文件名称：Learning Lightweight Lane Detection CNNs by Self Attention Distillation.pdf
文件大小：3.92MB
文件格式：PDF
更新时间：2023-05-11 05:11:17
Lane Detection CNN
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals in- herent in lane annotations. Without learning from much richer context, these models often fail in challenging sce- narios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowl- edge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps ex- tracted from a model trained to a reasonable level would encode rich contextual information. The valuable contex- tual information can be used as a form of ‘free’ supervision for further representation learning through performing top- down and layer-wise attention distillation within the net- work itself. SAD can be easily incorporated in any feed- forward convolutional neural networks (CNN) and does not increase the inference time. We validate SAD on three pop- ular lane detection benchmarks (TuSimple, CULane and BDD100K) using lightweight models such as ENet, ResNet- 18 and ResNet-34. The lightest model, ENet-SAD, per- forms comparatively or even surpasses existing algorithms. Notably, ENet-SAD has 20 × fewer parameters and runs 10 × faster compared to the state-of-the-art SCNN [16], while still achieving compelling performance in all bench- marks. Our code is available at https://github. com/cardwing/Codes-for-Lane-Detection.