One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
reViT 以單一 Transformer 區塊循環運作,並用小型共享專家庫的凸組合,恢復不同深度的 FFN 變換;在相若推理 FLOPs 下,其準確度可媲美完整深度的視覺編碼器,且不需中間特徵蒸餾。
Published on Oct 8
Authors:
,
Abstract
In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transformations by representing the FFN at each recurrent depth as a convex combination of a small shared expert bank. A continuous normalized-depth coordinate programs this mixture, defining a resampleable trajectory through FFN parameter space. We evaluate this design in two regimes: supervised ImageNet-1k training and distillation from a DINOv2 teacher. Across both regimes, controlled adaptations identify weight-space merging as the strongest tested MoE family at a matching one-FFN budget, ahead of the token-dispatch and output-mixture alternatives. Trained from scratch, reViT-B/16 attains DeiT III accuracy with about 70\% fewer stored parameters. An 8-experts model distilled using only the teacher's output features retains nearly all of its DINOv2 teacher's linear-probe accuracy and transfers across classification, segmentation, and depth prediction. Elastic-depth training allows one checkpoint (trained model) to operate at multiple tested depths by resampling the same normalized coordinate interval. For fixed-depth deployment, the recurrent block can be materialized as a conventional dense graph, removing online routing and merging without changing the one-FFN-per-depth compute but expanding deployment storage.
View arXiv page View PDF Project page Add to collection
Get this paper in your agent:
hf papers read 2610.12448
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.12448 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.12448 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.12448 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co