Look at here : Utilizing supervision to attend subtle key regions

Changhwan Lee, Yeesuk Kim, Bong Gun Lee, Doosup Kim, Jongseong Jang

Keywords: Medical image diagnosis, Deep learning, Regularization strategy, Data augmentation

Abstract: Despite the success of deep learning in computer vision, algorithms to recognize subtle and small objects (or regions) is still challenging. For example, recognizing a baseball or a frisbee on a ground scene or a bone fracture in an X-ray image can easily result in overfitting, unless a huge amount of training data is available. To mitigate this problem, we need a way to force a model should identify subtle regions in limited training data. In this paper, we propose a simple but efficient supervised augmentation method called Cut&Remain. It achieved better performance in multi-class classification tasks (clavicle and pelvic X-ray) and a multi-label classification task of small objects (MS-COCO$_s$) than other supervised augmentation and the explicit guidance methods. In addition, using the class activation map, we identified that the Cut&Remain methods drive a model to focus on relevant subtle and small regions efficiently. We also show that the performance monotonically increased along the Cut&Remain ratio, indicating that a model can be improved even though only limited amount of Cut&Remain is applied for, so that it allows low supervising(annotation) cost for improvement.

One-sentence Summary: We proposed a simple augmentation strategy utilizing supervision, called Cut&Remain, to allow a model to focus on subtle key regions.