sat, report DiChaViT yields a 1.5 - 5.0% gain over the state-of-the-art. Our code is publicly available at https://github.com/chaudatascience/diverse_channel_vit.

Multimodal data is available in many applications like e-commerce production listings, social media posts and short videos. However, existing algorithms dealing with those types of data still focus on uni-modal representation learning by vision-language alignment and cross-modal retrieval. In this workshop, we target to bring a new retrieval problem where both queries and documents are multimodal. With the popularity of vision language modeling, large language models (LLMs), retrieval augmented generation (RAG), and multimodal LLM, we see a lot of new opportunities for multimodal representation and retrieval tasks. This event will be a comprehensive half-day workshop focusing on the subject of multimodal representation and retrieval. The agenda includes keynote speeches, oral presentations, and an interactive panel discussion.

Most deep neural networks are trained under fixed network architectures and require retraining when the architecture changes. If expanding the network’s size is needed, it is necessary to retrain from scratch, which is expensive. To avoid this, one can grow from a small network by adding random weights over time to gradually achieve the target network size. However, this naive approach falls short in practice as it brings too much noise to the growing process. Prior work tackled this issue by leveraging the already learned weights and training data for generating new weights through conducting a computationally expensive analysis step. In this paper, we introduce MixtureGrowth, a new approach to growing networks that circumvents the initialization overhead in prior work. Before growing, each layer in our model is generated with a linear combination of parameter templates. Newly grown layer weights are generated by using a new linear combination of existing templates for a layer. On one hand, these templates are already trained for the task, providing a strong initialization. On the other, the new coefficients provide flexibility for the added layer weights to learn something new. We show that our approach boosts top-1 accuracy over the state-of-the-art by 2-2.5% on CIFAR-100 and ImageNet datasets, while achieving comparable performance with fewer FLOPs to a larger network trained from scratch. Code is available at https://github.com/chaudatascience/mixturegrowth.

Neural parameter allocation search (NPAS) automates parameter sharing by obtaining weights for a network given an arbitrary, fixed parameter budget. Prior work has two major drawbacks we aim to address. First, there is a disconnect in the sharing pattern between the search and training steps, where weights are warped for layers of different sizes during the search to measure similarity, but not during training, resulting in reduced performance. To address this, we generate layer weights by learning to compose sets of SuperWeights, which represent a group of trainable parameters. These SuperWeights are created to be large enough so they can be used to represent any layer in the network, but small enough that they are computationally efficient. The second drawback we address is the method of measuring similarity between shared parameters. Whereas prior work compared the weights themselves, we argue this does not take into account the amount of conflict between the shared weights. Instead, we use gradient information to identify layers with shared weights that wish to diverge from each other. We demonstrate that our SuperWeight Networks consistently boost performance over the state-of-the-art on the ImageNet and CIFAR datasets in the NPAS setting. We further show that our approach can generate parameters for many network architectures using the same set of weights. This enables us to support tasks like efficient ensembling and anytime prediction, outperforming fully-parameterized ensembles with 17% fewer parameters1.

Video-based movie genre classification has garnered considerable attention due to its various applications in recommendation systems. Prior work has typically addressed this task by adapting models from traditional video classification tasks, such as action recognition or event detection. However, these models often neglect language elements (e.g., narrations or conversations) present in videos, which can implicitly convey high-level semantics of movie genres, like storylines or background context. Additionally, existing approaches are primarily designed to encode the entire content of the input video, leading to inefficiencies in predicting movie genres. Movie genre prediction may require only a few shots1to accurately determine the genres, rendering a comprehensive understanding of the entire video unnecessary. To address these challenges, we propose a Movie genre Classification method based on Language augmentatIon and shot samPling (Movie-CLIP). MovieCLIP mainly consists of two parts: a language augmentation module to recognize language elements from the input audio, and a shot sampling module to select representative shots from the entire video. We evaluate our method on MovieNet and Condensed Movies datasets, achieving approximate 6 − 9% improvement in mean Average Precision (mAP) over the baselines. We also generalize Movie-CLIP to the scene boundary detection task, achieving 1.1% improvement in Average Precision (AP) over the state-of-the-art. We release our implementation at this http URL.

Diffusion models have demonstrated impressive performance in text-guided image generation. Current methods that leverage the knowledge of these models for image editing either fine-tune them using the input image (e.g., Imagic) or incorporate structure information as additional constraints (e.g., ControlNet). However, fine-tuning large-scale diffusion models on a single image can lead to severe overfitting issues and lengthy inference time. Information leakage from pretrained models also make it challenging to preserve image content not related to the text input. Additionally, methods that incorporate structural guidance (e.g., edge maps, semantic maps, keypoints) find retaining attributes like colors and textures difficult. Using the input image as a control could mitigate these issues, but since these models are trained via reconstruction, a model can simply hide information about the original image when encoding it to perfectly reconstruct the image without learning the editing task. To address these challenges, we propose a text-to-image editing model with an Image Information Removal module (IIR) that selectively erases color-related and texture-related information from the original image, allowing us to better preserve the text-irrelevant content and avoid issues arising from information hiding. Our experiments on CUB, Outdoor Scenes, and COCO reports our approach achieves the best editability-fidelity trade-off results. In addition, a user study on COCO shows that our edited images are preferred 35% more often than prior work.

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups$B$(e.g. Female) within class labels$Y$(e.g. Programmers). This dataset bias can lead to models that learn spurious correlations between class labels and bias groups such as age, gender, or race. Most recent methods that address this problem require significant architectural changes or additional loss functions requiring more hyper-parameter tuning. Alternatively, data sampling baselines from the class imbalance literature (e.g. Undersampling, Upweighting), which can often be implemented in a single line of code and often have no hyperparameters, offer a cheaper and more efficient solution. However, these methods suffer from significant shortcomings. For example, Undersampling drops a significant part of the input distribution per epoch while Oversampling repeats samples, causing overfitting. To address these shortcomings, we introduce a new class-conditioned sampling method: Bias Mimicking. The method is based on the observation that if a class$c$bias distribution, i.e.$P_{D}(B\vert Y=c)$is mimicked across every$c^{\prime}\neq c$, then$Y$and$B$are statistically independent. Using this notion, BM, through a novel training procedure, ensures that the model is exposed to the entire distribution per epoch without repeating samples. Consequently, Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks while maintaining and sometimes improving performance over nonsampling methods. Code: https://github.com/mqraitem/Bias-Mimicking

We propose a self-supervised approach for learning to perform audio source separation in videos based on natu-ral language queries, using only unlabeled video and au-dio pairs as training data. A key challenge in this task is learning to associate the linguistic description of a sound-emitting object to its visual features and the corresponding components of the audio waveform, all without access to annotations during training. To overcome this challenge, we adapt off-the-shelf vision-language foundation models to provide pseudo-target supervision via two novel loss functions and encourage a stronger alignment between the audio, visual and natural language modalities. During inference, our approach can separate sounds given text, video and audio input, or given text and audio input alone. We demonstrate the effectiveness of our self-supervised approach on three audio-visual separation datasets, including MUSIC, SOLOS and AudioSet, where we outperform state-of-the-art strongly supervised approaches despite not using object detectors or text labels during training. Our project page including publicly available code can be found at https://cs-people.bu.edu/rxtan/projectsNAST.

Andrea Burns, Krishna Srinivasan, Joshua Ainslie, Geoff Brown, Bryan Plummer, Kate Saenko, Jianmo Ni, Mandy Guo. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Human pose transfer synthesizes new view(s) of a person for a given pose. Recent work achieves this via self-reconstruction, which disentangles a person’s pose and texture information by breaking the person down into parts, then recombines them for reconstruction. However, part-level disentanglement preserves some pose information that can create unwanted artifacts. In this paper, we propose Pose Transfer by Permuting Textures (PT2), an approach for self-driven human pose transfer that disentangles pose from texture at the patch-level. Specifically, we remove pose from an input image by permuting image patches so only texture information remains. Then we reconstruct the input image by sampling from the permuted textures for patch-level disentanglement. To reduce noise and recover clothing shape information from the permuted patches, we employ encoders with multiple kernel sizes in a triple branch network. Extensive experiments on DeepFashion and Market-1501 PT2reports significant gains on automatic metrics over other self-driven methods, and even outperforms some fully-supervised methods. A user study also reports images generated by our method are preferred in 68% of cases over self-driven approaches from prior work. Code is available at https://github.com/NannanLi999/pt_square

Most neural networks assume that input images have a fixed number of channels (three for RGB images). However, there are many settings where the number of channels may vary, such as microscopy images where the number of channels changes depending on instruments and experimental goals. Yet, there has not been a systemic attempt to create and evaluate neural networks that are invariant to the number and type of channels. As a result, trained models remain specific to individual studies and are hardly reusable for other microscopy settings. In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework. In addition, we adapted several existing techniques to create channel-adaptive models and compared their performance on this benchmark to fixed-channel, baseline models. We find that channel-adaptive models can generalize better to out-of-domain tasks and can be computationally efficient. We contribute a curated dataset and an evaluation API to facilitate objective comparisons in future research and applications.

Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of compositional capability, we design Cola, a text-to-image retrieval benchmark to Compose Objects Localized with Attributes. To solve Cola, a model must retrieve images with the correct configuration of attributes and objects and avoid choosing a distractor image with the same objects and attributes but in the wrong configuration. Cola contains about 1.2k composed queries of 168 objects and 197 attributes on around 30K images. Our human evaluation finds that Cola is 83.33% accurate, similar to contemporary compositionality benchmarks. Using Cola as a testbed, we explore empirical modeling designs to adapt pre-trained vision-language models to reason compositionally. We explore 6 adaptation strategies on 2 seminal vision-language models, using compositionality-centric test benchmarks - Cola and CREPE. We find the optimal adaptation strategy is to train a multi-modal attention layer that jointly attends over the frozen pre-trained image and language features. Surprisingly, training multimodal layers on CLIP performs better than tuning a larger FLAVA model with already pre-trained multimodal layers. Furthermore, our adaptation strategy improves CLIP and FLAVA to comparable levels, suggesting that training multimodal layers using contrastive attribute-object data is key, as opposed to using them pre-trained. Lastly, we show that Cola is harder than a closely related contemporary benchmark, CREPE, since simpler fine-tuning strategies without multimodal layers suffice on CREPE, but not on Cola. However, we still see a significant gap between our best adaptation and human accuracy, suggesting considerable room for further research. Project page: https://cs-people.bu.edu/array/research/cola/

Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image and localize the phrase. This can also be viewed as a generalization of object detection to an open-ended vocabulary, introducing elements of few- and zero-shot detection. We propose an approach for this task that extends Faster R-CNN to relate image regions and phrases. By carefully initializing the classification layers of our network using canonical correlation analysis (CCA), we encourage a solution that is more discerning when reasoning between similar phrases, resulting in over double the performance compared to a naive adaptation on three popular phrase grounding datasets, Flickr30K Entities, ReferIt Game, and Visual Genome, with test-time phrase vocabulary sizes of 5K, 32K, and 159K, respectively.

We present a two-stage pre-training approach that improves the generalization ability of standard single-domain pre-training. While standard pre-training on a single large dataset (such as ImageNet) can provide a good initial representation for transfer learning tasks, this approach may result in biased representations that impact the success of learning with new multi-domain data (e.g., different artistic styles) via methods like domain adaptation. We propose a novel pre-training approach called Cross-Domain Self-supervision (CDS), which directly employs unlabeled multi-domain data for downstream domain transfer tasks. Our approach uses self-supervision not only within a single domain but also across domains. In-domain instance discrimination is used to learn discriminative features on new data in a domain-adaptive manner, while cross-domain matching is used to learn domain-invariant features. We apply our method as a second pre-training step (after ImageNet pre-training), resulting in a significant target accuracy boost to diverse domain transfer tasks compared to standard one-stage pre-training.

We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision on a large corpus of videos with accompanying transcribed narrations. To achieve this goal, we propose a multilayer cross-modal attention network that enables effective optimization of a contrastive loss during training. We introduce a divided strategy that alternates between computing inter- and intra-modal attention across the visual and natural language modalities, which allows effective training via directly contrasting the two modalities' representations. We demonstrate the effectiveness of our approach by self-training on the HowTo100M instructional video dataset and evaluating on a newly collected dataset of localized described interactions in the YouCook2 dataset. We show that our approach outperforms alternative baselines, including shallow co-attention and full cross-modal attention. We also apply our approach to grounding phrases in images with weak supervision on Flickr30K and show that stacking multiple attention layers is effective and, when combined with a word-to-region loss, achieves state of the art on recall-at-one and pointing hand accuracies.

The goal of weakly-supervised video moment retrieval is to localize the video segment most relevant to a description without access to temporal annotations during training. Prior work uses co-attention mechanisms to understand relationships between the vision and language data, but they lack contextual information between video frames that can be useful to determine how well a segment relates to the query. To address this, we propose an efficient Latent Graph Co-Attention Network (LoGAN) that exploits fine-grained frame-by-word interactions to jointly reason about the correspondences between all possible pairs of frames, providing context cues absent in prior work. Experiments on the DiDeMo and Charades-STA datasets demonstrate the effectiveness of our approach, where we improve Recall@1 by 520% over prior weakly-supervised methods, even boasting an 11% gain over strongly-supervised methods on DiDeMo, while also using significantly fewer model parameters than other co-attention mechanisms.

Existing vision-language methods typically support two languages at a time at most. In this paper, we present a modular approach which can easily be incorporated into existing vision-language methods in order to support many languages. We accomplish this by learning a single shared Multimodal Universal Language Embedding (MULE) which has been visually-semantically aligned across all languages. Then we learn to relate MULE to visual data as if it were a single language. Our method is not architecture specific, unlike prior work which typically learned separate branches for each language, enabling our approach to easily be adapted to many vision-language methods and tasks. Since MULE learns a single language branch in the multimodal model, we can also scale to support many languages, and languages with fewer annotations can take advantage of the good representation learned from other (more abundant) language data. We demonstrate the effectiveness of our embeddings on the bidirectional image-sentence retrieval task, supporting up to four languages in a single model. In addition, we show that Machine Translation can be used for data augmentation in multilingual learning, which, combined with MULE, improves mean recall by up to 20.2% on a single language compared to prior work, with the most significant gains seen on languages with relatively few annotations. Our code is publicly available1.

Large-scale dissemination of disinformation online intended to mislead or deceive the general population is a major societal problem.Rapid progression in image, video, and natural language generative models has only exacerbated this situation and intensified our need for an effective defense mechanism.While existing approaches have been proposed to defend against neural fake news, they are generally constrained to the very limited setting where articles only have text and metadata such as the title and authors.In this paper, we introduce the more realistic and challenging task of defending against machine-generated news that also includes images and captions.To identify the possible weaknesses that adversaries can exploit, we create a NeuralNews dataset composed of 4 different types of generated articles as well as conduct a series of human user study experiments based on this dataset.In addition to the valuable insights gleaned from our user study, we provide a relatively effective approach based on detecting visualsemantic inconsistencies, which will serve as an effective first line of defense and a useful reference for future work in defending against machine-generated disinformation.Our code and dataset can be downloaded from here.

We address the problem of text-based activity retrieval in video. Given a sentence describing an activity, our task is to retrieve matching clips from an untrimmed video. To capture the inherent structures present in both text and video, we introduce a multilevel model that integrates vision and language features earlier and more tightly than prior work. First, we inject text features early on when generating clip proposals, to help eliminate unlikely clips and thus speed up processing and boost performance. Second, to learn a fine-grained similarity metric for retrieval, we use visual features to modulate the processing of query sentences at the word level in a recurrent neural network. A multi-task loss is also employed by adding query re-generation as an auxiliary task. Our approach significantly outperforms prior work on two challenging benchmarks: Charades-STA and ActivityNet Captions.

Shouldn't language and vision features be treated equally in vision-language (VL) tasks? Many VL approaches treat the language component as an afterthought, using simple language models that are either built upon fixed word embeddings trained on text-only data or are learned from scratch. We conclude that language features deserve more attention, which has been informed by experiments which compare different word embeddings, language models, and embedding augmentation steps on five common VL tasks: image-sentence retrieval, image captioning, visual question answering, phrase grounding, and text-to-clip retrieval. Our experiments provide some striking results; an average embedding language model outperforms a LSTM on retrieval-style tasks; state-of-the-art representations such as BERT perform relatively poorly on vision-language tasks. From this comprehensive set of experiments we can propose a set of best practices for incorporating the language component of vision-language tasks. To further elevate language features, we also show that knowledge in vision-language problems can be transferred across tasks to gain performance with multi-task training. This multi-task training is applied to a new Graph Oriented Vision-Language Embedding (GrOVLE), which we adapt from Word2Vec using WordNet and an original visual-language graph built from Visual Genome, providing a ready-to-use vision-language embedding: http://ai.bu.edu/grovle.

Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning condition-aware embeddings. While such embeddings aid models in learning different notions of similarity, they also limit their capability to generalize to unseen categories since they require explicit labels at test time. To address this deficiency, we propose an approach that jointly learns representations for the different similarity conditions and their contributions as a latent variable without explicit supervision. Comprehensive experiments across three datasets, Polyvore-Outfits, Maryland-Polyvore and UT-Zappos50k, demonstrate the effectiveness of our approach: our model outperforms the state-of-the-art methods, even those that are strongly supervised with pre-defined similarity conditions, on fill-in-the-blank, outfit compatibility prediction and triplet prediction tasks. Finally, we show that our model learns different visually-relevant semantic sub-spaces that allow it to generalize well to unseen categories.

In this paper, we introduce an attribute-based interactive image search which can leverage human-in-the-loop feedback to iteratively refine image search results. We study active image search where human feedback is solicited exclusively in visual form, without using relative attribute annotations used by prior work which are not typically found in many datasets. In order to optimize the image selection strategy, a deep reinforcement model is trained to learn what images are informative rather than rely on hand-crafted measures typically leveraged in prior work. Additionally, we extend the recently introduced Conditional Similarity Network to incorporate global similarity in training visual embeddings, which results in more natural transitions as the user explores the learned similarity embeddings. Our experiments demonstrate the effectiveness of our approach, producing compelling results on both active image search and image attribute representation tasks.

This paper addresses video summarization, or the problem of distilling a raw video into a shorter form while still capturing the original story. We show that visual representations supervised by freeform language make a good fit for this application by extending a recent submodular summarization approach [9] with representativeness and interestingness objectives computed on features from a joint vision-language embedding space. We perform an evaluation on two diverse datasets, UT Egocentric [18] and TV Episodes [45], and show that our new objectives give improved summarization ability compared to standard visual features alone. Our experiments also show that the vision-language embedding need not be trained on domainspecific data, but can be learned from standard still image vision-language datasets and transferred to video. A further benefit of our model is the ability to guide a summary using freeform text input at test time, allowing user customization.

This paper presents a framework for localization or grounding of phrases in images using a large collection of linguistic and visual cues. We model the appearance, size, and position of entity bounding boxes, adjectives that contain attribute information, and spatial relationships between pairs of entities connected by verbs or prepositions. Special attention is given to relationships between people and clothing or body part mentions, as they are useful for distinguishing individuals. We automatically learn weights for combining these cues and at test time, perform joint inference over all phrases in a caption. The resulting system produces state of the art performance on phrase localization on the Flickr30k Entities dataset [33] and visual relationship detection on the Stanford VRD dataset [27].

The Flickr30k dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity. Such annotation is essential for continued progress in automatic image description and grounded language understanding. We present experiments demonstrating the usefulness of our annotations for text-to-image reference resolution, or the task of localizing textual entity mentions in an image, and for bidirectional image-sentence retrieval. These experiments confirm that we can further improve the accuracy of state-of-the-art retrieval methods by training with explicit region-to-phrase correspondence, but at the same time, they show that accurately inferring this correspondence given an image and a caption remains really challenging.