# Look at here : Utilizing supervision to attend subtle key regions

arXiv: https://arxiv.org/abs/2111.13233 · HTML: https://mlsanity.com/paper/2111.13233/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 25 Nov 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://mlsanity.com/paper/1908.10454/) (2019)
- [Tell Me Where to Look: Guided Attention Inference Network](https://mlsanity.com/paper/1802.10171/) (2018)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning](https://mlsanity.com/paper/1710.04043/) (2017)
- [Grounded Video Description](https://mlsanity.com/paper/1812.06587/) (2018)
- [T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos](https://mlsanity.com/paper/1604.02532/) (2016)
- [Multi-Label Classification with Label Graph Superimposing](https://mlsanity.com/paper/1911.09243/) (2019)
- [COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images](https://mlsanity.com/paper/2003.11055/) (2020)
- [Going Deeper into Action Recognition: A Survey](https://mlsanity.com/paper/1605.04988/) (2016)
- [Image Captioning and Visual Question Answering Based on Attributes and External Knowledge](https://mlsanity.com/paper/1603.02814/) (2016)
- [Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection](https://mlsanity.com/paper/1809.05884/) (2018)
- [Deep Learning for Medical Image Segmentation](https://mlsanity.com/paper/1505.02000/) (2015)
- [Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN](https://mlsanity.com/paper/1812.09025/) (2018)
- [Learning Visual Context by Comparison](https://mlsanity.com/paper/2007.07506/) (2020)

## Abstract (arXiv)

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 on various medical image domain (internally sourced- and public dataset) and a natural image domain (MS-COCOs) 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.