paper-with-me

Papers

Many Perception Tasks are Highly Redundant Functions of their Input Data

2024-07-18 · Rahul Ramesh, Anthony Bisulco, Ronald W. DiTullio, Linran Wei, Vijay Balasubramanian, Kostas Daniilidis, Pratik Chaudhari

We show that many perception tasks, from visual recognition, semantic segmentation, optical flow, depth estimation to vocalization discrimination, are highly redundant functions of their input data. Images or spectrograms, projected into different subspaces, formed by orthogonal bases in pixel, Fourier or wavelet domains, can be used to solve these tasks remarkably well regardless of whether it is the top subspace where data varies the most, some intermediate subspace with moderate variability--or the bottom subspace where data varies the least. This phenomenon occurs because different subspaces have a large degree of redundant information relevant to the task.

📄 PDF Abstract BibTeX arXiv:2407.13841

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationOptical Flow EstimationSemantic Segmentation

Similar Papers 제목 키워드 기반

Many Objective Bayesian Optimization

2021-07-08 · Lucia Asencio Martín, Eduardo C. Garrido-Merchán

Some real problems require the evaluation of expensive and noisy objective functions. Moreover, the analytical expression of these objective functions may be unknown. These functions are known as black-boxes, for example…

Bayesian Optimization

Redundant Information Neural Estimation

2021-03-04 · ICLR Workshop Neural_Compression 2021 5 · Michael Kleinman, Alessandro Achille, Stefano Soatto, Jonathan Kao

We introduce the Redundant Information Neural Estimator (RINE), a method that allows efficient estimation for the component of information about a target variable that is common to a set of sources, previously referred t…

image-classificationImage Classification

Assessment of scoring functions for computational models of protein-protein interfaces

2024-07-23 · Jacob Sumner, Grace Meng, Naomi Brandt, Alex T. Grigas 외

A goal of computational studies of protein-protein interfaces (PPIs) is to predict the binding site between two monomers that form a heterodimer. The simplest version of this problem is to rigidly re-dock the bound forms…

Efficient Bayer-Domain Video Computer Vision with Fast Motion Estimation and Learned Perception Residual

2025-08-08 · Haichao Wang, Jiangtao Wen, Yuxing Han arxiv

Video computer vision systems face substantial computational burdens arising from two fundamental challenges: eliminating unnecessary processing and reducing temporal redundancy in back-end inference while maintaining ac…

Continuous Online Extrinsic Calibration of Fisheye Camera and LiDAR

2023-06-22 · Jack Borer, Jeremy Tschirner, Florian Ölsner, Stefan Milz

Automated driving systems use multi-modal sensor suites to ensure the reliable, redundant and robust perception of the operating domain, for example camera and LiDAR. An accurate extrinsic calibration is required to fuse…

Depth EstimationMonocular Depth Estimation