Pixel Voting Decoder : A novel decoder that regresses pixel relationships for segmentation
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 116438 |
Journal / Publication | Expert Systems with Applications |
Volume | 193 |
Online published | 31 Dec 2021 |
Publication status | Published - 1 May 2022 |
Link(s)
Abstract
With the rapid development of the convolutional neural network, both instance segmentation and semantic segmentation have achieved remarkable performances. Recently, many efforts have been made to use a unified Encoder-Decoder architecture to solve these two segmentation tasks simultaneously. The encoder extracts high-level features from the input images for both tasks. However, existing decoders cannot meet the performance requirements of these two tasks: the semantic segmentation decoder is not flexible enough for instance segmentation, and the instance segmentation decoder lacks the precision of semantic segmentation. Therefore, we introduce a novel Pixel Voting Decoder to satisfy both precision and flexibility. The proposed decoder regresses the interlayer pixel relationships between the input and output feature maps across the convolutional layers. Then, the pixel relationships are regarded as the pixel votes for dynamically decoding the higher level information from the encoder. Finally, we propose the dynamic deconvolution to make full use of the votes for each pixel during the decoding process. Meanwhile, the matrix computation for the dynamic deconvolution is designed to boost the calculation. Experiments show that the proposed method can achieve better performance than the well-known methods on both instance segmentation on the COCO dataset and semantic segmentation on the Cityscapes dataset. The matrix implementation of the dynamic deconvolution also shows its high efficiency and feasibility.
Research Area(s)
- Convolutional neural network, Dynamic deconvolution, Encoder-Decoder, Image segmentation, Pixel voting, Residual block
Bibliographic Note
Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).
Citation Format(s)
Pixel Voting Decoder: A novel decoder that regresses pixel relationships for segmentation. / Xian, Pengfei; Po, Lai-Man; Xiong, Jingjing et al.
In: Expert Systems with Applications, Vol. 193, 116438, 01.05.2022.
In: Expert Systems with Applications, Vol. 193, 116438, 01.05.2022.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review