Incorporating Intra-Class Variance to Fine-Grained Visual Recognition

2017-03-01 · Yan Bai, Feng Gao, Yihang Lou, Shiqi Wang, Tiejun Huang, Ling-Yu Duan

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.

📄 PDF Abstract BibTeX arXiv:1703.00196

Code (0)

등록된 구현이 없습니다.

Tasks

Fine-Grained Visual Recognition Metric Learning RetrievalTriplet

Variational Feature Disentangling for Fine-Grained Few-Shot Classification

2020-10-07 · ICCV 2021 10 · Jingyi Xu, Hieu Le, Mingzhen Huang, ShahRukh Athar 외

Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories.The network tends to overfit and does not generalize well to unseen classes due to insufficient training dat…

Classification Few-Shot Image Classification image-classification Image Classification+2

Exploration of Class Center for Fine-Grained Visual Classification

2024-07-05 · Hang Yao, Qiguang Miao, Peipei Zhao, Chaoneng Li 외

Different from large-scale classification tasks, fine-grained visual classification is a challenging task due to two critical problems: 1) evident intra-class variances and subtle inter-class differences, and 2) overfitt…

Classification Fine-Grained Image Classification

Fine-Grained Few Shot Learning with Foreground Object Transformation

2021-09-13 · Chaofei Wang, Shiji Song, Qisen Yang, Xiang Li 외

Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However, in many scenarios we may have limited sa…

Data Augmentation Few-Shot Learning Fine-Grained Image Classification image-classification+2

TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples

2020-05-28 · Huaxi Huang, Jun-Jie Zhang, Jian Zhang, Qiang Wu 외

The challenges of high intra-class variance yet low inter-class fluctuations in fine-grained visual categorization are more severe with few labeled samples, \textit{i.e.,} Fine-Grained categorization problems under the F…

Fine-Grained Visual Categorization Image Categorization

Exploring Vision Transformers for Fine-grained Classification

2021-06-19 · Marcos V. Conde, Kerem Turgutlu

Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by…

Classification Fine-Grained Image Classification image-classification Image Classification