Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation
Not on the map. Why?
Abstract (arXiv)
Few-shot segmentation (FSS) for remote sensing (RS) imagery leverages supporting information from limited annotated samples to achieve query segmentation of novel classes. Previous efforts are dedicated to mining segmentation-guiding visual cues from a constrained set of support samples. However, they still struggle to address the pronounced intra-class differences in RS images, as sparse visual cues make it challenging to establish robust class-specific representations. In this paper, we propose a holistic semantic embedding (HSE) approach that effectively harnesses general semantic knowledge, i.e., class description (CD) embeddings.Instead of the naive combination of CD embeddings and visual features for segmentation decoding, we investigate embedding the general semantic knowledge during the feature extraction stage.Specifically, in HSE, a spatial dense interaction module allows the interaction of visual support features with CD embeddings along the spatial dimension via self-attention.Furthermore, a global content modulation module efficiently augments the global information of the target category in both support and query features, thanks to the transformative fusion of visual features and CD embeddings.These two components holistically synergize general CD embeddings and visual cues, constructing a robust class-specific representation.Through extensive experiments on the standard FSS benchmark, the proposed HSE approach demonstrates superior performance compared to peer work, setting a new state-of-the-art.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 55 of its 90 references that are in the map. First posted on arXiv 22 May 2024.
Builds on
55 of 90 references.
References · 55
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
38 more
- 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2019Language Models as Knowledge Bases?cited by 1,922
- 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
- 2018On First-Order Meta-Learning Algorithmscited by 1,003
- 2021Segmenter: Transformer for Semantic Segmentationcited by 855
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2017One-Shot Learning for Semantic Segmentationcited by 337
- 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
- 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
- 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
- 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
- 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
- 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
- 2020CrossTransformers: spatially-aware few-shot transfercited by 174
- 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
- 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
- 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
- 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
- 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
- 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
- 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
- 2023Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentationcited by 76
- 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
- 2020Multi-Attention-Network for Semantic Segmentation of Fine Resolution Remote Sensing Imagescited by 59
- 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
- 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
- 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
- 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
- 2020Multi-stage Attention ResU-Net for Semantic Segmentation of Fine-Resolution Remote Sensing Imagescited by 26
- 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
- 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
- 2017Gaussian Prototypical Networks for Few-Shot Learning on Omniglotcited by 20
- 2020RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classificationcited by 19
- 2022MSI: Maximize Support-Set Information for Few-Shot Segmentationcited by 18
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.