Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Compress image to patches for Vision Transformer

cs.CV · 2025-02-14 · conditional · novelty 5.0

Using a frozen learned-compression encoder as the ViT patch embedder yields a 4x token reduction and 63% FLOP savings, with accuracy gains shown only on one small dataset.

citing papers explorer

Showing 1 of 1 citing paper.

  • Compress image to patches for Vision Transformer cs.CV · 2025-02-14 · conditional · none · ref 1

    Using a frozen learned-compression encoder as the ViT patch embedder yields a 4x token reduction and 63% FLOP savings, with accuracy gains shown only on one small dataset.