Embedding Label Structures for Fine-Grained Feature Representation
Open Access
- 1 June 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1114-1123
- https://doi.org/10.1109/cvpr.2016.126
Abstract
Recent algorithms in convolutional neural networks (CNN) considerably advance the fine-grained image classification, which aims to differentiate subtle differences among subordinate classes. However, previous studies have rarely focused on learning a fined-grained and structured feature representation that is able to locate similar images at different levels of relevance, e.g., discovering cars from the same make or the same model, both of which require high precision. In this paper, we propose two main contributions to tackle this problem. 1) A multitask learning framework is designed to effectively learn fine-grained feature representations by jointly optimizing both classification and similarity constraints. 2) To model the multi-level relevance, label structures such as hierarchy or shared attributes are seamlessly embedded into the framework by generalizing the triplet loss. Extensive and thorough experiments have been conducted on three finegrained datasets, i.e., the Stanford car, the Car-333, and the food datasets, which contain either hierarchical labels or shared attributes. Our proposed method has achieved very competitive performance, i.e., among state-of-the-art classification accuracy when not using parts. More importantly, it significantly outperforms previous fine-grained feature representations for image retrieval at different levels of relevance.Keywords
This publication has 30 references indexed in Scilit:
- Deep feature learning with relative distance comparison for person re-identificationPattern Recognition, 2015
- Learning visual similarity for product design with convolutional neural networksACM Transactions on Graphics, 2015
- CaffePublished by Association for Computing Machinery (ACM) ,2014
- Birdsnap: Large-Scale Fine-Grained Visual Categorization of BirdsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Deformable Part Descriptors for Fine-Grained Recognition and Attribute PredictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Symbiotic Segmentation and Part Localization for Fine-Grained CategorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- 3D Object Representations for Fine-Grained CategorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute EstimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Fine-Grained Crowdsourcing for Fine-Grained RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Learning a Similarity Metric Discriminatively, with Application to Face VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005