35 citations · 321 across the 48 of their papers we have counts for
37 papers · 1 filter
FLatten Transformer: Vision Transformer using Focused Linear Attention
Dongchen Han, Xuran Pan, Yizeng Han +2
The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers…
Computation-efficient Deep Learning for Computer Vision: A Survey
Yulin Wang, Yizeng Han, Chaofei Wang +3
Over the past decade, deep learning models have exhibited considerable advancements, reaching or even exceeding human-level performance in a range of visual perception tasks. This…
Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Yizeng Han, Zeyu Liu, Zhihang Yuan +4
Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a redu…
Dynamic Perceiver for Efficient Visual Recognition
Yizeng Han, Dongchen Han, Zeyu Liu +7
Early exiting has become a promising approach to improving the inference efficiency of deep networks. By structuring models with multiple classifiers (exits), predictions for ``eas…
ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
Changyao Tian, Chenxin Tao, Jifeng Dai +7
Image recognition and generation have long been developed independently of each other. With the recent trend towards general-purpose representation learning, the development of gen…
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
Xingqian Xu, Jiayi Guo, Zhangyang Wang +3
Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches.…
Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention
Xuran Pan, Tianzhu Ye, Zhuofan Xia +2
Self-attention mechanism has been a key factor in the recent progress of Vision Transformer (ViT), which enables adaptive feature extraction from global contexts. However, existing…
Zero-shot Generative Model Adaptation via Image-specific Prompt Learning
Jiayi Guo, Chaofei Wang, You Wu +6
Recently, CLIP-guided image synthesis has shown appealing performance on adapting a pre-trained source-domain generator to an unseen target domain. It does not require any target-d…
Adaptive Rotated Convolution for Rotated Object Detection
Yifan Pu, Yiru Wang, Zhuofan Xia +6
Rotated object detection aims to identify and locate objects in images with arbitrary orientation. In this scenario, the oriented directions of objects vary considerably across dif…
Joint Representation Learning for Text and 3D Point Cloud
Rui Huang, Xuran Pan, Henry Zheng +4
Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have…
Deep Incubation: Training Large Models by Divide-and-Conquering
Zanlin Ni, Yulin Wang, Jiangwei Yu +3
Recent years have witnessed a remarkable success of large deep learning models. However, training these models is challenging due to high computational costs, painfully slow conver…
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
Weijie Su, Xizhou Zhu, Chenxin Tao +7
To effectively exploit the potential of large-scale models, various pre-training strategies supported by massive data from different sources are proposed, including supervised pre-…
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Chenyu Yang, Yuntao Chen, Hao Tian +9
We present a novel bird's-eye-view (BEV) detector with perspective supervision, which converges faster and better suits modern image backbones. Existing state-of-the-art BEV detect…
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
Yulin Wang, Yang Yue, Rui Lu +4
The superior performance of modern deep networks usually comes with a costly training procedure. This paper presents a new curriculum learning approach for the efficient training o…
Cross-Modal Adapter for Vision-Language Retrieval
Haojun Jiang, Jianke Zhang, Rui Huang +4
Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained…
Contrastive Language-Image Pre-Training with Knowledge Graphs
Xuran Pan, Tianzhu Ye, Dongchen Han +2
Recent years have witnessed the fast development of large-scale pre-training frameworks that can extract multi-modal representations in a unified form and achieve promising perform…
Latency-aware Spatial-wise Dynamic Networks
Yizeng Han, Zhihang Yuan, Yifan Pu +4
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixe…
AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition
Yulin Wang, Yang Yue, Xinhong Xu +6
Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of c…
ActiveNeRF: Learning where to See with Uncertainty Estimation
Xuran Pan, Zihang Lai, Shiji Song +1
Recently, Neural Radiance Fields (NeRF) has shown promising performances on reconstructing 3D scenes and synthesizing novel views from a sparse set of 2D images. Albeit effective,…
Learning to Weight Samples for Dynamic Early-exiting Networks
Yizeng Han, Yifan Pu, Zihang Lai +6
Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks…
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Chenxin Tao, Xizhou Zhu, Weijie Su +6
Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrim…
Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding
Haojun Jiang, Yuanze Lin, Dongchen Han +2
Visual grounding, i.e., localizing objects in images according to natural language queries, is an important topic in visual language understanding. The most effective approaches fo…
Learn From the Past: Experience Ensemble Knowledge Distillation
Chaofei Wang, Shaowei Zhang, Shiji Song +1
Traditional knowledge distillation transfers "dark knowledge" of a pre-trained teacher network to a student network, and ignores the knowledge in the training process of the teache…
Domain Adaptation via Prompt Learning
Chunjiang Ge, Rui Huang, Mixue Xie +4
Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approach…