Methods › General › Knowledge Distillation › STD

Spatial-Channel Token Distillation

STD

32 papers tagged archive 2025-07-28

Introduced by Yanxi Li et al. in Spatial-Channel Token Distillation for Vision MLPs

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

The Spatial-Channel Token Distillation method is proposed to improve the spatial and channel mixing from a novel knowledge distillation (KD) perspective. To be specific, we design a special KD mechanism for MLP-like Vision Models called Spatial-channel Token Distillation (STD), which improves the information mixing in both the spatial and channel dimensions of MLP blocks. Instead of modifying the mixing operations themselves, STD adds spatial and channel tokens to image patches. After forward propagation, the tokens are concatenated for distillation with the teachers’ responses as targets. Each token works as an aggregator of its dimension. The objective of them is to encourage each mixing operation to extract maximal task-related information from their specific dimension.

PaperSource

Papers archive 2025-07-28

30 shown of 32, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 56 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Pose Estimation3
3D Place Recognition2
Alzheimer's Disease Detection2
Language Modelling2
Prompt Learning2
Scene Text Detection2
Self-Supervised Learning2
Text Detection2
Adversarial Robustness1
Automatic Speech Recognition1
Automatic Speech Recognition (ASR)1
Deep Learning1
Depression Detection1
Depth Completion1
Depth Estimation1
Depth Prediction1
Document Shadow Removal1
Drift Detection1
Face Recognition1
Fairness1

Usage over time archive 2025-07-28

Papers per year tagged with STD: 2022 to 2025, peak 10 10 0 2022: 8 papers 2022 2023: 6 papers 2023 2024: 10 papers 2024 2025: 8 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (32 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Knowledge Distillation

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