Competitive Simplicity for Multi-Task Learning for Real-Time Foggy Scene Understanding via Domain Adaptation
Alshammari, N.; Akcay, S.; Breckon, T.P.
Professor Toby Breckon firstname.lastname@example.org
— Automotive scene understanding under adverse weather conditions raises a realistic and challenging problem attributable to poor outdoor scene visibility (e.g. foggy weather). However, because most contemporary scene understanding approaches are applied under ideal-weather conditions, such approaches may not provide genuinely optimal performance when compared to established a priori insights on extremeweather understanding. In this paper, we propose a complex but competitive multi-task learning approach capable of performing in real-time semantic scene understanding and monocular depth estimation under foggy weather conditions by leveraging both recent advances in adversarial training and domain adaptation. As an end-to-end pipeline, our model provides a novel solution to surpass degraded visibility in foggy weather conditions by transferring scenes from foggy to normal using a GAN-based model. For optimal performance in semantic segmentation, our model generates depth to be used as complementary source information with RGB in the segmentation network. We provide a robust method for foggy scene understanding by training two models (normal and foggy) simultaneously with shared weights (each model is trained on each weather condition). Our model incorporates RGB colour, depth, and luminance images via distinct encoders with dense connectivity and features fusing, and leverages skip connections to produce consistent depth and segmentation predictions. Using this architectural formulation with light computational complexity at inference time, we are able to achieve comparable performance to contemporary approaches at a fraction of the overall model complexity. Evaluation over several foggy weather condition datasets including synthetic and real-world examples illustrates our approach competitive performance compared to other contemporary state-of-the-art approaches.
Alshammari, N., Akcay, S., & Breckon, T. (2021). Competitive Simplicity for Multi-Task Learning for Real-Time Foggy Scene Understanding via Domain Adaptation.
|Conference Name||2021 IEEE Intelligent Vehicles Symposium (IV 2021)|
|Conference Location||Nagoya, Japan|
|Acceptance Date||Apr 23, 2021|
|Online Publication Date||Jul 11, 2021|
|Deposit Date||May 23, 2021|
|Publisher||Institute of Electrical and Electronics Engineers|
You might also like
Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery