Phase Marginalization for Patch-Grid Instability in Vision Transformers
Summary
Phase Marginalization is a post-hoc method that addresses phase-dependent instability in Vision Transformers by evaluating structured patch-grid phases and aggregating outputs. It improves segmentation, depth, and local matching over the canonical baseline with minimal extra cost.
View Cached Full Text
Cached at: 06/10/26, 12:13 AM
Paper page - Phase Marginalization for Patch-Grid Instability in Vision Transformers
Source: https://huggingface.co/papers/2606.08132
Abstract
Phase Marginalization is a post-hoc method that addresses phase-dependent instability in Vision Transformers by evaluating structured patch-grid phases and aggregating outputs in the original image coordinate system.
Vision Transformersoperate on fixedpatch grids, which can introducephase-dependent instabilityfordense prediction: changing the patch partition can change the token evidence available to a pixel, especially near boundaries. We formalizepatch-grid phaseas a nuisance variable and proposePhase Marginalization, a post-hoc marginalization method that evaluatesstructured patch-grid phases,inverse-alignsdense outputs, and aggregates them in the originalimage coordinate system. The central variant, UniformPhase Marginalizationwith K = 4, is training-free and improves over the canonical K = 1 baseline across measuredsegmentation, depth, andlocal matchingsettings. In a controlledCityscapesexperiment, UniformPhase Marginalizationprovides a modest compute-matched advantage over generic shift-based four-forwardtest-time augmentation(TTA) (+0.31 meanIntersection-over-Unionover the strongest tested generic row). A scaling study further shows that K = 4 is a practical cost-accuracy trade-off: K = 8 is essentially unchanged and K = 16 adds little accuracy at much higher latency. These results positionpatch-grid phaseas a measurable nuisance variable andPhase Marginalizationas a simple diagnostic and post-hoc marginalization baseline for dense ViT prediction.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2606\.08132
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.08132 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.08132 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.08132 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
ResilPhase is a training-free acceleration framework for diffusion models that reformulates accelerated inference as stable macro-trajectory extrapolation in ODE space, using derivative-free barycentric Lagrange extrapolation and bounded phase mapping to achieve state-of-the-art fidelity under high acceleration ratios.
Variable-Width Transformers
Proposes a nonuniform width allocation transformer (hourglass shape) that outperforms uniform baselines in language modeling, reducing FLOPs and KV cache size.
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT presents a minimalist pixel-space diffusion transformer using a plain ViT architecture for monocular geometry estimation, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.
Patch-PODiff-ViT: Structured Latent Diffusion with Patchwise POD for Super-Resolution and Uncertainty Quantification
Patch-PODiff-ViT introduces a structured latent diffusion framework using patchwise Proper Orthogonal Decomposition (POD) for super-resolution and uncertainty quantification, enabling efficient diffusion with a fixed linear orthonormal basis and analytic propagation of predictive variance.
Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback
This paper introduces Structured Defect Grounding (SDG), a method that models text-to-image defects as structured (location, type, reason, importance) tuples and uses VLMs for detection, along with a 30K-image dataset SDG-30K and a diagnosis-to-alignment framework called BoxFlow-GRPO.