TY - GEN
T1 - DEEP MARKOV CLUSTERING FOR PANOPTIC SEGMENTATION
AU - Ye, Minxiang
AU - Zhang, Yifei
AU - Zhu, Shiqiang
AU - Xie, Anhuan
AU - Zhang, Dan
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022/5
Y1 - 2022/5
N2 - Panoptic segmentation is a challenging scene understanding task that unifies semantic segmentation and instance segmentation. Namely, each pixel of an image is assigned a semantic label and an instance id. Existing works have elaborated end-to-end panoptic segmentation networks and made great progress in non-proposal-based methods. In this work, we adopt a box-free strategy and incorporate a graph-based clustering method to merge repetitive kernel weights for object instances. An alternative graph-based clustering algorithm like Markov clustering performs effective random walks for unsupervised clustering without pre-defined cluster numbers. Our proposed deep Markov clustering scheme provides an efficient alternative to guarantee instance-aware label prediction in both training and inference stages. On the COCO dataset, our method achieves promising accuracy (PQ=42.1), which is comparable with state-of-the-art methods.
AB - Panoptic segmentation is a challenging scene understanding task that unifies semantic segmentation and instance segmentation. Namely, each pixel of an image is assigned a semantic label and an instance id. Existing works have elaborated end-to-end panoptic segmentation networks and made great progress in non-proposal-based methods. In this work, we adopt a box-free strategy and incorporate a graph-based clustering method to merge repetitive kernel weights for object instances. An alternative graph-based clustering algorithm like Markov clustering performs effective random walks for unsupervised clustering without pre-defined cluster numbers. Our proposed deep Markov clustering scheme provides an efficient alternative to guarantee instance-aware label prediction in both training and inference stages. On the COCO dataset, our method achieves promising accuracy (PQ=42.1), which is comparable with state-of-the-art methods.
KW - Graph Clustering
KW - Panoptic Segmentation
KW - Scene Understanding
UR - http://www.scopus.com/inward/record.url?scp=85131232375&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9747507
DO - 10.1109/ICASSP43922.2022.9747507
M3 - Conference article published in proceeding or book
AN - SCOPUS:85131232375
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 2380
EP - 2384
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Y2 - 23 May 2022 through 27 May 2022
ER -