Pith. sign in

REVIEW 3 cited by

A Baseline for Few-Shot Image Classification

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 1909.02729 v5 pith:AEGWUFGX submitted 2019-09-06 cs.LG cs.CVstat.ML

Guneet S. Dhillon , Pratik Chaudhari , Avinash Ravichandran , Stefano Soatto This is my paper · ORCID
classification cs.LGcs.CVstat.ML
keywords few-shotlearningresultsapproachbaselineclassescurrentdatasets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approach as the solution for few-shot learning, but simply use the results to highlight limitations of current benchmarks and few-shot protocols. We perform extensive studies on benchmark datasets to propose a metric that quantifies the "hardness" of a few-shot episode. This metric can be used to report the performance of few-shot algorithms in a more systematic way.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. 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.

  2. Uncertainty-Driven Hierarchical Sampling for Unbalanced Continual Malware Detection with Time-Series Update-Based Retrieval

    cs.CE 2025-09 conditional novelty 4.0 of 10

    UGSR uses hierarchical uncertainty sampling plus codebook retrieval to improve continual Android malware detection under class imbalance and concept drift.

  3. Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation

    cs.LG 2025-07 conditional novelty 3.0 of 10

    FedAcross+ couples prototype-based few-shot adaptation with stream sampling on federated clients, but the experiments validate only the static configuration carried over from the authors' prior FedAcross work.

Pith tools