Sensitivity of sparse codes to image distortions
Not on the map. Why?
Abstract (arXiv)
Sparse coding has been proposed as a theory of visual cortex and as an unsupervised algorithm for learning representations. We show empirically with the MNIST dataset that sparse codes can be very sensitive to image distortions, a behavior that may hinder invariant object recognition. A locally linear analysis suggests that the sensitivity is due to the existence of linear combinations of active dictionary elements with high cancellation. A nearest neighbor classifier is shown to perform worse on sparse codes than original images. For a linear classifier with a sufficiently large number of labeled examples, sparse codes are shown to yield higher accuracy than original images, but no higher than a representation computed by a random feedforward net. Sensitivity to distortions seems to be a basic property of sparse codes, and one should be aware of this property when applying sparse codes to invariant object recognition.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 33 references that are in the map. First posted on arXiv 15 Apr 2022.
Builds on
12 of 33 references.
References · 12
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
- 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
- 2016Conditional Image Generation with PixelCNN Decoderscited by 859
- 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
- 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
- 2018The Sparse Manifold Transformcited by 36
- 2020Adversarial Robustness of Supervised Sparse Codingcited by 22
Built on by
Not cited yet.