Generalized uav object detection via frequency domain disentanglement

K Wang, X Fu, Y Huang, C Cao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract When deploying the Unmanned Aerial Vehicles object detection (UAV-OD) network
to complex and unseen real-world scenarios, the generalization ability is usually reduced …

Aloft: A lightweight mlp-like architecture with dynamic low-frequency transform for domain generalization

J Guo, N Wang, L Qi, Y Shi - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
Abstract Domain generalization (DG) aims to learn a model that generalizes well to unseen
target domains utilizing multiple source domains without re-training. Most existing DG works …

Decompose, adjust, compose: Effective normalization by playing with frequency for domain generalization

S Lee, J Bae, HY Kim - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
Abstract Domain generalization (DG) is a principal task to evaluate the robustness of
computer vision models. Many previous studies have used normalization for DG. In …

Unsupervised feature representation learning for domain-generalized cross-domain image retrieval

C Hu, C Zhang, GH Lee - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Cross-domain image retrieval has been extensively studied due to its high practical value. In
recently proposed unsupervised cross-domain image retrieval methods, efforts are taken to …

Treat noise as domain shift: Noise feature disentanglement for underwater perception and maritime surveys in side-scan sonar images

Y Yu, J Zhao, C Huang, X Zhao - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In underwater perception and maritime surveys, due to the scarcity of training data and
perturbation of speckle noise, the detection performance of underwater objects in side-scan …

Pasta: Proportional amplitude spectrum training augmentation for syn-to-real domain generalization

P Chattopadhyay, K Sarangmath… - Proceedings of the …, 2023 - openaccess.thecvf.com
Synthetic data offers the promise of cheap and bountiful training data for settings where
labeled real-world data is scarce. However, models trained on synthetic data significantly …

Distortion model-based spectral augmentation for generalized recaptured document detection

C Chen, B Li, R Cai, J Zeng… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Document recapturing is a presentation attack that covers the forensic traces in the digital
domain. Document presentation attack detection (DPAD) is an important step in the …

[HTML][HTML] Pseudo-set frequency refinement architecture for fine-grained few-shot class-incremental learning

Z Pan, W Zhang, X Yu, M Zhang, Y Gao - Pattern Recognition, 2024 - Elsevier
Few-shot class-incremental learning was introduced to solve the model adaptation problem
for new incremental classes with only a few examples while still remaining effective for old …

Spectral decomposition and transformation for cross-domain few-shot learning

Y Liu, Y Zou, R Li, Y Li - Neural Networks, 2024 - Elsevier
Cross-domain few-shot Learning (CDFSL) is proposed to first pre-train deep models on a
source domain dataset where sufficient data is available, and then generalize models to …

Learnable diffusion-based amplitude feature augmentation for object tracking in intelligent vehicles

Z Zhang, W Xue, Q Liu, K Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Data augmentation is an effective approach to enhance generalization of object tracking
models, which has been widely applied into intelligent transportation to handle the …