AMP: Adaptive Masked Proxies for Few-Shot Segmentation

Mennatullah Siam, Boris N. Oreshkin, Martin Jagersand; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 5249-5258


Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method that constructs the final segmentation layer weights from few labelled samples. It utilizes multi-resolution average pooling on base embeddings masked with the label to act as a positive proxy for the new class, while fusing it with the previously learned class signatures. Our method is evaluated on PASCAL-5^i dataset and outperforms the state-of-the-art in the few-shot semantic segmentation. Unlike previous methods, our approach does not require a second branch to estimate parameters or prototypes, which enables it to be used with 2-stream motion and appearance based segmentation networks. We further propose a novel setup for evaluating continual learning of object segmentation which we name incremental PASCAL (iPASCAL) where our method outperforms the baseline method. Our code is publicly available at

Related Material

[pdf] [supp]
author = {Siam, Mennatullah and Oreshkin, Boris N. and Jagersand, Martin},
title = {AMP: Adaptive Masked Proxies for Few-Shot Segmentation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}