Part-Stacked CNN for Fine-Grained Visual Categorization

Publisher:
IEEE Xplore
Publication Type:
Conference Proceeding
Citation:
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1173 - 1182
Issue Date:
2016
Full metadata record
Files in This Item:
Filename Description Size
Part-stacked CNN for fine-grained visual categorization.pdfPublished Version885.05 kB
Adobe PDF
In the context of fine-grained visual categorization, the ability to interpret models as human-understandable visual manuals is sometimes as important as achieving high classification accuracy. In this paper, we propose a novel Part-Stacked CNN architecture that explicitly explains the fine-grained recognition process by modeling subtle differences from object parts. Based on manually-labeled strong part annotations, the proposed architecture consists of a fully convolutional network to locate multiple object parts and a two-stream classification network that en- codes object-level and part-level cues simultaneously. By adopting a set of sharing strategies between the computation of multiple object parts, the proposed architecture is very efficient running at 20 frames/sec during inference. Experimental results on the CUB-200-2011 dataset reveal the effectiveness of the proposed architecture, from both the perspective of classification accuracy and model interpretability.
Please use this identifier to cite or link to this item: