244 citations · 714 across the 34 of their papers we have counts for
23 papers · 1 filter
Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation
Yuxi Wang, Jian Liang, Jun Xiao +3
Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labeled source data and unlabeled target data. These…
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
Jian Liang, Lijun Sheng, Zhengbo Wang +2
The emergence of vision-language models, such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks. Although some p…
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
Zhengbo Wang, Jian Liang, Ran He +3
With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising resu…
TALL: Thumbnail Layout for Deepfake Video Detection
Yuting Xu, Jian Liang, Gengyun Jia +3
The growing threats of deepfakes to society and cybersecurity have raised enormous public concerns, and increasing efforts have been devoted to this critical topic of deepfake vide…
Improving Generalization with Domain Convex Game
Fangrui Lv, Jian Liang, Shuang Li +2
Domain generalization (DG) tends to alleviate the poor generalization capability of deep neural networks by learning model with multiple source domains. A classical solution to DG…
Exploiting Semantic Attributes for Transductive Zero-Shot Learning
Zhengbo Wang, Jian Liang, Zilei Wang +1
Zero-shot learning (ZSL) aims to recognize unseen classes by generalizing the relation between visual features and semantic attributes learned from the seen classes. A recent parad…
MODIFY: Model-driven Face Stylization without Style Images
Yuhe Ding, Jian Liang, Jie Cao +2
Existing face stylization methods always acquire the presence of the target (style) domain during the translation process, which violates privacy regulations and limits their appli…
MAPS: A Noise-Robust Progressive Learning Approach for Source-Free Domain Adaptive Keypoint Detection
Yuhe Ding, Jian Liang, Bo Jiang +2
Existing cross-domain keypoint detection methods always require accessing the source data during adaptation, which may violate the data privacy law and pose serious security concer…
Learning Feature Recovery Transformer for Occluded Person Re-identification
Boqiang Xu, Lingxiao He, Jian Liang +1
One major issue that challenges person re-identification (Re-ID) is the ubiquitous occlusion over the captured persons. There are two main challenges for the occluded person Re-ID…
ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation
Yuhe Ding, Lijun Sheng, Jian Liang +2
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, s…
Reciprocal Normalization for Domain Adaptation
Zhiyong Huang, Kekai Sheng, Ke Li +5
Batch normalization (BN) is widely used in modern deep neural networks, which has been shown to represent the domain-related knowledge, and thus is ineffective for cross-domain tas…
UMAD: Universal Model Adaptation under Domain and Category Shift
Jian Liang, Dapeng Hu, Jiashi Feng +1
Learning to reject unknown samples (not present in the source classes) in the target domain is fairly important for unsupervised domain adaptation (UDA). There exist two typical UD…
Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
Boqiang Xu, Jian Liang, Lingxiao He +1
Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time, which is a realistic but cha…
Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning
Yujun Shi, Kuangqi Zhou, Jian Liang +5
Class Incremental Learning (CIL) aims at learning a multi-class classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Pre…
Semi-Supervised Domain Generalizable Person Re-Identification
Lingxiao He, Wu Liu, Jian Liang +4
Existing person re-identification (re-id) methods are stuck when deployed to a new unseen scenario despite the success in cross-camera person matching. Recent efforts have been sub…
A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation
Yuxi Wang, Jian Liang, Zhaoxiang Zhang
Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the po…
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
Jian Liang, Dapeng Hu, Jiashi Feng +1
To ease the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous and related labeled datasets (sources) to a new unlabeled dataset (targe…
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
Yifan Zhang, Bryan Hooi, Dapeng Hu +2
Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative vis…
Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
Dapeng Hu, Jian Liang, Qibin Hou +2
In this work, we attempt to address unsupervised domain adaptation by devising simple and compact conditional domain adversarial training methods. We first revisit the simple conca…
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
Jian Liang, Yunbo Wang, Dapeng Hu +2
This work addresses the unsupervised domain adaptation problem, especially in the case of class labels in the target domain being only a subset of those in the source domain. Such…
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
Jian Liang, Dapeng Hu, Jiashi Feng
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typica…
Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
Lingxiao He, Jian Liang, Haiqing Li +1
Partial person re-identification (re-id) is a challenging problem, where only several partial observations (images) of people are available for matching. However, few studies have…
Robust Localized Multi-view Subspace Clustering
Yanbo Fan, Jian Liang, Ran He +2
In multi-view clustering, different views may have different confidence levels when learning a consensus representation. Existing methods usually address this by assigning distinct…