Feature Transform Optimization for Pedestrian Classification
| Autor: | Joo Kooi Tan, Yuuki Nakashima |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Optimization problem
Contextual image classification Feature transform Computer science Image classification Pooling feature transform 02 engineering and technology Pedestrian 010501 environmental sciences 01 natural sciences Convolutional neural network Convolution Set (abstract data type) meta-heuristics 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing combinatorial optimization Algorithm 0105 earth and related environmental sciences |
| Zdroj: | 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE). |
| Popis: | In this paper, we propose a FTOP (Feature Transform Optimization Problem) and its solution. We propose a method to optimize both parameters and processing order of feature transform simultaneously, not limited to convolution and pooling included in CNN (Convolutional Neural Network). In order to realize the optimization, we formulate it as a combinatorial optimization problem and solve it by meta-heuristics. The effectiveness of the proposed method is shown by applying the proposed method to pedestrian classification based on a benchmark data set. SICE Annual Conference 2018 (SICE 2018), September 11–14, 2018, Nara, Japan |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|