Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval

• Published in: IEEE transactions on image processing Vol. 26; no. 6; pp. 2868 - 2881
• Main Authors: Wei, Xiu-Shen, Luo, Jian-Hao, Wu, Jianxin, Zhou, Zhi-Hua
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2017
• Subjects: Automobiles; Birds; Buildings; Convolution; Dogs; Fine-grained image retrieval; Image retrieval; Machine learning; selection and aggregation; unsupervised object localization
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2017.2688133

Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these tasks require annotations for images in the new domain. In this paper, we focus on a novel and challenging task in the pure unsupervised setting: fine-grained image retrieval. Even with image labels, fine-grained images are difficult to classify, letting alone the unsupervised retrieval task. We propose the selective convolutional descriptor aggregation (SCDA) method. The SCDA first localizes the main object in fine-grained images, a step that discards the noisy background and keeps useful deep descriptors. The selected descriptors are then aggregated and the dimensionality is reduced into a short feature vector using the best practices we found. The SCDA is unsupervised, using no image label or bounding box annotation. Experiments on six fine-grained data sets confirm the effectiveness of the SCDA for fine-grained image retrieval. Besides, visualization of the SCDA features shows that they correspond to visual attributes (even subtle ones), which might explain SCDA's high-mean average precision in fine-grained retrieval. Moreover, on general image retrieval data sets, the SCDA achieves comparable retrieval results with the state-of-the-art general image retrieval approaches.