Spatial-aware feature aggregation for image based cross-view geo-localization
In this paper, we develop a new deep network to explicitly address these inherent
differences between ground and aerial views. We observe there exist some approximate …
differences between ground and aerial views. We observe there exist some approximate …
Detecting prohibited objects with physical size constraint from cluttered X-ray baggage images
X-ray baggage image inspection aims to detect prohibited objects. Existing inspection
systems often rely on humans to scrutinize X-ray images. Although several deep-learning …
systems often rely on humans to scrutinize X-ray images. Although several deep-learning …
HyNet: Learning local descriptor with hybrid similarity measure and triplet loss
In this paper, we investigate how L2 normalisation affects the back-propagated descriptor
gradients during training. Based on our observations, we propose HyNet, a new local …
gradients during training. Based on our observations, we propose HyNet, a new local …
D2D: Keypoint extraction with describe to detect approach
In this paper, we present a novel approach that exploits the information within the descriptor
space to propose keypoint locations. Detect then describe, or detect and describe jointly are …
space to propose keypoint locations. Detect then describe, or detect and describe jointly are …
Weakly supervised RGB-D salient object detection with prediction consistency training and active scribble boosting
RGB-D salient object detection (SOD) has attracted increasingly more attention as it shows
more robust results in complex scenes compared with RGB SOD. However, state-of-the-art …
more robust results in complex scenes compared with RGB SOD. However, state-of-the-art …
Dsc-posenet: Learning 6dof object pose estimation via dual-scale consistency
Compared to 2D object bounding-box labeling, it is very difficult for humans to annotate 3D
object poses, especially when depth images of scenes are unavailable. This paper …
object poses, especially when depth images of scenes are unavailable. This paper …
Bilaterally normalized scale-consistent sinkhorn distance for few-shot image classification
Few-shot image classification aims at exploring transferable features from base classes to
recognize images of the unseen novel classes with only a few labeled images. Existing …
recognize images of the unseen novel classes with only a few labeled images. Existing …
A novel feature selection strategy based on Salp swarm algorithm for plant disease detection
Deep learning has been widely used for plant disease recognition in smart agriculture and
has proven to be a powerful tool for image classification and pattern recognition. However, it …
has proven to be a powerful tool for image classification and pattern recognition. However, it …
Learning with noisy labels via self-reweighting from class centroids
Although deep neural networks have been proved effective in many applications, they are
data hungry, and training deep models often requires laboriously labeled data. However …
data hungry, and training deep models often requires laboriously labeled data. However …
Revisiting unsupervised local descriptor learning
W Wang, L Zhang, H Huang - Proceedings of the AAAI conference on …, 2023 - ojs.aaai.org
Constructing accurate training tuples is crucial for unsupervised local descriptor learning, yet
challenging due to the absence of patch labels. The state-of-the-art approach constructs …
challenging due to the absence of patch labels. The state-of-the-art approach constructs …