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

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, th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 8047 - 8057
Hlavní autoři: Lang, Chunbo, Cheng, Gong, Tu, Binfei, Han, Junwei
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
Adaptation models
Computer vision
grouping and shape analysis
Image segmentation
Performance gain
Predictive models
Semantics
Sensitivity
Transfer/low-shot/long-tail learning; Deep learning architectures and techniques; Segmentation
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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-5 i and COCO-20 i 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.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.00789