paper-with-me

Papers

Deformably-Scaled Transposed Convolution

2022-10-17 · Stefano B. Blumberg, Daniele Raví, Mou-Cheng Xu, Matteo Figini, Iasonas Kokkinos, Daniel C. Alexander

Transposed convolution is crucial for generating high-resolution outputs, yet has received little attention compared to convolution layers. In this work we revisit transposed convolution and introduce a novel layer that allows us to place information in the image selectively and choose the `stroke breadth' at which the image is synthesized, whilst incurring a small additional parameter cost. For this we introduce three ideas: firstly, we regress offsets to the positions where the transpose convolution results are placed; secondly we broadcast the offset weight locations over a learnable neighborhood; and thirdly we use a compact parametrization to share weights and restrict offsets. We show that simply substituting upsampling operators with our novel layer produces substantial improvements across tasks as diverse as instance segmentation, object detection, semantic segmentation, generative image modeling, and 3D magnetic resonance image enhancement, while outperforming all existing variants of transposed convolutions. Our novel layer can be used as a drop-in replacement for 2D and 3D upsampling operators and the code will be publicly available.

📄 PDF Abstract BibTeX arXiv:2210.09446

Code (0)

등록된 구현이 없습니다.

Tasks

Image EnhancementInstance Segmentationobject-detectionObject DetectionSemantic Segmentation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Transposed convolution 설명 없음

Similar Papers 제목 키워드 기반

Efficient Accelerator for Dilated and Transposed Convolution with Decomposition

2022-05-02 · Kuo-Wei Chang, Tian-Sheuan Chang

Hardware acceleration for dilated and transposed convolution enables real time execution of related tasks like segmentation, but current designs are specific for these convolutional types or suffer from complex control f…

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

2020-07-14 · Guilin Liu, Rohan Taori, Ting-Chun Wang, Zhiding Yu 외

Conventional CNNs for texture synthesis consist of a sequence of (de)-convolution and up/down-sampling layers, where each layer operates locally and lacks the ability to capture the long-term structural dependency requir…

Texture Synthesis

A guide to convolution arithmetic for deep learning

2016-03-23 · Vincent Dumoulin, Francesco Visin

We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, z…

Deep Learning

DTC: A Deformable Transposed Convolution Module for Medical Image Segmentation

2026-01-25 · Chengkun Sun, Jinqian Pan, Renjie Liang, Zhengkang Fan 외 arxiv

In medical image segmentation, particularly in UNet-like architectures, upsampling is primarily used to transform smaller feature maps into larger ones, enabling feature fusion between encoder and decoder features and su…

Medical Image Segmentation

Transition Matrix Representation of Trees with Transposed Convolutions

2022-02-22 · Jaemin Yoo, Lee Sael

How can we effectively find the best structures in tree models? Tree models have been favored over complex black box models in domains where interpretability is crucial for making irreversible decisions. However, searchi…