Color as the Impetus: Transforming Few-Shot Learner

arXiv 2507.22136 ↗First posted 29 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Humans possess innate meta-learning capabilities, partly attributable to their exceptional color perception. In this paper, we pioneer an innovative viewpoint on few-shot learning by simulating human color perception mechanisms. We propose the ColorSense Learner, a bio-inspired meta-learning framework that capitalizes on inter-channel feature extraction and interactive learning. By strategically emphasizing distinct color information across different channels, our approach effectively filters irrelevant features while capturing discriminative characteristics. Color information represents the most intuitive visual feature, yet conventional meta-learning methods have predominantly neglected this aspect, focusing instead on abstract feature differentiation across categories. Our framework bridges the gap via synergistic color-channel interactions, enabling better intra-class commonality extraction and larger inter-class differences. Furthermore, we introduce a meta-distiller based on knowledge distillation, ColorSense Distiller, which incorporates prior teacher knowledge to augment the student network's meta-learning capacity. We've conducted comprehensive coarse/fine-grained and cross-domain experiments on eleven few-shot benchmarks for validation. Numerous experiments reveal that our methods have extremely strong generalization ability, robustness, and transferability, and effortless handle few-shot classification from the perspective of color perception.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 68 of its 96 references that are in the map. First posted on arXiv 29 Jul 2025.

Builds on

68 of 96 references.

References · 68

2015Deep Residual Learning for Image Recognitioncited by 52,096
2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
2016Wide Residual Networkscited by 3,070
2017Prototypical Networks for Few-shot Learningcited by 3,015
2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
2016Matching Networks for One Shot Learningcited by 2,255
2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
2013Fine-Grained Visual Classification of Aircraftcited by 1,726

38 more

2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
2020Meta-Learning in Neural Networks: A Surveycited by 950
2023Vision-Language Models for Vision Tasks: A Surveycited by 839
2019Meta-Learning with Differentiable Convex Optimizationcited by 461
2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
2022Decoupled Knowledge Distillationcited by 388
2017Few-Shot Learning with Graph Neural Networkscited by 324
2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 219
2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
2021Relational Embedding for Few-Shot Classificationcited by 74
2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
2020Self-supervised Knowledge Distillation for Few-shot Learningcited by 41
2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
2022Rethinking Generalization in Few-Shot Classificationcited by 36
2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
2019Few-Shot Learning with Localization in Realistic Settingscited by 34
2023Meta-Adapter: An Online Few-shot Learner for Vision-Language Modelcited by 31
2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
2020Variational Feature Disentangling for Fine-Grained Few-Shot Classificationcited by 26
2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentationcited by 26
2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
2022Masked Distillation with Receptive Tokenscited by 23
2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23
2022Self-Promoted Supervision for Few-Shot Transformercited by 22
2023Human-like Few-Shot Learning via Bayesian Reasoning over Natural Languagecited by 22
2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
2024AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learningcited by 22
2023Context-Aware Meta-Learningcited by 21

50 most cited of 68 All 68 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way