About

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

Datasets

Greatest papers with code

Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection

CVPR 2020 NVlabs/wetectron

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training.

VIDEO OBJECT DETECTION WEAKLY SUPERVISED OBJECT DETECTION

Soft Proposal Networks for Weakly Supervised Object Localization

ICCV 2017 yeezhu/SPN.pytorch

Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training.

WEAKLY SUPERVISED OBJECT DETECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

9 Jul 2018ppengtang/oicr

The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one.

MULTIPLE INSTANCE LEARNING OBJECT RECOGNITION WEAKLY SUPERVISED OBJECT DETECTION

Multiple Instance Detection Network with Online Instance Classifier Refinement

CVPR 2017 ppengtang/oicr

We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i. e., without object location information.

MULTIPLE INSTANCE LEARNING OBJECT RECOGNITION WEAKLY SUPERVISED OBJECT DETECTION

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

ICCV 2019 ppengtang/pcl.pytorch

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

Weakly Supervised Deep Detection Networks

CVPR 2016 hbilen/WSDDN

Weakly supervised learning of object detection is an important problem in image understanding that still does not have a satisfactory solution.

DATA AUGMENTATION WEAKLY SUPERVISED OBJECT DETECTION

Harmonizing Transferability and Discriminability for Adapting Object Detectors

CVPR 2020 chaoqichen/HTCN

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline.

WEAKLY SUPERVISED OBJECT DETECTION