Loading...
Please wait, while we are loading the content...
Similar Documents
Matrix completion for weakly-supervised multi-label Image classification
| Content Provider | CiteSeerX |
|---|---|
| Author | Cabral, Ricardo Torre, O. De La Costeira, João P. Bernardino, Re |
| Abstract | Abstract—In the last few years, image classification has become an incredibly active research topic, with widespread applications. Most methods for visual recognition are fully supervised, as they make use of bounding boxes or pixelwise segmentations to locate objects of interest. However, this type of manual labeling is time consuming, error prone and it has been shown that manual segmentations are not necessarily the optimal spatial enclosure for object classifiers. This paper proposes a weakly-supervised system for multi-label image classification. In this setting, training images are annotated with a set of keywords describing their contents, but the visual concepts are not explicitly segmented in the images. We formulate the weakly-supervised image classification as a low-rank matrix completion problem. Compared to previous work, our proposed framework has three advantages: (1) Unlike existing solutions based on multiple-instance learning methods, our model is convex. We propose two alternative algorithms for matrix completion specifically tailored to visual data, and prove their convergence. (2) Unlike existing discriminative methods, our algorithm is robust to labeling errors, background noise and partial occlusions. (3) Our method can potentially be used for semantic segmentation. Experimental validation on several datasets shows that our method outperforms state-of-the-art classification algorithms, while effectively capturing each class appearance. Index Terms—Weakly-supervised learning, multi-label image classification, segmentation, rank minimization, nuclear norm. I. |
| File Format | |
| Journal | IEEE Trans. Pattern Anal. Mach. Intell |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Matrix Completion Weakly-supervised Multi-label Image Classification Multi-label Image Classification Weakly-supervised Image Classification Multiple-instance Learning Method Experimental Validation Class Appearance State-of-the-art Classification Algorithm Image Classification Index Term Weakly-supervised Learning Last Year Training Image Discriminative Method Nuclear Norm Object Classifier Rank Minimization Visual Recognition Partial Occlusion Weakly-supervised System Active Research Topic Alternative Algorithm Manual Segmentation Manual Labeling Several Datasets Previous Work Background Noise Low-rank Matrix Completion Problem Visual Data Optimal Spatial Enclosure Visual Concept Semantic Segmentation Error Prone Widespread Application |
| Content Type | Text |
| Resource Type | Article |
