分割
计算机科学
编码(集合论)
人工智能
闭塞
对象(语法)
计算机视觉
机器学习
模式识别(心理学)
医学
集合(抽象数据类型)
心脏病学
程序设计语言
作者
Evan Ling,Dezhao Huang,Minhoe Hur
出处
期刊:Cornell University - arXiv
日期:2022-10-07
标识
DOI:10.48550/arxiv.2210.03686
摘要
Modern object detection and instance segmentation networks stumble when picking out humans in crowded or highly occluded scenes. Yet, these are often scenarios where we require our detectors to work well. Many works have approached this problem with model-centric improvements. While they have been shown to work to some extent, these supervised methods still need sufficient relevant examples (i.e. occluded humans) during training for the improvements to be maximised. In our work, we propose a simple yet effective data-centric approach, Occlusion Copy & Paste, to introduce occluded examples to models during training - we tailor the general copy & paste augmentation approach to tackle the difficult problem of same-class occlusion. It improves instance segmentation performance on occluded scenarios for "free" just by leveraging on existing large-scale datasets, without additional data or manual labelling needed. In a principled study, we show whether various proposed add-ons to the copy & paste augmentation indeed contribute to better performance. Our Occlusion Copy & Paste augmentation is easily interoperable with any models: by simply applying it to a recent generic instance segmentation model without explicit model architectural design to tackle occlusion, we achieve state-of-the-art instance segmentation performance on the very challenging OCHuman dataset. Source code is available at https://github.com/levan92/occlusion-copy-paste.
科研通智能强力驱动
Strongly Powered by AbleSci AI