Weakly Supervised Object Detection
51 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 implementationsDatasets
Latest papers
WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem.
Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling
Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision.
LEOD: Label-Efficient Object Detection for Event Cameras
On 1Mpx, RVT-S with 10% labels even surpasses its fully-supervised counterpart using 100% labels.
Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
We train our model on datasets obtained from both space-based and ground-based multi-band observations of variable stars and transients.
Text-image Alignment for Diffusion-based Perception
Our cross-domain segmentation method, trained on Cityscapes, achieves SOTA results on Dark Zurich-val and Nighttime Driving.
ALWOD: Active Learning for Weakly-Supervised Object Detection
In this work, we propose ALWOD, a new framework that addresses this problem by fusing active learning (AL) with weakly and semi-supervised object detection paradigms.
Anatomy-Driven Pathology Detection on Chest X-rays
Pathology detection and delineation enables the automatic interpretation of medical scans such as chest X-rays while providing a high level of explainability to support radiologists in making informed decisions.
PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers
Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags.
Cyclic-Bootstrap Labeling for Weakly Supervised Object Detection
These inaccurate high-scoring region proposals will mislead the training of subsequent refinement modules and thus hamper the detection performance.
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in Drawings
Drawings are powerful means of pictorial abstraction and communication.