ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions

1 code implementation • 12 Mar 2024 • Chunlong Xia, Xinliang Wang, Feng Lv, Xin Hao, Yifeng Shi

Compared to the state-of-the-art, ViT-CoMer has the following advantages: (1) We inject spatial pyramid multi-receptive field convolutional features into the ViT architecture, which effectively alleviates the problems of limited local information interaction and single-feature representation in ViT.

Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation

1 code implementation • 12 Apr 2023 • Yifeng Shi, Feng Lv, Xinliang Wang, Chunlong Xia, Shaojie Li, Shujie Yang, Teng Xi, Gang Zhang

To address these, we designed the 1st Foundation Model Challenge, with the goal of increasing the popularity of foundation model technology in traffic scenarios and promoting the rapid development of the intelligent transportation industry.

2D Object Detection Image Retrieval +1

RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition

10 code implementations • 5 May 2021 • Xiaohan Ding, Chunlong Xia, Xiangyu Zhang, Xiaojie Chu, Jungong Han, Guiguang Ding

We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition, which is composed of a series of fully-connected (FC) layers.

Face Recognition Image Classification +1