paper-with-me

Papers

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

2024-03-12 · CVPR 2024 1 · Chunlong Xia, Xinliang Wang, Feng Lv, Xin Hao, Yifeng Shi

Although Vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information interaction and the limited diversity of feature scale. Most existing studies are devoted to designing vision-specific transformers to solve the above problems, which introduce additional pre-training costs. Therefore, we present a plain, pre-training-free, and feature-enhanced ViT backbone with Convolutional Multi-scale feature interaction, named ViT-CoMer, which facilitates bidirectional interaction between CNN and transformer. 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. (2) We propose a simple and efficient CNN-Transformer bidirectional fusion interaction module that performs multi-scale fusion across hierarchical features, which is beneficial for handling dense prediction tasks. (3) We evaluate the performance of ViT-CoMer across various dense prediction tasks, different frameworks, and multiple advanced pre-training. Notably, our ViT-CoMer-L achieves 64.3% AP on COCO val2017 without extra training data, and 62.1% mIoU on ADE20K val, both of which are comparable to state-of-the-art methods. We hope ViT-CoMer can serve as a new backbone for dense prediction tasks to facilitate future research. The code will be released at https://github.com/Traffic-X/ViT-CoMer.

📄 PDF Abstract BibTeX arXiv:2403.07392

Code (1)

Traffic-X/ViT-CoMer 공식 구현 pytorch

Tasks

Prediction

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

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

2024-03-13 · CVPR2024 2024 3 · Chunlong Xia*, Xinliang Wang∗, Feng Lv∗, Xin Hao∗ 외

Although Vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information interaction and the limited diversity …

Instance SegmentationObject DetectionPredictionSemantic Segmentation

CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization

2024-05-23 · Zi Yang, Ziyue Liu, Samridhi Choudhary, Xinfeng Xie 외

Training large AI models such as LLMs and DLRMs costs massive GPUs and computing time. The high training cost has become only affordable to big tech companies, meanwhile also causing increasing concerns about the environ…

Code GenerationGPURecommendation Systems

CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition

2022-07-10 · Wenqi Zhao, Liangcai Gao

The Transformer-based encoder-decoder architecture has recently made significant advances in recognizing handwritten mathematical expressions. However, the transformer model still suffers from the lack of coverage proble…

DecoderHandwritten Mathmatical Expression Recognition

MPViT: Multi-Path Vision Transformer for Dense Prediction

2021-12-21 · CVPR 2022 1 · Youngwan Lee, Jonghee Kim, Jeff Willette, Sung Ju Hwang

Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes. While Convolutional Neural Ne…

Instance Segmentationobject-detectionObject DetectionPrediction+2

How to Train Vision Transformer on Small-scale Datasets?

2022-10-13 · Hanan Gani, Muzammal Naseer, Mohammad Yaqub

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. Ho…