Image Compression: Sparse Coding vs. Bottleneck Autoencoders
Open accessAbstract
Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we explore the ability of sparse coding to improve reconstructed image quality for the same degree of compression. We observe that sparse image compression produces visually superior reconstructed images and yields higher values of pixel-wise measures of reconstruction quality (PSNR and SSIM) compared to bottleneck autoencoders. In addition, we find that using alternative metrics that correlate better with human perception, such as feature perceptual loss and the classification accuracy, sparse image compression scores up to 18.06% and 2.7% higher, respectively, compared to bottleneck autoencoders. Although computationally much more intensive, we find that sparse coding is otherwise superior to bottleneck autoencoders for the same degree of compression.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Overcomplete AEs may learn a more generic representation of the input and provide better performances in various tasks than undercomplete AEs.
“several studies suggested that overcomplete AEs, compared to undercomplete, may learn a more generic representation of the input and therefore provide better performances in various tasks.38,53”
From Vibration-based structural health monitoring exploiting a combination of convolutional neural networks and autoencoders for temperature effects neutralization (2022) · cites this paper as [53]
The Introduction (p. 1) reports that overcomplete sparse coding outperformed bottleneck autoencoders on several measures of thumbnail-image compression. But the paper compares sparse coding with autoencoders, not overcomplete with undercomplete autoencoders; it does not establish that overcomplete autoencoders learn more generic representations or perform better across various tasks. (LLM, conf=0.83)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Donoho, D. L. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.871582 · Cited by 23,994 · see citing works
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,890 · see citing works
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928 · see citing works
Donoho, D. L. (2004) · Cited by 17,049 · see citing works
Candes, E. J., Romberg, J., & Tao, T. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2005.862083 · Cited by 15,639 · see citing works
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283 · see citing works
Salakhutdinov, R., & Hinton, G. E. (2009) · Cited by 1,890 · see citing works
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Sajjadi, M. S. M., Schölkopf, B., & Hirsch, M. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.481 · Cited by 1,088 · see citing works
Sparse Coding via Thresholding and Local Competition in Neural Circuits
Rozell, C. J., Johnson, D. H., Baraniuk, R. G., & Olshausen, B. A. (2008) · Neural Computation · doi:10.1162/neco.2008.03-07-486 · Cited by 457 · see citing works
Variable Rate Image Compression with Recurrent Neural NetworksPreprint
Toderici, G. D., O’Malley, S. M., Hwang, S. J., Vincent, D., Minnen, D. C., Baluja, S., Covell, M., & Sukthankar, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.06085 · Cited by 441 · see citing works
Image Data Compression and Noisy Channel Error Correction Using Deep Neural Network
Watkins, Y., & Sayeh, M. R. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.09.305 · Cited by 14 · see citing works
Self-citationAdaptive compressive sensing for low power wireless sensors
Watkins, A., Mudhireddy, V. N., Wang, H., et al. (2014) · doi:10.1145/2591513.2591537 · Cited by 11 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [4][4] A. D. et al. Generating images with perceptual similarity metrics based on deep networks. In Advances in Neural Information Processing Systems (NIPS) , 2016. -
Cited by
Sorted by citations
Parziale, M., Lomazzi, L., Giglio, M., & Cadini, F. (2022) · Structural Control and Health Monitoring · doi:10.1002/stc.3076 · Cited by 22 · see citing works
- Authors
- Watkins, Y., Iaroshenko, O., Sayeh, M., & Kenyon, G.
- Affiliations
- Los Alamos National Laboratory (US)
- Southern Illinois University Carbondale (US)
- Venue
- 2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI)
- Publisher
- IEEE
- Published
- 2018-04
- Pages
- 17-20
- OpenAlex
- W2766986296
- Cited by
- 0
- References
- 12
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (89233218CNA000001)
- U.S. Department of Energy (#89233218CNA000001)
- Defense Advanced Research Projects Agency
- National Nuclear Security Administration (89233218C-NA000001)
- Laboratory Directed Research and Development (89233218CNA000001)
- Los Alamos National Laboratory (89233218CNA 000001)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Data Compression Techniques
- Physical Sciences › Computer Science › Signal Processing › Video Coding and Compression Technologies
- Physical Sciences › Engineering › Computational Mechanics › Sparse and Compressive Sensing Techniques
- Keywords
- image compression, sparse coding, image reconstruction quality, perceptual loss, human perception, PSNR, SSIM, classification accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
