Selective Focus: Investigating Semantics Sensitivity in Post-training Quantization for Lane Detection

TL;DR

This paper introduces a novel approach to post-training quantization for lane detection models, focusing on semantic sensitivity to improve performance and robustness in autonomous driving applications.

Contribution

It pioneers the investigation of semantic sensitivity in PTQ for lane detection and proposes a Selective Focus framework with Semantic Guided Focus and Sensitivity Aware Selection modules.

Findings

Achieves 6.4% F1 score improvement on CULane dataset.

Produces quantized models in minutes on a single GPU.

Effectively handles intra-head and inter-head sensitivity issues.

Abstract

Lane detection (LD) plays a crucial role in enhancing the L2+ capabilities of autonomous driving, capturing widespread attention. The Post-Processing Quantization (PTQ) could facilitate the practical application of LD models, enabling fast speeds and limited memories without labeled data. However, prior PTQ methods do not consider the complex LD outputs that contain physical semantics, such as offsets, locations, etc., and thus cannot be directly applied to LD models. In this paper, we pioneeringly investigate semantic sensitivity to post-processing for lane detection with a novel Lane Distortion Score. Moreover, we identify two main factors impacting the LD performance after quantization, namely intra-head sensitivity and inter-head sensitivity, where a small quantization error in specific semantics can cause significant lane distortion. Thus, we propose a Selective Focus framework deployed with Semantic Guided Focus and Sensitivity Aware Selection modules, to incorporate post-processing information into PTQ reconstruction. Based on the observed intra-head sensitivity, Semantic Guided Focus is introduced to prioritize foreground-related semantics using a practical proxy. For inter-head sensitivity, we present Sensitivity Aware Selection, efficiently recognizing influential prediction heads and refining the optimization objectives at runtime. Extensive experiments have been done on a wide variety of models including keypoint-, anchor-, curve-, and segmentation-based ones. Our method produces quantized models in minutes on a single GPU and can achieve 6.4% F1 Score improvement on the CULane dataset.