TL;DR
A Decoupled-Projection Prototype Alignment (DPA) module and a Geometric Alignment (GA) module are proposed to strengthen cross-branch feature interaction and achieve competitive performance against representative FSOD methods.
A confusion-resistant learning (CRL) is proposed, which contains a classification reweighting scheme (CRS) and an Edge-Vectors Cosine Similarity (EVCS) Loss, which builds upon the Kalman filtering IoU (KFIoU) loss.
Few-shot image classification remains difficult because a model must identify novel classes from only one or a few labeled examples while preserving discriminative local information. Metric-learning methods based on Earth Mover’s Distance (EMD) improve local correspondence by representing an image as a set of regional...
Results suggest that decoupled matching improves robustness to appearance-driven confusion in indoor point-cloud segmentation and propose D2M-Net, a decoupled dual-matching network that separates backbone features into geometry-oriented and semantic-oriented subspaces before prototype comparison.
DLPANet is proposed, a novel dual-level prototype alignment network centered on Prototype-Guided Spatial Attention, enabling simultaneous modeling of scene context and fine-grained details and demonstrates that the decoupled dual cross-attention mechanism provides superior prototype-query alignment compared to prior gl...
Oriented object detection in remote sensing images is challenged by arbitrary object orientations, large-scale variations, and complex backgrounds. In Oriented R-CNN, direct top-down feature fusion may attenuate local structural cues, while the shared representation in the RoI head may not adequately accommodate the di...
Deep-learning-based detectors for remote sensing object detection have achieved remarkable success, but their performance heavily depends on large-scale annotated datasets, which are costly and time-consuming. Few-shot remote sensing object detection has, therefore, emerged as a promising paradigm to recognize novel ca...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
