Deep multi-context Network for FINE-GRAINED VISUAL RECOGNITION
| Autor: | Hefei Ling, Xiaochun Cao, Xinyu Ou, Zhen Wei, Si Liu |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Context model
business.industry Computer science Deep learning 05 social sciences Context (language use) 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Visualization 0502 economics and business Artificial intelligence Data mining 050207 economics business Set (psychology) Baseline (configuration management) computer 0105 earth and related environmental sciences |
| Zdroj: | ICME Workshops |
| DOI: | 10.1109/icmew.2016.7574666 |
| Popis: | In this paper, we tackle the FINE-GRAINED VISUAL RECOGNITION problem by proposing a deep multi-context framework. We employ deep Convolutional Neural Networks to model features of objects in images. Global context and local context are both taken into consideration, and are jointly modeled in a unified multi-context deep learning framework. To cleanse the relatively dirty data for training, a regional proposal method is designed to make the multi-context modeling suited for fine-grained visual recognition in the real world. Furthermore, recently proposed contemporary deep models are used, and their combination is investigated. Our approaches are evaluated on MSR-IRC 2016 and further assessed on the more complex validation set. The results show significant and consistent improvements over the baseline. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|