Scaling Laws for Galaxy Images

Mike Walmsley, Micah Bowles, Anna M. M. Scaife, Jason Shingirai Makechemu, Alexander J. Gordon, Annette M. N. Ferguson, Robert G. Mann, James Pearson, Jürgen J. Popp, Jo Bovy, Josh Speagle, Hugh Dickinson, Lucy Fortson, Tobias Géron, Sandor Kruk, Chris J. Lintott, Kameswara Mantha, Devina Mohan, David O'Ryan, Inigo V. Slijepevic

Published 2024-04-03Version 1

We present the first systematic investigation of supervised scaling laws outside of an ImageNet-like context - on images of galaxies. We use 840k galaxy images and over 100M annotations by Galaxy Zoo volunteers, comparable in scale to Imagenet-1K. We find that adding annotated galaxy images provides a power law improvement in performance across all architectures and all tasks, while adding trainable parameters is effective only for some (typically more subjectively challenging) tasks. We then compare the downstream performance of finetuned models pretrained on either ImageNet-12k alone vs. additionally pretrained on our galaxy images. We achieve an average relative error rate reduction of 31% across 5 downstream tasks of scientific interest. Our finetuned models are more label-efficient and, unlike their ImageNet-12k-pretrained equivalents, often achieve linear transfer performance equal to that of end-to-end finetuning. We find relatively modest additional downstream benefits from scaling model size, implying that scaling alone is not sufficient to address our domain gap, and suggest that practitioners with qualitatively different images might benefit more from in-domain adaption followed by targeted downstream labelling.