We explore the boundaries of scaling up a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. Our model advances the state-of-the-art on most vision-and-language benchmarks considered (20+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

Creativity is an indispensable part of human cognition and also an inherent part of how we make sense of the world. Metaphorical abstraction is fundamental in communicating creative ideas through nuanced relationships between abstract concepts such as feelings. While computer vision benchmarks and approaches predominantly focus on understanding and generating literal interpretations of images, metaphorical comprehension of images remains relatively unexplored. Towards this goal, we introduce Meta-CLUE, a set of vision tasks on visual metaphor. We also collect high-quality and rich metaphor annotations (abstract objects, concepts, relationships along with their corresponding object boxes) as there do not exist any datasets that facilitate the evaluation of these tasks. We perform a comprehensive analysis of state-of-the-art models in vision and language based on our annotations, highlighting strengths and weaknesses of current approaches in visual metaphor classification, localization, understanding (retrieval, question answering, captioning) and generation (text-to-image synthesis) tasks. We hope this work provides a concrete step towards developing AI systems with human-like creative capabilities. Project page: https://metaclue.github.io

We propose Video Localized Narratives, a new form of multimodal video annotations connecting vision and language. In the original Localized Narratives [36], annotators speak and move their mouse simultaneously on an image, thus grounding each word with a mouse trace segment. However, this is challenging on a video. Our new protocol empowers annotators to tell the story of a video with Localized Narratives, capturing even complex events involving multiple actors interacting with each other and with several passive objects. We annotated 20k videos of the OVIS, UVO, and Oops datasets, totalling 1.7M words. Based on this data, we also construct new benchmarks for the video narrative grounding and video question answering tasks, and provide reference results from strong baseline models. Our annotations are available at https://google.github.io/video-localized-narratives/

Pre-trained vision and language models (Chen et al., 2023b,a;Dai et al., 2023; Li et al., 2023b) have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering.However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and informationseeking.In this study, we introduce INFOS-EEK 1 , a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge.Using INFOSEEK, we analyze various pre-trained visual question answering models and gain insights into their characteristics.Our findings reveal that state-of-the-art pre-trained multi-modal models (e.g., PaLI-X, BLIP2, etc.) face challenges in answering visual information-seeking questions, but finetuning on the INFOSEEK dataset elicits models to use fine-grained knowledge that was learned during their pre-training.Furthermore, we show that accurate visual entity recognition can be used to improve performance on INFOSEEK by retrieving relevant documents, showing a significant space for improvement.* Work done when interned at Google 1 Our dataset is available at https:// open-vision-language.github.io/infoseek/.Dataset OK-VQA ViQuAE INFOSEEK PaLM (Q-only) 23.8 31.5 5.6 Current SotA 66.1 22.1 18.2 Require Knowledge † 29.2% 95.2% 95.6% † :% of questions that require knowledge to answer.PaLM (Q-only): a question-only baseline using PaLM.

The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training objective. In this paper, we propose PreSTU, a novel pre-training recipe dedicated to scene-text understanding (STU). PreSTU introduces OCR-aware pre-training objectives that encourage the model to recognize text from an image and connect it to the rest of the image content. We implement PreSTU using a simple transformer-based encoder-decoder architecture, combined with large-scale image-text datasets with scene text obtained from an off-the-shelf OCR system. We empirically demonstrate the effectiveness of this pre-training approach on eight visual question answering and four image captioning benchmarks.

Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In this work, we study methods for automatic text-image alignment evaluation. We first introduce SeeTRUE: a comprehensive evaluation set, spanning multiple datasets from both text-to-image and image-to-text generation tasks, with human judgements for whether a given text-image pair is semantically aligned. We then describe two automatic methods to determine alignment: the first involving a pipeline based on question generation and visual question answering models, and the second employing an end-to-end classification approach by finetuning multimodal pretrained models. Both methods surpass prior approaches in various text-image alignment tasks, with significant improvements in challenging cases that involve complex composition or unnatural images. Finally, we demonstrate how our approaches can localize specific misalignments between an image and a given text, and how they can be used to automatically re-rank candidates in text-to-image generation.

Training large-scale image captioning (IC) models demands access to a rich and diverse set of training examples that are expensive to curate both in terms of time and man-power. Instead, alt-text based captions gathered from the web is a far cheaper alternative to scale with the downside of being noisy. Recent modeling approaches to IC often fall short in terms of performance in leveraging these noisy datasets in favor of clean annotations. We address this problem with a simple yet effective technique of breaking down the task into two smaller, more controllable tasks – skeleton prediction and skeleton-based caption generation. Specifically, we show that sub-selecting content words as skeletons helps in generating improved and denoised captions when leveraging rich yet noisy alt-text–based uncurated datasets. We also show that the predicted English skeletons can further cross-lingually be leveraged to generate non-English captions, and present experimental results covering caption generation in French, Italian, German, Spanish and Hindi. We also show that skeleton-based prediction allows for better control of certain caption properties, such as length, content, and gender expression, providing a handle to perform human-in-the-loop interpretable semi-automatic corrections.

Soravit Changpinyo, Doron Kukliansy, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pretraining. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pretraining data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [54] and introduce the Conceptual 12M (CC12M), a dataset with 12 million image-text pairs specifically meant to be used for visionand-language pre-training. We perform an analysis of this dataset and benchmark its effectiveness against CC3M on multiple downstream tasks with an emphasis on long-tail visual recognition. Our results clearly illustrate the benefit of scaling up pre-training data for vision-and-language tasks, as indicated by the new state-of-the-art results on both the nocaps and Conceptual Captions benchmarks.1

One challenge in evaluating visual question answering (VQA) models in the cross-dataset adaptation setting is that the distribution shifts are multi-modal, making it difficult to identify if it is the shifts in visual or language features that play a key role.In this paper, we propose a semi-automatic framework for generating disentangled shifts by introducing a controllable visual question-answer generation (VQAG) module that is capable of generating highly-relevant and diverse questionanswer pairs with the desired dataset style.We use it to create CrossVQA, a collection of test splits for assessing VQA generalization based on the VQA2, VizWiz, and Open Images datasets.We provide an analysis of our generated datasets and demonstrate its utility by using them to evaluate several state-of-theart VQA systems.One important finding is that the visual shifts in cross-dataset VQA matter more than the language shifts.More broadly, we present a scalable framework for systematically evaluating the machine with little human intervention.

Most existing image retrieval systems use text queries as a way for the user to express what they are looking for. However, fine-grained image retrieval often requires the ability to also express where in the image the content they are looking for is. The text modality can only cumbersomely express such localization preferences, whereas pointing is a more natural fit. In this paper, we propose an image retrieval setup with a new form of multimodal queries, where the user simultaneously uses both spoken natural language (the what) and mouse traces over an empty canvas (the where) to express the characteristics of the desired target image. We then describe simple modifications to an existing image retrieval model, enabling it to operate in this setup. Qualitative and quantitative experiments show that our model effectively takes this spatial guidance into account, and provides significantly more accurate retrieval results compared to text-only equivalent systems.

Many objects do not appear frequently enough in complex scenes (e.g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e.g., in product images). Yet, these object-centric images are not effectively leveraged for improving object detection in scene-centric images. In this paper, we propose Mosaic of Object-centric images as Scene-centric images (MosaicOS), a simple and novel framework that is surprisingly effective at tackling the challenges of long-tailed object detection. Keys to our approach are three-fold: (i) pseudo scene-centric image construction from object-centric images for mitigating domain differences, (ii) high-quality bounding box imputation using the object-centric images’ class labels, and (iii) a multi-stage training procedure. On LVIS object detection (and instance segmentation), MosaicOS leads to a massive 60% (and 23%) relative improvement in average precision for rare object categories. We also show that our framework can be compatibly used with other existing approaches to achieve even further gains. Our pre-trained models are publicly available at https://github.com/czhang0528/MosaicOS/.

Neural module networks (NMN) are a popular approach for solving multi-modal tasks such as visual question answering (VQA) and visual referring expression recognition (REF). A key limitation in prior implementations of NMN is that the neural modules do not effectively capture the association between the visual input and the relevant neighbourhood context of the textual input. This limits their generalizability. For instance, NMN fail to understand new concepts such as “yellow sphere to the left" even when it is a combination of known concepts from train data: “blue sphere", “yellow cube", and “metallic cube to the left". In this paper, we address this limitation by introducing a language-guided adaptive convolution layer (LG-Conv) into NMN, in which the filter weights of convolutions are explicitly multiplied with a spatially varying language-guided kernel. Our model allows the neural module to adaptively co-attend over potential objects of interest from the visual and textual inputs. Extensive experiments on VQA and REF tasks demonstrate the effectiveness of our approach. Additionally, we propose a new challenging out-of-distribution test split for REF task, which we call C3-Ref+, for explicitly evaluating the NMN’s ability to generalize well to adversarial perturbations and unseen combinations of known concepts. Experiments on C3-Ref+ further demonstrate the generalization capabilities of our approach.

Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or re-weighting. In this paper, we investigate a largely overlooked approach --- post-processing calibration of confidence scores. We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size. We show that separately handling the background class and normalizing the scores over classes for each proposal are keys to achieving superior performance. On the LVIS dataset, NorCal can effectively improve nearly all the baseline models not only on rare classes but also on common and frequent classes. Finally, we conduct extensive analysis and ablation studies to offer insights into various modeling choices and mechanisms of our approach. Our code is publicly available at https://github.com/tydpan/NorCal.

As most users do not precisely know the structure and/or the content of databases, their queries do not exactly reflect their information needs. The database management system (DBMS) may interact with users and use their feedback on the returned results to learn the information needs behind their queries. Current query interfaces assume that users do not learn and modify the way they express their information needs in the form of queries during their interaction with the DBMS. Using a real-world interaction workload, we show that users learn and modify how to express their information needs during their interactions with the DBMS and their learning is accurately modeled by a well-known reinforcement learning mechanism. As current data interaction systems assume that users do not modify their strategies, they cannot discover the information needs behind users’ queries effectively. We model the interaction between the user and the DBMS as a game with identical interest between two rational agents whose goal is to establish a common language for representing information needs in the form of queries. We propose a reinforcement learning method that learns and answers the information needs behind queries and adapts to the changes in users’ strategies and proves that it improves the effectiveness of answering queries, stochastically speaking. We propose two efficient implementations of this method over large relational databases. Our extensive empirical studies over real-world query workloads indicate that our algorithms are efficient and effective.

Soravit Changpinyo, Bo Pang, Piyush Sharma, Radu Soricut. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We study three general multi-task learning (MTL) approaches on 11 sequence tagging tasks. Our extensive empirical results show that in about 50% of the cases, jointly learning all 11 tasks improves upon either independent or pairwise learning of the tasks. We also show that pairwise MTL can inform us what tasks can benefit others or what tasks can be benefited if they are learned jointly. In particular, we identify tasks that can always benefit others as well as tasks that can always be harmed by others. Interestingly, one of our MTL approaches yields embeddings of the tasks that reveal the natural clustering of semantic and syntactic tasks. Our inquiries have opened the doors to further utilization of MTL in NLP.

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot learning model that takes advantage of clustering structures in the semantic embedding space. The key idea is to impose the structural constraint that semantic representations must be predictive of the locations of their corresponding visual exemplars. To this end, this reduces to training multiple kernel-based regressors from semantic representation-exemplar pairs from labeled data of the seen object categories. Despite its simplicity, our approach significantly outperforms existing zero-shot learning methods on standard benchmark datasets, including the ImageNet dataset with more than 20,000 unseen categories.

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning. Our main idea is to align the semantic space that is derived from external information to the model space that concerns itself with recognizing visual features. To this end, we introduce a set of "phantom" object classes whose coordinates live in both the semantic space and the model space. Serving as bases in a dictionary, they can be optimized from labeled data such that the synthesized real object classifiers achieve optimal discriminative performance. We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen classes.

Measuring similarity is crucial to many learning tasks. It is also a richer and broader notion than what most metric learning algorithms can model. For example, similarity can arise from the process of aggregating the decisions of multiple latent components, where each latent component compares data in its own way by focusing on a different subset of features. In this paper, we propose Similarity Component Analysis (SCA), a probabilistic graphical model that discovers those latent components from data. In SCA, a latent component generates a local similarity value, computed with its own metric, independently of other components. The final similarity measure is then obtained by combining the local similarity values with a (noisy-)OR gate. We derive an EM-based algorithm for fitting the model parameters with similarity-annotated data from pairwise comparisons. We validate the SCA model on synthetic datasets where SCA discovers the ground-truth about the latent components. We also apply SCA to a multiway classification task and a link prediction task. For both tasks, SCA attains significantly better prediction accuracies than competing methods. Moreover, we show how SCA can be instrumental in exploratory analysis of data, where we gain insights about the data by examining patterns hidden in its latent components' local similarity values.