CVNov 21, 2024

WARLearn: Weather-Adaptive Representation Learning

arXiv:2411.14095v13 citationsh-index: 20Has CodeWACV
Originality Incremental advance
AI Analysis

This work addresses the challenge of maintaining model accuracy in autonomous driving or surveillance systems under varying weather conditions, though it is incremental as it builds on existing invariance principles.

The paper tackles the problem of adapting models trained on clear weather data to perform effectively in adverse weather conditions like fog and low-light, achieving a mean average precision of 52.6% on a foggy dataset and 55.7% on a low-light dataset.

This paper introduces WARLearn, a novel framework designed for adaptive representation learning in challenging and adversarial weather conditions. Leveraging the in-variance principal used in Barlow Twins, we demonstrate the capability to port the existing models initially trained on clear weather data to effectively handle adverse weather conditions. With minimal additional training, our method exhibits remarkable performance gains in scenarios characterized by fog and low-light conditions. This adaptive framework extends its applicability beyond adverse weather settings, offering a versatile solution for domains exhibiting variations in data distributions. Furthermore, WARLearn is invaluable in scenarios where data distributions undergo significant shifts over time, enabling models to remain updated and accurate. Our experimental findings reveal a remarkable performance, with a mean average precision (mAP) of 52.6% on unseen real-world foggy dataset (RTTS). Similarly, in low light conditions, our framework achieves a mAP of 55.7% on unseen real-world low light dataset (ExDark). Notably, WARLearn surpasses the performance of state-of-the-art frameworks including FeatEnHancer, Image Adaptive YOLO, DENet, C2PNet, PairLIE and ZeroDCE, by a substantial margin in adverse weather, improving the baseline performance in both foggy and low light conditions. The WARLearn code is available at https://github.com/ShubhamAgarwal12/WARLearn

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes