Deep Compressed Sensing

Authors: Yan Wu, Mihaela Rosca, Timothy Lillicrap

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We first evaluate the DCS model using the MNIST (Yann et al., 1998) and Celeb A (Liu et al., 2015) datasets. ... Tables 2 and 3 summarise the results from our models as well as the baseline model from Bora et al. (2017). ... We use the CIFAR dataset ... and evaluate them using the Inception Score (IS) (Salimans et al., 2016) and Frchet Inception Distance (FID) (Heusel et al., 2017).
Researcher Affiliation Industry 1DeepMind, London, UK. Correspondence to: Yan Wu <yanwu@google.com>.
Pseudocode Yes Algorithm 1 Compressed Sensing with Meta Learning
Open Source Code Yes Our code will be available at https://github.com/deepmind/deep-compressed-sensing.
Open Datasets Yes We first evaluate the DCS model using the MNIST (Yann et al., 1998) and Celeb A (Liu et al., 2015) datasets. ... We use the CIFAR dataset which contains various categories of natural images, whose features from an Inception Network (Ioffe & Szegedy, 2015) are meaningful for evaluating the IS and FID.
Dataset Splits No Tables 2 and 3 summarise the results from our models as well as the baseline model from Bora et al. (2017). ... The reconstruction loss for the baseline model is estimated from Figure 1 in Bora et al. (2017). DCS performs significantly better than the baseline. In addition, while the baseline model used hundreds or thousands of gradient-descent steps with several re-starts, we only used 3 steps without any restarting, achieving orders of magnitudes higher efficiency.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., PyTorch 1.9, TensorFlow 2.x) needed to replicate the experiment beyond general mentions of concepts or methods.
Experiment Setup Yes Unless otherwise specified, we use 3 gradient descent steps for latent optimisation. More details, including hyperparameter values, are reported in the Appendix.