Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields
The visual world is vast and varied, but its variations divide into structured and unstructured factors. We compose free-form filters and structured Gaussian filters, optimized end-to-end, to factorize deep representations and learn both local features and their degree of locality. Our semi-structured composition is strictly more expressive than free-form filtering, and changes in its structured parameters would require changes in free-form architecture. In effect this optimizes over receptive field size and shape, tuning locality to the data and task. Dynamic inference, in which the Gaussian structure varies with the input, adapts receptive field size to compensate for local scale variation. Optimizing receptive field size improves semantic segmentation accuracy on Cityscapes by 1-2 points for strong dilated and skip architectures and by up to 10 points for suboptimal designs. Adapting receptive fields by dynamic Gaussian structure further improves results, equaling the accuracy of free-form deformation while improving efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
FormSemantic SegmentationSimilar Papers 제목 키워드 기반
Towards Efficient Image Deblurring for Edge Deployment
Image deblurring is a critical stage in mobile image signal processing pipelines, where the ability to restore fine structures and textures must be balanced with real-time constraints on edge devices. While recent deep n…
Image DeblurringALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation
Existing works address the problem of generating high frame-rate sharp videos by separately learning the frame deblurring and frame interpolation modules. Most of these approaches have a strong prior assumption that all …
DeblurringVideo DeblurringBlurring Structure and Learning to Optimize and Adapt Receptive Fields
The visual world is vast and varied, but its variations divide into structured and unstructured factors. We compose free-form filters and structured Gaussian filters, optimized end-to-end, to factorize deep representatio…
FormSemantic SegmentationSemantic-aware Image Deblurring
Image deblurring has achieved exciting progress in recent years. However, traditional methods fail to deblur severely blurred images, where semantic contents appears ambiguously. In this paper, we conduct image deblurrin…
DeblurringImage CaptioningImage DeblurringControlling sharpness, SNR and SAR for 3D FSE at 7T by end-to-end learning
Purpose: To non-heuristically identify dedicated variable flip angle (VFA) schemes optimized for the point-spread function (PSF) and signal-to-noise ratio (SNR) of multiple tissues in 3D FSE sequences with very long echo…