DistillCvT: Self-supervised distillation of Convolutional Vision Transformers for few-shot fine-grained classification

2026/07/17 by Jia Min Lim, Kian Ming Lim, Jit Yan Lim +2

paper · doi:10.1016/j.imavis.2026.106119

crossref created 2026/07/17 · crossref deposited 2026/08/05 · crossref indexed 2026/08/05 · crossref issued 2026/10/01 · crossref published 2026/10/01 · crossref published-print 2026/10/01

Citations

• Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditions
• Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
• A Task-aware Dual Similarity Network for Fine-grained Few-shot Learning
• Boosting Few-Shot Fine-Grained Recognition With Background Suppression and Foreground Alignment
• Query-Guided Networks for Few-shot Fine-grained Classification and Person Search
• Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification
• R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction
• Disentangled Feature Representation for Few-shot Image Classification
• TransFG: A Transformer Architecture for Fine-grained Recognition
• Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
• SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
• Multi-scale Adaptive Task Attention Network for Few-Shot Learning
• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• Bootstrap your own latent: A new approach to self-supervised Learning
• A Simple Framework for Contrastive Learning of Visual Representations
• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• Revisiting Metric Learning for Few-Shot Image Classification
• Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• Prototypical Networks for Few-shot Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Matching Networks for One Shot Learning
• Cross-sample feature interaction enhancement for few-shot fine-grained classification