Search Results for author: Zhun Zhong

Found 54 papers, 38 papers with code

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

1 code implementation24 Oct 2024 Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong

To address these issues, we propose a novel Prototypical Hash Encoding (PHE) framework consisting of Category-aware Prototype Generation (CPG) and Discriminative Category Encoding (DCE) to mitigate the sensitivity of hash code while preserving rich discriminative information contained in high-dimension feature space, in a two-stage projection fashion.

EntityCLIP: Entity-Centric Image-Text Matching via Multimodal Attentive Contrastive Learning

no code implementations23 Oct 2024 Yaxiong Wang, Lianwei Wu, Lechao Cheng, Zhun Zhong, Meng Wang

Recent advancements in image-text matching have been notable, yet prevailing models predominantly cater to broad queries and struggle with accommodating fine-grained query intention.

Contrastive Learning Image-text matching +1

Happy: A Debiased Learning Framework for Continual Generalized Category Discovery

1 code implementation9 Oct 2024 Shijie Ma, Fei Zhu, Zhun Zhong, Wenzhuo LIU, Xu-Yao Zhang, Cheng-Lin Liu

We delve into the conflicts and identify that models are susceptible to prediction bias and hardness bias.

Novel Concepts

Organizing Unstructured Image Collections using Natural Language

no code implementations7 Oct 2024 Mingxuan Liu, Zhun Zhong, Jun Li, Gianni Franchi, Subhankar Roy, Elisa Ricci

Our framework, Text Driven Semantic Multiple Clustering (TeDeSC), uses text as a proxy to concurrently reason over large image collections, discover partitioning criteria, expressed in natural language, and reveal semantic substructures.

Clustering Deep Clustering

Stable Neighbor Denoising for Source-free Domain Adaptive Segmentation

1 code implementation CVPR 2024 Dong Zhao, Shuang Wang, Qi Zang, Licheng Jiao, Nicu Sebe, Zhun Zhong

Specifically, we introduce the Stable Neighbor Denoising (SND) approach, which effectively discovers highly correlated stable and unstable samples by nearest neighbor retrieval and guides the reliable optimization of unstable samples by bi-level learning.

Denoising Pseudo Label +2

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

1 code implementation2 Jun 2024 Chentao Cao, Zhun Zhong, Zhanke Zhou, Yang Liu, Tongliang Liu, Bo Han

In this paper, we propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to Envision potential Outlier Exposure, termed EOE, without access to any actual OOD data.

Out-of-Distribution Detection

FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation

no code implementations27 May 2024 Yuting Ma, Lechao Cheng, Yaxiong Wang, Zhun Zhong, Xiaohua Xu, Meng Wang

Specifically, we employ a local prompt tuning scheme that leverages a few learnable visual prompts to efficiently fine-tune the frozen pre-trained foundation model for downstream tasks, thereby accelerating training and improving model performance under limited local resources and data heterogeneity.

Federated Learning Privacy Preserving

ReMamber: Referring Image Segmentation with Mamba Twister

1 code implementation26 Mar 2024 Yuhuan Yang, Chaofan Ma, Jiangchao Yao, Zhun Zhong, Ya zhang, Yanfeng Wang

In this paper, we propose ReMamber, a novel RIS architecture that integrates the power of Mamba with a multi-modal Mamba Twister block.

Image Segmentation Mamba +1

Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery

no code implementations12 Mar 2024 Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong

In this paper, we study the problem of Generalized Category Discovery (GCD), which aims to cluster unlabeled data from both known and unknown categories using the knowledge of labeled data from known categories.

Descriptive Retrieval +1

Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture

2 code implementations CVPR 2024 Fei Wang, Dan Guo, Kun Li, Zhun Zhong, Meng Wang

To this end, we present FD4MM, a new paradigm of Frequency Decoupling for Motion Magnification with a Multi-level Isomorphic Architecture to capture multi-level high-frequency details and a stable low-frequency structure (motion field) in video space.

Motion Magnification Representation Learning

Active Generalized Category Discovery

1 code implementation CVPR 2024 Shijie Ma, Fei Zhu, Zhun Zhong, Xu-Yao Zhang, Cheng-Lin Liu

Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes.

Active Learning imbalanced classification +1

Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery

no code implementations24 Jan 2024 Yuanpeng Tu, Zhun Zhong, Yuxi Li, Hengshuang Zhao

Generalized category discovery (GCD) aims at addressing a more realistic and challenging setting of semi-supervised learning, where only part of the category labels are assigned to certain training samples.

Contrastive Learning

Democratizing Fine-grained Visual Recognition with Large Language Models

no code implementations24 Jan 2024 Mingxuan Liu, Subhankar Roy, Wenjing Li, Zhun Zhong, Nicu Sebe, Elisa Ricci

Identifying subordinate-level categories from images is a longstanding task in computer vision and is referred to as fine-grained visual recognition (FGVR).

Fine-Grained Visual Recognition World Knowledge

Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation

1 code implementation11 Dec 2023 Dong Zhao, Ruizhi Yang, Shuang Wang, Qi Zang, Yang Hu, Licheng Jiao, Nicu Sebe, Zhun Zhong

This approach formulates pseudo-labels at the connectivity level and thus can facilitate learning structured and low-noise semantics.

Domain Adaptation Semantic Segmentation

Federated Generalized Category Discovery

no code implementations CVPR 2024 Nan Pu, Zhun Zhong, Xinyuan Ji, Nicu Sebe

On each client, GCL builds class-level contrastive learning with both local and global GMMs.

Contrastive Learning

Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature

1 code implementation2 May 2023 Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li, Zhun Zhong

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-box models.

Adversarial Attack

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

1 code implementation CVPR 2023 Nan Pu, Zhun Zhong, Nicu Sebe

This leads traditional novel category discovery (NCD) methods to be incapacitated for GCD, due to their assumption of unlabeled data are only from novel categories.

Contrastive Learning Fine-Grained Visual Recognition +2

Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery

1 code implementation28 Mar 2023 Mingxuan Liu, Subhankar Roy, Zhun Zhong, Nicu Sebe, Elisa Ricci

Discovering novel concepts in unlabelled datasets and in a continuous manner is an important desideratum of lifelong learners.

Novel Class Discovery Novel Concepts

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

2 code implementations7 Mar 2023 Juanjuan Weng, Zhiming Luo, Zhun Zhong, Shaozi Li, Nicu Sebe

In this work, we provide a comprehensive investigation of the CE loss function and find that the logit margin between the targeted and untargeted classes will quickly obtain saturation in CE, which largely limits the transferability.

Adversarial Attack

Dynamically Instance-Guided Adaptation: A Backward-Free Approach for Test-Time Domain Adaptive Semantic Segmentation

1 code implementation CVPR 2023 Wei Wang, Zhun Zhong, Weijie Wang, Xi Chen, Charles Ling, Boyu Wang, Nicu Sebe

In this paper, we study the application of Test-time domain adaptation in semantic segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial.

Domain Adaptation Semantic Segmentation

Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures

1 code implementation CVPR 2023 Linshan Wu, Zhun Zhong, Leyuan Fang, Xingxin He, Qiang Liu, Jiayi Ma, Hao Chen

Our AGMM can effectively endow reliable supervision for unlabeled pixels based on the distributions of labeled and unlabeled pixels.

Contrastive Learning Semantic Segmentation

Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization

1 code implementation18 Dec 2022 Yuyang Zhao, Zhun Zhong, Na Zhao, Nicu Sebe, Gim Hee Lee

Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.

Domain Generalization Hallucination +4

Class-incremental Novel Class Discovery

1 code implementation18 Jul 2022 Subhankar Roy, Mingxuan Liu, Zhun Zhong, Nicu Sebe, Elisa Ricci

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 pre-trained model that has been trained on a labelled data set containing disjoint yet related categories.

Incremental Learning Knowledge Distillation +1

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation

1 code implementation11 Jul 2022 Zhun Zhong, Yuyang Zhao, Gim Hee Lee, Nicu Sebe

Experiments on two synthetic-to-real semantic segmentation benchmarks demonstrate that AdvStyle can significantly improve the model performance on unseen real domains and show that we can achieve the state of the art.

Domain Generalization Image Classification +1

Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization

1 code implementation IEEE Transactions on Image Processing (TIP) 2022 Jinliang Lin, Zhedong Zheng, Zhun Zhong, Zhiming Luo, Shaozi Li, Yi Yang, Nicu Sebe

Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network.

Drone navigation Drone-view target localization +4

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

2 code implementations6 Apr 2022 Yuyang Zhao, Zhun Zhong, Na Zhao, Nicu Sebe, Gim Hee Lee

Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.

Domain Generalization Hallucination +3

Federated and Generalized Person Re-identification through Domain and Feature Hallucinating

no code implementations5 Mar 2022 Fengxiang Yang, Zhun Zhong, Zhiming Luo, Shaozi Li, Nicu Sebe

During local training, the DFS are used to synthesize novel domain statistics with the proposed domain hallucinating, which is achieved by re-weighting DFS with random weights.

Domain Generalization Person Re-Identification

Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification

no code implementations3 Mar 2022 Yongguo Ling, Zhun Zhong, Donglin Cao, Zhiming Luo, Yaojin Lin, Shaozi Li, Nicu Sebe

In this manner, the model will focus on reducing the inter-modality discrepancy while paying less attention to intra-identity variations, leading to a more effective modality alignment.

Person Re-Identification

Novel Class Discovery in Semantic Segmentation

1 code implementation CVPR 2022 Yuyang Zhao, Zhun Zhong, Nicu Sebe, Gim Hee Lee

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 labeled set of disjoint classes.

Image Classification Novel Class Discovery +3

3D-Aware Semantic-Guided Generative Model for Human Synthesis

1 code implementation2 Dec 2021 Jichao Zhang, Enver Sangineto, Hao Tang, Aliaksandr Siarohin, Zhun Zhong, Nicu Sebe, Wei Wang

However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications.

3D-Aware Image Synthesis

Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation

1 code implementation19 Nov 2021 Guanglei Yang, Zhun Zhong, Hao Tang, Mingli Ding, Nicu Sebe, Elisa Ricci

Specifically, in the image translation stage, Bi-Mix leverages the knowledge of day-night image pairs to improve the quality of nighttime image relighting.

Autonomous Driving Image Relighting +3

Neighborhood Contrastive Learning for Novel Class Discovery

1 code implementation CVPR 2021 Zhun Zhong, Enrico Fini, Subhankar Roy, Zhiming Luo, Elisa Ricci, Nicu Sebe

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.

Clustering Contrastive Learning +1

Source-Free Open Compound Domain Adaptation in Semantic Segmentation

1 code implementation7 Jun 2021 Yuyang Zhao, Zhun Zhong, Zhiming Luo, Gim Hee Lee, Nicu Sebe

Second, CPSS can reduce the influence of noisy pseudo-labels and also avoid the model overfitting to the target domain during self-supervised learning, consistently boosting the performance on the target and open domains.

Domain Generalization Self-Supervised Learning +1

Transformer-Based Source-Free Domain Adaptation

1 code implementation28 May 2021 Guanglei Yang, Hao Tang, Zhun Zhong, Mingli Ding, Ling Shao, Nicu Sebe, Elisa Ricci

In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation.

Knowledge Distillation Source-Free Domain Adaptation

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

1 code implementation CVPR 2021 Subhankar Roy, Evgeny Krivosheev, Zhun Zhong, Nicu Sebe, Elisa Ricci

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 task is to learn a robust predictor for all the target domains.

Blended-target Domain Adaptation Multi-target Domain Adaptation

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

1 code implementation CVPR 2021 Yuyang Zhao, Zhun Zhong, Fengxiang Yang, Zhiming Luo, Yaojin Lin, Shaozi Li, Nicu Sebe

In this paper, we study the problem of multi-source domain generalization in ReID, which aims to learn a model that can perform well on unseen domains with only several labeled source domains.

Domain Generalization Meta-Learning +1

Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification

1 code implementation3 Dec 2019 Fengxiang Yang, Ke Li, Zhun Zhong, Zhiming Luo, Xing Sun, Hao Cheng, Xiaowei Guo, Feiyue Huang, Rongrong Ji, Shaozi Li

This procedure encourages that the selected training samples can be both clean and miscellaneous, and that the two models can promote each other iteratively.

Clustering Miscellaneous +2

Learning to Adapt Invariance in Memory for Person Re-identification

no code implementations1 Aug 2019 Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

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.

Person Re-Identification Unsupervised Domain Adaptation

Leveraging Virtual and Real Person for Unsupervised Person Re-identification

1 code implementation5 Nov 2018 Fengxiang Yang, Zhun Zhong, Zhiming Luo, Sheng Lian, Shaozi Li

For training of deep re-ID model, we divide it into three steps: 1) pre-training a coarse re-ID model by using virtual data; 2) collaborative filtering based positive pair mining from the real data; and 3) fine-tuning of the coarse re-ID model by leveraging the mined positive pairs and virtual data.

Collaborative Filtering Style Transfer +1

Generalizing A Person Retrieval Model Hetero- and Homogeneously

1 code implementation ECCV 2018 Zhun Zhong, Liang Zheng, Shaozi Li, Yi Yang

Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras.

Person Re-Identification Person Retrieval +2

Random Erasing Data Augmentation

18 code implementations16 Aug 2017 Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, Yi Yang

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).

General Classification Image Augmentation +4

Re-ranking Person Re-identification with k-reciprocal Encoding

no code implementations CVPR 2017 Zhun Zhong, Liang Zheng, Donglin Cao, Shaozi Li

Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance.

Person Re-Identification Re-Ranking +1

Re-ranking Object Proposals for Object Detection in Automatic Driving

no code implementations19 May 2016 Zhun Zhong, Mingyi Lei, Shaozi Li, Jianping Fan

In this paper, we propose a semantic, class-specific approach to re-rank object proposals, which can consistently improve the recall performance even with less proposals.

Object object-detection +3

Detecting Ground Control Points via Convolutional Neural Network for Stereo Matching

no code implementations8 May 2016 Zhun Zhong, Songzhi Su, Donglin Cao, Shaozi Li

Secondly, we present a ground control points selection scheme according to the maximum matching confidence of each pixel.

Stereo Matching Stereo Matching Hand

Unsupervised domain adaption dictionary learning for visual recognition

no code implementations3 Jun 2015 Zhun Zhong, Zongmin Li, Runlin Li, Xiaoxia Sun

However, when the data instances of a target domain have a different distribution than that of a source domain, the dictionary learning method may fail to perform well.

Dictionary Learning Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.