A survey on instance segmentation: state of the art

AM Hafiz, GM Bhat - International journal of multimedia information …, 2020 - Springer
Object detection or localization is an incremental step in progression from coarse to fine
digital image inference. It not only provides the classes of the image objects, but also …

Image segmentation using deep learning: A survey

S Minaee, Y Boykov, F Porikli, A Plaza… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
Image segmentation is a key task in computer vision and image processing with important
applications such as scene understanding, medical image analysis, robotic perception …

Rtmdet: An empirical study of designing real-time object detectors

C Lyu, W Zhang, H Huang, Y Zhou, Y Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO
series and is easily extensible for many object recognition tasks such as instance …

Exploring cross-image pixel contrast for semantic segmentation

W Wang, T Zhou, F Yu, J Dai… - Proceedings of the …, 2021 - openaccess.thecvf.com
Current semantic segmentation methods focus only on mining" local" context, ie,
dependencies between pixels within individual images, by context-aggregation modules …

Max-deeplab: End-to-end panoptic segmentation with mask transformers

H Wang, Y Zhu, H Adam, A Yuille… - Proceedings of the …, 2021 - openaccess.thecvf.com
Abstract We present MaX-DeepLab, the first end-to-end model for panoptic segmentation.
Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks …

Learning equivariant segmentation with instance-unique querying

W Wang, J Liang, D Liu - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in
which instance masks are derived by querying the image feature using a set of instance …

Axial-deeplab: Stand-alone axial-attention for panoptic segmentation

H Wang, Y Zhu, B Green, H Adam, A Yuille… - European conference on …, 2020 - Springer
Convolution exploits locality for efficiency at a cost of missing long range context. Self-
attention has been adopted to augment CNNs with non-local interactions. Recent works …

Panoptic-deeplab: A simple, strong, and fast baseline for bottom-up panoptic segmentation

B Cheng, MD Collins, Y Zhu, T Liu… - Proceedings of the …, 2020 - openaccess.thecvf.com
In this work, we introduce Panoptic-DeepLab, a simple, strong, and fast system for panoptic
segmentation, aiming to establish a solid baseline for bottom-up methods that can achieve …

Cmt-deeplab: Clustering mask transformers for panoptic segmentation

Q Yu, H Wang, D Kim, S Qiao… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based
framework for panoptic segmentation designed around clustering. It rethinks the existing …

Polarmask: Single shot instance segmentation with polar representation

E Xie, P Sun, X Song, W Wang, X Liu… - Proceedings of the …, 2020 - openaccess.thecvf.com
In this paper, we introduce an anchor-box free and single shot instance segmentation
method, which is conceptually simple, fully convolutional and can be used by easily …