748 citations · 1.4k across the 31 of their papers we have counts for
33 papers
Federated Generalized Category Discovery
Nan Pu, Zhun Zhong, Xinyuan Ji +1
Generalized category discovery (GCD) aims at grouping unlabeled samples from known and unknown classes, given labeled data of known classes. To meet the recent decentralization tre…
Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature
Juanjuan Weng, Zhiming Luo, Dazhen Lin +2
Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black…
Dynamic Conceptional Contrastive Learning for Generalized Category Discovery
Nan Pu, Zhun Zhong, Nicu Sebe
Generalized category discovery (GCD) is a recently proposed open-world problem, which aims to automatically cluster partially labeled data. The main challenge is that the unlabeled…
Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration
Juanjuan Weng, Zhiming Luo, Zhun Zhong +2
Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted advers…
Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
Mingxuan Liu, Subhankar Roy, Zhun Zhong +2
Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners. In the literature such problems have been partially a…
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
Yuyang Zhao, Zhun Zhong, Na Zhao +2
Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalizat…
Class-incremental Novel Class Discovery
Subhankar Roy, Mingxuan Liu, Zhun Zhong +2
We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a…
Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
Zhun Zhong, Yuyang Zhao, Gim Hee Lee +1
In this paper, we consider the problem of domain generalization in semantic segmentation, which aims to learn a robust model using only labeled synthetic (source) data. The model i…
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
Yuyang Zhao, Zhun Zhong, Na Zhao +2
In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only sy…
Federated and Generalized Person Re-identification through Domain and Feature Hallucinating
Fengxiang Yang, Zhun Zhong, Zhiming Luo +2
In this paper, we study the problem of federated domain generalization (FedDG) for person re-identification (re-ID), which aims to learn a generalized model with multiple decentral…
Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification
Yongguo Ling, Zhun Zhong, Donglin Cao +4
Visible thermal person re-identification (VT-ReID) suffers from the inter-modality discrepancy and intra-identity variations. Distribution alignment is a popular solution for VT-Re…
Novel Class Discovery in Semantic Segmentation
Yuyang Zhao, Zhun Zhong, Nicu Sebe +1
We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a…
3D-Aware Semantic-Guided Generative Model for Human Synthesis
Jichao Zhang, Enver Sangineto, Hao Tang +4
Generative Neural Radiance Field (GNeRF) models, which extract implicit 3D representations from 2D images, have recently been shown to produce realistic images representing rigid/s…
Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation
Guanglei Yang, Zhun Zhong, Hao Tang +3
In autonomous driving, learning a segmentation model that can adapt to various environmental conditions is crucial. In particular, copying with severe illumination changes is an im…
A Unified Objective for Novel Class Discovery
Enrico Fini, Enver Sangineto, Stéphane Lathuilière +3
In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labele…
Neighborhood Contrastive Learning for Novel Class Discovery
Zhun Zhong, Enrico Fini, Subhankar Roy +3
In this paper, we address Novel Class Discovery (NCD), the task of unveiling new classes in a set of unlabeled samples given a labeled dataset with known classes. We exploit the pe…
Source-Free Open Compound Domain Adaptation in Semantic Segmentation
Yuyang Zhao, Zhun Zhong, Zhiming Luo +2
In this work, we introduce a new concept, named source-free open compound domain adaptation (SF-OCDA), and study it in semantic segmentation. SF-OCDA is more challenging than the t…
Transformer-Based Source-Free Domain Adaptation
Guanglei Yang, Hao Tang, Zhun Zhong +4
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation. Previous works on SFDA mainly focus on a…
Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation
Subhankar Roy, Evgeny Krivosheev, Zhun Zhong +2
In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the…
Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
Fengxiang Yang, Zhun Zhong, Zhiming Luo +4
This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. One popular method is to obtain ps…
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
Yuyang Zhao, Zhun Zhong, Fengxiang Yang +4
Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to tr…
OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World
Zhun Zhong, Linchao Zhu, Zhiming Luo +3
In this paper, we tackle the problem of discovering new classes in unlabeled visual data given labeled data from disjoint classes. Existing methods typically first pre-train a mode…
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification
Fengxiang Yang, Ke Li, Zhun Zhong +7
Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achi…
Learning to Adapt Invariance in Memory for Person Re-identification
Zhun Zhong, Liang Zheng, Zhiming Luo +2
This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain.…