Detrs with collaborative hybrid assignments training
In this paper, we provide the observation that too few queries assigned as positive samples
in DETR with one-to-one set matching leads to sparse supervision on the encoder's output …
in DETR with one-to-one set matching leads to sparse supervision on the encoder's output …
Detrdistill: A universal knowledge distillation framework for detr-families
Transformer-based detectors (DETRs) are becoming popular for their simple framework, but
the large model size and heavy time consumption hinder their deployment in the real world …
the large model size and heavy time consumption hinder their deployment in the real world …
Fully sparse transformer 3D detector for LiDAR point cloud
The 3-D object detector usually uses a framework similar to 2-D detection and benefits from
the advancements of 2-D detection tasks. In these frameworks, it is necessary to make the …
the advancements of 2-D detection tasks. In these frameworks, it is necessary to make the …
An improved YOLOv5 underwater detector based on an attention mechanism and multi-branch Reparameterization module
J Zhang, H Chen, X Yan, K Zhou, J Zhang, Y Zhang… - Electronics, 2023 - mdpi.com
Underwater target detection is a critical task in various applications, including environmental
monitoring, underwater exploration, and marine resource management. As the demand for …
monitoring, underwater exploration, and marine resource management. As the demand for …
Visual Detection Algorithm for Enhanced Environmental Perception of Unmanned Surface Vehicles in Complex Marine Environments
K Dong, T Liu, Y Zheng, Z Shi, H Du… - Journal of Intelligent & …, 2024 - Springer
Unmanned surface vehicles (USVs) are distinguished by their intelligence, compactness,
and absence of human casualties, making them a vital component of the maritime industry …
and absence of human casualties, making them a vital component of the maritime industry …
Spatial-temporal enhanced transformer towards multi-frame 3d object detection
The Detection Transformer (DETR) has revolutionized the design of CNN-based object
detection systems, showcasing impressive performance. However, its potential in the …
detection systems, showcasing impressive performance. However, its potential in the …
Efficient Task-specific Feature Re-fusion for More Accurate Object Detection and Instance Segmentation
Feature pyramid representations have been widely adopted in the object detection literature
for better handling of variations in scale, which provide abundant information from various …
for better handling of variations in scale, which provide abundant information from various …
Dynamic Cascade Query Slection for Oriented Object Detection
Q Zeng, X Ran, H Zhu, Y Gao, X Qiu… - IEEE Geoscience and …, 2023 - ieeexplore.ieee.org
Most of the existing object detection methods have complicated hand-designed
components, such as nonmaximum suppression procedures and manual resizing of anchor …
components, such as nonmaximum suppression procedures and manual resizing of anchor …
Lightweight image super-resolution based on stepwise feedback mechanism and multi-feature maps fusion
X Yao, H Chen, Y Li, J Sun, J Wei - Multimedia Systems, 2024 - Springer
In recent years, deep learning has made remarkable breakthroughs in single-image super-
resolution (SISR). However, the improvements often come with the increased network size …
resolution (SISR). However, the improvements often come with the increased network size …
Multi‐Scale Feature Attention‐DEtection TRansformer: Multi‐Scale Feature Attention for security check object detection
X‐ray security checks aim to detect contraband in luggage; however, the detection accuracy
is hindered by the overlapping and significant size differences of objects in X‐ray images. To …
is hindered by the overlapping and significant size differences of objects in X‐ray images. To …