5 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…
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…
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…