# From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning

arXiv: https://arxiv.org/abs/2310.03843 · HTML: https://mlsanity.com/paper/2310.03843/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 72 references that are in the map.
- First posted on arXiv 5 Oct 2023.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?](https://mlsanity.com/paper/2003.11539/) (2020)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning](https://mlsanity.com/paper/2003.04390/) (2020)
- [CrossTransformers: spatially-aware few-shot transfer](https://mlsanity.com/paper/2007.11498/) (2020)
- [Charting the Right Manifold: Manifold Mixup for Few-shot Learning](https://mlsanity.com/paper/1907.12087/) (2019)
- [Task-Specific Skill Localization in Fine-tuned Language Models](https://mlsanity.com/paper/2302.06600/) (2023)
- [DePT: Decoupled Prompt Tuning](https://mlsanity.com/paper/2309.07439/) (2023)

## Built on by (most cited first, 10 of 10)

- [Dual-branch Prompting for Multimodal Machine Translation](https://mlsanity.com/paper/2507.17588/) (2025)
- [SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM](https://mlsanity.com/paper/2511.14143/) (2025)
- [Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols](https://mlsanity.com/paper/2603.00478/) (2026)
- [MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval](https://mlsanity.com/paper/2510.15470/) (2025)
- [Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation](https://mlsanity.com/paper/2602.06512/) (2026)
- [Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning](https://mlsanity.com/paper/2603.03815/) (2026)
- [ESIA: An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention Prediction](https://mlsanity.com/paper/2604.23728/) (2026)
- [M^2C-EvDet: Multi-Domain Multi-Order Cross-Modal Knowledge Distillation for Event-based Object Detection](https://mlsanity.com/paper/2606.24248/) (2026)
- [The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering](https://mlsanity.com/paper/2608.04589/) (2026)
- [DuSRFlow: Dual-Lens Super-Resolution via Parallax-Aware Flow Estimation and Complementary Reference Warping](https://mlsanity.com/paper/2610.14630/) (2026)

## Abstract (arXiv)

Deep neural networks often fail to adapt representations to novel tasks under distribution shifts, especially when only a few examples are available. This paper identifies a core obstacle behind this failure: channel bias, where networks develop a rigid emphasis on feature dimensions that were discriminative for the source task, but this emphasis is misaligned and fails to adapt to the distinct needs of a novel task. This bias leads to a striking and detrimental consequence: feature redundancy. We demonstrate that for few-shot tasks, classification accuracy is significantly improved by using as few as 1-5% of the most discriminative feature dimensions, revealing that the vast majority are actively harmful. Our theoretical analysis confirms that this redundancy originates from confounding feature dimensions-those with high intra-class variance but low inter-class separability-which are especially problematic in low-data regimes. This "less is more" phenomenon is a defining characteristic of the few-shot setting, diminishing as more samples become available. To address this, we propose a simple yet effective soft-masking method, Augmented Feature Importance Adjustment (AFIA), which estimates feature importance from augmented data to mitigate the issue. By establishing the cohesive link from channel bias to its consequence of extreme feature redundancy, this work provides a foundational principle for few-shot representation transfer and a practical method for developing more robust few-shot learning algorithms.