arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.07615cs.CV
收藏

学习什么不需要分割:一种新的Few-Shot分割方法

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Northwestern Polytechnical University(西北工业大学)

Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han

摘要:

近年来,Few-Shot分割(FSS)得到了广泛的发展。大多数以前的工作都努力通过分类任务衍生的元学习框架来实现泛化;然而,训练的模型偏向于所看到的类,而不是理想的类不可知论,从而阻碍了新概念的识别。本文提出了一个新的和直接的见解,以减轻这个问题。具体地说,我们将一个额外的分支(基本学习器)应用于传统的FSS模型(Meta学习器),以显式地识别基类的目标,即,不需要分割的区域。然后,这两个学习器并行输出的粗糙结果自适应地集成,以产生精确的分割预测。考虑到Meta学习器的敏感性,我们进一步引入一个调整因子来估计输入图像对之间的场景差异,以促进模型集成预测。PASCAL-5i和COCO-20 i上的大量性能增益验证了有效性,令人惊讶的是,我们的多功能方案即使使用两个普通学习器也可以设置一个新的最先进的状态。此外,鉴于所提出的方法的独特性,我们还将其扩展到更现实但具有挑战性的环境,即,广义FSS,其中需要确定基本类和新类两者的像素。源代码可在github.com/chunbolang/BAM上获得。

英文摘要:

Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks; however, the trained models are biased towards the seen classes instead of being ideally class-agnostic, thus hindering the recognition of new concepts. This paper proposes a fresh and straightforward insight to alleviate the problem. Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i.e., the regions that do not need to be segmented. Then, the coarse results output by these two learners in parallel are adaptively integrated to yield precise segmentation prediction. Considering the sensitivity of meta learner, we further introduce an adjustment factor to estimate the scene differences between the input image pairs for facilitating the model ensemble forecasting. The substantial performance gains on PASCAL-5i and COCO-20i verify the effectiveness, and surprisingly, our versatile scheme sets a new state-of-the-art even with two plain learners. Moreover, in light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting, i.e., generalized FSS, where the pixels of both base and novel classes are required to be determined. The source code is available at github.com/chunbolang/BAM.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑