Source Code of AAAI22-2171

Introduction

The source code includes training and inference procedures for the proposed method of the paper submitted to the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022) with title "Shape-Adaptive Selection and Measurement for Oriented Object Detection" (ID: 2171).

The the effectiveness of the proposed method is verified on two baseline methods. Corresponding source code and configurations reside in following two sub-directories:

sasm_reppoints: the implementation and verification using RepPoints as baseline;
sasm_s2anet: the implementation and verification using s2anet(https://ieeexplore.ieee.org/document/9377550) as baseline.

We provide only the source code related to the proposed method in the sub-directories so that reviewers can check them quickly and conveniently.

Please refer to the README.md file in each sub-directory for the detailed instructions of usage.

Introduction

Method	Assignment	Reg. Loss	Tricks	mAP
RepPoints	MaxIoU	GIoU	-	70.46
RepPoints	SASM	BCLoss + GIoU	-	74.27
RepPoints	SASM	BCLoss + GIoU	MS training	77.19
s2anet	SASM	Smooth L1	MS training	79.17

Reference

1、https://github.com/open-mmlab/mmdetection

2、https://github.com/LiWentomng/OrientedRepPoints

3、https://github.com/SDL-GuoZonghao/BeyondBoundingBox

4、https://github.com/csuhan/s2anet

5、https://github.com/sfzhang15/ATSS

Shape-Adaptive Selection and Measurement for Oriented Object Detection

Related tags

Overview

Source Code of AAAI22-2171

Introduction

Introduction

Reference

Owner

houliping

A foreign language learning aid using a neural network to predict probability of translating foreign words

code for Multi-scale Matching Networks for Semantic Correspondence, ICCV

This is a simple framework to make object detection dataset very quickly

Improving Query Representations for DenseRetrieval with Pseudo Relevance Feedback:A Reproducibility Study.

SHIFT15M: multiobjective large-scale fashion dataset with distributional shifts

a Pytorch easy re-implement of "YOLOX: Exceeding YOLO Series in 2021"

PyTorch for Semantic Segmentation

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

Code and hyperparameters for the paper "Generative Adversarial Networks"

TDmatch is a Python library developed to perform matching tasks in three categories:

Inference code for "StylePeople: A Generative Model of Fullbody Human Avatars" paper. This code is for the part of the paper describing video-based avatars.

Open-source implementation of Google Vizier for hyper parameters tuning

PyTorch implementation of the end-to-end coreference resolution model with different higher-order inference methods.

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

Additional environments compatible with OpenAI gym

Code for the paper "Reinforced Active Learning for Image Segmentation"

Using Streamlit to host a multi-page tool with model specs and classification metrics, while also accepting user input values for prediction.

Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods

The code repository for EMNLP 2021 paper "Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization".

Supplemental Code for "ImpressionNet :A Multi view Approach to Predict Socio Facial Impressions"