A quaternion deterministic monogenic CNN layer for contrast invariance
Deep learning (DL) is attracting considerable interest as it currently achieves remarkable performance in many branches of science and technology. However, current DL cannot guarantee capabilities of the mammalian visual systems such as lighting changes. This paper proposes a deterministic entry lay...
| Authors: | , , , , |
|---|---|
| Format: | book part |
| Publication Date: | 2021 |
| Country: | España |
| Institution: | Universitat Politècnica de Catalunya (UPC) |
| Repository: | UPCommons. Portal del coneixement obert de la UPC |
| Language: | English |
| OAI Identifier: | oai:upcommons.upc.edu:2117/349717 |
| Online Access: | https://hdl.handle.net/2117/349717 https://dx.doi.org/10.1007/978-3-030-74486-1_7 |
| Access Level: | Open access |
| Keyword: | Machine learning Image analysis Neural networks (Computer science) Aprenentatge automàtic Imatges -- Anàlisi Xarxes neuronals (Informàtica) Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic |
| Summary: | Deep learning (DL) is attracting considerable interest as it currently achieves remarkable performance in many branches of science and technology. However, current DL cannot guarantee capabilities of the mammalian visual systems such as lighting changes. This paper proposes a deterministic entry layer capable of classifying images even with low-contrast conditions. We achieve this through an improved version of the quaternion monogenic wavelets. We have simulated the atmospheric degradation of the CIFAR-10 and the Dogs and Cats datasets to generate realistic contrast degradations of the images. The most important result is that the accuracy gained by using our layer is substantially more robust to illumination changes than nets without such a layer. |
|---|