paper-with-me

Papers

Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement

2025-02-27 · Nan An, Long Ma, Guangchao Han, Xin Fan, Risheng Liu

Deep learning-based low-light image enhancers have made significant progress in recent years, with a trend towards achieving satisfactory visual quality while gradually reducing the number of parameters and improving computational efficiency. In this work, we aim to delving into the limits of image enhancers both from visual quality and computational efficiency, while striving for both better performance and faster processing. To be concrete, by rethinking the task demands, we build an explicit connection, i.e., visual quality and computational efficiency are corresponding to model learning and structure design, respectively. Around this connection, we enlarge parameter space by introducing the re-parameterization for ample model learning of a pre-defined minimalist network (e.g., just one layer), to avoid falling into a local solution. To strengthen the structural representation, we define a hierarchical search scheme for discovering a task-oriented re-parameterized structure, which also provides powerful support for efficiency. Ultimately, this achieves efficient low-light image enhancement using only a single convolutional layer, while maintaining excellent visual quality. Experimental results show our sensible superiority both in quality and efficiency against recently-proposed methods. Especially, our running time on various platforms (e.g., CPU, GPU, NPU, DSP) consistently moves beyond the existing fastest scheme. The source code will be released at https://github.com/vis-opt-group/AR-LLIE.

📄 PDF Abstract BibTeX arXiv:2502.19867

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyCPUGPUImage EnhancementLow-Light Image Enhancement

Similar Papers 제목 키워드 기반

Self-Distilled Self-Supervised Representation Learning

2021-11-25 · Jiho Jang, Seonhoon Kim, KiYoon Yoo, Chaerin Kong 외

State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost compared to conventional CNN models. Striving to maximize the mutual…

Linear evaluationRepresentation LearningSelf-Supervised Learning

Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections

2021-08-18 · Taewoon Kim

A multilayer perceptron (MLP) is typically made of multiple fully connected layers with nonlinear activation functions. There have been several approaches to make them better (e.g. faster convergence, better convergence …

Age And Gender ClassificationAge EstimationGender Prediction

Striving for Simplicity: The All Convolutional Net

2014-12-21 · Jost Tobias Springenberg, Alexey Dosovitskiy, Thomas Brox, Martin Riedmiller

Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re…

AllImage ClassificationObjectObject Recognition

Fast Feedforward Networks

2023-08-28 · Peter Belcak, Roger Wattenhofer

We break the linear link between the layer size and its inference cost by introducing the fast feedforward (FFF) architecture, a log-time alternative to feedforward networks. We demonstrate that FFFs are up to 220x faste…

Mixture-of-Experts

Leveraging Batch Normalization for Vision Transformers

2021-01-01 · ICCVW 2021 1 · Zhuliang Yao, Yue Cao, Yutong Lin, Ze Liu 외

Transformer-based vision architectures have attracted great attention because of the strong performance over the convolutional neural networks (CNNs). Inherited from the NLP tasks, the architectures take Layer Normalizat…