A review on 2D instance segmentation based on deep neural networks

W Gu, S Bai, L Kong - Image and Vision Computing, 2022 - Elsevier
Image instance segmentation involves labeling pixels of images with classes and instances,
which is one of the pivotal technologies in many domains, such as natural scenes …

Recent advances in open set recognition: A survey

C Geng, S Huang, S Chen - IEEE transactions on pattern …, 2020 - ieeexplore.ieee.org
In real-world recognition/classification tasks, limited by various objective factors, it is usually
difficult to collect training samples to exhaust all classes when training a recognizer or …

Learning open-world object proposals without learning to classify

D Kim, TY Lin, A Angelova, IS Kweon… - IEEE Robotics and …, 2022 - ieeexplore.ieee.org
Object proposals have become an integral pre-processing step of many vision pipelines
including object detection, weakly supervised detection, object discovery, tracking, etc …

Towards unsupervised object detection from lidar point clouds

L Zhang, AJ Yang, Y ** and 3D object discovery
M Grinvald, F Furrer, T Novkovic… - IEEE Robotics and …, 2019 - ieeexplore.ieee.org
To autonomously navigate and plan interactions in real-world environments, robots require
the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides …

A survey on open-vocabulary detection and segmentation: Past, present, and future

C Zhu, L Chen - IEEE Transactions on Pattern Analysis and …, 2024 - ieeexplore.ieee.org
As the most fundamental scene understanding tasks, object detection and segmentation
have made tremendous progress in deep learning era. Due to the expensive manual …

Shapemask: Learning to segment novel objects by refining shape priors

W Kuo, A Angelova, J Malik… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Instance segmentation aims to detect and segment individual objects in a scene. Most
existing methods rely on precise mask annotations of every category. However, it is difficult …

Delving into shape-aware zero-shot semantic segmentation

X Liu, B Tian, Z Wang, R Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Thanks to the impressive progress of large-scale vision-language pretraining, recent
recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a …

Identifying unknown instances for autonomous driving

K Wong, S Wang, M Ren, M Liang… - Conference on Robot …, 2020 - proceedings.mlr.press
In the past few years, we have seen great progress in perception algorithms, particular
through the use of deep learning. However, most existing approaches focus on a few …

Opental: Towards open set temporal action localization

W Bao, Q Yu, Y Kong - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Abstract Temporal Action Localization (TAL) has experienced remarkable success under the
supervised learning paradigm. However, existing TAL methods are rooted in the closed set …