Complementary Frequency-Varying Awareness Network for Open-Set Fine-Grained Image Recognition
This work addresses the challenge of improving recognition accuracy for fine-grained images in open-set scenarios, which is important for applications like species identification or product categorization, but it appears incremental as it builds on existing feature learning approaches.
The paper tackles the problem of open-set fine-grained image recognition by proposing a Complementary Frequency-varying Awareness Network (CFAN) that captures both high- and low-frequency components in features, resulting in significantly better performance than 9 state-of-the-art methods on multiple datasets.
Open-set image recognition is a challenging topic in computer vision. Most of the existing works in literature focus on learning more discriminative features from the input images, however, they are usually insensitive to the high- or low-frequency components in features, resulting in a decreasing performance on fine-grained image recognition. To address this problem, we propose a Complementary Frequency-varying Awareness Network that could better capture both high-frequency and low-frequency information, called CFAN. The proposed CFAN consists of three sequential modules: (i) a feature extraction module is introduced for learning preliminary features from the input images; (ii) a frequency-varying filtering module is designed to separate out both high- and low-frequency components from the preliminary features in the frequency domain via a frequency-adjustable filter; (iii) a complementary temporal aggregation module is designed for aggregating the high- and low-frequency components via two Long Short-Term Memory networks into discriminative features. Based on CFAN, we further propose an open-set fine-grained image recognition method, called CFAN-OSFGR, which learns image features via CFAN and classifies them via a linear classifier. Experimental results on 3 fine-grained datasets and 2 coarse-grained datasets demonstrate that CFAN-OSFGR performs significantly better than 9 state-of-the-art methods in most cases.