Methods › General › Regularization › DropPathway
DropPathway
Introduced by Fanyi Xiao et al. in Audiovisual SlowFast Networks for Video Recognition
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
DropPathway randomly drops an audio pathway during training as a regularization technique for audiovisual recognition models. Specifically, at each training iteration, we drop the Audio pathway altogether with probability P_d. This way, we slow down the learning of the Audio pathway and make its learning dynamics more compatible with its visual counterpart. When dropping the audio pathway, we sum zero tensors with the visual pathways.
Note that DropPathway is different from simply setting different learning rates for the audio/visual pathways in that it 1) ensures the audio pathway has fewer parameter updates, 2) hinders the visual pathway to 'shortcut' training by memorizing audio information, and 3) provides extra regularization as different audio clips are dropped in each epoch.
Papers archive 2025-07-28
1 shown of 1, 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.
-
Audiovisual SlowFast Networks for Video Recognition 23 Jan 2020 · 3 repositories · arXiv:2001.08740
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Action Classification | 1 |
| Video Recognition | 1 |
Usage over time archive 2025-07-28
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
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