Vehicle re-identification (Vehicle ReID) aims at retrieving vehicle images across disjoint surveillance camera views. The majority of vehicle ReID research is heavily reliant upon supervisory labels from specific human-collected datasets for training. When applied to the large-scale real-world scenario, these models will experience dreadful performance declines due to the notable domain discrepancy between the source dataset and the target. To address this challenge, in this paper, we propose an unsupervised vehicle ReID framework (MGR-GCL). It integrates a multi-granularity CNN representation for learning discriminative transferable features and a contrastive learning module responsible for efficient domain adaptation in the unlabeled target domain. Specifically, after training the proposed Multi-Granularity Representation (MGR) on the labeled source dataset, we propose a group contrastive learning module (GCL) to generate pseudo labels for the target dataset, facilitating the domain adaptation process. We conducted extensive experiments and the results demonstrated our superiority against existing state-of-the-art methods.
Imperial College London（帝国理工学院）；Shanghai Jiao Tong University（上海交通大学）
The success of most advanced facial expression recognition works relies heavily on large-scale annotated datasets. However, it poses great challenges in acquiring clean and consistent annotations for facial expression datasets. On the other hand, self-supervised contrastive learning has gained great popularity due to its simple yet effective instance discrimination training strategy, which can potentially circumvent the annotation issue. Nevertheless, there remain inherent disadvantages of instance-level discrimination, which are even more challenging when faced with complicated facial represe…
Beijing University of Posts and Telecommunications（北京邮电大学）
Unsupervised person re-identification (ReID) aims to match a query image of a pedestrian to the images in gallery set without supervision labels. The most popular approaches to tackle unsupervised person ReID are usually performing a clustering algorithm to yield pseudo labels at first and then exploit the pseudo labels to train a deep neural network. However, the pseudo labels are noisy and sensitive to the hyper-parameter(s) in clustering algorithm. In this paper, we propose a Hybrid Contrastive Learning (HCL) approach for unsupervised person ReID, which is based on a hybrid between instance…
China University of Geosciences（中国地质大学）；Nanjing University of Science and Technology（南京理工大学）；University of Chinese Academy of Sciences（中国科学院大学）
RGB-Infrared person re-identification (RGB-IR ReID) aims to associate people across disjoint RGB and IR camera views. Currently, state-of-the-art performance of RGB-IR ReID is not as impressive as that of conventional ReID. Much of that is due to the notorious modality bias training issue brought by the single-modality ImageNet pre-training, which might yield RGB-biased representations that severely hinder the cross-modality image retrieval. This paper makes first attempt to tackle the task from a pre-training perspective. We propose a self-supervised pre-training solution, named Modality-Awar…
MIT（麻省理工学院）；MSU（密歇根州立大学）；IBM Research AI（IBM研究院人工智能中心）；UCSD（加州大学圣地亚哥分校）
As a seminal tool in self-supervised representation learning, contrastive learning has gained unprecedented attention in recent years. In essence, contrastive learning aims to leverage pairs of positive and negative samples for representation learning, which relates to exploiting neighborhood information in a feature space. By investigating the connection between contrastive learning and neighborhood component analysis (NCA), we provide a novel stochastic nearest neighbor viewpoint of contrastive learning and subsequently propose a series of contrastive losses that outperform the existing ones…
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. Our results show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets. Second, given the generality of the approach, we try to realize further gains with minor…
Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimod…
Incorporating granularity bias as the margin into contrastive loss for video captioning
The School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；The School of Aeronautics and Astronautics, University of Electronic Science and Technology of China（电子科技大学航空航天学院）
针对视频描述中短语长尾分布导致的粒度偏差问题，提出基于统计的偏差提取器量化偏差影响，并将粒度偏差作为间隔融入双向三元组对比损失（GMC Loss），为头部和尾部句子建立不同训练目标，在 MSRVTT 和 MSVD 上达到 SOTA 性能。
What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations can be useful in the foundation model setting, where the goal is to learn diverse, general-purpose representations for multiple downstream tasks. We perform contrastive learning experiments on a range of image and audio datasets with multiple downstream tasks (e.g. for digits superimposed on photographs, predicting the class of one vs. the other). We find t…
Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering
School of Information Science and Technology, Hangzhou Normal University（杭州师范大学信息科学与技术学院）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）；Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）计算机科学与技术系）
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting. While memory replay has shown promising results, the recency bias in online learning caused by the commonly used Softmax classifier remains an unsolved challenge. Although the Nearest-Class-Mean (NCM) classifier is significantly undervalued in the CL community, we demonstrate that it is a simple yet effective substitute for the Softmax classifier. It addresses the recency bias…
Beihang University（北京航空航天大学）；RIKEN AIP（理化学研究所先进智能项目中心）；The University of Tokyo（东京大学）；Griffith University（格里菲斯大学）；University of York（约克大学）
Despite recent stereo matching networks achieving impressive performance given sufficient training data, they suffer from domain shifts and generalize poorly to unseen domains. We argue that maintaining feature consistency between matching pixels is a vital factor for promoting the generalization capability of stereo matching networks, which has not been adequately considered. Here we address this issue by proposing a simple pixel-wise contrastive learning across the viewpoints. The stereo contrastive feature loss function explicitly constrains the consistency between learned features of match…
Institute for Infocomm Research (I2R), A-STAR（新加坡科技研究局资讯通信研究院）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labels could be incorrect, a.k.a. the confirmation bias, and the pseudo labels will in turn harm the network training. Recent studies combined finetuning (FT) from pretrained weights with SSL to mitigate the challenges and claimed superior results in the low-label regime. In this work, we first show that the better pretrained weights brought in by FT account for the state-of-the-art performance, and importantly that they…
The University of Sydney（悉尼大学）；Wuhan University（武汉大学）；Hubei Luojia Laboratory（湖北珞珈实验室）；Beijing Institute of Technology（北京理工大学）；Nanyang Technological University（南洋理工大学）
MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)（南方海洋科学与工程广东省实验室（广州））；Gaoling School of Artificial Intelligence（高瓴人工智能学院）；Renmin University of China（中国人民大学）；Beijing Key Laboratory of Big Data Management and Analysis Methods（北京市大数据管理与分析方法重点实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangzhou HKUST Fok Ying Tung Research Institute（广州香港科技大学霍英东研究院）
Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding
Dept. of Electrical & Computer Engineering, University of Pittsburgh, USA（宾夕法尼亚大学电气与计算机工程系）；Dept. of Biomedical Engineering, Tsinghua University, China（清华大学生物医学工程系）；Dept. of Neurology, University of Southern California, USA（美国南加州大学神经病学系）；Dept. of Computer Science, University of Texas Rio Grande Valley, USA（德克萨斯理工大学里奥格兰德谷分校计算机科学系）
Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts
Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）
We focus on better understanding the critical factors of augmentation-invariant representation learning. We revisit MoCo v2 and BYOL and try to prove the authenticity of the following assumption: different frameworks bring about representations of different characteristics even with the same pretext task. We establish the first benchmark for fair comparisons between MoCo v2 and BYOL, and observe: (i) sophisticated model configurations enable better adaptation to pre-training dataset; (ii) mismatched optimization strategies of pre-training and fine-tuning hinder model from achieving competitive…
A recent work from Bello shows that training and scaling strategies may be more significant than model architectures for visual recognition. This short note studies effective training and scaling strategies for video recognition models. We propose a simple scaling strategy for 3D ResNets, in combination with improved training strategies and minor architectural changes. The resulting models, termed 3D ResNet-RS, attain competitive performance of 81.0 on Kinetics-400 and 83.8 on Kinetics-600 without pre-training. When pre-trained on a large Web Video Text dataset, our best model achieves 83.5 an…
Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学PCA实验室）；PCA Lab, School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学PCA实验室）
IBM Research AI（IBM研究院人工智能部门）；Tel-Aviv University（特拉维夫大学）；Penta-AI（Penta人工智能）；Boston University（波士顿大学）
Few-shot learning methods offer pre-training techniques optimized for easier later adaptation of the model to new classes (unseen during training) using one or a few examples. This adaptivity to unseen classes is especially important for many practical applications where the pre-trained label space cannot remain fixed for effective use and the model needs to be "specialized" to support new categories on the fly. One particularly interesting scenario, essentially overlooked by the few-shot literature, is Coarse-to-Fine Few-Shot (C2FS), where the training classes (e.g. animals) are of much `coar…
Caltech（加州理工学院）；Google（谷歌）；University of Edinburgh（爱丁堡大学）；Alan Turing Institute（艾伦·图灵研究所）；University of Copenhagen（哥本哈根大学）
Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well understood, the field still lacks widely accepted best practices for replicating this success on other datasets. As a first step in this direction, we study contrastive self-supervised learning on four diverse large-scale datasets. By looking through the lenses of data quantity, data domain, data quality, and task granularity, we provide new insights into the necess…
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林技术大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Centre of eXplainable Artificial Intelligence, Technological University Dublin（可解释人工智能中心，都柏林技术大学）
SenseTime Research（商汤科技研究院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）
This technical report presents an overview of our solution used in the submission to 2021 HACS Temporal Action Localization Challenge on both Supervised Learning Track and Weakly-Supervised Learning Track. Temporal Action Localization (TAL) requires to not only precisely locate the temporal boundaries of action instances, but also accurately classify the untrimmed videos into specific categories. However, Weakly-Supervised TAL indicates locating the action instances using only video-level class labels. In this paper, to train a supervised temporal action localizer, we adopt Temporal Context Ag…
University of Oxford（牛津大学）；Tel-Aviv University（特拉维夫大学）
Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pa…
The University of Hong Kong（香港大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；University of Cambridge（剑桥大学）
Learning medical visual representations directly from paired radiology reports has become an emerging topic in representation learning. However, existing medical image-text joint learning methods are limited by instance or local supervision analysis, ignoring disease-level semantic correspondences. In this paper, we present a novel Multi-Granularity Cross-modal Alignment (MGCA) framework for generalized medical visual representation learning by harnessing the naturally exhibited semantic correspondences between medical image and radiology reports at three different levels, i.e., pathological r…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could actually improve GANs, and in particular, how to apply a wider range of augmentations in training. In this paper, we propose a novel way to address these questions by incorporating a recent contrastive representation learning scheme into the GAN discriminator, coined ContraD. This "fusion" enables the discriminators to work with much stronger augmentations withou…
Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment
Southwest Jiaotong University（西南交通大学）；Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education（教育部可持续城市智能交通工程研究中心）；Carnegie Mellon University（卡内基梅隆大学）
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper aims to address this problem by revisiting the locally supervised learning, where a network is split into gradient-isolated modules and trained with local supervision. We experimentally show that simply training local modules with E2E loss tends to collapse task-relevant information at early layers, and hence hurts the performance of the full model. To avoid this issue, we propose an information propagation (InfoPro) …
Beijing University of Posts and Telecommunications（北京邮电大学）；China Mobile Research Institute（中国移动研究院）
Retrieving tracked-vehicles by natural language descriptions plays a critical role in smart city construction. It aims to find the best match for the given texts from a set of tracked vehicles in surveillance videos. Existing works generally solve it by a dual-stream framework, which consists of a text encoder, a visual encoder and a cross-modal loss function. Although some progress has been made, they failed to fully exploit the information at various levels of granularity. To tackle this issue, we propose a novel framework for the natural language-based vehicle retrieval task, OMG, which Obs…
