pith. sign in

arxiv: 1703.05175 · v2 · pith:Y7WC326Pnew · submitted 2017-03-15 · 💻 cs.LG · stat.ML

Prototypical Networks for Few-shot Learning

Jake Snell , Kevin Swersky , Richard S. Zemel This is my paper
classification 💻 cs.LG stat.ML
keywords networksprototypicalfew-shotlearningachieveapproachesclassclassification
0
0 comments X
read the original abstract

We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    Creativity is defined as meta-learning where a frozen diffusion creator optimizes candidates for rapid improvement by an adapting appraiser such as an autoencoder or CLIP adapter.

  2. SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 6.0

    SegRAG augments SAM3 with class-specific point prompts retrieved via DINOv3 features and filtered by ICCD, using TSG at inference to improve open-vocabulary segmentation.

  3. SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation

    cs.CV 2026-05 unverdicted novelty 6.0

    SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.

  4. Revisiting Feature Prediction for Learning Visual Representations from Video

    cs.CV 2024-02 conditional novelty 6.0

    V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.

  5. Using predefined vector systems to speed up neural network multimillion class classification

    cs.LG 2026-04 unverdicted novelty 5.0

    Predefined vector systems structure neural network latent spaces to allow O(1) label prediction via index searches on embedding vectors, delivering up to 11.6x speedup on multimillion-class tasks while preserving accu...

  6. 3D Foundation Model for Generalizable Disease Detection in Head Computed Tomography

    cs.CV 2025-02 unverdicted novelty 5.0

    A 3D self-supervised foundation model trained on over 360k head CT scans improves downstream disease classification on limited-label internal and external datasets versus scratch-trained and prior models.