Inter-Region Affinity Distillation for Road Marking Segmentation

By Yuenan Hou, Zheng Ma, Chunxiao Liu, Tak-Wai Hui, Chen Change Loy. 2020

146 citations recorded by the source corpus.

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.

Subfields: Civil and Structural Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Civil and Structural Engineering

In Computer Vision and Pattern Recognition

In Environmental Engineering

Citations in the corpus

Knowledge Distillation: A Survey (2020, background): “2020b), image/video segmentation (He et al. 2019; Mullapudi et al. 2019; Dou et al. 2020; Liu et al. 2019h; Siam et al. 2019; Hou et al. 2020; Bergmann et al. 2020), action recognition (Luo et al.”
Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection (2020, methodology): “As noted in [23], many of the cited works do not publish the code to reproduce the results reported [13, 18, 27], or, in some cases, the code is only partially public [11, 10].”
Channel-wise Knowledge Distillation for Dense Prediction* (2020, methodology): “Our method outperforms SKD and IFVD on seven student networks and three benchmarks, which further indicates that the channel-wise distillation is effective for semantic segmentation.”
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution (2021, background): “Besides, in terms of efficiency, some recent row-wise detection methods[30, 41, 11] have achieved advantages.”
Knowledge Distillation Meets Self-Supervision (2020, background): “These representations include attention map [46], gram matrix [44], gradient [39], pre-activation [15], and feature distribution statistics [17].”