Dense Prediction Task

Dense prediction tasks in computer vision aim to generate a prediction for every pixel in an image, crucial for applications like semantic segmentation and depth estimation. Current research focuses on improving efficiency and generalizability through techniques like curriculum learning (e.g., progressively increasing patch size), attention mechanisms to reduce computational cost, and the adaptation of transformer architectures for improved performance and scalability across diverse tasks. These advancements are significant because they address the computational demands of dense prediction, enabling more accurate and efficient solutions for a wide range of real-world applications.

Papers

March 27, 2023

Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong
Shot Learning Visual Token Dense Prediction Task

October 4, 2022

Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search
Thanh Vu, Yanqi Zhou, Chunfeng Wen, Yueqi Li, Jan-Michael Frahm
Neural Architecture Search Multitask Learning Dense Prediction Dense Prediction Task Hardware Aware Neural Architecture Search

July 20, 2022

EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching
Qiang Wang, Shaohuai Shi, Kaiyong Zhao, Xiaowen Chu
Neural Architecture Search Stereo Matching Scene Flow Dense Prediction Task GPU Inference Elastic Band

May 30, 2022

Self-Supervised Pre-training of Vision Transformers for Dense Prediction Tasks
Jaonary Rabarisoa, Valentin Belissen, Florian Chabot, Quoc-Cuong Pham
Vision Transformer Contrastive Loss Self Supervised Pre Training Contrastive Pre Training Dense Prediction Task

May 27, 2022

X-ViT: High Performance Linear Vision Transformer without Softmax
Jeonggeun Song, Heung-Chang Lee
Vision Transformer Self Attention Transformer Based Model Computer Vision Task Softmax Function Dense Prediction Task ViT LoS V2X

May 17, 2022

Vision Transformer Adapter for Dense Predictions
Zhe Chen, Yuchen Duan, Wenhai Wang, Junjun He, Tong Lu, Jifeng Dai, Yu Qiao
Vision Transformer Inductive Bias Dense Prediction Dense Prediction Task Transformer Adapter

April 28, 2022

Depth Estimation with Simplified Transformer
John Yang, Le An, Anurag Dixit, Jinkyu Koo, Su Inn Park
Transformer Based Depth Estimation Monocular Depth Estimation Dense Prediction Dense Prediction Task Simple Transformer

March 21, 2022

Dense Siamese Network for Dense Unsupervised Learning
Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy
Siamese Network Dense Prediction Task Semantic Segmentation Benchmark Dense Self Supervised Learning Region Embeddings

March 3, 2022

Fast Neural Architecture Search for Lightweight Dense Prediction Networks
Lam Huynh, Esa Rahtu, Jiri Matas, Janne Heikkila
Neural Architecture Search Monocular Depth Estimation Dense Prediction Dense Prediction Task Dense Recognition

February 15, 2022

Neural Architecture Search for Dense Prediction Tasks in Computer Vision
Thomas Elsken, Arber Zela, Jan Hendrik Metzen, Benedikt Staffler, Thomas Brox, Abhinav Valada, Frank Hutter
Computer Vision Neural Architecture Search Large Scale Neural Architecture Dense Prediction Task Pixel Wise Prediction

January 21, 2022

A Comprehensive Study of Vision Transformers on Dense Prediction Tasks
Kishaan Jeeveswaran, Senthilkumar Kathiresan, Arnav Varma, Omar Magdy, Bahram Zonooz, Elahe Arani
Convolutional Neural Network Vision Transformer Convolutional Layer Comprehensive Study Dense Prediction Task

December 2, 2021

DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting
Yongming Rao, Wenliang Zhao, Guangyi Chen, Yansong Tang, Zheng Zhu, Guan Huang, Jie Zhou, Jiwen Lu
Image Text Pair Dense Prediction Dense Prediction Task

November 22, 2021

Topological Regularization for Dense Prediction
Deqing Fu, Bradley J. Nelson
Semantic Segmentation Topological Feature Persistent Homology Dense Prediction Dense Prediction Task Topological Regularization