40 citations · 157 across the 30 of their papers we have counts for
15 papers · 1 filter
Bridging the Divide: Reconsidering Softmax and Linear Attention
Dongchen Han, Yifan Pu, Zhuofan Xia +6
Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when d…
A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
Wangbo Zhao, Yizeng Han, Jiasheng Tang +5
Vision-language models (VLMs) have shown remarkable success across various multi-modal tasks, yet large VLMs encounter significant efficiency challenges due to processing numerous…
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
Zanlin Ni, Yulin Wang, Renping Zhou +5
Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-q…
DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Yang Yue, Yulin Wang, Bingyi Kang +5
MLLMs have demonstrated remarkable comprehension and reasoning capabilities with complex language and visual data. These advances have spurred the vision of establishing a generali…
Exploring contextual modeling with linear complexity for point cloud segmentation
Yong Xien Chng, Xuchong Qiu, Yizeng Han +3
Point cloud segmentation is an important topic in 3D understanding that has traditionally has been tackled using either the CNN or Transformer. Recently, Mamba has emerged as a pro…
OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength
Le Yang, Ziwei Zheng, Yizeng Han +3
Differentiable architecture search (DARTS) has emerged as a promising technique for effective neural architecture search, and it mainly contains two steps to find the high-performa…
Adapting Vision-Language Model with Fine-grained Semantics for Open-Vocabulary Segmentation
Yong Xien Chng, Xuchong Qiu, Yizeng Han +3
Despite extensive research, open-vocabulary segmentation methods still struggle to generalize across diverse domains. To reduce the computational cost of adapting Vision-Language M…
Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators
Yifan Pu, Zhuofan Xia, Jiayi Guo +9
This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of…
UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation
Chaoqun Du, Yulin Wang, Jiayi Guo +3
Test-Time Adaptation (TTA) aims to adapt pre-trained models to the target domain during testing. In reality, this adaptability can be influenced by multiple factors. Researchers ha…
DyFADet: Dynamic Feature Aggregation for Temporal Action Detection
Le Yang, Ziwei Zheng, Yizeng Han +4
Recent proposed neural network-based Temporal Action Detection (TAD) models are inherently limited to extracting the discriminative representations and modeling action instances wi…
EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Yulin Wang, Yang Yue, Rui Lu +3
The superior performance of modern visual backbones usually comes with a costly training procedure. We contribute to this issue by generalizing the idea of curriculum learning beyo…
Demystify Mamba in Vision: A Linear Attention Perspective
Dongchen Han, Ziyi Wang, Zhuofan Xia +7
Mamba is an effective state space model with linear computation complexity. It has recently shown impressive efficiency in dealing with high-resolution inputs across various vision…
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Wangbo Zhao, Jiasheng Tang, Yizeng Han +5
Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the e…
GRA: Detecting Oriented Objects through Group-wise Rotating and Attention
Jiangshan Wang, Yifan Pu, Yizeng Han +4
Oriented object detection, an emerging task in recent years, aims to identify and locate objects across varied orientations. This requires the detector to accurately capture the or…
SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
Chaoqun Du, Yizeng Han, Gao Huang
Recent advancements in semi-supervised learning have focused on a more realistic yet challenging task: addressing imbalances in labeled data while the class distribution of unlabel…