[Re] Learning to Learn By Self-Critique
This work validates the original paper's claims for SCA but highlights reproducibility issues in incremental research for the meta-learning community.
This reproducibility study of Antoniou and Storkey [2019] found that the Self-Critique and Adapt (SCA) method improves MAML++ performance, with additional experiments on the Caltech-UCSD Birds 200 dataset confirming SCA's superiority, but could not reproduce results for a novel high-end version due to omitted implementation details.
This work is a reproducibility study of the paper of Antoniou and Storkey [2019], published at NeurIPS 2019. Our results are in parts similar to the ones reported in the original paper, supporting the central claim of the paper that the proposed novel method, called Self-Critique and Adapt (SCA), improves the performance of MAML++. The conducted additional experiments on the Caltech-UCSD Birds 200 dataset confirm the superiority of SCA compared to MAML++. In addition, the reproduced paper suggests a novel high-end version of MAML++ for which we could not reproduce the same results. We hypothesize that this is due to the many implementation details that were omitted in the original paper.