Pith. sign in

REVIEW 3 cited by

The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop

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 2103.06937 v1 pith:FZDAC3NT submitted 2021-03-11 cs.CV cs.LG

Jong-Chyi Su , Subhransu Maji This is my paper · ORCID
classification cs.CVcs.LG
keywords classesdatasetimagessemi-supervisedchallengefgvc7recognitionworkshop
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This document describes the details and the motivation behind a new dataset we collected for the semi-supervised recognition challenge~\cite{semi-aves} at the FGVC7 workshop at CVPR 2020. The dataset contains 1000 species of birds sampled from the iNat-2018 dataset for a total of nearly 150k images. From this collection, we sample a subset of classes and their labels, while adding the images from the remaining classes to the unlabeled set of images. The presence of out-of-domain data (novel classes), high class-imbalance, and fine-grained similarity between classes poses significant challenges for existing semi-supervised recognition techniques in the literature. The dataset is available here: \url{https://github.com/cvl-umass/semi-inat-2020}

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. Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Flat VLM softmax scores make standard semi-supervised pseudo-labeling never fire; temperature sharpening fixes the failure and, combined with retrieved open data and stage-wise training, yields state-of-the-art few-sh...

  2. Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors

    cs.LG 2025-12 conditional novelty 5.0 of 10

    LMMs underperform few-shot experts on species recognition, but re-ranking the expert's top-5 candidates with an LMM improves mean accuracy by 6.4 points across five benchmarks.

  3. Active Learning via Vision-Language Model Adaptation with Open Data

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ALOR combines retrieval-augmented open data, contrastive finetuning of a VLM, and tail-first sampling to improve active learning accuracy on five image benchmarks.

Pith tools