Weakly Supervised Object Detection

50 papers with code • 17 benchmarks • 13 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 )

Libraries

Use these libraries to find Weakly Supervised Object Detection models and implementations

ImaginaryNet: Learning Object Detectors without Real Images and Annotations

kodenii/imaginarynet 13 Oct 2022

Given a class label, the language model is used to generate a full description of a scene with a target object, and the text-to-image model deployed to generate a photo-realistic image.

23
13 Oct 2022

Object Discovery via Contrastive Learning for Weakly Supervised Object Detection

jinhseo/od-wscl 16 Aug 2022

Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations.

39
16 Aug 2022

Active Learning Strategies for Weakly-supervised Object Detection

huyvvo/bib 25 Jul 2022

On COCO, using on average 10 fully-annotated images per class, or equivalently 1% of the training set, BiB also reduces the performance gap (in AP) between the weakly-supervised detector and the fully-supervised Fast RCNN by over 70%, showing a good trade-off between performance and data efficiency.

29
25 Jul 2022

W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection

1170300714/w2n_wsod 25 Jul 2022

Generally, with given pseudo ground-truths generated from the well-trained WSOD network, we propose a two-module iterative training algorithm to refine pseudo labels and supervise better object detector progressively.

28
25 Jul 2022

Scaling Novel Object Detection with Weakly Supervised Detection Transformers

tmlabonte/weakly-supervised-DETR 11 Jul 2022

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect.

9
11 Jul 2022

SESS: Saliency Enhancing with Scaling and Sliding

neouyghur/sess 5 Jul 2022

High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation.

7
05 Jul 2022

Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxes

akhilpm/semiwsod 1 Apr 2022

Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models.

10
01 Apr 2022

SIOD: Single Instance Annotated Per Category Per Image for Object Detection

solicucu/siod CVPR 2022

Object detection under imperfect data receives great attention recently.

20
29 Mar 2022

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

YangtaoWANG95/TokenCut CVPR 2022

For unsupervised saliency detection, we improve IoU for 4. 9%, 5. 2%, 12. 9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art.

285
23 Feb 2022

Weakly Supervised Rotation-Invariant Aerial Object Detection Network

xiaoxfeng/rinet CVPR 2022

Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images.

29
01 Jan 2022