Prototypical Region Proposal Networks for Few-Shot Localization and Classification
Not on the map. Why?
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 8 Apr 2021.
Builds on
31 of 37 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
- 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
- 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2017One-Shot Learning for Semantic Segmentationcited by 337
- 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
19 more
- 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
- 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
- 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
- 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
- 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
- 2020Learning What to Learn for Video Object Segmentationcited by 89
- 2019The Omniglot challenge: a 3-year progress reportcited by 54
- 2020On the Texture Bias for Few-Shot CNN Segmentationcited by 38
- 2019Few-Shot Learning with Localization in Realistic Settingscited by 34
- 2020Semi-supervised few-shot learning for medical image segmentationcited by 34
- 2017Gaussian Prototypical Networks for Few-Shot Learning on Omniglotcited by 20
- 2019A New Local Transformation Module for Few-shot Segmentationcited by 15
- 2020Prototype Refinement Network for Few-Shot Segmentationcited by 11
- 2018One-Shot Segmentation in Cluttercited by 7
- 2020Few-Shot Few-Shot Learning and the role of Spatial Attentioncited by 4
- 2020StarNet: towards Weakly Supervised Few-Shot Object Detectioncited by 2
- 2018Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusterscited by 1
- 2019Towards Contextual Learning in Few-shot Object Classificationcited by 1
- 2020Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learningcited by 1
Built on by
Not cited yet.