6 papers
SfMamba: Efficient Source-Free Domain Adaptation via Selective Scan Modeling
Xi Chen, Hongxun Yao, Sicheng Zhao +3
Source-free domain adaptation (SFDA) tackles the critical challenge of adapting source-pretrained models to unlabeled target domains without access to source data, overcoming data…
PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
Zhaopan Xu, Pengfei Zhou, Weidong Tang +7
Multimodal large language models (MLLMs) have achieved remarkable success in vision-language tasks, but their reliance on vast, internet-sourced data raises significant privacy and…
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
Zhaopan Xu, Pengfei Zhou, Jiaxin Ai +6
Reasoning is an essential capacity for large language models (LLMs) to address complex tasks, where the identification of process errors is vital for improving this ability. Recent…
Multi-source Domain Adaptation for Panoramic Semantic Segmentation
Jing Jiang, Sicheng Zhao, Jiankun Zhu +7
Unsupervised domain adaptation methods for panoramic semantic segmentation utilize real pinhole images or low-cost synthetic panoramic images to transfer segmentation models to rea…
Bridge then Begin Anew: Generating Target-relevant Intermediate Model for Source-free Visual Emotion Adaptation
Jiankun Zhu, Sicheng Zhao, Jing Jiang +5
Visual emotion recognition (VER), which aims at understanding humans' emotional reactions toward different visual stimuli, has attracted increasing attention. Given the subjective…
Dataset Growth
Ziheng Qin, Zhaopan Xu, Yukun Zhou +10
Deep learning benefits from the growing abundance of available data. Meanwhile, efficiently dealing with the growing data scale has become a challenge. Data publicly available are…