Multi-scale contrastive adaptor learning for segmenting anything in underperformed scenes
K Zhou, Z Qiu, D Fu - Neurocomputing, 2024 - Elsevier
Foundational vision models, such as the Segment Anything Model (SAM), have achieved
significant breakthroughs through extensive pre-training on large-scale visual datasets …
significant breakthroughs through extensive pre-training on large-scale visual datasets …
Zero-Reference Low-Light Enhancement via Physical Quadruple Priors
Understanding illumination and reducing the need for supervision pose a significant
challenge in low-light enhancement. Current approaches are highly sensitive to data usage …
challenge in low-light enhancement. Current approaches are highly sensitive to data usage …
A Wavelet-Based Memory Autoencoder for Noncontact Fingerprint Presentation Attack Detection
YP Liu, H Yu, H Fang, Z Li, P Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Fingerprint presentation attack detection (FPAD) is essential in fingerprint identification
systems. Noncontact methods such as fingerprint biometrics are becoming popular because …
systems. Noncontact methods such as fingerprint biometrics are becoming popular because …
3DAttGAN: A 3D Attention-Based Generative Adversarial Network for Joint Space-Time Video Super-Resolution
Joint space-time video super-resolution aims to increase both the spatial resolution and the
frame rate of a video sequence. As a result, details become more apparent, leading to a …
frame rate of a video sequence. As a result, details become more apparent, leading to a …
A Hybrid Transformer-Mamba Network for Single Image Deraining
Existing deraining Transformers employ self-attention mechanisms with fixed-range
windows or along channel dimensions, limiting the exploitation of non-local receptive fields …
windows or along channel dimensions, limiting the exploitation of non-local receptive fields …
Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Data
G Song, D Fu, Z Qiu, J Meng, D Zhang - arXiv preprint arXiv:2409.07942, 2024 - arxiv.org
Uncertainty estimation is crucial in scientific data for machine learning. Current uncertainty
estimation methods mainly focus on the model's inherent uncertainty, while neglecting the …
estimation methods mainly focus on the model's inherent uncertainty, while neglecting the …
Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution
By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution
ones, space-time video super-resolution techniques can enhance visual experiences and …
ones, space-time video super-resolution techniques can enhance visual experiences and …