Semantic-aware domain generalized segmentation
Deep models trained on source domain lack generalization when evaluated on unseen
target domains with different data distributions. The problem becomes even more …
target domains with different data distributions. The problem becomes even more …
Towards a Transitional Weather Scene Recognition Approach for Autonomous Vehicles
Driving in adverse weather conditions is a key challenge for autonomous vehicles (AV).
Typical scene perception models perform poorly in rainy, foggy, snowy, and cloudy …
Typical scene perception models perform poorly in rainy, foggy, snowy, and cloudy …
Attention, please! A survey of neural attention models in deep learning
A de Santana Correia, EL Colombini - Artificial Intelligence Review, 2022 - Springer
In humans, Attention is a core property of all perceptual and cognitive operations. Given our
limited ability to process competing sources, attention mechanisms select, modulate, and …
limited ability to process competing sources, attention mechanisms select, modulate, and …
Multi-scale self-guided attention for medical image segmentation
Even though convolutional neural networks (CNNs) are driving progress in medical image
segmentation, standard models still have some drawbacks. First, the use of multi-scale …
segmentation, standard models still have some drawbacks. First, the use of multi-scale …
Scene segmentation with dual relation-aware attention network
In this article, we propose a Dual Relation-aware Attention Network (DRANet) to handle the
task of scene segmentation. How to efficiently exploit context is essential for pixel-level …
task of scene segmentation. How to efficiently exploit context is essential for pixel-level …
ABMDRNet: Adaptive-weighted bi-directional modality difference reduction network for RGB-T semantic segmentation
Semantic segmentation models gain robustness against poor lighting conditions by virtue of
complementary information from visible (RGB) and thermal images. Despite its importance …
complementary information from visible (RGB) and thermal images. Despite its importance …
Glaucoma detection using image processing techniques: A literature review
The term glaucoma refers to a group of heterogeneous diseases that cause the
degeneration of retinal ganglion cells (RGCs). The degeneration of RGCs leads to two main …
degeneration of retinal ganglion cells (RGCs). The degeneration of RGCs leads to two main …
Decoders matter for semantic segmentation: Data-dependent decoding enables flexible feature aggregation
Recent semantic segmentation methods exploit encoder-decoder architectures to produce
the desired pixel-wise segmentation prediction. The last layer of the decoders is typically a …
the desired pixel-wise segmentation prediction. The last layer of the decoders is typically a …
CANet: Co-attention network for RGB-D semantic segmentation
Incorporating the depth (D) information to RGB images has proven the effectiveness and
robustness in semantic segmentation. However, the fusion between them is not trivial due to …
robustness in semantic segmentation. However, the fusion between them is not trivial due to …
Efficient semantic segmentation with pyramidal fusion
Emergence of large datasets and resilience of convolutional models have enabled
successful training of very large semantic segmentation models. However, high capacity …
successful training of very large semantic segmentation models. However, high capacity …