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

arXiv: https://arxiv.org/abs/2405.06264 · HTML: https://mlsanity.com/paper/2405.06264/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 10 May 2024.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2106.14156/) (2021)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [LSQ+: Improving low-bit quantization through learnable offsets and better initialization](https://mlsanity.com/paper/2004.09576/) (2020)
- [Spatial As Deep: Spatial CNN for Traffic Scene Understanding](https://mlsanity.com/paper/1712.06080/) (2017)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection](https://mlsanity.com/paper/2010.12035/) (2020)
- [Ultra Fast Structure-aware Deep Lane Detection](https://mlsanity.com/paper/2004.11757/) (2020)
- [End-to-end Lane Shape Prediction with Transformers](https://mlsanity.com/paper/2011.04233/) (2020)
- [CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution](https://mlsanity.com/paper/2105.05003/) (2021)
- [Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming](https://mlsanity.com/paper/2006.10518/) (2020)
- [Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://mlsanity.com/paper/1903.08066/) (2019)
- [Rethinking Efficient Lane Detection via Curve Modeling](https://mlsanity.com/paper/2203.02431/) (2022)
- [CLRNet: Cross Layer Refinement Network for Lane Detection](https://mlsanity.com/paper/2203.10350/) (2022)
- [CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending](https://mlsanity.com/paper/2007.12147/) (2020)
- [RESA: Recurrent Feature-Shift Aggregator for Lane Detection](https://mlsanity.com/paper/2008.13719/) (2020)
- [A Keypoint-based Global Association Network for Lane Detection](https://mlsanity.com/paper/2204.07335/) (2022)
- [EasyQuant: Post-training Quantization via Scale Optimization](https://mlsanity.com/paper/2006.16669/) (2020)

## Built on by (most cited first, 1 of 1)

- [D2-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models](https://mlsanity.com/paper/2501.08180/) (2025)

## Abstract (arXiv)

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.