mlsanityData to 14 Oct 2026

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

arXiv 2409.17453 ↗First posted 26 Sep 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 62 of its 107 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

62 of 107 references.

References · 62

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2017Graph Attention Networkscited by 8,923
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  11. 2016Pyramid Scene Parsing Networkcited by 2,479
  12. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
38 more
  1. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  2. 2016Matching Networks for One Shot Learningcited by 2,255
  3. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  5. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  6. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  7. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  8. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  9. 2017One-Shot Learning for Semantic Segmentationcited by 337
  10. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  12. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  13. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  14. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 261
  15. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  16. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  17. 2019iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Imagescited by 197
  18. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  19. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  20. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  21. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  22. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  23. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  24. 2014Simultaneous Detection and Segmentationcited by 159
  25. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  26. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  27. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  28. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  29. 2019Improved Few-Shot Visual Classificationcited by 115
  30. 2022An Empirical Study of Remote Sensing Pretrainingcited by 105
  31. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  32. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  33. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  34. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  35. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  36. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  37. 2020BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentationcited by 28
  38. 2023Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentationcited by 28

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretationcited by 16
  2. 2025UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenescited by 10
  3. 2025A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learningcited by 5
  4. 2025ViRefSAM: Visual Reference-Guided Segment Anything Model for Remote Sensing Segmentationcited by 1
  5. 2025Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentationcited by 1
  6. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1