Instance segmentation requires a large number of training samples to achieve satisfactory performance and benefits from proper data augmentation. To enlarge the training set and …
Z Tian, C Shen, X Wang… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the …
H Zhao, D Sheng, J Bao, D Chen… - International …, 2023 - proceedings.mlr.press
Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training …
Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks …
S Lan, X Yang, Z Yu, Z Wu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask auto-labeling framework for instance segmentation using only box annotations. MAL takes …
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods …
Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic …
Z Liu, JH Liew, X Chen, J Feng - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Contour-based instance segmentation methods are attractive due to their efficiency. However, existing contour-based methods either suffer from lossy representation, complex …
Open-world instance segmentation is the task of grouping pixels into object instances without any pre-determined taxonomy. This is challenging, as state-of-the-art methods rely …