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 )
Benchmarks
These leaderboards are used to track progress in Weakly Supervised Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Weakly Supervised Object Detection models and implementationsDatasets
ImageNet
MS COCO
Charades
Foggy Cityscapes
HICO-DET
PASCAL VOC 2007
PASCAL VOC 2012 test
Clipart1k
Latest papers with no code
D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation
In its warm-up domain adaptation stage, the model learns a fully-supervised object detector (FSOD) to improve the precision of the object proposals in the target domain, and at the same time learns target-domain-specific and detection-aware proposal features.
Online progressive instance-balanced sampling for weakly supervised object detection
The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances.
Compositional Mixture Representations for Vision and Text
Learning a common representation space between vision and language allows deep networks to relate objects in the image to the corresponding semantic meaning.
Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
In the exploiting stage, we utilize the extracted NDI to construct a novel negative contrastive learning mechanism and a negative guided instance selection strategy for dealing with the issues of part domination and missing instances, respectively.
Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection
The likelihood maps generated by the SLV module are used to supervise the feature learning of the backbone network, encouraging the network to attend to wider and more diverse areas of the image.
Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) is a challenging task that requires simultaneously learn object classifiers and estimate object locations under the supervision of image category labels.
Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection
Inspired by the habit of observing things by the human, we propose a new method by comparing the initial proposals and the extension ones to optimize those initial proposals.
Learning Better Visual Representations for Weakly-Supervised Object Detection Using Natural Language Supervision
We present a framework to better leverage natural language supervision for a specific downstream task, namely weakly-supervised object detection (WSOD).
PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement
There are two main problems hindering the performance of the two-phase WSOD approaches, i. e., insufficient learning problem and strict reliance between the FSD and the pseudo ground truth (PGT) generated by the WSOD model.
Pseudo-Label Generation-Evaluation Framework For Cross Domain Weakly Supervised Object Detection
Cross domain weakly supervised object detection (CDWSOD), where we can get access to instance-level annotations in the source domain while only image-level annotations are available in the target domain, adapts object detectors from label-rich to label-poor domains.
