VALSE 论文速览 第124期：BAM: A New Perspective on Few-shot Segmentation

论文题目：Base and Meta: A New Perspective on Few-shot Segmentation

作者列表：

郎春博 (西北工业大学)、程塨 (西北工业大学)、屠斌飞 (西北工业大学)、李超 (之江实验室)、韩军伟 (西北工业大学)

B站观看网址：

https://www.bilibili.com/video/BV1cP411a7QR/

论文摘要：

Despite the progress made by few-shot segmentation (FSS) in low-data regimes, the generalization capability of most previous works could be fragile when countering hard query samples with seen-class objects. This paper proposes a fresh and powerful scheme to tackle such an intractable bias problem, dubbed base and meta (BAM). Concretely, we apply an auxiliary branch (base learner) to the conventional FSS framework (meta learner) to explicitly identify base-class objects, 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 derive accurate segmentation predictions. Considering the sensitivity of meta learner, we further introduce adjustment factors to estimate the scene differences between support and query image pairs from both style and appearance perspectives, so as to facilitate the model ensemble forecasting. The remarkable performance gains on standard benchmarks (PASCAL-5i, COCO-20i, and FSS-1000) manifest the effectiveness, and surprisingly, our versatile scheme sets new state-of-the-arts even with two plain learners. Furthermore, in light of its unique nature, we also discuss several more practical but challenging extensions, including generalized FSS, 3D point cloud FSS, class-agnostic FSS, cross-domain FSS, weak-label FSS, and zero-shot segmentation. Our source code is available at https://github.com/chunbolang/BAM.

论文信息：

[1] Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han, “Learning What Not To Segment: A New Perspective on Few-Shot Segmentation,” Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022.

[2] Chunbo Lang, Gong Cheng, Binfei Tu, Chao Li, Junwei Han, “Base and Meta: A New Perspective on Few-shot Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.

论文链接：

[https://ieeexplore.ieee.org/abstract/document/10098188]

代码链接：

[https://github.com/chunbolang/BAM]

视频讲者简介：

郎春博，西北工业大学博士生，研究方向为计算机视觉和图像处理，目前专注于少样本学习、语义分割和遥感图像解译。

个人主页：

https://sites.google.com/view/chunbolang/

特别鸣谢本次论文速览主要组织者：

月度轮值AC：张磊 (重庆大学)、谢雨彤 (阿德莱德大学)