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

This repository consists of Blender python scripts and corresponding assets to generate variants of the CANDLE dataset

Providing the solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data.

SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

GrailQA: Strongly Generalizable Question Answering

Open source repository for the code accompanying the paper 'Non-Rigid Neural Radiance Fields Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video'.

A clean and scalable template to kickstart your deep learning project 🚀 ⚡ 🔥

Frequency Domain Image Translation: More Photo-realistic, Better Identity-preserving

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

Quasi-Dense Similarity Learning for Multiple Object Tracking, CVPR 2021 (Oral)

EsViT: Efficient self-supervised Vision Transformers

CycleTransGAN-EVC: A CycleGAN-based Emotional Voice Conversion Model with Transformer

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL [Deep Graph Library] and PyTorch.

A decent AI that solves daily Wordle puzzles. Works with different websites with similar wordlists,.

Torch code for our CVPR 2018 paper "Residual Dense Network for Image Super-Resolution" (Spotlight)

Lipschitz-constrained Unsupervised Skill Discovery

Source code for Transformer-based Multi-task Learning for Disaster Tweet Categorisation (UCD's participation in TREC-IS 2020A, 2020B and 2021A).

Tools for robust generative diffeomorphic slice to volume reconstruction

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

This project deals with the detection of skin lesions within the ISICs dataset using YOLOv3 Object Detection with Darknet.

Code for our work "Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection".