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

Semantic segmentation in adverse weather scenar- ios is a critical task for autonomous driving systems. While foundation models have shown promise, the need for special- ized 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 ∇HFC (High Frequency Components) based 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: diffprompter.github.io * denotes equal contribution 1are with RRC, IIIT Hyderabad, India {sankethkalwar, mihir.ungarala, shrutipraveenjain, aaronmonis22}@gmail.com, mkrishna@iiit.ac.in 2is with the Australian Institute for Machine Learning, University of Adelaide, Australia sourav.garg@adelaide.edu.au 3is with ZF TCI, Hyderabad, India krishna.konda@zf.com †Code: https://github.com/DiffPrompter/diff-prompter ⋄Paper full version: https://arxiv.org/pdf/2310.04181