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 )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Then, we present an adaptive supervision aggregation function that dynamically changes the aggregation criteria for selecting boxes related to one of the ground-truth classes, background, or even ignored during the generation of each refinement module supervision.
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training.
Weakly supervised object detection (WSOD) using only image-level annotations has attracted growing attention over the past few years.
#6 best model for Weakly Supervised Object Detection on PASCAL VOC 2007
In the source domain, we fully train an object detector and the RRPN with full supervision of HOI.
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors.
#5 best model for Weakly Supervised Object Detection on PASCAL VOC 2007
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.
#13 best model for Weakly Supervised Object Detection on PASCAL VOC 2007
Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student.
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.
Can we detect common objects in a variety of image domains without instance-level annotations?
SOTA for Weakly Supervised Object Detection on Clipart1k (using extra training data)