Contrastive learning methods train visual encoders by comparing views from one instance to others. Typically, the views created from one instance are set as positive, while views from other instances are negative. This binary instance discrimination is studied extensively to improve feature representations in self-supervised learning. In this paper, we rethink the instance discrimination framework and find the binary instance labeling insufficient to measure correlations between different samples. For an intuitive example, given a random image instance, there may exist other images in a mini-batch whose content meanings are the same (i.e., belonging to the same category) or partially related (i.e., belonging to a similar category). How to treat the images that correlate similarly to the current image instance leaves an unexplored problem. We thus propose to support the current image by exploring other correlated instances (i.e., soft neighbors). We first carefully cultivate a candidate neighbor set, which will be further utilized to explore the highly-correlated instances. A cross-attention module is then introduced to predict the correlation score (denoted as positiveness) of other correlated instances with respect to the current one. The positiveness score quantitatively measures the positive support from each correlated instance, and is encoded into the objective for pretext training. To this end, our proposed method benefits in discriminating uncorrelated instances while absorbing correlated instances for SSL. We evaluate our soft neighbor contrastive learning method (SNCLR) on standard visual recognition benchmarks, including image classification, object detection, and instance segmentation. The state-of-the-art recognition performance shows that SNCLR is effective in improving feature representations from both ViT and CNN encoders.
Neighborhood Contrastive Transformer for Change Captioning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Peng Cheng Laboratory（鹏城实验室）
Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Hong Kong University of Science and Technology（香港科技大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
University of Science and Technology of China（中国科学技术大学）；SenseTime Research（商汤科技研究院）；Tsinghua University（清华大学）；The Chinese University of Hong Kong（香港中文大学）；The University of Sydney（悉尼大学）
CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance
Kyung Hee University（庆熙大学）；The University of Danang—Vietnam-Korea University of Information and Communication Technology（岘港大学—越韩信息与通信技术大学）；Digital Science and Technology Institute（数字科学技术研究院）
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University（北京大学深圳研究生院机器感知重点实验室）；The School of Intelligent Systems Engineering, Sun Yat-sen University（中山大学智能系统工程学院）
近年来，随着对比学习方法的发展，用于基于手势的动作识别的自监督表示学习得到了发展。现有的对比学习方法使用正常的增强来构造相似的正样本，这限制了探索新的运动模式的能力。在本文中，更好地利用极端扩增引入的运动模式，一个对比学习框架，利用丰富的信息挖掘的自我监督的行动表示（Aimmatis）的建议。首先，提出了极端增强和基于能量的注意力引导下降模块（EADM）来获得不同的正样本，这带来了新的运动模式，以提高学习表示的通用性。其次，由于原始恒等式的剧烈变化，直接使用极端增广可能无法提高性能，因此提出了双分布发散最小化损失（Dual DistributionalDivergenceMinimizationLoss，$^3$ M Loss），以更温和的方式最小化分布发散。第三，提出了最近邻挖掘（NNM），进一步扩大正样本，使丰富的信息挖掘过程更加合理。在NTU RGB+D 60，PKU-MMD，NTU RGB+D 120数据集上的详尽实验已经验证了我们的Aimestant可以在各种评估协议下显著优于最先进的方法，并观察到更高质量的动作表示。我们的代码可在https://github.com/Levigty/AimCLR上获得。
CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer
Huazhong University of Science and Technology（华中科技大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Beijing University of Posts and Telecommunications（北京邮电大学）
Global-Graph Guided and Local-Graph Weighted Contrastive Learning for Unified Clustering on Incomplete and Noise Multi-View Data
Guangxi Normal University（广西师范学院）；University of Electronic Science and Technology of China（电子科技大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Hainan University（海南大学）
Mask-informed Deep Contrastive Incomplete Multi-view Clustering
Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；School of Computer Science, China University of Geosciences（中国地质大学计算机学院）
