SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.06290 · 2019

Meta-Learning Initializations for Image Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1912.06290")
get_code_for_paper("1912.06290")
have("1912.06290")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1912.06290.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1912.06290.svg)](https://syntology.ai/paper/1912.06290)

Connect an agent — have() is free.