ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance Segmentation
This work addresses accurate and fast cell segmentation for biomedical imaging, presenting an incremental improvement over existing YOLO-based methods.
The paper tackles cell instance segmentation by proposing ASF-YOLO, a model that integrates attentional scale sequence fusion, achieving a mask mAP of 0.887 and 47.3 FPS on a dataset, outperforming state-of-the-art methods.
We propose a novel Attentional Scale Sequence Fusion based You Only Look Once (YOLO) framework (ASF-YOLO) which combines spatial and scale features for accurate and fast cell instance segmentation. Built on the YOLO segmentation framework, we employ the Scale Sequence Feature Fusion (SSFF) module to enhance the multi-scale information extraction capability of the network, and the Triple Feature Encoder (TFE) module to fuse feature maps of different scales to increase detailed information. We further introduce a Channel and Position Attention Mechanism (CPAM) to integrate both the SSFF and TPE modules, which focus on informative channels and spatial position-related small objects for improved detection and segmentation performance. Experimental validations on two cell datasets show remarkable segmentation accuracy and speed of the proposed ASF-YOLO model. It achieves a box mAP of 0.91, mask mAP of 0.887, and an inference speed of 47.3 FPS on the 2018 Data Science Bowl dataset, outperforming the state-of-the-art methods. The source code is available at https://github.com/mkang315/ASF-YOLO.