Browse SoTA > Computer Vision > Object Detection

Object Detection

821 papers with code · Computer Vision

Object detection is the task of detecting instances of objects of a certain class within an image. The state-of-the-art methods can be categorized into two main types: one-stage methods and two stage-methods. One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet. Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.

The most popular benchmark is the MSCOCO dataset. Models are typically evaluated according to a Mean Average Precision metric.

( Image credit: Detectron )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers with code

The 1st Tiny Object Detection Challenge:Methods and Results

16 Sep 2020ucas-vg/TinyBenchmark

The 1st Tiny Object Detection (TOD) Challenge aims toencourage research in developing novel and accurate methods for tinyobject detection in images which have wide views, with a current focuson tiny person detection.

HUMAN DETECTION OBJECT DETECTION

274
16 Sep 2020

Reverse-engineering Bar Charts Using Neural Networks

5 Sep 2020csuvis/BarchartReverseEngineering

Reverse-engineering bar charts extracts textual and numeric information from the visual representations of bar charts to support application scenarios that require the underlying information.

OBJECT DETECTION

0
05 Sep 2020

Regularized Densely-connected Pyramid Network for Salient Instance Segmentation

28 Aug 2020yuhuan-wu/RDPNet

To this end, we propose a new pipeline for end-to-end salient instance segmentation (SIS) that predicts a class-agnostic mask for each detected salient instance.

INSTANCE SEGMENTATION RGB SALIENT OBJECT DETECTION SEMANTIC SEGMENTATION

2
28 Aug 2020

Siamese Network for RGB-D Salient Object Detection and Beyond

26 Aug 2020kerenfu/JLDCF

Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.

 Ranked #1 on RGB-D Salient Object Detection on SIP (using extra training data)

RGB-D SALIENT OBJECT DETECTION VIDEO SALIENT OBJECT DETECTION

41
26 Aug 2020

Label Decoupling Framework for Salient Object Detection

CVPR 2020 weijun88/LDF

Though remarkable progress has been achieved, we observe that the closer the pixel is to the edge, the more difficult it is to be predicted, because edge pixels have a very imbalance distribution.

RGB SALIENT OBJECT DETECTION

26
25 Aug 2020

Graphical Object Detection in Document Images

25 Aug 2020rnjtsh/graphical-object-detector

Graphical elements: particularly tables and figures contain a visual summary of the most valuable information contained in a document.

DOMAIN ADAPTATION OBJECT DETECTION TRANSFER LEARNING

6
25 Aug 2020

Align Deep Features for Oriented Object Detection

21 Aug 2020csuhan/s2anet

However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.

OBJECT DETECTION

49
21 Aug 2020

Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations

20 Aug 2020AutoVision-cloud/Deformable-PV-RCNN

We present Deformable PV-RCNN, a high-performing point-cloud based 3D object detector.

3D OBJECT DETECTION

33
20 Aug 2020

TIDE: A General Toolbox for Identifying Object Detection Errors

ECCV 2020 dbolya/tide

We introduce TIDE, a framework and associated toolbox for analyzing the sources of error in object detection and instance segmentation algorithms.

INSTANCE SEGMENTATION OBJECT DETECTION SEMANTIC SEGMENTATION

118
18 Aug 2020

AP-Loss for Accurate One-Stage Object Detection

17 Aug 2020cccorn/AP-loss

This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem.

OBJECT DETECTION

112
17 Aug 2020