Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization
| Autor: | Wenju Xu, Wenchi Ma, Guanghui Wang, Yuanwei Wu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Computer Networks and Communications business.industry Computer science General Neuroscience Network on Noise reduction Computer Vision and Pattern Recognition (cs.CV) Complex system Computer Science - Computer Vision and Pattern Recognition Pattern recognition Computational intelligence 02 engineering and technology Pascal (programming language) Overlap ratio 020901 industrial engineering & automation Artificial Intelligence 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business computer Software computer.programming_language |
| Popis: | In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the training dataset is a collection of background, object parts, and objects. Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. A multiple instance learning (MIL) algorithm enhanced by mask-out strategy is adopted to collect the class-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, the detection results from the detection network are re-weighted by jointly considering the detection scores and the overlap ratio of proposals in a proposal subset optimization framework. The optimal proposals work as object-level labels that enable a pseudo-strongly supervised dataset for training the detection network. Consequently, we establish a fully adaptive detection network. Extensive evaluations on the PASCAL VOC 2007 and 2012 datasets demonstrate a significant improvement compared with the state-of-the-art methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|