paper-with-me

Papers

Compressive Feature Selection for Remote Visual Multi-Task Inference

2024-05-15 · Saeed Ranjbar Alvar, Ivan V. Bajić

Deep models produce a number of features in each internal layer. A key problem in applications such as feature compression for remote inference is determining how important each feature is for the task(s) performed by the model. The problem is especially challenging in the case of multi-task inference, where the same feature may carry different importance for different tasks. In this paper, we examine how effective is mutual information (MI) between a feature and a model's task output as a measure of the feature's importance for that task. Experiments involving hard selection and soft selection (unequal compression) based on MI are carried out to compare the MI-based method with alternative approaches. Multi-objective analysis is provided to offer further insight.

📄 PDF Abstract BibTeX arXiv:2405.09077

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Compressionfeature selection

Similar Papers 제목 키워드 기반

Remote Multilinear Compressive Learning with Adaptive Compression

2021-09-02 · Dat Thanh Tran, Moncef Gabbouj, Alexandros Iosifidis

Multilinear Compressive Learning (MCL) is an efficient signal acquisition and learning paradigm for multidimensional signals. The level of signal compression affects the detection or classification performance of a MCL m…

Compressive Sensing

Feature Fusion via Multiresolution Compressive Measurement Matrix Analysis For Spectral Image Classification

2020-09-15 · Juan Marcos Ramirez, Jose Ignacio Martinez-Torre, Henry Arguello

In the compressive spectral imaging (CSI) framework, different architectures have been proposed to recover high-resolution spectral images from compressive measurements. Since CSI architectures compactly capture the rele…

Classificationimage-classificationImage Classification

Compressive Sampling Using a Pushframe Camera

2021-04-27 · Stuart Bennett, Yoann Noblet, Paul F. Griffin, Paul Murray 외

The recently described pushframe imager, a parallelized single pixel camera capturing with a pushbroom-like motion, is intrinsically suited to both remote-sensing and compressive sampling. It optically applies a 2D mask …

Compressive Regularized Discriminant Analysis of High-Dimensional Data with Applications to Microarray Studies

2018-04-11 · Muhammad Naveed Tabassum, Esa Ollila

We propose a modification of linear discriminant analysis, referred to as compressive regularized discriminant analysis (CRDA), for analysis of high-dimensional datasets. CRDA is specially designed for feature eliminatio…

feature selection

Compressive Pattern Matching on Multispectral Data

2014-03-27 · S. Rousseau, D. Helbert, P. Carré, J. Blanc-Talon

We introduce a new constrained minimization problem that performs template and pattern detection on a multispectral image in a compressive sensing context. We use an original minimization problem from Guo and Osher that …

Compressive Sensing