Pith. sign in

Class-weighted classification: Trade-offs and robust approaches

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels

cs.CV · 2025-08-29 · conditional · novelty 4.0

ICPL generates pseudo-labels by clustering embeddings with KMeans, keeps only confident ones, and uses them to train class-incremental models without human labels, losing about 10 points versus supervised CIL but beating class-iNCD baselines by more than 5.

citing papers explorer

Showing 1 of 1 citing paper.

  • Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels cs.CV · 2025-08-29 · conditional · none · ref 48

    ICPL generates pseudo-labels by clustering embeddings with KMeans, keeps only confident ones, and uses them to train class-incremental models without human labels, losing about 10 points versus supervised CIL but beating class-iNCD baselines by more than 5.