DiffPrompter: Differentiable Implicit Visual Prompts for Semantic-Segmentation in Adverse Conditions

TL;DR

DiffPrompter introduces differentiable visual and latent prompts to improve semantic segmentation in adverse weather, significantly enhancing performance in challenging conditions for autonomous driving.

Contribution

It proposes a novel differentiable prompting mechanism that expands foundation model capabilities specifically for adverse weather scenarios.

Findings

Enhanced segmentation accuracy in adverse conditions.

Joint training of visual and latent prompts improves out-of-distribution performance.

Empirical results validate the effectiveness of DiffPrompter.

Abstract

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.