Part-Stacked CNN for Fine-Grained Visual Categorization

Abstract

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.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Fully Convolutional Networks for Semantic Segmentation
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Bilinear CNNs for Fine-grained Visual Recognition
• The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
• Actions and Attributes from Wholes and Parts

Cited by in corpus (3)

• Low-rank Bilinear Pooling for Fine-Grained Classification
• Query-free Clothing Retrieval via Implicit Relevance Feedback
• Cascade one-vs-rest detection network for fine-grained recognition without part annotations