Multiscale attention dynamic aware network for fine-grained visual categorization

Proceedings Paper Computer Science, Artificial Intelligence

Graph-based High-Order Relation Discovery for Fine-grained Recognition

Yifan Zhao et al.

Summary: This study proposes an effective graph-based relation discovery approach to build a contextual understanding of high-order relationships in fine-grained object recognition. The approach utilizes a high-dimensional feature bank with semantic- and positional-aware high-order constraints, and embeds it into a low-dimensional space through a graph-based semantic grouping strategy. Collaborative learning of three modules helps achieve new state-of-the-art performance on widely-used benchmarks in fine-grained object recognition.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Intra-class Part Swapping for Fine-Grained Image Classification

Lianbo Zhang et al.

Summary: The paper introduces a new data augmentation method, Intra-class Part Swapping (InPS), which avoids introducing noisy labels and ensures the holistic structure of objects in generated images. InPS outperforms previous methods and demonstrates superior performance in fine-grained recognition and weak object localization. Additionally, by incorporating mid-level feature learning, the proposed method achieves state-of-the-art performance in the literature while maintaining simplicity and inference efficiency.

2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021 (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

AP-CNN: Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification

Yifeng Ding et al.

Summary: The proposed AP-CNN integrates low-level and high-level information, improving the performance of fine-grained visual classification through feature enhancement and region localization, achieving state-of-the-art results without the need for additional bounding box/part annotation.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multi-Objective Matrix Normalization for Fine-Grained Visual Recognition

Shaobo Min et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Dongliang Chang et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition

Qilong Wang et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Deformable Convolutional Networks

Jifeng Dai et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Multiscale attention dynamic aware network for fine-grained visual categorization

相关参考文献

Graph-based High-Order Relation Discovery for Fine-grained Recognition

Intra-class Part Swapping for Fine-Grained Image Classification

AP-CNN: Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification

Multi-Objective Matrix Normalization for Fine-Grained Visual Recognition

The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition

Deformable Convolutional Networks

导出引文

分享论文