ﻻ يوجد ملخص باللغة العربية
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations. Recent progress in fewshot semantic segmentation tackles the issue by only a few pixel-level annotated examples. However, these few-shot approaches cannot easily be applied to multi-way or weak annotation settings. In this paper, we advance the few-shot segmentation paradigm towards a scenario where image-level annotations are available to help the training process of a few pixel-level annotations. Our key idea is to learn a better prototype representation of the class by fusing the knowledge from the image-level labeled data. Specifically, we propose a new framework, called PAIA, to learn the class prototype representation in a metric space by integrating image-level annotations. Furthermore, by considering the uncertainty of pseudo-masks, a distilled soft masked average pooling strategy is designed to handle distractions in image-level annotations. Extensive empirical results on two datasets show superior performance of PAIA.
Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus be
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention. Previous arts extract fea
Few-shot semantic segmentation models aim to segment images after learning from only a few annotated examples. A key challenge for them is overfitting. Prior works usually limit the overall model capacity to alleviate overfitting, but the limited cap
Few-shot image classification (FSIC), which requires a model to recognize new categories via learning from few images of these categories, has attracted lots of attention. Recently, meta-learning based methods have been shown as a promising direction
This paper studies the problem of learning semantic segmentation from image-level supervision only. Current popular solutions leverage object localization maps from classifiers as supervision signals, and struggle to make the localization maps captur