AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensing

TL;DR

This paper introduces AgMTR, a transformer-based method for few-shot segmentation in remote sensing that uses agent-level semantic correlation to improve accuracy amidst intra-class variation and cluttered backgrounds.

Contribution

The paper proposes a novel Agent Mining Transformer (AgMTR) with local-aware agents and decoders to enhance semantic clarity and leverage unlabeled data for few-shot segmentation.

Findings

Achieves state-of-the-art results on iSAID remote sensing benchmark.

Performs competitively on natural image datasets PASCAL-5i and COCO-20i.

Demonstrates robustness in complex remote sensing scenarios.

Abstract

Few-shot Segmentation (FSS) aims to segment the interested objects in the query image with just a handful of labeled samples (i.e., support images). Previous schemes would leverage the similarity between support-query pixel pairs to construct the pixel-level semantic correlation. However, in remote sensing scenarios with extreme intra-class variations and cluttered backgrounds, such pixel-level correlations may produce tremendous mismatches, resulting in semantic ambiguity between the query foreground (FG) and background (BG) pixels. To tackle this problem, we propose a novel Agent Mining Transformer (AgMTR), which adaptively mines a set of local-aware agents to construct agent-level semantic correlation. Compared with pixel-level semantics, the given agents are equipped with local-contextual information and possess a broader receptive field. At this point, different query pixels can selectively aggregate the fine-grained local semantics of different agents, thereby enhancing the semantic clarity between query FG and BG pixels. Concretely, the Agent Learning Encoder (ALE) is first proposed to erect the optimal transport plan that arranges different agents to aggregate support semantics under different local regions. Then, for further optimizing the agents, the Agent Aggregation Decoder (AAD) and the Semantic Alignment Decoder (SAD) are constructed to break through the limited support set for mining valuable class-specific semantics from unlabeled data sources and the query image itself, respectively. Extensive experiments on the remote sensing benchmark iSAID indicate that the proposed method achieves state-of-the-art performance. Surprisingly, our method remains quite competitive when extended to more common natural scenarios, i.e., PASCAL-5i and COCO-20i.