Closed-loop Transcription via Convolutional Sparse Coding

Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang, Xingjian Gao, Yuexiang Zhai, Mingyang Li, Xiaojun Yuan, Heung-Yeung Shum, Lionel Ni, Yi Ma

Keywords: Convolutional Sparse Coding, Inverse Models, Rate Reduction

TL;DR: This paper combines the recent closed-loop transcription framework with convolutional sparse coding layers and demonstrates superior generative autoencoding performance.

Abstract: Autoencoding has been a popular and effective framework for learning generative models for images, with much empirical success. Autoencoders often use generic deep networks as the encoder and decoder, which are difficult to interpret, and the learned representations lack clear structure. In this work, we replace the encoder and decoder with standard convolutional sparse coding and decoding layers, obtained from unrolling an optimization algorithm for solving a (convexified) sparse coding program. Furthermore, to avoid computational difficulties in minimizing distributional distance between the real and generated images, we utilize the recent closed-loop transcription (CTRL) framework that maximizes the rate reduction of the learned sparse representations. We show that such a simple framework demonstrates surprisingly competitive performance on large datasets, such as ImageNet-1K, compared to existing autoencoding and generative methods under fair conditions. Even with simpler networks and less computational resources, our method demonstrates splendid visual quality in regenerated images with striking sample-wise consistency. More surprisingly, the learned autoencoder generalizes to unseen datasets. Our method enjoys several side benefits, including more structured and interpretable representations, more stable convergence, scalability to large datasets -- indeed, our method is the first sparse coding generative method to scale up to ImageNet -- and trainability with smaller batch sizes.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2302.09347/code)