Exploring a substantial amount of unlabeled data, semi-supervised learning boosts the recognition performance when only a limited number of labels are provided. However, conventional methods assume a class-balanced data distribution, which is difficult to realize in practice due to the long-tailed nature of real-world data. While addressing the data imbalance is a well-explored area in supervised learning paradigms, directly transferring existing approaches to SSL is nontrivial, as prior knowledge about unlabeled data distribution remains unknown in SSL. In light of this, we introduce the Balanced Memory Bank (BMB), a framework for long-tailed semi-supervised learning. The core of BMB is an online-updated memory bank that caches historical features alongside their corresponding pseudo-labels, and the memory is also carefully maintained to ensure the data therein are class-rebalanced. Furthermore, an adaptive weighting module is incorporated to work jointly with the memory bank to further re-calibrate the biased training process. Experimental results across various datasets demonstrate the superior performance of BMB compared with state-of-the-art approaches. For instance, an improvement of 8.2% on the 1% labeled subset of ImageNet127 and 4.3% on the 50% labeled subset of ImageNet-LT.

With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video information in a memory bank. This allows our model to reference historical video content for long-term analysis without exceeding LLMs' context length constraints or GPU memory limits. Our memory bank can be seamlessly integrated into current multimodal LLMs in an off-the-shelf manner. We conduct extensive experiments on various video understanding tasks, such as long-video understanding, video question answering, and video captioning, and our model can achieve state-of-the-art performances across multiple datasets.

We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels. To ground this prediction process in auto-regression, we customize a non-causal attention mask for the decoder, incorporating two key features: modeling tokens from different labels to be independent, and treating image tokens as a prefix. This masking mechanism inspires an efficient method - one-shot sampling - to simultaneously sample tokens of multiple labels in parallel and rank generated labels by their probabilities during inference. To further enhance the efficiency, we propose a simple strategy to construct a compact decoder by simply discarding the intermediate blocks of a pretrained language model. This approach yields a decoder that matches the full model's performance while being notably more efficient. The code is available at github.com/kaiyuyue/nxtp.

Videos are multimodal in nature. Conventional video recognition pipelines typically fuse multimodal features for improved performance. However, this is not only computationally expensive but also neglects the fact that different videos rely on different modalities for predictions. This article introduces Hierarchical and Conditional Modality Selection (HCMS), a simple yet efficient multimodal learning framework for efficient video recognition. HCMS operates on a low-cost modality, i.e., audio clues, by default, and dynamically decides on-the-fly whether to use computationally expensive modalities, including appearance and motion clues, on a per-input basis. This is achieved by the collaboration of three LSTMs that are organized in a hierarchical manner. In particular, LSTMs that operate on high-cost modalities contain a gating module, which takes as inputs lower-level features and historical information to adaptively determine whether to activate its corresponding modality; otherwise, it simply reuses historical information. We conduct extensive experiments on two large-scale video benchmarks, FCVID and ActivityNet, and the results demonstrate the proposed approach can effectively explore multimodal information for improved classification performance while requiring much less computation.

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels, there is a lack of consideration in localization precision and amplified class imbalance, both of which are critical for detection tasks. In this paper, we introduce certainty-aware pseudo labels tailored for object detection, which can effectively estimate the classification and localization quality of derived pseudo labels. This is achieved by converting conventional localization as a classification task followed by refinement. Conditioned on classification and localization quality scores, we dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Extensive experiments demonstrate that our method improves state-of-the-art SSOD performance by 1-2% AP on COCO and PASCAL VOC while being orthogonal and complementary to most existing methods. In the limited-annotation regime, our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.

Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of tasks recently. While achieving excellent performance, they still require relatively intensive computational cost that scales up drastically as the numbers of patches, self-attention heads and transformer blocks increase. In this paper, we argue that due to the large variations among images, their need for modeling long-range dependencies between patches differ. To this end, we introduce AdaViT, an adaptive computation framework that learns to derive usage policies on which patches, self-attention heads and transformer blocks to use throughout the backbone on a per-input basis, aiming to improve inference efficiency of vision transformers with a minimal drop of accuracy for image recognition. Optimized jointly with a transformer backbone in an end-to-end manner, a light-weight decision network is attached to the backbone to produce decisions on-the-fly. Extensive experiments on ImageNet demonstrate that our method obtains more than 2 × improvement on efficiency compared to state-of-the-art vision transformers with only 0.8% drop of accuracy, achieving good efficiency/accuracy trade-offs conditioned on different computational budgets. We further conduct quantitative and qualitative analysis on learned usage polices and provide more insights on the redundancy in vision transformers. Code is available at ht tps: / / gi thub. com/MengLcool/AdaVi T.

We introduce AdaFrame, a conditional computation framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame, which contains a Long Short-Term Memory augmented with a global memory to provide context information, operates as an agent to interact with video sequences aiming to search over time which frames to use. Trained with policy search methods, at each time step, AdaFrame computes a prediction, decides where to observe next, and estimates a utility, i.e., expected future rewards, of viewing more frames in the future. Exploring predicted utilities at testing time, AdaFrame is able to achieve adaptive lookahead inference so as to minimize the overall computational cost without incurring a degradation in accuracy. We conduct extensive experiments on two large-scale video benchmarks, FCVID and ActivityNet. With a vanilla ResNet-101 model, AdaFrame achieves similar performance of using all frames while only requiring, on average, 8.21 and 8.65 frames on FCVID and ActivityNet, respectively. We also demonstrate AdaFrame is compatible with modern 2D and 3D networks for video recognition. Furthermore, we show, among other things, learned frame usage can reflect the difficulty of making prediction decisions both at instance-level within the same class and at class-level among different categories.

3D convolutional networks are prevalent for video recognition. While achieving excellent recognition performance on standard benchmarks, they operate on a sequence of frames with 3D convolutions and thus are computationally demanding. Exploiting large variations among different videos, we introduce Ada3D, a conditional computation framework that learns instance-specific 3D usage policies to determine frames and convolution layers to be used in a 3D network. These policies are derived with a two-head lightweight selection network conditioned on each input video clip. Then, only frames and convolutions that are selected by the selection network are used in the 3D model to generate predictions. The selection network is optimized with policy gradient methods to maximize a reward that encourages making correct predictions with limited computation. We conduct experiments on three video recognition benchmarks and demonstrate that our method achieves similar accuracies to state-of-the-art 3D models while requiring 20% − 50% less computation across different datasets. We also show that learned policies are transferable and Ada3D is compatible to different backbones and modern clip selection approaches. Our qualitative analysis indicates that our method allocates fewer 3D convolutions and frames for "static" inputs, yet uses more for motion-intensive clips.

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding ground-truth objects. Such a harsh split conditioned on IoU results in binary labels that are potentially noisy and challenging for training. In this paper, we propose to mitigate noise incurred by imperfect label assignment such that the contributions of anchors are dynamically determined by a carefully constructed cleanliness score associated with each anchor. Exploring outputs from both regression and classification branches, the cleanliness scores, estimated without incurring any additional computational overhead, are used not only as soft labels to supervise the training of the classification branch but also sample re-weighting factors for improved localization and classification accuracy. We conduct extensive experiments on COCO, and demonstrate, among other things, the proposed approach steadily improves RetinaNet by ~2% with various backbones.

In this paper, we explore clean-label poisoning attacks on deep convolutional networks with access to neither the network’s output nor its architecture or parameters. Our goal is to ensure that after injecting the poisons into the training data, a model with unknown architecture and parameters trained on that data will misclassify the target image into a specific class. To achieve this goal, we generate multiple poison images from the base class by adding small perturbations which cause the poison images to trap the target image within their convex polytope in feature space. We also demonstrate that using Dropout during crafting of the poisons and enforcing this objective in multiple layers enhances transferability, enabling attacks against both the transfer learning and end-to-end training settings. We demonstrate transferable attack success rates of over 50% by poisoning only 1% of the training set.

We propose a modular approach towards large-scale real-time object detection by decoupling objectness detection and classification. We exploit the fact that many object classes are visually similar and share parts. Thus, a universal objectness detector can be learned for class-agnostic object detection followed by fine-grained classification using a (non)linear classifier. Our approach is a modification of the R-FCN architecture to learn shared filters for performing localization across different object classes. We trained a detector for 3000 object classes, called R-FCN-3000, that obtains an mAP of 34.9% on the ImageNet detection dataset. It outperforms YOLO-9000 by 18% while processing 30 images per second. We also show that the objectness learned by R-FCN-3000 generalizes to novel classes and the performance increases with the number of training object classes - supporting the hypothesis that it is possible to learn a universal objectness detector. Code will be made available.

With the development of depth cameras such as Kinect and Intel Realsense, RGB-D based human detection receives continuous research attention due to its usage in a variety of applications. In this paper, we propose a new Multi-Glimpse LSTM (MG-LSTM) network, in which multi-scale contextual information is sequentially integrated to promote the human detection performance. Furthermore, we propose a feature fusion strategy based on our MG-LSTM network to better incorporate the RGB and depth information. To the best of our knowledge, this is the first attempt to utilize LSTM structure for RGB-D based human detection. Our method achieves superior performance on two publicly available datasets.

We propose a multistream multitask deep network for joint human detection and head pose estimation in RGB-D videos. To achieve high accuracy, we jointly utilize appearance, shape, and motion information as inputs. Based on the depth information, we generate scale invariant proposals, which are then fed into a novel contextual region of interest pooling (CRP) layer in our deep network. This CRP has two branches to deal with contextual information for each subject. The proposed method outperforms state-of-the-art approaches on three public datasets.