AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation

TL;DR

AFANet introduces an adaptive frequency-aware approach for weakly-supervised few-shot semantic segmentation, leveraging frequency decoupling and cross-modal guidance to improve segmentation accuracy with minimal annotations.

Contribution

The paper proposes a novel frequency-aware module and a CLIP-guided spatial adapter for enhanced weakly-supervised few-shot segmentation, integrating frequency and cross-modal information online.

Findings

Achieves state-of-the-art results on Pascal-5i and COCO-20i datasets.

Effectively decouples high- and low-frequency information for better segmentation.

Utilizes online CLIP-guided adaptation for enriched semantic understanding.

Abstract

Few-shot learning aims to recognize novel concepts by leveraging prior knowledge learned from a few samples. However, for visually intensive tasks such as few-shot semantic segmentation, pixel-level annotations are time-consuming and costly. Therefore, in this paper, we utilize the more challenging image-level annotations and propose an adaptive frequency-aware network (AFANet) for weakly-supervised few-shot semantic segmentation (WFSS). Specifically, we first propose a cross-granularity frequency-aware module (CFM) that decouples RGB images into high-frequency and low-frequency distributions and further optimizes semantic structural information by realigning them. Unlike most existing WFSS methods using the textual information from the multi-modal language-vision model, e.g., CLIP, in an offline learning manner, we further propose a CLIP-guided spatial-adapter module (CSM), which performs spatial domain adaptive transformation on textual information through online learning, thus providing enriched cross-modal semantic information for CFM. Extensive experiments on the Pascal-5\textsuperscript{i} and COCO-20\textsuperscript{i} datasets demonstrate that AFANet has achieved state-of-the-art performance. The code is available at https://github.com/jarch-ma/AFANet.