Spatial As Deep: Spatial CNN for Traffic Scene Understanding

17 Dec 2017 Xingang Pan Jianping Shi Ping Luo Xiaogang Wang Xiaoou Tang

Convolutional neural networks (CNNs) are usually built by stacking convolutional operations layer-by-layer. Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of pixels across rows and columns of an image is not fully explored... (read more)

PDF Abstract

Datasets


Introduced in the Paper:

CULane

Mentioned in the Paper:

Cityscapes TuSimple

Results from the Paper


Ranked #4 on Lane Detection on TuSimple (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Lane Detection CULane SCNN F1 score 71.6 # 13

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
SOURCE PAPER COMPARE
Lane Detection TuSimple Spatial CNN Accuracy 96.53% # 4
F1 score 95.97 # 12

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet