Rethinking Transformer-based Set Prediction for Object Detection

Last update: Dec 03, 2022

Related tags

Deep Learning TSP-Detection

Overview

Rethinking Transformer-based Set Prediction for Object Detection

Here are the code for the ICCV paper. The code is adapted from Detectron2 and AdelaiDet.

All the model are trained on 4 V100 GPUs.

Prerequisites

Modify the environment name and environment prefix in environment.yml and run

conda env create -f environment.yml

git clone https://github.com/facebookresearch/detectron2.git
cd detectron2
git reset --hard b88c6c06563e4db1139aafbd6d8d97d1fa7a57e4
pip install -e .

Rreproducing Results

For TSP-FCOS,

bash tsp_fcos.sh

For TSP-RCNN,

bash tsp_rcnn.sh

Citation

@InProceedings{Sun_2021_ICCV,
    author    = {Sun, Zhiqing and Cao, Shengcao and Yang, Yiming and Kitani, Kris M.},
    title     = {Rethinking Transformer-Based Set Prediction for Object Detection},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {3611-3620}
}

Owner

Zhiqing Sun

Third-year Ph.D. student at LTI, CMU

GitHub Repository

the code for our CVPR 2021 paper Bilateral Grid Learning for Stereo Matching Network [BGNet]

BGNet This repository contains the code for our CVPR 2021 paper Bilateral Grid Learning for Stereo Matching Network [BGNet] Environment Python 3.6.* C

87 Nov 29, 2022

Amazing-Python-Scripts - 🚀 Curated collection of Amazing Python scripts from Basics to Advance with automation task scripts.

📑 Introduction A curated collection of Amazing Python scripts from Basics to Advance with automation task scripts. This is your Personal space to fin

1.1k Dec 29, 2022

以孤立语假设和宽度优先搜索为基础，构建了一种多通道堆叠注意力Transformer结构的斗地主ai

ddz-ai 介绍斗地主是一种扑克游戏。游戏最少由3个玩家进行，用一副54张牌（连鬼牌），其中一方为地主，其余两家为另一方，双方对战，先出完牌的一方获胜。 ddz-ai以孤立语假设和宽度优先搜索为基础，构建了一种多通道堆叠注意力Transformer结构的系统，使其经过大量训练后，能在实际游戏中获

88 May 15, 2022

Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

ACSC Automatic extrinsic calibration for non-repetitive scanning solid-state LiDAR and camera systems. System Architecture 1. Dependency Tested with U

192 Dec 13, 2022

DeconvNet : Learning Deconvolution Network for Semantic Segmentation

DeconvNet: Learning Deconvolution Network for Semantic Segmentation Created by Hyeonwoo Noh, Seunghoon Hong and Bohyung Han at POSTECH Acknowledgement

325 Oct 20, 2022

Code for Efficient Visual Pretraining with Contrastive Detection

Code for DetCon This repository contains code for the ICCV 2021 paper "Efficient Visual Pretraining with Contrastive Detection" by Olivier J. Hénaff,

56 Nov 13, 2022

FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing

FairEdit Relevent Publication FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing

5 Feb 04, 2022

[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️⚠️

Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples This repository is the official implementation of "Tow

4 Jul 12, 2022

Tensorflow Implementation of ECCV'18 paper: Multimodal Human Motion Synthesis

MT-VAE for Multimodal Human Motion Synthesis This is the code for ECCV 2018 paper MT-VAE: Learning Motion Transformations to Generate Multimodal Human

36 Oct 02, 2022

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).

Adaptive Segmentation Mask Attack This repository contains the implementation of the Adaptive Segmentation Mask Attack (ASMA), a targeted adversarial

53 Jul 04, 2022

Jetson Nano-based smart camera system that measures crowd face mask usage in real-time.

MaskCam MaskCam is a prototype reference design for a Jetson Nano-based smart camera system that measures crowd face mask usage in real-time, with all

212 Dec 29, 2022

Embeddinghub is a database built for machine learning embeddings.

1.2k Jan 01, 2023

A scientific and useful toolbox, which contains practical and effective long-tail related tricks with extensive experimental results

Bag of tricks for long-tailed visual recognition with deep convolutional neural networks This repository is the official PyTorch implementation of AAA

181 Dec 28, 2022

Repository aimed at compiling code, papers, demos etc.. related to my PhD on 3D vision and machine learning for fruit detection and shape estimation at the university of Lincoln

PhD_3DPerception Repository aimed at compiling code, papers, demos etc.. related to my PhD on 3D vision and machine learning for fruit detection and s

2 Oct 06, 2022

Rethinking Transformer-based Set Prediction for Object Detection

Related tags

Overview

Rethinking Transformer-based Set Prediction for Object Detection

Prerequisites

Rreproducing Results

Citation

Owner

Zhiqing Sun

the code for our CVPR 2021 paper Bilateral Grid Learning for Stereo Matching Network [BGNet]

Amazing-Python-Scripts - 🚀 Curated collection of Amazing Python scripts from Basics to Advance with automation task scripts.

以孤立语假设和宽度优先搜索为基础，构建了一种多通道堆叠注意力Transformer结构的斗地主ai

Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems

DeconvNet : Learning Deconvolution Network for Semantic Segmentation

Code for Efficient Visual Pretraining with Contrastive Detection

FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing

[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️⚠️

Tensorflow Implementation of ECCV'18 paper: Multimodal Human Motion Synthesis

Pre-trained model, code, and materials from the paper "Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation" (MICCAI 2019).

Jetson Nano-based smart camera system that measures crowd face mask usage in real-time.

Embeddinghub is a database built for machine learning embeddings.

A scientific and useful toolbox, which contains practical and effective long-tail related tricks with extensive experimental results

Repository aimed at compiling code, papers, demos etc.. related to my PhD on 3D vision and machine learning for fruit detection and shape estimation at the university of Lincoln

deep learning model that learns to code with drawing in the Processing language

Pytorch implementation for DFN: Distributed Feedback Network for Single-Image Deraining.

Implementation of Monocular Direct Sparse Localization in a Prior 3D Surfel Map (DSL)

Code for the AI lab course 2021/2022 of the University of Verona

[ICCV2021] Official Pytorch implementation for SDGZSL (Semantics Disentangling for Generalized Zero-Shot Learning)

Repository for Multimodal AutoML Benchmark