Method Details

Details for method 'Naive-Student (iterative semi-supervised learning with Panoptic-DeepLab)'


Method overview

name Naive-Student (iterative semi-supervised learning with Panoptic-DeepLab)
challenge instance-level semantic labeling
details Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of supervised learning may be limited by the size of the human annotated dataset. This limitation is particularly notable for image segmentation tasks, where the expense of human annotation is especially large, yet large amounts of unlabeled data may exist. In this work, we ask if we may leverage semi-supervised learning in unlabeled video sequences to improve the performance on urban scene segmentation, simultaneously tackling semantic, instance, and panoptic segmentation. The goal of this work is to avoid the construction of sophisticated, learned architectures specific to label propagation (e.g., patch matching and optical flow). Instead, we simply predict pseudo-labels for the unlabeled data and train subsequent models with both human-annotated and pseudo-labeled data. The procedure is iterated for several times. As a result, our Naive-Student model, trained with such simple yet effective iterative semi-supervised learning, attains state-of-the-art results at all three Cityscapes benchmarks, reaching the performance of 67.8% PQ, 42.6% AP, and 85.2% mIOU on the test set. We view this work as a notable step towards building a simple procedure to harness unlabeled video sequences to surpass state-of-the-art performance on core computer vision tasks.
publication Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng, Maxwell D. Collins, Ekin D. Cubuk, Barret Zoph, Hartwig Adam, Jonathon Shlens
project page / code
used Cityscapes data fine annotations, video
used external data ImageNet, Mapillary Vistas Research Edition. Cityscapes train-extra set (coarse labels are not used but only images).
runtime n/a
subsampling no
submission date April, 2020
previous submissions


Average results

Metric Value
AP 42.5605
AP50% 67.6073
AP100m 57.9371
AP50m 59.7797


Class results

Class AP AP50% AP100m AP50m
person 40.4725 71.8091 59.8944 60.0752
rider 35.3419 69.0848 50.807 51.3686
car 59.96 82.9472 80.1792 82.5748
truck 44.6579 56.5959 59.4973 65.6651
bus 53.4191 68.81 73.2215 79.6308
train 44.1044 65.6381 55.6078 53.7842
motorcycle 35.8067 66.2296 45.0608 45.9902
bicycle 26.7219 59.7432 39.2291 39.1488



Download results as .csv file

Benchmark page