8 papers
LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation
Jinhong Zhu, Weiqi Yan, Shengchuan Zhang +1
Domain Generalization Semantic Segmentation (DGSS) focuses on generalizing knowledge from labeled source domains to unseen target domains where data is unavailable during the train…
AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization
Wenlun Zhang, Yunshan Zhong, Weiqi Yan +3
The Segment Anything Model (SAM) has revolutionized image and video segmentation with its powerful zero-shot capabilities. However, its massive parameter scale and high computation…
SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia
Pengfei Yue, Xingran Zhao, Juntao Chen +6
Multilingual document and scene text understanding plays an important role in applications such as search, finance, and public services. However, most existing benchmarks focus on…
KVSlimmer: Theoretical Insights and Practical Optimizations for Asymmetric KV Merging
Lianjun Liu, Hongli An, Weiqi Yan +4
The growing computational and memory demands of the Key-Value (KV) cache significantly limit the ability of Large Language Models (LLMs). While KV merging has emerged as a promisin…
Referring Industrial Anomaly Segmentation
Pengfei Yue, Xiaokang Jiang, Yilin Lu +3
Industrial Anomaly Detection (IAD) is vital for manufacturing, yet traditional methods face significant challenges: unsupervised approaches yield rough localizations requiring manu…
STeacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection
Yu Lin, Jianghang Lin, Kai Ye +5
Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotati…