1.1k citations · 1.2k across the 35 of their papers we have counts for
7 papers · 1 filter
RepViT-SAM: Towards Real-Time Segmenting Anything
Ao Wang, Hui Chen, Zijia Lin +2
Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting fo…
MiLe Loss: a New Entropy-Weighed Loss for Mitigating the Bias of Learning Difficulties in Large Language Models
Zhenpeng Su, Xing Wu, Xue Bai +5
Generative language models are usually pretrained on large text corpus via predicting the next token (i.e., sub-word/word/phrase) given the previous ones. Recent works have demonst…
Confidence-based Visual Dispersal for Few-shot Unsupervised Domain Adaptation
Yizhe Xiong, Hui Chen, Zijia Lin +2
Unsupervised domain adaptation aims to transfer knowledge from a fully-labeled source domain to an unlabeled target domain. However, in real-world scenarios, providing abundant lab…
CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs
Ao Wang, Hui Chen, Zijia Lin +3
Vision Transformers (ViTs) have emerged as state-of-the-art models for various vision tasks recently. However, their heavy computation costs remain daunting for resource-limited de…
Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval
Guangyuan Ma, Xing Wu, Peng Wang +2
In this paper, we systematically study the potential of pre-training with Large Language Model(LLM)-based document expansion for dense passage retrieval. Concretely, we leverage th…
RepViT: Revisiting Mobile CNN From ViT Perspective
Ao Wang, Hui Chen, Zijia Lin +2
Recently, lightweight Vision Transformers (ViTs) demonstrate superior performance and lower latency, compared with lightweight Convolutional Neural Networks (CNNs), on resource-con…
CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval
Xing Wu, Guangyuan Ma, Peng Wang +4
Growing techniques have been emerging to improve the performance of passage retrieval. As an effective representation bottleneck pretraining technique, the contextual masked auto-e…