Pith. sign in

REVIEW 1 cited by

Semi-Supervised Learning with Taxonomic Labels

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 2111.11595 v1 pith:AMYNEOKT submitted 2021-11-23 cs.CV cs.LG

classification cs.CVcs.LG
keywords labelslearningdomainsfine-grainedimprovessemi-supervisedtaxonomicclassifiers
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are organized according to a biological taxonomy. On the Semi-iNat dataset consisting of 810 species across three Kingdoms, incorporating Phylum labels improves the Species level classification accuracy by 6% in a transfer learning setting using ImageNet pre-trained models. Incorporating the hierarchical label structure with a state-of-the-art semi-supervised learning algorithm called FixMatch improves the performance further by 1.3%. The relative gains are larger when detailed labels such as Class or Order are provided, or when models are trained from scratch. However, we find that most methods are not robust to the presence of out-of-domain data from novel classes. We propose a technique to select relevant data from a large collection of unlabeled images guided by the hierarchy which improves the robustness. Overall, our experiments show that semi-supervised learning with coarse taxonomic labels are practical for training classifiers in fine-grained domains.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Global and Local Entailment Learning for Natural World Imagery

    cs.CV 2025-06 conditional novelty 6.0 of 10

    RCME enforces a transitivity constraint in radial embeddings, producing a hierarchical vision-language model that orders taxonomic labels better and improves hierarchical classification and retrieval.

Pith tools