# Inter-Region Affinity Distillation for Road Marking Segmentation

arXiv: https://arxiv.org/abs/2004.05304 · HTML: https://mlsanity.com/paper/2004.05304/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2020.

## Built on by (most cited first, 30 of 58)

- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution](https://mlsanity.com/paper/2105.05003/) (2021)
- [OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.13540/) (2023)
- [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023)
- [MonoDistill: Learning Spatial Features for Monocular 3D Object Detection](https://mlsanity.com/paper/2201.10830/) (2022)
- [UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View](https://mlsanity.com/paper/2303.15083/) (2023)
- [LaneAF: Robust Multi-Lane Detection with Affinity Fields](https://mlsanity.com/paper/2103.12040/) (2021)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation](https://mlsanity.com/paper/2205.00858/) (2022)
- [InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learning](https://mlsanity.com/paper/2301.04470/) (2023)
- [Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification](https://mlsanity.com/paper/2206.07389/) (2022)
- [Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation](https://mlsanity.com/paper/2109.01801/) (2021)
- [Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes](https://mlsanity.com/paper/2203.15302/) (2022)
- [Structure Guided Lane Detection](https://mlsanity.com/paper/2105.05403/) (2021)
- [RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation](https://mlsanity.com/paper/2312.11829/) (2023)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection](https://mlsanity.com/paper/2108.08482/) (2021)
- [RCLane: Relay Chain Prediction for Lane Detection](https://mlsanity.com/paper/2207.09399/) (2022)
- [IDEAL: Query-Efficient Data-Free Learning from Black-box Models](https://mlsanity.com/paper/2205.11158/) (2022)
- [BPKD: Boundary Privileged Knowledge Distillation For Semantic Segmentation](https://mlsanity.com/paper/2306.08075/) (2023)
- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2208.14143/) (2022)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [Distilling Knowledge from Object Classification to Aesthetics Assessment](https://mlsanity.com/paper/2206.00809/) (2022)
- [Robust Lane Detection via Expanded Self Attention](https://mlsanity.com/paper/2102.07037/) (2021)
- [Self-supervised Correlation Mining Network for Person Image Generation](https://mlsanity.com/paper/2111.13307/) (2021)
- [Recursive Video Lane Detection](https://mlsanity.com/paper/2308.11106/) (2023)
- [Rail Detection: An Efficient Row-based Network and A New Benchmark](https://mlsanity.com/paper/2304.05667/) (2023)
- [Lane Detection with Versatile AtrousFormer and Local Semantic Guidance](https://mlsanity.com/paper/2203.04067/) (2022)
- [Graph Flow: Cross-layer Graph Flow Distillation for Dual Efficient Medical Image Segmentation](https://mlsanity.com/paper/2203.08667/) (2022)

## Abstract (arXiv)

We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation. In this work, we explore a novel knowledge distillation (KD) approach that can transfer 'knowledge' on scene structure more effectively from a teacher to a student model. Our method is known as Inter-Region Affinity KD (IntRA-KD). It decomposes a given road scene image into different regions and represents each region as a node in a graph. An inter-region affinity graph is then formed by establishing pairwise relationships between nodes based on their similarity in feature distribution. To learn structural knowledge from the teacher network, the student is required to match the graph generated by the teacher. The proposed method shows promising results on three large-scale road marking segmentation benchmarks, i.e., ApolloScape, CULane and LLAMAS, by taking various lightweight models as students and ResNet-101 as the teacher. IntRA-KD consistently brings higher performance gains on all lightweight models, compared to previous distillation methods. Our code is available at https://github.com/cardwing/Codes-for-IntRA-KD.