Search Results for author: Kunchang Li

Found 11 papers, 8 papers with code

UniFormer: Unifying Convolution and Self-attention for Visual Recognition

3 code implementations24 Jan 2022 Kunchang Li, Yali Wang, Junhao Zhang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning.

Image Classification Object Detection +4

UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning

2 code implementations12 Jan 2022 Kunchang Li, Yali Wang, Peng Gao, Guanglu Song, Yu Liu, Hongsheng Li, Yu Qiao

For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 9% and 71. 2% top-1 accuracy respectively.

Representation Learning

PointCLIP: Point Cloud Understanding by CLIP

2 code implementations4 Dec 2021 Renrui Zhang, Ziyu Guo, Wei zhang, Kunchang Li, Xupeng Miao, Bin Cui, Yu Qiao, Peng Gao, Hongsheng Li

On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D.

Few-Shot Learning Transfer Learning

MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video

1 code implementation24 Nov 2021 David Junhao Zhang, Kunchang Li, Yunpeng Chen, Yali Wang, Shashwat Chandra, Yu Qiao, Luoqi Liu, Mike Zheng Shou

Self-attention has become an integral component of the recent network architectures, e. g., Transformer, that dominate major image and video benchmarks.

Ranked #11 on Action Recognition on Something-Something V2 (using extra training data)

Action Recognition Image Classification +1

Self-slimmed Vision Transformer

no code implementations24 Nov 2021 Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu

Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks.

Knowledge Distillation

Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling

1 code implementation6 Nov 2021 Renrui Zhang, Rongyao Fang, Wei zhang, Peng Gao, Kunchang Li, Jifeng Dai, Yu Qiao, Hongsheng Li

To further enhance CLIP's few-shot capability, CLIP-Adapter proposed to fine-tune a lightweight residual feature adapter and significantly improves the performance for few-shot classification.

Language Modelling Transfer Learning

Self-Slimming Vision Transformer

no code implementations29 Sep 2021 Zhuofan Zong, Kunchang Li, Guanglu Song, Yali Wang, Yu Qiao, Biao Leng, Yu Liu

Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.

Knowledge Distillation

CT-Net: Channel Tensorization Network for Video Classification

1 code implementation ICLR 2021 Kunchang Li, Xianhang Li, Yali Wang, Jun Wang, Yu Qiao

It can learn to exploit spatial, temporal and channel attention in a high-dimensional manner, to improve the cooperative power of all the feature dimensions in our CT-Module.

Action Classification Action Recognition +1

End-to-End Object Detection with Adaptive Clustering Transformer

1 code implementation18 Nov 2020 Minghang Zheng, Peng Gao, Renrui Zhang, Kunchang Li, Xiaogang Wang, Hongsheng Li, Hao Dong

In this paper, a novel variant of transformer named Adaptive Clustering Transformer(ACT) has been proposed to reduce the computation cost for high-resolution input.

Object Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.