Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
| Autor: | Seyran Khademi, Xiangwei Shi, Yunqiang Li, Jan C. van Gemert |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Creative visualization Class (computer programming) Pixel Computer science business.industry media_common.quotation_subject Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Pattern recognition 02 engineering and technology Object (computer science) Discriminative model 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence Zoom Focus (optics) business media_common |
| Zdroj: | ICPR |
| DOI: | 10.48550/arxiv.2010.08644 |
| Popis: | Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activation mapping (CAM) and Grad-CAM, use only the deepest, lowest resolution convolutional layer, missing all information in intermediate layers. We propose Zoom-CAM: going beyond the last lowest resolution layer by integrating the importance maps over all activations in intermediate layers. Zoom-CAM captures fine-grained small-scale objects for various discriminative class instances, which are commonly missed by the baseline visualization methods. We focus on generating pixel-level pseudo-labels from class labels. The quality of our pseudo-labels evaluated on the ImageNet localization task exhibits more than 2.8% improvement on top-1 error. For weakly supervised semantic segmentation our generated pseudo-labels improve a state of the art model by 1.1%. Comment: ICPR 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|