Weakly Supervised Fog Detection
Authors: Galdran, A., Costa, P., Vazquez-Corral, J. and Campilho, A.
Journal: Proceedings - International Conference on Image Processing, ICIP
Pages: 2875-2879
ISBN: 9781479970612
ISSN: 1522-4880
DOI: 10.1109/ICIP.2018.8451196
Abstract:Image dehazing tries to solve an undesired loss of visibility in outdoor images due to the presence of fog. Recently, machine-learning techniques have shown great dehazing ability. However, in order to be trained, they require training sets with pairs of foggy images and their clean counterparts, or a depth-map. In this paper, we propose to learn the appearance of fog from weakly-labeled data. Specifically, we only require a single label per-image stating if it contains fog or not. Based on the Multiple-Instance Learning framework, we propose a model that can learn from image-level labels to predict if an image contains haze reasoning at a local level. Fog detection performance of the proposed method compares favorably with two popular techniques, and the attention maps generated by the model demonstrate that it effectively learns to disregard sky regions as indicative of the presence of fog, a common pitfall of current image dehazing techniques.
Source: Scopus
WEAKLY SUPERVISED FOG DETECTION
Authors: Galdran, A., Costa, P., Vazquez-Corral, J. and Campilho, A.
Journal: 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Pages: 2875-2879
ISSN: 1522-4880
Source: Web of Science (Lite)
Weakly Supervised Fog Detection.
Authors: Galdran, A., Costa, P., Vazquez-Corral, J. and Campilho, A.
Journal: ICIP
Pages: 2875-2879
Publisher: IEEE
ISBN: 978-1-4799-7061-2
https://ieeexplore.ieee.org/xpl/conhome/8436606/proceeding
Source: DBLP