Recent researches on unsupervised person re-identification~(reID) have demonstrated that pre-training on unlabeled person images achieves superior performance on downstream reID tasks than pre-training on ImageNet. However, those pre-trained methods are specifically designed for reID and suffer flexible adaption to other pedestrian analysis tasks. In this paper, we propose VAL-PAT, a novel framework that learns transferable representations to enhance various pedestrian analysis tasks with multimodal information. To train our framework, we introduce three learning objectives, \emph{i.e.,} self-supervised contrastive learning, image-text contrastive learning and multi-attribute classification. The self-supervised contrastive learning facilitates the learning of the intrinsic pedestrian properties, while the image-text contrastive learning guides the model to focus on the appearance information of pedestrians.Meanwhile, multi-attribute classification encourages the model to recognize attributes to excavate fine-grained pedestrian information. We first perform pre-training on LUPerson-TA dataset, where each image contains text and attribute annotations, and then transfer the learned representations to various downstream tasks, including person reID, person attribute recognition and text-based person search. Extensive experiments demonstrate that our framework facilitates the learning of general pedestrian representations and thus leads to promising results on various pedestrian analysis tasks.
Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion
School of Artificial Intelligence and Robotics, Hunan University(湖南大学人工智能与机器人学院);National Engineering Research Center of Robot Visual Perception and Control Technology(机器人视觉感知与控制技术国家工程研究中心);College of Information Science and Engineering, Hunan Normal University(湖南师范大学信息科学与工程学院)
CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision
Tsinghua University(清华大学);Information Engineering University(信息工程大学);University of Electronic Science and Technology of China(电子科技大学);Beijing University of Technology(北京工业大学)
CLIP-based Camera-Agnostic Feature Learning for Intra-camera Person Re-Identification
Tangshan Research Institute, Southwest Jiaotong University(西南交通大学唐山研究院);School of Computing and Artificial Intelligence, Southwest Jiaotong University(西南交通大学计算机与人工智能学院);Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China(教育部可持续城市智能交通工程研究中心);Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province(四川省产业链协同与信息支撑技术重点实验室)
Biologically Informed Representation Learning for Robust Cross-Center Generalization of MALDI-TOF Mass Spectrometry
Universidad Carlos III de Madrid(卡洛斯三世大学);Instituto de Investigación Sanitaria Gregorio Marañón(格雷戈里奥·马拉尼翁卫生研究所);Hospital General Universitario Gregorio Marañón(格雷戈里奥·马拉尼翁大学总医院)
Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head
Meta AI;Cranberry-Lemon University(蔓越莓柠檬大学);University of the Witwatersrand(威特沃特斯兰德大学)
如果我们希望学习廉价、可靠和可转移的模型,那么代价高昂、嘈杂和过度专业化的标签将被搁置一边,转而支持无监督学习。为此,谱嵌入、自监督学习或生成式建模提供了有竞争力的解决方案。然而,这些方法带来了许多挑战,\textit{e.g.}估计测地线距离,指定投影仪架构和抗崩溃损失,或指定解码器架构和重建损失。相比之下,我们引入了一个简单的可解释的替代方案-创造的\textbf{DIET} -从未标记的数据中学习表示,没有这些挑战。\textbf{DIET}非常简单:采用自己喜欢的分类设置,并使用\textbf{D} atum \textbf{I} nd \textbf{E} x作为其\textbf{T}目标类,\textit{i.e. each sample is its own class},无需进一步更改。\textbf{DIET}不需要解码器/投影器网络,不基于正对也不基于重构,不引入超参数,并且可以跨数据集和架构进行开箱即用。尽管\textbf{DIET}很简单,但学习到的表示具有高质量,并且通常与最先进的\textit{e.g.}相当,在DIET的学习表示之上使用线性分类器,在CIFAR 100上使用Resnet 101达到$71.4\%$,在TinyImagenet上使用Resnext 50达到$52.5\%$。
Princeton University(普林斯顿大学);University of Cambridge(剑桥大学);Alan Turing Institute(艾伦·图灵研究所);Max Planck Institute for Empirical Aesthetics(马克斯·普朗克经验美学研究所)
3D Human Pose, Shape and Texture from Low-Resolution Images and Videos
Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所);Electrical and Computer Engineering, Carnegie Mellon University(卡内基梅隆大学电气与计算机工程学院);Institut de Robòtica i Informàtica Industrial (CSIC-UPC)(机器人与工业信息研究所(西班牙国家研究委员会-加泰罗尼亚理工大学));Facebook Reality Lab (Oculus)(Facebook现实实验室(Oculus))
A Deep Generative Model for Resting-State EEG Synthesis and Transferable Representation Learning
Institute of Psychology, Eötvös Loránd University(埃斯特哈兹·洛朗大学心理学研究所);Doctoral School of Psychology, Eötvös Loránd University(埃斯特哈兹·洛朗大学心理学博士学院);Department of Behavioural and Cognitive Sciences, University of Luxembourg(卢森堡大学行为与认知科学系)
MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);School of Information Engineering, Minzu University of China(中央民族大学信息工程学院);University of Adelaide(阿德莱德大学)
Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision
College of Electronics and Information Engineering, Shenzhen University(深圳大学电子与信息工程学院);Guangdong Key Laboratory of Intelligent Information Processing(广东省智能信息处理重点实验室);Department of Computer and Information Science, University of Macau(澳门大学计算机与信息科学系);State Key Laboratory of Internet of Things for Smart City(物联网与智慧城市国家重点实验室)
A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision
University of Maryland, Baltimore County(马里兰大学巴尔的摩郡分校);Facebook AI(Facebook 人工智能研究院);UC Davis(加州大学戴维斯分校)
使用自然语言作为训练视觉识别模型的监督具有很大的希望。最近的工作表明,如果这种监督以大型训练数据集中图像和字幕之间的对齐形式使用,那么所得到的对齐模型在作为下游任务的zero-shot分类上表现良好2。在本文中,我们专注于梳理出哪些部分的语言监督是必不可少的训练zero-shot图像分类模型。通过大量细致的实验,我们发现:1)一个简单的词袋(BoW)标题可以用来代替数据集中的大多数图像标题。令人惊讶的是,我们观察到,这种方法提高了zero-shot分类性能时,结合字平衡。2)使用BoW预训练模型,我们可以通过在没有字幕的图像上生成伪BoW字幕来获得更多的训练数据。在具有真实和伪BoW字幕的图像上训练的模型实现了更强的zero-shot性能。在ImageNet-1k zero-shot评估中,我们的最佳模型仅使用3M图像-标题对,与在15M图像-标题对上训练的CLIP模型表现相当(31.5% vs 31.3%)。
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Youedata Co., Ltd.(优数数据有限公司);University of Electronic Science and Technology of China(电子科技大学);University of Science and Technology Beijing(北京科技大学)
Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
South China University of Technology(华南理工大学);Pazhou Lab(琶洲实验室);JD Explore Academy(京东探索研究院);Yunnan University(云南大学);Yunnan United Vision Technology Co., Ltd.(云南联慧视觉科技有限公司)