Understanding Cross-Model Perceptual Invariances Through Ensemble Metamers
Not on the map. Why?
Abstract (arXiv)
Understanding the perceptual invariances of artificial neural networks is essential for improving explainability and aligning models with human vision. Metamers - stimuli that are physically distinct yet produce identical neural activations - serve as a valuable tool for investigating these invariances. We introduce a novel approach to metamer generation by leveraging ensembles of artificial neural networks, capturing shared representational subspaces across diverse architectures, including convolutional neural networks and vision transformers. To characterize the properties of the generated metamers, we employ a suite of image-based metrics that assess factors such as semantic fidelity and naturalness. Our findings show that convolutional neural networks generate more recognizable and human-like metamers, while vision transformers produce realistic but less transferable metamers, highlighting the impact of architectural biases on representational invariances.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 55 references that are in the map. First posted on arXiv 2 Apr 2025.
Builds on
22 of 55 references.
References · 22
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2022Generative Adversarial Networkscited by 5,603
- 2013Intriguing properties of neural networkscited by 5,114
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2021Transformers in Vision: A Surveycited by 1,009
- 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
- 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
10 more
- 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
- 2021Intriguing Properties of Vision Transformerscited by 446
- 2014Understanding Deep Image Representations by Inverting Themcited by 399
- 2018Generalisation in humans and deep neural networkscited by 237
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
- 2018MEAL: Multi-Model Ensemble via Adversarial Learningcited by 52
- 2023An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferabilitycited by 42
- 2023Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalizationcited by 14
- 2020Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attackscited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.