선동이의 삶

목차 Improved Regularization of Convolutional Neural Networks with Cutout arXiv 2017 https://arxiv.org/abs/1708.04552 Improved Regularization of Convolutional Neural Networks with Cutout Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks. However, due to the model capacity required to capture such represen..

목차 Emerging Properties in Self-Supervised Vision Transformers ICCV 2021 https://arxiv.org/abs/2104.14294 Emerging Properties in Self-Supervised Vision Transformers In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this arc..

목차 Cut and Learn for Unsupervised Object Detection and Instance Segmentation CVPR 2023 https://arxiv.org/abs/2301.11320 Cut and Learn for Unsupervised Object Detection and Instance Segmentation We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'discover' objects without su..

목차 ObjectStitch: Object Compositing with Diffusion Model CVPR 2023 https://arxiv.org/abs/2212.00932 ObjectStitch: Generative Object Compositing Object compositing based on 2D images is a challenging problem since it typically involves multiple processing stages such as color harmonization, geometry correction and shadow generation to generate realistic results. Furthermore, annotating training d..

목차 Image Segmentation Using Deep Learning: A Survey https://ieeexplore.ieee.org/abstract/document/9356353 Image Segmentation Using Deep Learning: A Survey Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among o..

목차 Image Segmentation Using Deep Learning: A Survey https://ieeexplore.ieee.org/abstract/document/9356353 Image Segmentation Using Deep Learning: A Survey Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among o..

목차 Image Segmentation Using Deep Learning: A Survey https://ieeexplore.ieee.org/abstract/document/9356353 Image Segmentation Using Deep Learning: A Survey Image segmentation is a key task in computer vision and image processing with important applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among o..

목차 Object Insertion Based Data Augmentation for Semantic Segmentation ICRA 2022 http://ieeexplore.ieee.org/abstract/document/9811816 Object Insertion Based Data Augmentation for Semantic Segmentation Neural network used for the LiDAR semantic segmentation task needs the point-wise labeled point clouds for training, which is more expensive than bounding box annotations. Enhancing the diversity of..

목차 Class-Balanced Loss Based on Effective Number of Samples CVPR 2019 https://arxiv.org/abs/1901.05555 Class-Balanced Loss Based on Effective Number of Samples With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existin..