Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
arXiv:2208.01997 · doi:10.1109/TIP.2022.3197931
Abstract
Fine-grained visual classification can be addressed by deep representation learning under supervision of manually pre-defined targets (e.g., one-hot or the Hadamard codes). Such target coding schemes are less flexible to model inter-class correlation and are sensitive to sparse and imbalanced data distribution as well. In light of this, this paper introduces a novel target coding scheme -- dynamic target relation graphs (DTRG), which, as an auxiliary feature regularization, is a self-generated structural output to be mapped from input images. Specifically, online computation of class-level feature centers is designed to generate cross-category distance in the representation space, which can thus be depicted by a dynamic graph in a non-parametric manner. Explicitly minimizing intra-class feature variations anchored on those class-level centers can encourage learning of discriminative features. Moreover, owing to exploiting inter-class dependency, the proposed target graphs can alleviate data sparsity and imbalanceness in representation learning. Inspired by recent success of the mixup style data augmentation, this paper introduces randomness into soft construction of dynamic target relation graphs to further explore relation diversity of target classes. Experimental results can demonstrate the effectiveness of our method on a number of diverse benchmarks of multiple visual classification tasks, especially achieving the state-of-the-art performance on popular fine-grained object benchmarks and superior robustness against sparse and imbalanced data. Source codes are made publicly available at https://github.com/AkonLau/DTRG.
arXiv commentAccepted by TIP, 15 pages, 8 figures, 11 tables
References in corpus (15)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Prototypical Networks for Few-shot Learning
- mixup: Beyond Empirical Risk Minimization
- A systematic study of the class imbalance problem in convolutional neural networks
- Fine-Grained Visual Classification of Aircraft
- The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
- Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
- Delving Deep into Label Smoothing
- Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification
- Attention for Fine-Grained Categorization
- Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
- Feature Fusion Vision Transformer for Fine-Grained Visual Categorization
- Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
- Graph-based Knowledge Distillation by Multi-head Attention Network