# Alignment with human representations supports robust few-shot learning

arXiv: https://arxiv.org/abs/2301.11990 · HTML: https://mlsanity.com/paper/2301.11990/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [Relative representations enable zero-shot latent space communication](https://mlsanity.com/paper/2209.15430/) (2022)
- [Revisiting ResNets: Improved Training and Scaling Strategies](https://mlsanity.com/paper/2103.07579/) (2021)
- [Human alignment of neural network representations](https://mlsanity.com/paper/2211.01201/) (2022)
- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [Learning as the Unsupervised Alignment of Conceptual Systems](https://mlsanity.com/paper/1906.09012/) (2019)
- [On the Informativeness of Supervision Signals](https://mlsanity.com/paper/2211.01407/) (2022)
- [Predicting Human Similarity Judgments Using Large Language Models](https://mlsanity.com/paper/2202.04728/) (2022)
- [Researching Alignment Research: Unsupervised Analysis](https://mlsanity.com/paper/2206.02841/) (2022)

## Built on by (most cited first, 25 of 25)

- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [Improving neural network representations using human similarity judgments](https://mlsanity.com/paper/2306.04507/) (2023)
- [Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex](https://mlsanity.com/paper/2306.03779/) (2023)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [What Matters to You? Towards Visual Representation Alignment for Robot Learning](https://mlsanity.com/paper/2310.07932/) (2023)
- [Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception](https://mlsanity.com/paper/2306.03229/) (2023)
- [Learning Human-like Representations to Enable Learning Human Values](https://mlsanity.com/paper/2312.14106/) (2023)
- [Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment](https://mlsanity.com/paper/2412.04835/) (2024)
- [How Aligned are Different Alignment Metrics?](https://mlsanity.com/paper/2407.07530/) (2024)
- [Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning](https://mlsanity.com/paper/2403.07078/) (2024)
- [TurtleBench: A Visual Programming Benchmark in Turtle Geometry](https://mlsanity.com/paper/2411.00264/) (2024)
- [Dimensions of Disagreement: Unpacking Divergence and Misalignment in Cognitive Science and Artificial Intelligence](https://mlsanity.com/paper/2310.12994/) (2023)
- [Representational Alignment Supports Effective Machine Teaching](https://mlsanity.com/paper/2406.04302/) (2024)
- [Knowledge graphs for empirical concept retrieval](https://mlsanity.com/paper/2404.07008/) (2024)
- [A Nurse is Blue and Elephant is Rugby: Cross Domain Alignment in Large Language Models Reveal Human-like Patterns](https://mlsanity.com/paper/2405.14863/) (2024)
- [Alignment and Adversarial Robustness: Are More Human-Like Models More Secure?](https://mlsanity.com/paper/2502.12377/) (2025)
- [Connecting Concept Convexity and Human-Machine Alignment in Deep Neural Networks](https://mlsanity.com/paper/2409.06362/) (2024)
- [Geometry matters: insights from Ollivier Ricci Curvature and Ricci Flow into representational alignment through Ollivier-Ricci Curvature and Ricci Flow](https://mlsanity.com/paper/2501.00919/) (2025)
- [Uncovering the Computational Ingredients of Human-Like Representations in LLMs](https://mlsanity.com/paper/2510.01030/) (2025)
- [Learning to Communicate Across Modalities: Perceptual Heterogeneity in Multi-Agent Systems](https://mlsanity.com/paper/2601.22041/) (2026)
- [Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundational Models](https://mlsanity.com/paper/2408.01431/) (2024)
- [Replicating Human Social Perception in Generative AI: Evaluating the Valence-Dominance Model](https://mlsanity.com/paper/2503.04842/) (2025)
- [Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation](https://mlsanity.com/paper/2604.13803/) (2026)
- [Capability neq Interpretability: Human Interpretability of Vision Foundation Models](https://mlsanity.com/paper/2605.20337/) (2026)

## Abstract (arXiv)

Should we care whether AI systems have representations of the world that are similar to those of humans? We provide an information-theoretic analysis that suggests that there should be a U-shaped relationship between the degree of representational alignment with humans and performance on few-shot learning tasks. We confirm this prediction empirically, finding such a relationship in an analysis of the performance of 491 computer vision models. We also show that highly-aligned models are more robust to both natural adversarial attacks and domain shifts. Our results suggest that human-alignment is often a sufficient, but not necessary, condition for models to make effective use of limited data, be robust, and generalize well.