TGADHead: An efficient and accurate task-guided attention-decoupled head for single-stage object detection
F Zuo, J Liu, Z Chen, M Fu, L Wang - Knowledge-Based Systems, 2024 - Elsevier
In object detection, localization and classification of the targets are two fundamental
subtasks that underpin the application of many knowledge-based intelligent models in …
subtasks that underpin the application of many knowledge-based intelligent models in …
IdeNet: Making Neural Network Identify Camouflaged Objects Like Creatures
Camouflaged objects often blend in with their surroundings, making the perception of a
camouflaged object a more complex procedure. However, most neural-network-based …
camouflaged object a more complex procedure. However, most neural-network-based …
SDRNet: Camouflaged object detection with independent reconstruction of structure and detail
The simultaneous reconstruction of structure and detail is a prevalent strategy in
camouflaged object detection. However, the reconstruction features required for structure …
camouflaged object detection. However, the reconstruction features required for structure …
PFPS: Polymerized Feature Panoptic Segmentation Based on Fully Convolutional Networks
Panoptic segmentation requires the prediction of a pixel-level mask with a category label in
an image. In recent years, panoptic segmentation has been gaining more attention since it …
an image. In recent years, panoptic segmentation has been gaining more attention since it …
Cascade contour-enhanced panoptic segmentation for robotic vision perception
Y Xu, R Liu, D Zhu, L Chen, X Zhang, J Li - Frontiers in Neurorobotics, 2024 - frontiersin.org
Panoptic segmentation plays a crucial role in enabling robots to comprehend their
surroundings, providing fine-grained scene understanding information for robots' intelligent …
surroundings, providing fine-grained scene understanding information for robots' intelligent …
An Improved Shared Encoder-Based Model for Fast Panoptic Segmentation
J Ni, S Ren, G Tang, W Cao, P Shi - IEEE Sensors Journal, 2023 - ieeexplore.ieee.org
Panoptic segmentation aims to generate coherent scene segmentation by unifying semantic
segmentation and instance segmentation, which is one of the important tasks in the scene …
segmentation and instance segmentation, which is one of the important tasks in the scene …
Center-Guided Transformer for Panoptic Segmentation
A panoptic segmentation network to predict masks and classes for things and stuff in images
is proposed in this work. Recently, panoptic segmentation has been advanced through the …
is proposed in this work. Recently, panoptic segmentation has been advanced through the …