AI Chat AI Image Generator AI Video Text to Speech

Domain-Size Pooling in Local Descriptors: DSP-SIFT

12/30/2014

∙

by Jingming Dong, et al.

∙

∙

We introduce a simple modification of local image descriptors, such as SIFT, based on pooling gradient orientations across different domain sizes, in addition to spatial locations. The resulting descriptor, which we call DSP-SIFT, outperforms other methods in wide-baseline matching benchmarks, including those based on convolutional neural networks, despite having the same dimension of SIFT and requiring no training.

Jingming Dong
6 publications
Stefano Soatto
136 publications

research

∙ 05/15/2019

Local Features and Visual Words Emerge in Activations

We propose a novel method of deep spatial matching (DSM) for image retri...

6 Oriane Siméoni, et al. ∙

research

∙ 07/17/2018

GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints

Learned local descriptors based on Convolutional Neural Networks (CNNs) ...

6 Zixin Luo, et al. ∙

research

∙ 07/02/2020

Learning ordered pooling weights in image classification

Spatial pooling is an important step in computer vision systems like Con...

0 J. I. Forcen, et al. ∙

research

∙ 11/27/2013

Image forgery detection based on the fusion of machine learning and block-matching methods

Dense local descriptors and machine learning have been used with success...

0 Davide Cozzolino, et al. ∙

research

∙ 03/21/2016

Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence

We present a novel descriptor, called deep self-convolutional activation...

0 Seungryong Kim, et al. ∙

research

∙ 01/19/2016

A Theory of Local Matching: SIFT and Beyond

Why has SIFT been so successful? Why its extension, DSP-SIFT, can furthe...

0 Hossein Mobahi, et al. ∙

research

∙ 06/02/2014

Generalized Max Pooling

State-of-the-art patch-based image representations involve a pooling ope...

0 Naila Murray, et al. ∙