Context (archaeology)

Detector

Object detection

Pascal (unit)

Biology

Contextual image classification

Telecommunications

Computer science

Minimum bounding box

Image segmentation

Paleontology

Segmentation

Supervised learning

Pattern recognition (psychology)

Image (mathematics)

Object (grammar)

Face detection

Artificial intelligence

Programming language

Bounding overwatch

Artificial neural network

Facial recognition system

Machine learning

Viola–Jones object detection framework

Computer vision

Weakly supervised object detection aims at learning precise object detectors, given image category labels. In recent prevailing works, this problem is generally formulated as a multiple instance learning module guided by an image classification loss. The object bounding box is assumed to be the one contributing most to the classification among all proposals. However, the region contributing most is also likely to be a crucial part or the supporting context of an object. To obtain a more accurate detector, in this work we propose a novel end-to-end weakly supervised detection approach, where a newly introduced generative adversarial segmentation module interacts with the conventional detection module in a collaborative loop. The collaboration mechanism takes full advantages of the complementary interpretations of the weakly supervised localization task, namely detection and segmentation tasks, forming a more comprehensive solution. Consequently, our method obtains more precise object bounding boxes, rather than parts or irrelevant surroundings. Expectedly, the proposed method achieves an accuracy of 53.7% on the PASCAL VOC 2007 dataset, outperforming the state-of-the-arts and demonstrating its superiority for weakly supervised object detection.

Weakly Supervised Object Detection With Segmentation Collaboration