Pith. sign in

REVIEW 8 cited by

A Closer Look at Few-shot Classification

Not yet reviewed by Pith; the record is open.

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 1904.04232 v2 pith:OCZBWQUU submitted 2019-04-08 cs.CV

classification cs.CV
keywords few-shotalgorithmsclassificationdifferenceswhenbackbonesbaselinecross-domain
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the \miniI and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting

    cs.CV 2025-07 conditional novelty 7.0 of 10

    Unlearning benchmark classes from CLIP creates a fairer few-shot test, on which most existing CLIP methods lose over half their accuracy, but the new method SEPRES remains strong.

  2. Language-Aware Information Maximization for Transductive Few-Shot CLIP

    cs.CV 2025-08 conditional novelty 5.0 of 10

    LIMO, a transductive loss combining mutual information, zero-shot KL regularization, and LoRA, sets new state-of-the-art few-shot accuracy for CLIP on 11 datasets.

  3. Advancing Medical Image Segmentation via Self-supervised Instance-adaptive Prototype Learning

    stat.ME 2025-07 conditional novelty 5.0 of 10

    SIPL fuses common and instance-specific prototype proposals and reports the best mean Dice scores on BTCV, Lungs, and BraTS benchmarks.

  4. Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track

    cs.LG 2025-06 conditional novelty 5.0 of 10

    ML conferences should create an official peer-reviewed track dedicated to refuting and critiquing previously published work.

  5. A Discrepancy-Based Perspective on Dataset Condensation

    cs.LG 2025-09 conditional novelty 4.0 of 10

    Dataset condensation is reframed as minimizing distribution discrepancies, and existing methods are sorted into a taxonomy; no new algorithm or experiments are provided.

  6. Object-Centric Cropping for Visual Few-Shot Classification

    cs.CV 2025-07 unverdicted novelty 4.0 of 10

    The supplied full text (arXiv:2508.00225) is a different paper from the claimed metadata (arXiv:2508.00218), so no claim about few-shot classification is backed by the manuscript.

  7. DExNet: Combining Observations of Domain Adapted Critics for Leaf Disease Classification with Limited Data

    cs.CV 2025-06 reject novelty 4.0 of 10

    A few-shot pipeline that fuses features from nine domain-adapted CNN critics and classifies via Bi-LSTM reaches 98.09% on 80-shot tomato leaf disease classification.

  8. Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A meta-learning dissertation showing that distributed memory and hypernetworks can adapt to new tasks with few samples, applied to image classification, text-to-3D generation, and molecular binding prediction, with th...

Pith tools