CVMay 10, 2022

Learning Non-target Knowledge for Few-shot Semantic Segmentation

arXiv:2205.04903v1156 citationsh-index: 120
Originality Incremental advance
AI Analysis

This addresses a specific challenge in few-shot semantic segmentation for computer vision applications, representing an incremental improvement.

The paper tackles the problem of ambiguous regions in few-shot semantic segmentation by proposing a Non-Target Region Eliminating (NTRE) network to explicitly mine and eliminate background and distracting object regions, achieving effective results on PASCAL-5i and COCO-20i datasets.

Existing studies in few-shot semantic segmentation only focus on mining the target object information, however, often are hard to tell ambiguous regions, especially in non-target regions, which include background (BG) and Distracting Objects (DOs). To alleviate this problem, we propose a novel framework, namely Non-Target Region Eliminating (NTRE) network, to explicitly mine and eliminate BG and DO regions in the query. First, a BG Mining Module (BGMM) is proposed to extract the BG region via learning a general BG prototype. To this end, we design a BG loss to supervise the learning of BGMM only using the known target object segmentation ground truth. Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result. Furthermore, we propose a prototypical contrastive learning algorithm to improve the model ability of distinguishing the target object from DOs. Extensive experiments on both PASCAL-5i and COCO-20i datasets show that our approach is effective despite its simplicity.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes