Does Pooling Really Matter? An Evaluation on Gait Recognition

Author(s)

Goncalves dos Santos, Claudio Filipi ; Moreira, Thierry Pinheiro ; Colombo, Danilo ; Papa, Joao Paulo ; Nystrom, I ; Heredia, YH ; Nunez, VM

• Document type: Journal article
• Source: PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS (CIARP 2019); v. 11896, p. 10-pg., 2019-01-01.

Abstract

Most Convolutional Neural Networks make use of subsampling layers to reduce dimensionality and keep only the most essential information, besides turning the model more robust to rotation and translation variations. One of the most common sampling methods is the one who keeps only the maximum value in a given region, known as max-pooling. In this study, we provide pieces of evidence that, by removing this subsampling layer and changing the stride of the convolution layer, one can obtain comparable results but much faster. Results on the gait recognition task show the robustness of the proposed approach, as well as its statistical similarity to other pooling methods. (AU)

• FAPESP's process: 16/06441-7 - Semantic information retrieval in large video databases
• Grantee: Jurandy Gomes de Almeida Junior
• Support Opportunities: Regular Research Grants
• FAPESP's process: 17/25908-6 - Weakly supervised learning for compressed video analysis on retrieval and classification tasks for visual alert
• Grantee: João Paulo Papa
• Support Opportunities: Research Grants - Research Partnership for Technological Innovation - PITE
• FAPESP's process: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?
• Grantee: Alexandre Xavier Falcão
• Support Opportunities: Research Projects - Thematic Grants
• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC