Logo image
Semantic Segmentation for Real-World Data by Jointly Exploiting Supervised and Transferrable Knowledge
Conference paper   Open access

Semantic Segmentation for Real-World Data by Jointly Exploiting Supervised and Transferrable Knowledge

Li-Hsien Lu and Chiou-Ting Hsu
British Machine Vision Conference 2016, BMVC 2016, Vol.2016-September, pp.84.1-84.12
2016

Abstract

Computer Vision and Pattern Recognition
This paper addresses two major challenges in semantic segmentation for real-world data. First, with ever-increasing semantic labels, we need a more pragmatic approach other than existing fully-supervised methods. Second, semantic segmentation for very small or rarely-appeared objects are still very challenging for existing methods. In this paper, we propose to (1) fully utilize the predicted label information from an existing supervised model and to (2) infer newly generated labels via label transfer from a real-world dataset. We propose a “content-adaptive” and “label-aware” MRF framework to jointly exploiting both the supervised and label-transferrable knowledge. The proposed method needs no off-line training and can easily adapt to real-world data. Experimental results on SIFT Flow and LMSun datasets demonstrate the effectiveness of the proposed method, and show promising performance over state-of-the-art methods under the real-world scenario.
url
https://doi.org/10.5244/C.30.84View
Published (Version of record) Open

Related links

Metrics

1 Record Views

Details

Logo image