Скачать или смотреть Enhancing the performance of indoor-outdoor image classifications using depth-map features

This presentation tackles a problem from Computer Vision, that of classifying indoors and outdoor images using Deep Learning models. To do so, we are going to perform an unsupervised learning based analysis with the aim of determining the relevance of depth maps in the context of classification. For further tests to decide on the granularity of information extraction means, features are aggregated from sub-images of different sizes from DIODE dataset to compare multiple scales of region attention. The results are then compared with other supervised methods so that the clear advantage of using depth information is confirmed. The broader goal of this research is to identify suitable networks for indoors-outdoor classification and, additionally, to emphasise the benefits of training Deep Learning models for dense visual tasks such as Depth Estimation on large data sets with a wide variety of scenes to boost their performance and test their potential to perform in any situation.

This presentation was part of the WeADL 2021 workshop (http://www.cs.ubbcluj.ro/weadl/), organized under the umbrella of WeaMyL (https://weamyl.met.no/), a project funded by the Norway Grants under the number RO-NO-2019-0133. Contract: No 26/2020.