# Prototypical Region Proposal Networks for Few-Shot Localization and Classification

arXiv: https://arxiv.org/abs/2104.03496 · HTML: https://mlsanity.com/paper/2104.03496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 37 references that are in the map.
- First posted on arXiv 8 Apr 2021.

## Builds on (most cited first, 30 of 31)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (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)
- [CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning](https://mlsanity.com/paper/1903.02351/) (2019)
- [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)
- [FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation](https://mlsanity.com/paper/1907.12347/) (2019)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)
- [CRNet: Cross-Reference Networks for Few-Shot Segmentation](https://mlsanity.com/paper/2003.10658/) (2020)
- [Learning What to Learn for Video Object Segmentation](https://mlsanity.com/paper/2003.11540/) (2020)
- [The Omniglot challenge: a 3-year progress report](https://mlsanity.com/paper/1902.03477/) (2019)
- [On the Texture Bias for Few-Shot CNN Segmentation](https://mlsanity.com/paper/2003.04052/) (2020)
- [Few-Shot Learning with Localization in Realistic Settings](https://mlsanity.com/paper/1904.08502/) (2019)
- [Semi-supervised few-shot learning for medical image segmentation](https://mlsanity.com/paper/2003.08462/) (2020)
- [Gaussian Prototypical Networks for Few-Shot Learning on Omniglot](https://mlsanity.com/paper/1708.02735/) (2017)
- [A New Local Transformation Module for Few-shot Segmentation](https://mlsanity.com/paper/1910.05886/) (2019)
- [Prototype Refinement Network for Few-Shot Segmentation](https://mlsanity.com/paper/2002.03579/) (2020)
- [One-Shot Segmentation in Clutter](https://mlsanity.com/paper/1803.09597/) (2018)
- [Few-Shot Few-Shot Learning and the role of Spatial Attention](https://mlsanity.com/paper/2002.07522/) (2020)
- [StarNet: towards Weakly Supervised Few-Shot Object Detection](https://mlsanity.com/paper/2003.06798/) (2020)
- [Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters](https://mlsanity.com/paper/1802.00383/) (2018)
- [Towards Contextual Learning in Few-shot Object Classification](https://mlsanity.com/paper/1912.06679/) (2019)

## Abstract (arXiv)

Recently proposed few-shot image classification methods have generally focused on use cases where the objects to be classified are the central subject of images. Despite success on benchmark vision datasets aligned with this use case, these methods typically fail on use cases involving densely-annotated, busy images: images common in the wild where objects of relevance are not the central subject, instead appearing potentially occluded, small, or among other incidental objects belonging to other classes of potential interest. To localize relevant objects, we employ a prototype-based few-shot segmentation model which compares the encoded features of unlabeled query images with support class centroids to produce region proposals indicating the presence and location of support set classes in a query image. These region proposals are then used as additional conditioning input to few-shot image classifiers. We develop a framework to unify the two stages (segmentation and classification) into an end-to-end classification model -- PRoPnet -- and empirically demonstrate that our methods improve accuracy on image datasets with natural scenes containing multiple object classes.