Inter-Region Affinity Distillation for Road Marking Segmentation
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.
Code (1)
Tasks
Knowledge DistillationLane DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Lane Marking Detection Algorithm Using Drivable Area Segmentation and Extended SLT
In this paper, a robust lane detection algorithm is proposed, where the vertical road profile of the road is estimated using dynamic programming from the v-disparity map and, based on the estimated profile, the road area…
Lane DetectionTinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
In this paper, we propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models. The method introduces two core techniques: affinity mimicking and weight inheritance.…
Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction
The trade-off between predictive accuracy and data availability makes it difficult to predict protein--protein binding affinity accurately. The lack of experimentally resolved protein structures limits the performance of…
Knowledge DistillationTowards a Unified View of Affinity-Based Knowledge Distillation
Knowledge transfer between artificial neural networks has become an important topic in deep learning. Among the open questions are what kind of knowledge needs to be preserved for the transfer, and how it can be effectiv…
image-classificationImage ClassificationKnowledge DistillationRelation+1Graph Relation Distillation for Efficient Biomedical Instance Segmentation
Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring di…
Instance SegmentationKnowledge DistillationRelationSemantic Segmentation