HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
G Xu, W Jia, T Wu, L Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Both Convolutional Neural Networks (CNNs) and Transformers have shown great success
in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer …
in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer …
[HTML][HTML] DFLM-YOLO: A Lightweight YOLO Model with Multiscale Feature Fusion Capabilities for Open Water Aerial Imagery
C Sun, Y Zhang, S Ma - Drones, 2024 - mdpi.com
Object detection algorithms for open water aerial images present challenges such as small
object size, unsatisfactory detection accuracy, numerous network parameters, and …
object size, unsatisfactory detection accuracy, numerous network parameters, and …
Interactive segmentation based on deformable convolution and context feature calibration
S Song - … on Electronic Information Engineering and Data …, 2024 - spiedigitallibrary.org
The advantage of interactive segmentation is that it can be adjusted in real-time according to
user requests and feedback, leading to more precise and expected segmentation results …
user requests and feedback, leading to more precise and expected segmentation results …