Towards interpreting computer vision based on transformation invariant optimization
Not on the map. Why?
Abstract (arXiv)
Interpreting how does deep neural networks (DNNs) make predictions is a vital field in artificial intelligence, which hinders wide applications of DNNs. Visualization of learned representations helps we humans understand the vision of DNNs. In this work, visualized images that can activate the neural network to the target classes are generated by back-propagation method. Here, rotation and scaling operations are applied to introduce the transformation invariance in the image generating process, which we find a significant improvement on visualization effect. Finally, we show some cases that such method can help us to gain insight into neural networks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 24 references that are in the map. First posted on arXiv 18 Jun 2021.
Builds on
12 of 24 references.
References · 12
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2016Adversarial examples in the physical worldcited by 1,769
- 2015Understanding Neural Networks Through Deep Visualizationcited by 334
- 2019AdvHat: Real-world adversarial attack on ArcFace Face ID systemcited by 163
- 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
- 2020Understanding Adversarial Examples from the Mutual Influence of Images and Perturbationscited by 59
- 2019Fooling a Real Car with Adversarial Traffic Signscited by 29
- 2021The Definitions of Interpretability and Learning of Interpretable Modelscited by 1
Built on by
Not cited yet.