Many Perception Tasks are Highly Redundant Functions of their Input Data
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth EstimationOptical Flow EstimationSemantic SegmentationSimilar Papers 제목 키워드 기반
Many Objective Bayesian Optimization
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 OptimizationRedundant Information Neural Estimation
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 ClassificationAssessment of scoring functions for computational models of protein-protein interfaces
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
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
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