paper-with-me

Papers

Kernel Modulation: A Parameter-Efficient Method for Training Convolutional Neural Networks

2022-03-29 · Yuhuang Hu, Shih-Chii Liu

Deep Neural Networks, particularly Convolutional Neural Networks (ConvNets), have achieved incredible success in many vision tasks, but they usually require millions of parameters for good accuracy performance. With increasing applications that use ConvNets, updating hundreds of networks for multiple tasks on an embedded device can be costly in terms of memory, bandwidth, and energy. Approaches to reduce this cost include model compression and parameter-efficient models that adapt a subset of network layers for each new task. This work proposes a novel parameter-efficient kernel modulation (KM) method that adapts all parameters of a base network instead of a subset of layers. KM uses lightweight task-specialized kernel modulators that require only an additional 1.4% of the base network parameters. With multiple tasks, only the task-specialized KM weights are communicated and stored on the end-user device. We applied this method in training ConvNets for Transfer Learning and Meta-Learning scenarios. Our results show that KM delivers up to 9% higher accuracy than other parameter-efficient methods on the Transfer Learning benchmark.

📄 PDF Abstract BibTeX arXiv:2203.15297

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningModel CompressionTransfer Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

KernelDNA: Dynamic Kernel Sharing via Decoupled Naive Adapters

2025-03-30 · Haiduo Huang, Yadong Zhang, Pengju Ren

Dynamic convolution enhances model capacity by adaptively combining multiple kernels, yet faces critical trade-offs: prior works either (1) incur significant parameter overhead by scaling kernel numbers linearly, (2) com…

Computational Efficiencyimage-classificationImage Classification

Image-specific Convolutional Kernel Modulation for Single Image Super-resolution

2021-11-16 · Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao 외

Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples. Yet intuitively, each image has its…

Image Super-ResolutionSuper-Resolution

Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning

2026-03-22 · Shih-Wen Liu, Yen-Chang Chen, Wei-Ta Chu, Fu-En Yang 외 arxiv

Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; however, current parameter-efficient fine-tuning (PEFT) methods remain largely limited to single-task adaptation. We introduce …

parameter-efficient fine-tuningMulti-Task Learning

Rep3D: Re-parameterize Large 3D Kernels with Low-Rank Receptive Modeling for Medical Imaging

2025-05-26 · Ho Hin Lee, Quan Liu, Shunxing Bao, Yuankai Huo 외

In contrast to vision transformers, which model long-range dependencies through global self-attention, large kernel convolutions provide a more efficient and scalable alternative, particularly in high-resolution 3D volum…

Inductive BiasMedical Image Analysis

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

2021-10-15 · ICLR 2022 4 · David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak, Erik J. Bekkers 외

When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but explor…

DescriptiveImage ClassificationSequential Image ClassificationTime Series Analysis