# Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

arXiv: https://arxiv.org/abs/2204.09903 · HTML: https://mlsanity.com/paper/2204.09903/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 21 Apr 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [One-Shot Learning for Semantic Segmentation](https://mlsanity.com/paper/1709.03410/) (2017)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [Feature Weighting and Boosting for Few-Shot Segmentation](https://mlsanity.com/paper/1909.13140/) (2019)
- [SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation](https://mlsanity.com/paper/1810.09091/) (2018)
- [Learning What Not to Segment: A New Perspective on Few-Shot Segmentation](https://mlsanity.com/paper/2203.07615/) (2022)
- [Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer](https://mlsanity.com/paper/2108.03032/) (2021)
- [Self-Guided and Cross-Guided Learning for Few-Shot Segmentation](https://mlsanity.com/paper/2103.16129/) (2021)
- [Image Deformation Meta-Networks for One-Shot Learning](https://mlsanity.com/paper/1905.11641/) (2019)
- [Learning Meta-class Memory for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.02958/) (2021)

## Built on by (most cited first, 28 of 28)

- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation](https://mlsanity.com/paper/2303.14652/) (2023)
- [Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2210.06780/) (2022)
- [Self-Calibrated Cross Attention Network for Few-Shot Segmentation](https://mlsanity.com/paper/2308.09294/) (2023)
- [Hybrid Mamba for Few-Shot Segmentation](https://mlsanity.com/paper/2409.19613/) (2024)
- [Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation](https://mlsanity.com/paper/2405.08458/) (2024)
- [Eliminating Feature Ambiguity for Few-Shot Segmentation](https://mlsanity.com/paper/2407.09842/) (2024)
- [Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2311.17626/) (2023)
- [Query-guided Prototype Evolution Network for Few-Shot Segmentation](https://mlsanity.com/paper/2403.06488/) (2024)
- [Not Just Learning from Others but Relying on Yourself: A New Perspective on Few-Shot Segmentation in Remote Sensing](https://mlsanity.com/paper/2310.12452/) (2023)
- [Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation](https://mlsanity.com/paper/2309.11172/) (2023)
- [Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation](https://mlsanity.com/paper/2303.13724/) (2023)
- [Few-Shot Rotation-Invariant Aerial Image Semantic Segmentation](https://mlsanity.com/paper/2306.11734/) (2023)
- [RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentation](https://mlsanity.com/paper/2410.01110/) (2024)
- [Dense Affinity Matching for Few-Shot Segmentation](https://mlsanity.com/paper/2307.08434/) (2023)
- [Boosting Few-Shot Semantic Segmentation Via Segment Anything Model](https://mlsanity.com/paper/2401.09826/) (2024)
- [Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching](https://mlsanity.com/paper/2503.04826/) (2025)
- [Multi-Content Interaction Network for Few-Shot Segmentation](https://mlsanity.com/paper/2303.06304/) (2023)
- [Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentation](https://mlsanity.com/paper/2405.13686/) (2024)
- [LERENet: Eliminating Intra-class Differences for Metal Surface Defect Few-shot Semantic Segmentation](https://mlsanity.com/paper/2403.11122/) (2024)
- [ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotations](https://mlsanity.com/paper/2505.12547/) (2025)
- [Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation](https://mlsanity.com/paper/2507.19140/) (2025)
- [Object-level Correlation for Few-Shot Segmentation](https://mlsanity.com/paper/2509.07917/) (2025)
- [Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract](https://mlsanity.com/paper/2306.15278/) (2023)
- [Reflection Invariance Learning for Few-shot Semantic Segmentation](https://mlsanity.com/paper/2309.15850/) (2023)
- [Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attention](https://mlsanity.com/paper/2401.09866/) (2024)
- [Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labeling](https://mlsanity.com/paper/2410.09967/) (2024)
- [P3-SAM: SAM with Perceptual Parallel Prompt for Few-Shot Strip Steel Surface Defect Segmentation](https://mlsanity.com/paper/2609.21424/) (2026)

## Abstract (arXiv)

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasoning scheme is first implemented on the annotated support image, and then the coarse segmentation mask is divided into multiple regions with different properties. Leveraging effective masked average pooling operations, a series of support-induced proxies are thus derived, each playing a specific role in conquering the above challenges. Moreover, we devise a unique parallel decoder structure that integrates proxies with similar attributes to boost the discrimination power. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information as a guide at the "episode" level, not just about the object cues themselves. Extensive experiments on PASCAL-5i and COCO-20i demonstrate the superiority of DCP over conventional prototype-based approaches (up to 5~10% on average), which also establishes a new state-of-the-art. Code is available at github.com/chunbolang/DCP.