Papers › DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Transformer and Mamba

DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Transformer and Mamba

12 Jun 2025arXiv:2506.10390archive 2025-07-28

Shicheng Yin, Kaixuan Yin, Yang Liu, Weixing Chen, Liang Lin

Recently, non-convolutional models such as the Vision Transformer (ViT) and Vision Mamba (Vim) have achieved remarkable performance in computer vision tasks. However, their reliance on fixed-size patches often results in excessive encoding of background regions and omission of critical local details, especially when informative objects are sparsely distributed. To address this, we introduce a fully differentiable Dynamic Adaptive Region Tokenizer (DART), which adaptively partitions images into content-dependent patches of varying sizes. DART combines learnable region scores with piecewise differentiable quantile operations to allocate denser tokens to information-rich areas. Despite introducing only approximately 1 million (1M) additional parameters, DART improves accuracy by 2.1% on DeiT (ImageNet-1K). Unlike methods that uniformly increase token density to capture fine-grained details, DART offers a more efficient alternative, achieving 45% FLOPs reduction with superior performance. Extensive experiments on DeiT, Vim, and VideoMamba confirm that DART consistently enhances accuracy while incurring minimal or even reduced computational overhead. Code is available at https://github.com/HCPLab-SYSU/DART.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

hcplab-sysu/dart officialmentioned in paperpytorch 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.

Tasks

Mamba

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAttentionAttention DropoutBPEDARTDeiTDense ConnectionsDropoutFeedforward NetworkLabel SmoothingLayer NormalizationLinear LayerMambaMulti-Head AttentionSoftmaxTransformerVision Transformer

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