Extreme Image Transformations Facilitate Robust Latent Object Representations
Not on the map. Why?
Abstract (arXiv)
Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. While networks are expected to do automated feature selection, it is not effective at the scale of the object. Humans, however, are able to select the minimum set of features required to form a robust representation of an object. In this work, we show that finetuning any pretrained off-the-shelf network with Extreme Image Transformations (EIT) not only helps in learning a robust latent representation, it also improves the performance of these networks against common adversarial attacks of various intensities. Our EIT trained networks show strong activations in the object regions even when tested with more intense noise, showing promising generalizations across different kinds of adversarial attacks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 77 references that are in the map. First posted on arXiv 19 Sep 2023.
Builds on
32 of 77 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2020Shortcut Learning in Deep Neural Networkscited by 1,969
- 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
- 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
- 2017Countering Adversarial Images using Input Transformationscited by 520
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 314
20 more
- 2019Adversarial Examples Improve Image Recognitioncited by 286
- 2018Generalisation in humans and deep neural networkscited by 237
- 2020Bag of Tricks for Adversarial Trainingcited by 200
- 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
- 2019Are Labels Required for Improving Adversarial Robustness?cited by 163
- 2017Generative Adversarial Perturbationscited by 153
- 2021Learning to See by Looking at Noisecited by 92
- 2020RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Realcited by 91
- 2019Improving Adversarial Robustness of Ensembles with Diversity Trainingcited by 69
- 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
- 2021Robust and Accurate Object Detection via Adversarial Learningcited by 42
- 2020Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networkscited by 25
- 2020Encoding Robustness to Image Style via Adversarial Feature Perturbationscited by 18
- 2021Tracking Without Re-recognition in Humans and Machinescited by 12
- 2022Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptationcited by 4
- 2022Extreme Image Transformations Affect Humans and Machines Differentlycited by 4
- 2014The constitution of visual perceptual units in the functional architecture of V1cited by 3
- 2021The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networkscited by 3
- 2022Robustness of Humans and Machines on Object Recognition with Extreme Image Transformationscited by 3
- 2014Cortical spatio-temporal dimensionality reduction for visual groupingcited by 2
Built on by
Not cited yet.