Pith. sign in

REVIEW 11 cited by

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.04623 v2 pith:ER37RR3N submitted 2019-11-12 cs.CV

SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning

Yan Wang , Wei-Lun Chao , Kilian Q. Weinberger , Laurens van der Maaten This is my paper
classification cs.CV
keywords few-shotnearest-neighborclassificationclassifierfindlearnerslearningmeta-learning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization outperforms prior results in three out of five settings on the miniImageNet dataset.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. Unlocking Compositional Generalization in Continual Few-Shot Learning

    cs.LG 2026-05 unverdicted novelty 7.0

    A dual-phase framework using self-supervised ViT slots optimizes representations for class identity during training and composes them dynamically at inference to achieve state-of-the-art generalization to unseen conce...

  2. Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects

    cs.CR 2026-04 unverdicted novelty 7.0

    Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.

  3. Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation

    cs.CV 2026-03 unverdicted novelty 7.0

    DREAM introduces Masking Warmup and Semantically Aligned Decoding to let a single encoder handle both contrastive alignment and masked generation, yielding gains over CLIP and FLUID on understanding and generation benchmarks.

  4. Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    Mochi aligns pre-training with inference via meta-learning for efficient graph foundation models, matching or exceeding prior models on 25 datasets with 8-27x less training time.

  5. Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects

    cs.CR 2026-04 unverdicted novelty 6.0

    Injecting a few vectors near the embedding-space centroid can make them appear in top-k results for up to 94.4% of queries via centrality-driven hubness.

  6. Unlocking Compositional Generalization in Continual Few-Shot Learning

    cs.LG 2026-05 unverdicted novelty 5.0

    A decoupling strategy optimizes object slots for holistic class identity during training and composes them at inference to achieve better generalization to unseen concepts in continual few-shot settings.

  7. Self-Supervised Learning of Plant Image Representations

    cs.CV 2026-04 unverdicted novelty 5.0

    Domain-specific augmentations and plant-only training data produce stronger self-supervised representations for fine-grained plant recognition than standard SSL pipelines or ImageNet pretraining.

  8. Self-Supervised Learning of Plant Image Representations

    cs.CV 2026-04 unverdicted novelty 5.0

    Domain-adapted augmentations and plant-specific training data improve self-supervised representations for fine-grained plant species recognition over standard SSL pipelines.

  9. Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net

    cs.CV 2025-10 conditional novelty 5.0

    ABHFA-Net is a novel few-shot classification framework that models prototypes as distributions, applies spatial-channel attention, and uses Bhattacharyya-based contrastive loss, achieving state-of-the-art accuracies o...

  10. 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.

  11. Few-Shot Learning Pipeline for Monkeypox Skin Disease Classification Using CNN Feature Extractors

    cs.CV 2026-05 unverdicted novelty 4.0

    A few-shot learning framework using frozen CNN backbones and SimpleShot achieves competitive accuracy for Monkeypox and pox-like skin disease classification on public datasets across 2/4/6-way 1/5/10-shot tasks, with ...