Fine-grained image categorization by localizing tiny object parts from unannotated images

Publisher:
ACM
Publication Type:
Conference Proceeding
Citation:
Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, 2015, pp. 107 - 114
Issue Date:
2015
Full metadata record
Files in This Item:
Filename Description Size
p107-zhang_small.pdfPublished version991.98 kB
Adobe PDF
This paper proposes a novel fine-grained image categorization model where no object annotation is required in the training/testing stage. The key technique is a dense graph mining algorithm that localizes multi-scale discriminative object parts in each image. In particular, to mimick human hierarchical perception mechanism, a super-pixel pyramid is generated for each image, based on which graphlets from each layer are constructed to seamlessly describe object parts. We observe that graphlets representative to each category are densely distributed in the feature space. Therefore a dense graph mining algorithm is developed to discover graphlets representative to each sub- super-category. Finally, the discovered graphlets from pairwise images are encoded into an image kernel for fine-grained recognition. Experiments on the UCB-200 [32] shown that our method performs competitively to many models relying on the annotated bird parts.
Please use this identifier to cite or link to this item: