There have been a fairly of research interests in exploring the disentanglement of appearance and shape from human images. Most existing endeavours pursuit this goal by either using training images with annotations or regulating the training process with external clues such as human skeleton, body segmentation or cloth patches etc. In this paper, we aim to address this challenge in a more unsupervised manner---we do not require any annotation nor any external task-specific clues. To this end, we formulate an encoder-decoder-like network to extract both the shape and appearance features from input images at the same time, and train the parameters by three losses: feature adversarial loss, color consistency loss and reconstruction loss. The feature adversarial loss mainly impose little to none mutual information between the extracted shape and appearance features, while the color consistency loss is to encourage the invariance of person appearance conditioned on different shapes. More importantly, our unsupervised (Unsupervised learning has many interpretations in different tasks. To be clear, in this paper, we refer unsupervised learning as learning without task-specific human annotations, pairs or any form of weak supervision.) framework utilizes learned shape features as masks which are applied to the input itself in order to obtain clean appearance features. Without using fixed input human skeleton, our network better preserves the conditional human posture while requiring less supervision. Experimental results on DeepFashion and Market1501 demonstrate that the proposed method achieves clean disentanglement and is able to synthesis novel images of comparable quality with state-of-the-art weakly-supervised or even supervised methods.
While recent person re-identification (ReID) methods achieve high accuracy in a supervised setting, their generalization to an unlabelled domain is still an open problem. In this paper, we introduce a novel unsupervised disentanglement generative adversarial network (UD-GAN) to address the domain adaptation issue of supervised person ReID. Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation, and adapts the ReID model to an unlabelled target domain by learning disentangled latent representations on the domain. …
National Taiwan University（台湾大学）；MOST Joint Research Center for AI Technology and All Vista Healthcare（科技部AI技术与全视医疗照护联合研究中心）；ASUS Intelligent Cloud Services（华硕智能云服务）
Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras. To address this challenging task, existing re-ID models typically rely on a large amount of labeled training data, which is not practical for real-world applications. To alleviate this limitation, researchers now targets at cross-dataset re-ID which focuses on generalizing the discriminative ability to the unlabeled target domain when given a labeled source domain dataset. To achieve this goal, our proposed Pose Disentanglement and Adaptation Network (PDA-Net) aims at learning deep …
Yonsei University（延世大学）；Korea Institute of Science and Technology (KIST)（韩国科学技术研究院）
In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames. Existing methods tend to focus only on how to use temporal information, which often leads to networks being fooled by similar appearances and same backgrounds. In this paper, we propose a Disentanglement and Switching and Aggregation Network (DSANet), which segregates the features representing identity and features based on camera characteristics, and pays more attention to ID information. We also introduce an auxiliary task that utilizes a new pair of features…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching. One challenge is how to generate target domain samples with reliable labels for training. To address this problem, we propose a Disentanglement-based Cross-Domain Feature Augmentation (DCDFA) strategy, where the augmented features characterize well the target and source domain data distributions while inheriting reliable identity labels. Particularly, we disentangle each sample feature into a robust domain-invariant…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance information under poor illumination conditions. Compared to traditional person re-identification that handles only the intra-modality discrepancy, VI-ReID suffers from additional cross-modality discrepancy caused by different types of imaging systems. To reduce both intra- and cross-modality discrepancies, we propose a Hierarchical Cross-Modality Disentanglement (Hi-CMD) method, which automatically disentangles ID-disc…
Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
Wangxuan Institute of Computer Technology, Peking University, Beijing, China（北京大学王轩计算机技术研究院，北京，中国）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）；School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China（华中科技大学人工智能与自动化学院，武汉，中国）
Visible-infrared person re-identification (VI-ReID) is a challenging and essential task in night-time intelligent surveillance systems. Except for the intra-modality variance that RGB-RGB person re-identification mainly overcomes, VI-ReID suffers from additional inter-modality variance caused by the inherent heterogeneous gap. To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standar…
Kunming University of Science and Technology（昆明理工大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera styles, illumination and backgrounds, there exists a large gap between source domain and target domain, introducing a great challenge on cross-domain matching. To tackle this problem, in this paper we propose a novel method named Dual-stream Reciprocal Disentanglement Learning (DRDL), which is quite efficient in learning domain-invariant features. In DRDL, two enc…
Tel Aviv University（特拉维夫大学）；Hebrew University of Jerusalem（希伯来大学）
We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose. Our encoder is stable and consistent, meaning that the shape encoding is purely pose-invariant, while the extracted rotation and translation are able to semantically align different input shapes of the same class to a common canonical pose. Specifically, we design an auto-encoder based on Vector Neuron Networks, a rotation-equivariant neural network, whose layers we extend to provide translation-equivariance in addition to rotation-equivariance only. The resu…
UC, Santa Barbara（加州大学圣巴巴拉分校）；Adobe Research（奥多比研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Generative models have been widely studied in computer vision. Recently, diffusion models have drawn substantial attention due to the high quality of their generated images. A key desired property of image generative models is the ability to disentangle different attributes, which should enable modification towards a style without changing the semantic content, and the modification parameters should generalize to different images. Previous studies have found that generative adversarial networks (GANs) are inherently endowed with such disentanglement capability, so they can perform disentangled…
Disentangled representations support a range of downstream tasks including causal reasoning, generative modeling, and fair machine learning. Unfortunately, disentanglement has been shown to be impossible without the incorporation of supervision or inductive bias. Given that supervision is often expensive or infeasible to acquire, we choose to incorporate structural inductive bias and present an unsupervised, deep State-Space-Model for Video Disentanglement (VDSM). The model disentangles latent time-varying and dynamic factors via the incorporation of hierarchical structure with a dynamic prior…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）；National Taiwan University（国立台湾大学）
Most person re-identification (ReID) approaches assume that person images are captured under relatively similar illumination conditions. In reality, long-term person retrieval is common, and person images are often captured under different illumination conditions at different times across a day. In this situation, the performances of existing ReID models often degrade dramatically. This paper addresses the ReID problem with illumination variations and names it as {\em Illumination-Adaptive Person Re-identification (IA-ReID)}. We propose an Illumination-Identity Disentanglement (IID) network to…
Clothing changes and lack of data labels are both crucial challenges in person ReID. For the former challenge, people may occur multiple times at different locations wearing different clothing. However, most of the current person ReID research works focus on the benchmarks in which a person's clothing is kept the same all the time. For the last challenge, some researchers try to make model learn information from a labeled dataset as a source to an unlabeled dataset. Whereas purely unsupervised training is less used. In this paper, we aim to solve both problems at the same time. We design a nov…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）；University of Oxford（牛津大学）
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in filtering out identity-irrelevant interference and learning domain-invariant person representations. In this paper, we aim to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains. To achieve this goal, we propose a simple yet effective Style Normalization and Restitution (SNR) module. Specifically, we filter out style variations (…
Person re-identification (re-ID) aims to recognize instances of the same person contained in multiple images taken across different cameras. Existing methods for re-ID tend to rely heavily on the assumption that both query and gallery images of the same person have the same clothing. Unfortunately, this assumption may not hold for datasets captured over long periods of time (e.g., weeks, months or years). To tackle the re-ID problem in the context of clothing changes, we propose a novel representation learning model which is able to generate a body shape feature representation without being af…
Tel Aviv University（特拉维夫大学）；Facebook AI Research（脸书人工智能研究院）
We study the problem of learning to map, in an unsupervised way, between domains A and B, such that the samples b in B contain all the information that exists in samples a in A and some additional information. For example, ignoring occlusions, B can be people with glasses, A people without, and the glasses, would be the added information. When mapping a sample a from the first domain to the other domain, the missing information is replicated from an independent reference sample b in B. Thus, in the above example, we can create, for every person without glasses a version with the glasses observ…
East China Normal University（华东师范大学）；Youtu Lab, Tencent（腾讯优图实验室）
Face anti-spoofing is crucial to security of face recognition systems. Previous approaches focus on developing discriminative models based on the features extracted from images, which may be still entangled between spoof patterns and real persons. In this paper, motivated by the disentangled representation learning, we propose a novel perspective of face anti-spoofing that disentangles the liveness features and content features from images, and the liveness features is further used for classification. We also put forward a Convolutional Neural Network (CNN) architecture with the process of dis…
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
Institute of Automation, CAS（中国科学院自动化研究所）；School of Artificial Intelligence, UCAS（中国科学院大学人工智能学院）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；Kuaishou Technology（快手科技）；National Cheng-Kung University（国立成功大学）；University of Konstanz（康斯坦茨大学）
DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification
organization= Department of Imaging Science, Graduate School of Advanced Imaging Science, Multimedia \& Film, Chung-Ang University , addressline= , city= Seoul , postcode= 06974 , state= , country= South Korea；organization= Department of Metaverse Convergence, Graduate School of Advanced Imaging Science, Multimedia \& Film, Chung-Ang University , addressline= , city= Seoul , postcode= 06974 , state= , country= South Korea
We propose RANA, a relightable and articulated neural avatar for the photorealistic synthesis of humans under arbitrary viewpoints, body poses, and lighting. We only require a short video clip of the person to create the avatar and assume no knowledge about the lighting environment. We present a novel framework to model humans while disentangling their geometry, texture, and also lighting environment from monocular RGB videos. To simplify this otherwise ill-posed task we first estimate the coarse geometry and texture of the person via SMPL+D model fitting and then learn an articulated neural r…
LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models
Computer Vision Center, Spain（西班牙计算机视觉中心）；City University of Hong Kong（香港城市大学）；Computer Sciences Department, Universitat Autònoma de Barcelona, Spain（西班牙巴塞罗那自治大学计算机科学系）；Program of Computer Science, City University of Hong Kong (Dongguan)（香港城市大学（东莞）计算机科学项目）
A Dual-stage Prompt-driven Privacy-preserving Paradigm for Person Re-Identification
School of Artificial Intelligence and Robotics at 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 at Hunan Normal University（湖南师范大学信息科学与工程学院）
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning System（马克斯·普朗克-苏黎世联邦理工学院学习系统中心）
While current monocular 3D face reconstruction methods can recover fine geometric details, they suffer several limitations. Some methods produce faces that cannot be realistically animated because they do not model how wrinkles vary with expression. Other methods are trained on high-quality face scans and do not generalize well to in-the-wild images. We present the first approach that regresses 3D face shape and animatable details that are specific to an individual but change with expression. Our model, DECA (Detailed Expression Capture and Animation), is trained to robustly produce a UV displ…
FaceTracer: Unveiling Source Identities from Swapped Face Images and Videos for Fraud Prevention
School of Cyber Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学与技术学院）；Centre for Frontier AI Research, Agency for Science, Technology and Research (A*STAR)（科技研究局前沿人工智能研究中心）；College of Computing and Data Science at Nanyang Technological University（南洋理工大学计算与数据科学学院）
Unsupervised person re-identification (Re-Id) has attracted increasing attention due to its practical application in the read-world video surveillance system. The traditional unsupervised Re-Id are mostly based on the method alternating between clustering and fine-tuning with the classification or metric learning objectives on the grouped clusters. However, since person Re-Id is an open-set problem, the clustering based methods often leave out lots of outlier instances or group the instances into the wrong clusters, thus they can not make full use of the training samples as a whole. To solve t…
Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（机器智能与先进计算教育部重点实验室）；Pazhou Lab (HuangPu)（琶洲实验室（黄埔））
Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to allow for localized image manipulations. We use face images as our example of choice. Depending on the image region, identity and other facial attributes can be modified. The proposed network can transfer parts of a face such as shape and color of eyes, hair, mouth, etc.~directly between persons while all other parts of the face remain unchanged. The network …
This paper tackles the purely unsupervised person re-identification (Re-ID) problem that requires no annotations. Some previous methods adopt clustering techniques to generate pseudo labels and use the produced labels to train Re-ID models progressively. These methods are relatively simple but effective. However, most clustering-based methods take each cluster as a pseudo identity class, neglecting the large intra-ID variance caused mainly by the change of camera views. To address this issue, we propose to split each single cluster into multiple proxies and each proxy represents the instances …
An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval
School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Frontis；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artifcial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Wuhan AI Research, Wuhan, China（武汉人工智能研究所，武汉，中国）；School of Computer Science, Wuhan University（武汉大学计算机学院）
State-of-the-art unsupervised re-ID methods train the neural networks using a memory-based non-parametric softmax loss. Instance feature vectors stored in memory are assigned pseudo-labels by clustering and updated at instance level. However, the varying cluster sizes leads to inconsistency in the updating progress of each cluster. To solve this problem, we present Cluster Contrast which stores feature vectors and computes contrast loss at the cluster level. Our approach employs a unique cluster representation to describe each cluster, resulting in a cluster-level memory dictionary. In this wa…
Rethinking Sampling Strategies for Unsupervised Person Re-identification
University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Institute of North Electronic Equipment（北方电子设备研究所）；Peng Cheng Laboratory（鹏城实验室）；Tianjin University（天津大学）
本文研究无监督行人重识别中的采样策略，提出 group sampling 分组采样以缓解过拟合并增强统计稳定性，在三个基准上取得与最先进方法相当或更优的性能。
Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgery
Wellcome/EPSRC Centre for Interventional and Surgical Sciences（Wellcome/EPSRC介入与外科科学中心）；University College London（伦敦大学学院）；Xiamen University（厦门大学）；The University of Hong Kong（香港大学）；National University of Singapore（新加坡国立大学）
Investigating Identity Signals in Conversational Facial Dynamics via Disentangled Expression Features
1 Department of Computational Linguistics, University of Zurich , Zurich, Switzerland 2 UZH Digital Society Initiative 3 Idiap Research Institute, Martigny, Switzerland 4 \'E cole Polytechnique F \'e d \'e rale de Lausanne (EPFL), Lausanne, Switzerland
University of Oxford（牛津大学）；Federal University of Rio Grande（南里奥格兰德联邦大学）；Australian National University（澳大利亚国立大学）
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility. In this work, we present deep generative models for human body analysis in which the body pose and the visual appearance are disentangled. Such a disentanglement allows independent manipulation of pose and appearance, and hence enables applications such as pose-transfer without specific training for such a task. Our proposed models, the Conditional-DGPose and the Semi-DGPo…
