Transformer Based Decoder

Transformer-based decoders are increasingly used in various applications requiring complex data reconstruction and generation, such as image segmentation, medical image analysis, and channel decoding. Current research focuses on improving decoder architectures, including incorporating mechanisms like multi-scale attention, iterative calibration of multi-modal features, and task-aware designs to enhance performance and efficiency. These advancements aim to address limitations of traditional decoders, leading to more accurate and robust solutions in diverse fields, from improving wireless communication reliability to enabling more precise medical image analysis. The ability to handle multiple tasks and data types within a unified framework is a key area of ongoing development.

Papers

November 12, 2024

Decision Feedback In-Context Symbol Detection over Block-Fading Channels
Li Fan, Jing Yang, Cong Shen
Context Learning Pre Trained Transformer Human Decision Symbol Detection Large Scale Fading Transformer Based Decoder

October 21, 2024

On the Design and Performance of Machine Learning Based Error Correcting Decoders
Yuncheng Yuan, Péter Scheepers, Lydia Tasiou, Yunus Can Gültekin, Federico Corradi, Alex Alvarado
Product Design System Performance High Quality Decoder Learning With Error Transformer Based Decoder

October 8, 2024

Accelerating Error Correction Code Transformers
Matan Levy, Yoni Choukroun, Lior Wolf
Low Precision Quantization Ternary Quantization Transformer Based Decoder

October 4, 2024

Error Correction Code Transformer: From Non-Unified to Unified
Yongli Yan, Jieao Zhu, Tianyue Zheng, Jiaqi He, Linglong Dai
Unified View Low Density Parity Check Linear Code Transformer Based Decoder

April 12, 2024

Calibration & Reconstruction: Deep Integrated Language for Referring Image Segmentation
Yichen Yan, Xingjian He, Sihan Chen, Jing Liu
Full State Reconstruction Calibration Performance Transformer Decoder Referring Image Segmentation New Language Calibration Method Transformer Based Decoder

March 26, 2024

Automated Report Generation for Lung Cytological Images Using a CNN Vision Classifier and Multiple-Transformer Text Decoders: Preliminary Study
Atsushi Teramoto, Ayano Michiba, Yuka Kiriyama, Tetsuya Tsukamoto, Kazuyoshi Imaizumi, Hiroshi Fujita
Convolutional Neural Network Preliminary Study Report Generation Biopsy Core Cytology Image Transformer Based Decoder

January 9, 2023

DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction
Yangyang Xu, Yibo Yang, Lefei Zhang
Multi Task Learning Deformable Convolution Dense Prediction Deformable Transformer Query Transformer Transformer Based Decoder

November 25, 2022

MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation
Jing Xu, Wentao Shi, Pan Gao, Zhengwei Wang, Qizhu Li
Semantic Segmentation Transformer Based Multi Scale Segmentation Performance Transformer Decoder Transformer Based Decoder

October 18, 2022

Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attention
Yu Yuan, Jiaqi Wu, Zhongliang Jing, Henry Leung, Han Pan
Image Fusion Cross Modal Attention Attention Block Hybrid CNN Transformer Multi Modal Image Convolutional Encoder Fusion Model Transformer Based Decoder

April 1, 2022

UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation
Ali Hatamizadeh, Ziyue Xu, Dong Yang, Wenqi Li, Holger Roth, Daguang Xu
Convolutional Neural Network Vision Transformer Pre Training 3D Medical Image Segmentation Transformer Encoders Liver Tumor Segmentation Vision Transformer Model Transformer Based Decoder

Transformer Based Decoder

Papers

Decision Feedback In-Context Symbol Detection over Block-Fading Channels

On the Design and Performance of Machine Learning Based Error Correcting Decoders

Accelerating Error Correction Code Transformers

Error Correction Code Transformer: From Non-Unified to Unified

Calibration & Reconstruction: Deep Integrated Language for Referring Image Segmentation

Automated Report Generation for Lung Cytological Images Using a CNN Vision Classifier and Multiple-Transformer Text Decoders: Preliminary Study

DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction

MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation

Multimodal Image Fusion based on Hybrid CNN-Transformer and Non-local Cross-modal Attention

UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation