433 citations · 440 across the 11 of their papers we have counts for
12 papers
DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations
Longtian Qiu, Shan Ning, Chuyu Zhang +2
Direct Preference Optimization (DPO) has shown strong potential for mitigating hallucinations in Multimodal Large Language Models (MLLMs). However, existing multimodal DPO approach…
Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery
Xinhang Wan, Jiyuan Liu, Qian Qu +6
In this paper, we address the problem of novel class discovery (NCD), which aims to cluster novel classes by leveraging knowledge from disjoint known classes. While recent advances…
Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery
Chuyu Zhang, Xueyang Yu, Peiyan Gu +1
This paper addresses the problem of Rehearsal-Free Continual Category Discovery (RF-CCD), which focuses on continuously identifying novel class by leveraging knowledge from labeled…
Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discovery
Chuyu Zhang, Peiyan Gu, Xueyang Yu +1
We tackle the generalized category discovery (GCD) problem, which aims to discover novel classes in unlabeled datasets by leveraging the knowledge of known classes. Previous works…
Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation
Ruijie Xu, Chuyu Zhang, Hui Ren +1
We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online poi…
SPOT: Semantic-Regularized Progressive Partial Optimal Transport for Imbalanced Clustering
Chuyu Zhang, Hui Ren, Xuming He
Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant pro…
POT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
Chuyu Zhang, Hui Ren, Xuming He
Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant pro…
Class-relation Knowledge Distillation for Novel Class Discovery
Peiyan Gu, Chuyu Zhang, Ruijie Xu +1
We tackle the problem of novel class discovery, which aims to learn novel classes without supervision based on labeled data from known classes. A key challenge lies in transferring…
Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
Zhitong Gao, Yucong Chen, Chuyu Zhang +1
Equipping predicted segmentation with calibrated uncertainty is essential for safety-critical applications. In this work, we focus on capturing the data-inherent uncertainty (aka a…
Mutual Information-guided Knowledge Transfer for Novel Class Discovery
Chuyu Zhang, Chuanyang Hu, Ruijie Xu +3
We tackle the novel class discovery problem, aiming to discover novel classes in unlabeled data based on labeled data from seen classes. The main challenge is to transfer knowledge…
Cascaded Sparse Feature Propagation Network for Interactive Segmentation
Chuyu Zhang, Chuanyang Hu, Hui Ren +2
We aim to tackle the problem of point-based interactive segmentation, in which the key challenge is to propagate the user-provided annotations to unlabeled regions efficiently. Exi…
Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images
Shuailin Li, Chuyu Zhang, Xuming He
Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for buildin…