Lookahead adversarial learning for near real-time semantic segmentation

作者：

Highlights：

• We propose lookahead adversarial learning (LoAd) for adversarial semantic segmentation.

• LoAd runs as fast as the baselines methods upon which it is applied.

• This makes LoAd suitable for near real-time field applications.

• Besides avoiding class confusion, LoAd improves the performance of the baseline.

• LoAd also creates structurally more consistent label maps than the baselines.

摘要

•We propose lookahead adversarial learning (LoAd) for adversarial semantic segmentation.•LoAd runs as fast as the baselines methods upon which it is applied.•This makes LoAd suitable for near real-time field applications.•Besides avoiding class confusion, LoAd improves the performance of the baseline.•LoAd also creates structurally more consistent label maps than the baselines.

论文关键词：Semantic segmentation,Conditional adversarial training,Computer vision,Deep learning

论文评审过程：Received 21 January 2021, Revised 18 June 2021, Accepted 20 August 2021, Available online 3 September 2021, Version of Record 20 September 2021.

论文官网地址：https://doi.org/10.1016/j.cviu.2021.103271