paper-with-me

Papers

Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields

2019-04-25 · Evan Shelhamer, Dequan Wang, Trevor Darrell

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.

📄 PDF Abstract BibTeX arXiv:1904.11487

Code (0)

등록된 구현이 없습니다.

Tasks

FormSemantic Segmentation

Similar Papers 제목 키워드 기반

Towards Efficient Image Deblurring for Edge Deployment

2026-01-16 · Srinivas Miriyala, Sowmya Vajrala, Sravanth Kodavanti arxiv

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 Deblurring

ALANET: Adaptive Latent Attention Network forJoint Video Deblurring and Interpolation

2020-08-31 · Akash Gupta, Abhishek Aich, Amit K. Roy-Chowdhury

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 Deblurring

Blurring Structure and Learning to Optimize and Adapt Receptive Fields

2019-09-25 · Evan Shelhamer, Dequan Wang, Trevor Darrell

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 Segmentation

Semantic-aware Image Deblurring

2019-10-09 · Fuhai Chen, Rongrong Ji, Chengpeng Dai, Xiaoshuai Sun 외

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 Deblurring

Controlling sharpness, SNR and SAR for 3D FSE at 7T by end-to-end learning

2024-09-30 · Peter Dawood, Martin Blaimer, Jürgen Herrler, Patrick Liebig 외

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…