DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions
This addresses the problem of robust semantic segmentation for autonomous driving systems in adverse conditions, representing an incremental advancement by building on existing foundation models with specialized adaptors.
The paper tackles semantic segmentation in adverse weather for autonomous driving by introducing DiffPrompter, a differentiable prompting mechanism that enhances existing adaptors in foundation models, achieving significant performance improvements in out-of-distribution scenarios with concrete gains demonstrated through experiments.
Semantic segmentation in adverse weather scenarios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for specialized adaptors becomes evident for handling more challenging scenarios. We introduce DiffPrompter, a novel differentiable visual and latent prompting mechanism aimed at expanding the learning capabilities of existing adaptors in foundation models. Our proposed $\nabla$HFC image processing block excels particularly in adverse weather conditions, where conventional methods often fall short. Furthermore, we investigate the advantages of jointly training visual and latent prompts, demonstrating that this combined approach significantly enhances performance in out-of-distribution scenarios. Our differentiable visual prompts leverage parallel and series architectures to generate prompts, effectively improving object segmentation tasks in adverse conditions. Through a comprehensive series of experiments and evaluations, we provide empirical evidence to support the efficacy of our approach. Project page at https://diffprompter.github.io.