| Full text | |
| Author(s): |
Nazare, Tiago S.
;
Paranhos da Costa, Gabriel B.
;
de Mello, Rodrigo F.
;
Ponti, Moacir A.
;
IEEE
Total Authors: 5
|
| Document type: | Journal article |
| Source: | PROCEEDINGS 2018 31ST SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI); v. N/A, p. 7-pg., 2018-01-01. |
| Abstract | |
Transfer learning is seen as one of the most promising areas of machine learning. Lately, features from pre-trained models have been used to achieve state-of-the-art results in several machine vision problems. Those models are usually employed when the problem of interest does not have enough supervised examples to support the network training from scratch. Most applications use networks pre-trained on noise-free RGB image datasets, what is observed even when the target domain counts on grayscale images or when data is degraded by noise. In this paper, we evaluate the use of Convolutional Neural Networks (CNNs) on such transfer learning scenarios and the impact of using RGB trained networks on grayscale image tasks. Our results confirm that the use of networks trained using colored images on grayscale tasks hinders the overall performance when compared to a similar network trained on a quantized version of the original dataset. Results also show that higher quantization levels (resulting in less colors) increase the robustness of CNN features in the presence of noise. (AU) | |
| FAPESP's process: | 15/05310-3 - Representation Learning of spatio-temporal features from video |
| Grantee: | Gabriel de Barros Paranhos da Costa |
| Support Opportunities: | Scholarships in Brazil - Doctorate |
| FAPESP's process: | 17/16548-6 - Providing theoretical guarantees to the detection of concept drift in data streams |
| Grantee: | Rodrigo Fernandes de Mello |
| Support Opportunities: | Scholarships abroad - Research |
| 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 |
| FAPESP's process: | 15/04883-0 - Unusual event detection in surveillance videos |
| Grantee: | Tiago Santana de Nazare |
| Support Opportunities: | Scholarships in Brazil - Doctorate (Direct) |
| FAPESP's process: | 16/16111-4 - Feature learning applied to sketch-based image retrieval and low-altitude remote sensing |
| Grantee: | Moacir Antonelli Ponti |
| Support Opportunities: | Regular Research Grants |