English

Meta-Learning Initializations for Image Segmentation

Machine Learning 2020-05-11 v4 Computer Vision and Pattern Recognition Image and Video Processing Machine Learning

Abstract

We extend first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, present a novel neural network architecture built for fast learning which we call EfficientLab, and leverage a formal definition of the test error of meta-learning algorithms to decrease error on out of distribution tasks. We show state of the art results on the FSS-1000 dataset by meta-training EfficientLab with FOMAML and using Bayesian optimization to infer the optimal test-time adaptation routine hyperparameters. We also construct a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. On the FP-k dataset, we show that meta-learned initializations provide value for canonical few-shot image segmentation but their performance is quickly matched by conventional transfer learning with performance being equal beyond 10 labeled examples. Our code, meta-learned model, and the FP-k dataset are available at https://github.com/ml4ai/mliis .

Keywords

Cite

@article{arxiv.1912.06290,
  title  = {Meta-Learning Initializations for Image Segmentation},
  author = {Sean M. Hendryx and Andrew B. Leach and Paul D. Hein and Clayton T. Morrison},
  journal= {arXiv preprint arXiv:1912.06290},
  year   = {2020}
}
R2 v1 2026-06-23T12:44:45.518Z