MViT: A vision transformer with fractal path reordering and dynamic positional encoding
Bomin Liu, Linjun He, Yan Zhu, Anil Yaman, Anil Yaman, Anil Yaman, Anil Yaman
TL;DR
MViT is a new Vision Transformer that improves spatial coherence and structural adaptability using fractal path reordering and dynamic positional encoding.
Contribution
The novel use of a recursive Moore curve and fractal-based components to enhance spatial continuity and structural modeling in Vision Transformers.
Findings
MViT improves classification accuracy by 0.52% on CIFAR-100 and 0.31% on ImageNet-21k compared to ViT-B/16.
The model achieves better PSNR and SSIM scores, indicating improved structural representation.
MViT shows robustness to rotation and maintains performance across different Transformer backbones and tasks.
Abstract
Vision Transformers have demonstrated remarkable performance in image classification and structural modeling; however, fixed patch partitioning and static positional encoding often disrupt spatial continuity, thereby limiting their ability to represent rotated structures and irregular boundary regions. To address these limitations, we propose the Moore-curve Vision Transformer (MViT), a Vision Transformer (ViT) framework based on a recursive Moore curve. The proposed framework comprises three key components. First, a multi-order fractal mapping is employed to optimize patch reordering and enhance the spatial coherence of the token sequence. Second, a 7×7 dynamic partitioning template together with a boundary compensation algorithm jointly optimizes dense structural representation and resolution adaptability. Third, a period-aware positional encoding module integrates fractal periodic…
Genes, proteins, chemicals, diseases, species, mutations and cell lines named across the full text — each resolved to its canonical identifier and authoritative record.
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Figure 23
Figure 24
Figure 25
Figure 26
Figure 27
Figure 28
Figure 29
Figure 30
Figure 31
Figure 32
Figure 33
Figure 34
Figure 35
Figure 36
Figure 37
Figure 38
Figure 39
Figure 40
Figure 41
Figure 42
Figure 43
Figure 44
Figure 45
Figure 46
Figure 47
Figure 48
Figure 49
Figure 50Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Face Recognition and Perception · Advanced Optical Imaging Technologies