paper-with-me

Papers

PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture

2022-01-04 · Kai Han, Jianyuan Guo, Yehui Tang, Yunhe Wang

Transformer networks have achieved great progress for computer vision tasks. Transformer-in-Transformer (TNT) architecture utilizes inner transformer and outer transformer to extract both local and global representations. In this work, we present new TNT baselines by introducing two advanced designs: 1) pyramid architecture, and 2) convolutional stem. The new "PyramidTNT" significantly improves the original TNT by establishing hierarchical representations. PyramidTNT achieves better performances than the previous state-of-the-art vision transformers such as Swin Transformer. We hope this new baseline will be helpful to the further research and application of vision transformer. Code will be available at https://github.com/huawei-noah/CV-Backbones/tree/master/tnt_pytorch.

📄 PDF Abstract BibTeX arXiv:2201.00978

Code (1)

huawei-noah/CV-backbones 공식 구현 tf

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Stochastic Depth Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Residual Connection 설명 없음
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 $x$…

Similar Papers 제목 키워드 기반

PVT v2: Improved Baselines with Pyramid Vision Transformer

2021-06-25 · Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan 외

Transformer recently has presented encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs, including (1) line…

Image ClassificationObject DetectionPanoptic Segmentation

Aggregated Pyramid Vision Transformer: Split-transform-merge Strategy for Image Recognition without Convolutions

2022-03-02 · Rui-Yang Ju, Ting-Yu Lin, Jen-Shiun Chiang, Jia-Hao Jian 외

With the achievements of Transformer in the field of natural language processing, the encoder-decoder and the attention mechanism in Transformer have been applied to computer vision. Recently, in multiple tasks of comput…

Decoderimage-classificationImage Classificationobject-detection+2

Feature Pyramid Transformer

2020-07-18 · ECCV 2020 8 · Dong Zhang, Hanwang Zhang, Jinhui Tang, Meng Wang 외

Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN's increasing rec…

Instance Segmentationobject-detectionObject DetectionSegmentation+1

Leveraging Transformer Decoder for Automotive Radar Object Detection

2026-01-19 · Changxu Zhang, Zhaoze Wang, Tai Fei, Christopher Grimm 외 arxiv

In this paper, we present a Transformer-based architecture for 3D radar object detection that uses a novel Transformer Decoder as the prediction head to directly regress 3D bounding boxes and class scores from radar feat…

Object Detection

PVTAdpNet: Polyp Segmentation using Pyramid vision transformer with a novel Adapter block

2025-09-28 · Arshia Yousefi Nezhad, Helia Aghaei, Hedieh Sajedi arxiv

Colorectal cancer ranks among the most common and deadly cancers, emphasizing the need for effective early detection and treatment. To address the limitations of traditional colonoscopy, including high miss rates due to …

Polyp Segmentation