TY - GEN
T1 - Learning Task-Aligned Mask Query for Instance Segmentation
AU - Fu, Bin
AU - He, Hongliang
AU - Wei, Pengxu
AU - Chen, Jie
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Recently, query-based instance segmentation methods have achieved comparable performance to previous state-of-the-art methods. However, the query lacks the learning of the consistency between classification and segmentation tasks, which may lead to misalignment between classification score and mask quality (i.e., mask IoU) and can not result in a reliable ranking for predictions. In this work, we propose a novel instance segmentation method, termed AlignMask, which effectively learns task-aligned mask queries for instance end-toend. Specifically, we propose Aligned Query Learning (AQL) to learn task-aligned features for pixel embedding and transformer decoder, which helps segmentation quality estimation of the mask query. We also use Aligned Label Assignment to explicitly align the optimization goals for classification score and mask quality of the query. Extensive experiments on MSCOCO show that our proposed AlignMask achieves competitive performance with state-of-the-art models.
AB - Recently, query-based instance segmentation methods have achieved comparable performance to previous state-of-the-art methods. However, the query lacks the learning of the consistency between classification and segmentation tasks, which may lead to misalignment between classification score and mask quality (i.e., mask IoU) and can not result in a reliable ranking for predictions. In this work, we propose a novel instance segmentation method, termed AlignMask, which effectively learns task-aligned mask queries for instance end-toend. Specifically, we propose Aligned Query Learning (AQL) to learn task-aligned features for pixel embedding and transformer decoder, which helps segmentation quality estimation of the mask query. We also use Aligned Label Assignment to explicitly align the optimization goals for classification score and mask quality of the query. Extensive experiments on MSCOCO show that our proposed AlignMask achieves competitive performance with state-of-the-art models.
KW - Instance segmentation
KW - Label assignment
KW - Task-aligned query
KW - Transformer on set prediction
UR - https://www.scopus.com/pages/publications/85177551585
U2 - 10.1109/ICASSP49357.2023.10095603
DO - 10.1109/ICASSP49357.2023.10095603
M3 - Conference contribution
AN - SCOPUS:85177551585
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Y2 - 4 June 2023 through 10 June 2023
ER -