paper-with-me

Papers

Zero-Aliasing Correlation Filters for Object Recognition

2014-11-10 · Joseph A. Fernandez, Vishnu Naresh Boddeti, Andres Rodriguez, B. V. K. Vijaya Kumar

Correlation filters (CFs) are a class of classifiers that are attractive for object localization and tracking applications. Traditionally, CFs have been designed in the frequency domain using the discrete Fourier transform (DFT), where correlation is efficiently implemented. However, existing CF designs do not account for the fact that the multiplication of two DFTs in the frequency domain corresponds to a circular correlation in the time/spatial domain. Because this was previously unaccounted for, prior CF designs are not truly optimal, as their optimization criteria do not accurately quantify their optimization intention. In this paper, we introduce new zero-aliasing constraints that completely eliminate this aliasing problem by ensuring that the optimization criterion for a given CF corresponds to a linear correlation rather than a circular correlation. This means that previous CF designs can be significantly improved by this reformulation. We demonstrate the benefits of this new CF design approach with several important CFs. We present experimental results on diverse data sets and present solutions to the computational challenges associated with computing these CFs. Code for the CFs described in this paper and their respective zero-aliasing versions is available at http://vishnu.boddeti.net/projects/correlation-filters.html

📄 PDF Abstract BibTeX arXiv:1411.2316

Code (0)

등록된 구현이 없습니다.

Tasks

ObjectObject LocalizationObject Recognition

Similar Papers 제목 키워드 기반

Deep learning based spatial aliasing reduction in beamforming for audio capture

2025-05-26 · Mateusz Guzik, Giulio Cengarle, Daniel Arteaga

Spatial aliasing affects spaced microphone arrays, causing directional ambiguity above certain frequencies, degrading spatial and spectral accuracy of beamformers. Given the limitations of conventional signal processing …

De-aliasingDeep Learning

Low Pass Filter for Anti-aliasing in Temporal Action Localization

2021-04-23 · Cece Jin, Yuanqi Chen, Ge Li, Tao Zhang 외

In temporal action localization methods, temporal downsampling operations are widely used to extract proposal features, but they often lead to the aliasing problem, due to lacking consideration of sampling rates. This pa…

Action LocalizationTemporal Action Localization

Latent Constrained Correlation Filter

2017-11-11 · Baochang Zhang, Shangzhen Luan, Chen Chen, Jungong Han 외

Correlation filters are special classifiers designed for shift-invariant object recognition, which are robust to pattern distortions. The recent literature shows that combining a set of sub-filters trained based on a sin…

Object RecognitionObject Tracking

How Convolutional Neural Networks Deal with Aliasing

2021-02-15 · Antônio H. Ribeiro, Thomas B. Schön

The convolutional neural network (CNN) remains an essential tool in solving computer vision problems. Standard convolutional architectures consist of stacked layers of operations that progressively downscale the image. A…

Impact of Aliasing on Generalization in Deep Convolutional Networks

2021-08-07 · ICCV 2021 10 · Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders 외

We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limitations in widely used architectures. Dr…

Data AugmentationFew-Shot Learningimage-classificationImage Classification