Incorporating Intra-Class Variance to Fine-Grained Visual Recognition
This work addresses fine-grained recognition for computer vision applications, but it is incremental as it builds on existing triplet network methods by adding intra-class variance handling.
The paper tackles the problem of fine-grained visual recognition by incorporating intra-class variance into metric learning with a triplet network, proposing Group Sensitive Triplet Sampling (GS-TRS) to improve performance. Experiments on CompCar and VehicleID datasets show that GS-TRS significantly outperforms state-of-the-art approaches in classification and retrieval tasks.
Fine-grained visual recognition aims to capture discriminative characteristics amongst visually similar categories. The state-of-the-art research work has significantly improved the fine-grained recognition performance by deep metric learning using triplet network. However, the impact of intra-category variance on the performance of recognition and robust feature representation has not been well studied. In this paper, we propose to leverage intra-class variance in metric learning of triplet network to improve the performance of fine-grained recognition. Through partitioning training images within each category into a few groups, we form the triplet samples across different categories as well as different groups, which is called Group Sensitive TRiplet Sampling (GS-TRS). Accordingly, the triplet loss function is strengthened by incorporating intra-class variance with GS-TRS, which may contribute to the optimization objective of triplet network. Extensive experiments over benchmark datasets CompCar and VehicleID show that the proposed GS-TRS has significantly outperformed state-of-the-art approaches in both classification and retrieval tasks.