Meta-Learning Initializations for Image Segmentation

by   Sean M. Hendryx, et al.

While meta-learning approaches that utilize neural network representations have made progress in few-shot image classification, reinforcement learning, and, more recently, image semantic segmentation, the training algorithms and model architectures have become increasingly specialized to the few-shot domain. A natural question that arises is how to develop learning systems that scale from few-shot to many-shot settings while yielding competitive performance in both. One scalable potential approach that does not require ensembling many models nor the computational costs of relation networks, is to meta-learn an initialization. In this work, we study first-order meta-learning of initializations for deep neural networks that must produce dense, structured predictions given an arbitrary amount of training data for a new task. Our primary contributions include (1), an extension and experimental analysis of first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, (2) a novel neural network architecture built for parameter efficiency and fast learning which we call EfficientLab, (3) a formalization of the generalization error of meta-learning algorithms, which we leverage to decrease error on unseen tasks, and (4) a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. We show that meta-learned initializations for image segmentation provide value for both canonical few-shot learning problems and larger datasets, outperforming ImageNet-trained initializations for up to 400 densely labeled examples. We find that our network, with an empirically estimated optimal update procedure, yields state of the art results on the FSS-1000 dataset while only requiring one forward pass through a single model at evaluation time.



There are no comments yet.


page 12


Meta-DRN: Meta-Learning for 1-Shot Image Segmentation

Modern deep learning models have revolutionized the field of computer vi...

Meta-Learning of Neural Architectures for Few-Shot Learning

The recent progress in neural architectures search (NAS) has allowed sca...

Meta-Learning for Few-Shot Time Series Classification

Deep neural networks (DNNs) have achieved state-of-the-art results on ti...

MetaHistoSeg: A Python Framework for Meta Learning in Histopathology Image Segmentation

Few-shot learning is a standard practice in most deep learning based his...

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

The design of neural network architectures is an important component for...

Learning to Stop While Learning to Predict

There is a recent surge of interest in designing deep architectures base...

Few-shot segmentation of medical images based on meta-learning with implicit gradients

Classical supervised methods commonly used often suffer from the require...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.