Wildcat: In-The-Wild Color-And-Thermal Patch Comparison with Deep Residual Pseudo-Siamese Networks
| Autor: | Wayne Treible, Chandra Kambhamettu, Philip Saponaro |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Matching (graph theory)
Computer science business.industry Deep learning 010401 analytical chemistry Process (computing) Pattern recognition 02 engineering and technology Residual 01 natural sciences 0104 chemical sciences Histogram of oriented gradients 0202 electrical engineering electronic engineering information engineering Code (cryptography) 020201 artificial intelligence & image processing Artificial intelligence business Curse of dimensionality |
| Zdroj: | ICIP |
| DOI: | 10.1109/icip.2019.8803742 |
| Popis: | Multi-modal color-thermal matching is a difficult task due to innate appearance differences. Previous methods either use hand crafted features such as Histogram of Oriented Gradients (HOG), or use deep learning within a limited domain (faces, pedestrians). We improve on the state-of-the-art methods by creating a novel deep residual pseudo-siamese architecture trained on in-the-wild data. The siamese branches of the architecture learn to process each modality in a modular fashion, and the residual blocks allow for a deeper network without reducing branch dimensionality too quickly or making training infeasible. We compare our proposed network against other state-of-the-art networks, trained and tested on the CATS and KAIST dataset, respectively. Our experiments show an increase in performance when using the proposed network. The WILDCAT model, along with training and testing code, will be made available upon publication. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|