paper-with-me

홈 › Papers

Exploiting Convolution Filter Patterns for Transfer Learning

2017-08-23 · Mehmet Aygün, Yusuf Aytar, Hazim Kemal Ekenel

In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters learned from a well-trained network and transfer this knowledge to another network. Since convolution filters of the prevalent deep Convolutional Neural Network (CNN) models share a number of similar patterns, in order to speed up the learning procedure, we capture such correlations by Gaussian Mixture Models (GMMs) and transfer them using a regularization term. We have conducted extensive experiments on the CIFAR10, Places2, and CMPlaces datasets to assess generalizability, task transferability, and cross-model transferability of the proposed approach, respectively. The experimental results show that the feature representations have efficiently been learned and transferred through the proposed statistical regularization scheme. Moreover, our method is an architecture independent approach, which is applicable for a variety of CNN architectures.

📄 PDF Abstract BibTeX arXiv:1708.06973

Code (0)

등록된 구현이 없습니다.

Tasks

Transfer Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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…

Similar Papers 제목 키워드 기반

Learning with Multigraph Convolutional Filters

2022-10-28 · Landon Butler, Alejandro Parada-Mayorga, Alejandro Ribeiro

In this paper, we introduce a convolutional architecture to perform learning when information is supported on multigraphs. Exploiting algebraic signal processing (ASP), we propose a convolutional signal processing model …

The Master Key Filters Hypothesis: Deep Filters Are General

2024-12-21 · Zahra Babaiee, Peyman M. Kiasari, Daniela Rus, Radu Grosu

This paper challenges the prevailing view that convolutional neural network (CNN) filters become increasingly specialized in deeper layers. Motivated by recent observations of clusterable repeating patterns in depthwise …

Transfer Learning

SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images

2018-09-01 · ECCV 2018 9 · Benjamin Coors, Alexandru Paul Condurache, Andreas Geiger

Omnidirectional cameras offer great benefits over classical cameras wherever a wide field of view is essential, such as in virtual reality applications or in autonomous robots. Unfortunately, standard convolutional neura…

General Classificationimage-classificationImage Classificationobject-detection+1

Transfer learning RGB models to hyperspectral images with trainable tensor decompositions

2026-05-27 · Mariette Schönfeld, Laurens Devos, Wannes Meert, Hendrik Blockeel arxiv

Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channe…

Transfer Learning

The Quest for Universal Master Key Filters in DS-CNNs

2025-09-15 · Zahra Babaiee, Peyman M. Kiassari, Daniela Rus, Radu Grosu arxiv

A recent study has proposed the "Master Key Filters Hypothesis" for convolutional neural network filters. This paper extends this hypothesis by radically constraining its scope to a single set of just 8 universal filters…

Transfer Learning