Browse SoTA > Computer Vision > Object Detection > Weakly Supervised Object Detection

Weakly Supervised Object Detection

16 papers with code ยท Computer Vision
Subtask of Object Detection

Weakly Supervised Object Detection (WSOD) is the task of training object detectors with only image tag supervisions.

( Image credit: Soft Proposal Networks for Weakly Supervised Object Localization )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers without code

Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

3 Aug 2020

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years.

MULTIPLE INSTANCE LEARNING WEAKLY SUPERVISED OBJECT DETECTION

SLV: Spatial Likelihood Voting for Weakly Supervised Object Detection

CVPR 2020

In this paper, we propose a spatial likelihood voting (SLV) module to converge the proposal localizing process without any bounding box annotations.

MULTIPLE INSTANCE LEARNING MULTI-TASK LEARNING WEAKLY SUPERVISED OBJECT DETECTION

Learning Object Scale With Click Supervision for Object Detection

20 Feb 2020

Finally, we fuse these CAMs together to generate pseudoground-truths and train a fully-supervised object detector withthese ground-truths.

WEAKLY SUPERVISED OBJECT DETECTION

Weakly Supervised Instance Segmentation by Deep Community Learning

30 Jan 2020

We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks.

INSTANCE SEGMENTATION SEMANTIC SEGMENTATION WEAKLY-SUPERVISED INSTANCE SEGMENTATION WEAKLY SUPERVISED OBJECT DETECTION

Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images

arXiv 2019

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set.

Ranked #20 on Weakly Supervised Object Detection on PASCAL VOC 2012 test (using extra training data)

WEAKLY SUPERVISED OBJECT DETECTION

Towards Precise End-to-end Weakly Supervised Object Detection Network

ICCV 2019

It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations.

MULTIPLE INSTANCE LEARNING WEAKLY SUPERVISED OBJECT DETECTION

WSOD with PSNet and Box Regression

26 Nov 2019

To solve this problem, we added the box regression module to the weakly supervised object detection network and proposed a proposal scoring network (PSNet) to supervise it.

WEAKLY SUPERVISED OBJECT DETECTION

Adaptively Denoising Proposal Collection forWeakly Supervised Object Localization

arXiv 2019

In this paper, we address the problem of weakly supervisedobject localization (WSL), which trains a detection network on the datasetwith only image-level annotations.

DENOISING MULTIPLE INSTANCE LEARNING OBJECT LOCALIZATION WEAKLY SUPERVISED OBJECT DETECTION