Pith. sign in

Big self-supervised mod- els are strong semi-supervised learners.Advances in neural information processing systems, 33:22243–22255, 2020

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

Aligned Contrastive Loss for Long-Tailed Recognition

cs.CV · 2025-06-01 · conditional · novelty 5.0

ACL modifies supervised contrastive loss by removing non-effective positives from the denominator, adding class centers, and re-weighting negatives by inverse class frequency, yielding new state-of-the-art accuracy on four long-tailed benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Aligned Contrastive Loss for Long-Tailed Recognition cs.CV · 2025-06-01 · conditional · none · ref 5

    ACL modifies supervised contrastive loss by removing non-effective positives from the denominator, adding class centers, and re-weighting negatives by inverse class frequency, yielding new state-of-the-art accuracy on four long-tailed benchmarks.