Papers › Training Noise Token Pruning

Training Noise Token Pruning

27 Nov 2024arXiv:2411.18092archive 2025-07-28

Mingxing Rao, Bohan Jiang, Daniel Moyer

In the present work we present Training Noise Token (TNT) Pruning for vision transformers. Our method relaxes the discrete token dropping condition to continuous additive noise, providing smooth optimization in training, while retaining discrete dropping computational gains in deployment settings. We provide theoretical connections to Rate-Distortion literature, and empirical evaluations on the ImageNet dataset using ViT and DeiT architectures demonstrating TNT's advantages over previous pruning methods.

PaperPDFCode

Code

mx-ethan-rao/tnt officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionAttention DropoutDeiTDense ConnectionsDropoutFeedforward NetworkLinear LayerMulti-Head AttentionPruningSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections