Date.md

2019-10-11 Update 1 Project

Detectron2

• intro: Detectron2 is FAIR's next-generation research platform for object detection and segmentation.
• blog
• code: https://github.com/facebookresearch/detectron2

2019-09-06 Update 1 paper

Imbalance Problems in Object Detection: A Review

• intro: under review at TPAMI
• arXiv: https://arxiv.org/abs/1909.00169

2019-08-14 Update 1 paper

Recent Advances in Deep Learning for Object Detection

• intro: From 2013 (OverFeat) to 2019 (DetNAS)
• arXiv: https://arxiv.org/abs/1908.03673

2019-07-24 Update 1 paper

A Survey of Deep Learning-based Object Detection

• intro：From Fast R-CNN to NAS-FPN

• arXiv：https://arxiv.org/abs/1907.09408

2019-05-17 Update 1 paper

Object Detection in 20 Years: A Survey

• intro：This work has been submitted to the IEEE TPAMI for possible publication
• arXiv：https://arxiv.org/abs/1905.05055

2019-04-05 Update 1 paper

Comparison Network for One-Shot Conditional Object Detection

• arXiv: https://arxiv.org/abs/1904.02317

2019-03-05 Update 1 paper

Feature Selective Anchor-Free Module for Single-Shot Object Detection

• intro: CVPR 2019
• arXiv: https://arxiv.org/abs/1903.00621

2019-02-15 Update 3 detection toolbox

• Detectron(FAIR): Detectron is Facebook AI Research's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework.

• maskrcnn-benchmark(FAIR): Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

• mmdetection(SenseTime&CUHK): mmdetection is an open source object detection toolbox based on PyTorch. It is a part of the open-mmlab project developed by Multimedia Laboratory, CUHK.

2019-01-25 Update 5 papers

3D Backbone Network for 3D Object Detection

• arXiv: https://arxiv.org/abs/1901.08373

Object Detection based on Region Decomposition and Assembly

• intro: AAAI 2019

• arXiv: https://arxiv.org/abs/1901.08225

Bottom-up Object Detection by Grouping Extreme and Center Points

• intro: one stage 43.2% on COCO test-dev
• arXiv: https://arxiv.org/abs/1901.08043
• github: https://github.com/xingyizhou/ExtremeNet

ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features

• intro: IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

• arXiv: https://arxiv.org/abs/1901.07925

Consistent Optimization for Single-Shot Object Detection

• intro: improves RetinaNet from 39.1 AP to 40.1 AP on COCO datase

• arXiv: https://arxiv.org/abs/1901.06563

2019-01-15 Update 1 paper

Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes

• arXiv: https://arxiv.org/abs/1901.03796

2019-01-14 Update 1 paper

RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

• arXiv: https://arxiv.org/abs/1901.03353
• github: https://github.com/chengyangfu/retinamask

2019-01-12 Update 1 paper

Region Proposal by Guided Anchoring

• intro: CUHK - SenseTime Joint Lab
• arXiv: https://arxiv.org/abs/1901.03278

2019-01-08 Update 1 paper

Scale-Aware Trident Networks for Object Detection

• intro: mAP of 48.4 on the COCO dataset
• arXiv: https://arxiv.org/abs/1901.01892

2019-01-04 Update 1 paper

Large-Scale Object Detection of Images from Network Cameras in Variable Ambient Lighting Conditions

• arXiv: https://arxiv.org/abs/1812.11901

2018-12-13 Update 1 paper

Strong-Weak Distribution Alignment for Adaptive Object Detection

• arXiv: https://arxiv.org/abs/1812.04798

2018-12-05 Update 3 papers

AutoFocus: Efficient Multi-Scale Inference

• intro: AutoFocus obtains an mAP of 47.9% (68.3% at 50% overlap) on the COCO test-dev set while processing 6.4 images per second on a Titan X (Pascal) GPU
• arXiv: https://arxiv.org/abs/1812.01600

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

• intro: Google Could
• arXiv: https://arxiv.org/abs/1812.00124

SPLAT: Semantic Pixel-Level Adaptation Transforms for Detection

• intro: UC Berkeley
• arXiv: https://arxiv.org/abs/1812.00929

2018-12-04 Update 10 papers

Grid R-CNN

• intro: SenseTime
• arXiv: https://arxiv.org/abs/1811.12030

Deformable ConvNets v2: More Deformable, Better Results

• intro: Microsoft Research Asia

• arXiv: https://arxiv.org/abs/1811.11168

Anchor Box Optimization for Object Detection

• intro: Microsoft Research
• arXiv: https://arxiv.org/abs/1812.00469

Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects

• intro: https://arxiv.org/abs/1811.12152

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

• arXiv: https://arxiv.org/abs/1812.00124

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

• arXiv: https://arxiv.org/abs/1812.00155

Integrated Object Detection and Tracking with Tracklet-Conditioned Detection

• intro: Microsoft Research Asia
• arXiv: https://arxiv.org/abs/1811.11167

Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection

• arXiv: https://arxiv.org/abs/1811.11318

Gradient Harmonized Single-stage Detector

• intro: AAAI 2019
• arXiv: https://arxiv.org/abs/1811.05181

CFENet: Object Detection with Comprehensive Feature Enhancement Module

• intro: ACCV 2018
• github: https://github.com/qijiezhao/CFENet

2018-11-19

DeRPN: Taking a further step toward more general object detection

• intro: AAAI 2019
• arXiv: https://arxiv.org/abs/1811.06700
• github: https://github.com/HCIILAB/DeRPN

2018-11-14

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

• intro: AAAI 2019
• arXiv: https://arxiv.org/abs/1811.04533
• github: https://github.com/qijiezhao/M2Det

2018-10-31

Hybrid Knowledge Routed Modules for Large-scale Object Detection

• intro: Sun Yat-Sen University & Huawei Noah’s Ark Lab
• arXiv: https://arxiv.org/abs/1810.12681
• github: https://github.com/chanyn/HKRM

2018-10-08

Weakly Supervised Object Detection in Artworks

• intro: ECCV 2018 Workshop Computer Vision for Art Analysis
• arXiv: https://arxiv.org/abs/1810.02569
• Datasets: https://wsoda.telecom-paristech.fr/downloads/dataset/IconArt_v1.zip

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation

• intro: CVPR 2018
• arXiv: https://arxiv.org/abs/1803.11365
• homepage: https://naoto0804.github.io/cross_domain_detection/
• paper: http://openaccess.thecvf.com/content_cvpr_2018/html/Inoue_Cross-Domain_Weakly-Supervised_Object_CVPR_2018_paper.html
• github: https://github.com/naoto0804/cross-domain-detection

2018-09-26

Object Detection from Scratch with Deep Supervision

• intro: This is an extended version of DSOD
• arXiv: https://arxiv.org/abs/1809.09294

2018-09-25

《Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection》

• intro: CMU & Face++
• arXiv: https://arxiv.org/abs/1809.08545
• github: https://github.com/yihui-he/softer-NMS

2018-09-21

《Receptive Field Block Net for Accurate and Fast Object Detection》

• intro: ECCV 2018
• arXiv: https://arxiv.org/abs/1711.07767
• github: https://github.com/ruinmessi/RFBNet

2018-09-11

《Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks》

• intro: awesome

• arXiv: https://arxiv.org/abs/1809.03193

2018-09-10

《Deep Learning for Generic Object Detection: A Survey》

• intro: Submitted to IJCV 2018
• arXiv: https://arxiv.org/abs/1809.02165

2018-08-27

Deep Feature Pyramid Reconfiguration for Object Detection

• intro: ECCV 2018
• arXiv: https://arxiv.org/abs/1808.07993

2018-08-17

R3-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos

• arxiv: https://arxiv.org/abs/1808.05560
• youtube: https://youtu.be/xCYD-tYudN0

2018-08-14

《Unsupervised Hard Example Mining from Videos for Improved Object Detection》

• intro: ECCV 2018
• arXiv: https://arxiv.org/abs/1808.04285

2018-08-10

CornerNet: Detecting Objects as Paired Keypoints

• intro: ECCV 2018
• arXiv: https://arxiv.org/abs/1808.01244

2018-07-30

Acquisition of Localization Confidence for Accurate Object Detection

• intro: ECCV 2018
• arXiv: https://arxiv.org/abs/1807.11590
• github: https://github.com/vacancy/PreciseRoIPooling