Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Weakly Supervised Object Detection

3260 papers • 126 benchmarks • 313 datasets

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 )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in weakly-supervised-object-detection

Trend

Dataset

Best Model

Actions

PASCAL VOC 2007

PASCAL VOC 2007

PASCAL VOC 2012 test

PASCAL VOC 2012 test

Watercolor2k

Libraries

i

Use these libraries to find weakly-supervised-object-detection models and implementations

ppengtang/pcl.pytorch

4 papers 253

Datasets

ImageNet

Charades

Foggy Cityscapes

Foggy Cityscapes

HICO-DET

PASCAL VOC 2007

PASCAL VOC 2007

Subtasks

No subtasks available.

Most implemented papers

Weakly Supervised Deep Detection Networks

A. Vedaldi, Hakan Bilen•Sun Nov 08 2015

This paper proposes a weakly supervised deep detection architecture that modifies one such network to operate at the level of image regions, performing simultaneously region selection and classification.

827

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Watercolor2k

Comic2k

Comic2k

Clipart1k

Clipart1k

MS-COCO-2014

MS-COCO-2014

Charades

Charades

MS COCO

MS COCO

ImageNet

ImageNet

HICO-DET

HICO-DET

COCO test-dev

COCO test-dev

PeopleArt

PeopleArt

IconArt

IconArt

Cityscapes-to-Foggy Cityscapes

Cityscapes-to-Foggy Cityscapes

CASPAPaintings

CASPAPaintings

MSCOCO

MSCOCO

MS-COCO-2017

MS-COCO-2017

researchmm/WSOD2

4 papers 48

PASCAL VOC 2012 test

PASCAL VOC 2012 test

MSCOCO

Clipart1k

Watercolor2k

0

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

Naoto Inoue, Ryosuke Furuta, T. Yamasaki, K. Aizawa•Thu Mar 29 2018

This paper proposes a two-step progressive domain adaptation technique by fine-tuning the detector on two types of artificially and automatically generated samples, and achieves an improvement of approximately 5 to 20 percentage points in terms of mean average precision (mAP) compared to the best-performing baselines.

594 0

Multiple Instance Detection Network with Online Instance Classifier Refinement

Xinggang Wang, X. Bai, Peng Tang•Fri Mar 31 2017

This work formulate weakly supervised object detection as a Multiple Instance Learning (MIL) problem, where instance classifiers (object detectors) are put into the network as hidden nodes and instance labels inferred from weak supervision are propagated to their spatially overlapped instances to refine instance classifier online.

469 0

Weakly Supervised Object Detection in Artworks

Nicolas Gonthier, Y. Gousseau, Saïd Ladjal, Olivier Bonfait•Fri Sep 07 2018

This work proposes a method for the weakly supervised detection of objects in paintings, and introduces a new database, IconArt, on which it performs detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian.

82 0

Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection

A. Schwing, Jan Kautz, Xiaodong Yang, Zhiding Yu, Yong Jae Lee, Zhongzheng Ren, Ming-Yu Liu•Wed Apr 08 2020

This work develops an instance-aware and context-focused unified framework for weakly supervised video object detection that achieves state-of-the-art results on COCO, VOC 2007, and VOC 2012 while devising a memory-efficient sequential batch back-propagation.

221 0

Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings

Deniz Yuret, Baris Batuhan Topal, T. M. Sezgin•Fri Dec 31 2021

This work shows how self-supervised learning, based on a teacher-student network with a modiﬁed student network update design, can be used to build face and body detectors and demonstrates that style transfer can be incorporated into the learning pipeline to bootstrap detectors using a vast amount of out-of-domain labeled images from natural images.

10 0

Self Paced Deep Learning for Weakly Supervised Object Detection

N. Sebe, E. Sangineto, Moin Nabi, D. Ćulibrk•Mon May 23 2016

This paper is the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline, built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes.

121 0

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

Nicolas Gonthier, Y. Gousseau, Saïd Ladjal•Sun Aug 02 2020

Despite its simplicity, the proposed weakly supervised object detection method shows competitive results on a range of publicly available datasets, including paintings, watercolors, cliparts and comics and allows to quickly learn unseen visual categories.

31 0

PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Xinggang Wang, A. Yuille, X. Bai, Wei Shen, S. Bai, Peng Tang•Sun Jul 08 2018

This paper first shows that instances can be assigned object or background labels directly based on proposal clusters for instance classifier refinement, and then shows that treating each cluster as a small new bag yields fewer ambiguities than the directly assigning label method.

395 0

Adding a benchmark result helps the community track progress.

Weakly Supervised Object Detection | State-of-the-Art