Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

05/20/2020
by   Liang-Chieh Chen, et al.
7

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 AP, and 85.2 building a simple procedure to harness unlabeled video sequences to surpass state-of-the-art performance on core computer vision tasks.

READ FULL TEXT
research
05/20/2020

Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation

Supervised learning in large discriminative models is a mainstay for mod...
research
02/29/2020

VideoSSL: Semi-Supervised Learning for Video Classification

We propose a semi-supervised learning approach for video classification,...
research
02/11/2019

Domain Constraint Approximation based Semi Supervision

Deep learning for supervised learning has achieved astonishing performan...
research
04/21/2022

SelfD: Self-Learning Large-Scale Driving Policies From the Web

Effectively utilizing the vast amounts of ego-centric navigation data th...
research
06/09/2015

Learning to Linearize Under Uncertainty

Training deep feature hierarchies to solve supervised learning tasks has...
research
05/06/2022

Revisiting Pretraining for Semi-Supervised Learning in the Low-Label Regime

Semi-supervised learning (SSL) addresses the lack of labeled data by exp...
research
07/22/2023

Self-Supervised and Semi-Supervised Polyp Segmentation using Synthetic Data

Early detection of colorectal polyps is of utmost importance for their t...

Please sign up or login with your details

Forgot password? Click here to reset