Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
| Autor: | Seokju Lee, In So Kweon, Francois Rameau, Fei Pan, Inkyu Shin |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Convolutional neural network Data modeling Machine Learning (cs.LG) Computer Science - Robotics 0202 electrical engineering electronic engineering information engineering Entropy (information theory) Segmentation 0105 earth and related environmental sciences business.industry Image segmentation Real image 020201 artificial intelligence & image processing Artificial intelligence business computer Robotics (cs.RO) |
| Zdroj: | CVPR |
| Popis: | Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically annotated data generated from graphic engines are used to train segmentation models. However, the models trained from synthetic data are difficult to transfer to real images. To tackle this issue, previous works have considered directly adapting models from the source data to the unlabeled target data (to reduce the inter-domain gap). Nonetheless, these techniques do not consider the large distribution gap among the target data itself (intra-domain gap). In this work, we propose a two-step self-supervised domain adaptation approach to minimize the inter-domain and intra-domain gap together. First, we conduct the inter-domain adaptation of the model; from this adaptation, we separate the target domain into an easy and hard split using an entropy-based ranking function. Finally, to decrease the intra-domain gap, we propose to employ a self-supervised adaptation technique from the easy to the hard split. Experimental results on numerous benchmark datasets highlight the effectiveness of our method against existing state-of-the-art approaches. The source code is available at https://github.com/feipan664/IntraDA.git. Accepted to CVPR 2020 as an Oral Presentation. Code is available at https://github.com/feipan664/IntraDA |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|