Category-Aware Spatial Constraint for Weakly Supervised Detection
- 22 August 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 843-858
Abstract
Weakly supervised object detection has attracted increasing research attention recently. To this end, most existing schemes rely on scoring category-independent region proposals, which is formulated as a multiple instance learning problem. During this process, the proposal scores are aggregated and supervised by only image-level labels, which often fails to locate object boundaries precisely. In this paper, we break through such a restriction by taking a deeper look into the score aggregation stage and propose a Category-aware Spatial Constraint (CSC) scheme for proposals, which is integrated into weakly supervised object detection in an end-to-end learning manner. In particular, we incorporate the global shape information of objects as an unsupervised constraint, which is inferred from build-in foreground-and-background cues, termed Category-specific Pixel Gradient (CPG) maps. Specifically, each region proposal is weighted according to how well it covers the estimated shape of objects. For each category, a multi-center regularization is further introduced to penalize the violations between centers cluster and high-score proposals in a given image. Extensive experiments are done on the most widely-used benchmark Pascal VOC and COCO, which shows that our approach significantly improves weakly supervised object detection without adding new learnable parameters to the existing models nor changing the structures of CNNs.Keywords
Funding Information
- National Basic Research Program of China (2017YFC0113000, 2016YFB1001503)
- National Natural Science Foundation of China (U1705262, 61772443, 61572410)
- Post-doctoral Innovative Talent Support Program (BX201600094)
- China Postdoctoral Science Foundation (2017M612134)
- Scientific Research Project of National Language Committee of China (YB135-49)
- Natural Science Foundation of Fujian Province (2017J01125, 2018J01106)
This publication has 61 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Large-Scale Weakly Supervised Object Localization via Latent Category LearningIEEE Transactions on Image Processing, 2015
- Caffe2014
- Multiscale Combinatorial Grouping2014
- Multiple instance classification: Review, taxonomy and comparative studyArtificial Intelligence, 2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- In Defence of Negative Mining for Annotating Weakly Labelled Data2012
- Diagnosing Error in Object Detectors2012
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Robust Real-Time Face DetectionInternational Journal of Computer Vision, 2004