The paper proposes a method that first pre‑trains a feature extractor on the target dataset using in‑domain self‑supervised learning (SSL) without labels, then performs standard supervised training on the same noisy dataset. This two‑stage approach eliminates the need for a clean label subset and consistently improves classification accuracy and label‑error detection across synthetic and real‑world noise, especially as noise rates increase. Experiments show that the method matches or surpasses ImageNet and DinoV2 pre‑training, particularly under high noise conditions.
By David Szczecina, Nicholas Pellegrino, Paul Fieguth
arXiv:2407.05389v2 Announce Type: replace-cross
Abstract: Underwater image enhancement (UIE) has attracted much attention owing to its importance for underwater operation and marine engineering. Moti...
By Xingyang Nie, Caoliang Zhang, Xiaoyu Zhai, Fengzhong Qu, Biao Wang, Huilin Ge
Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\textbf{AquaStereo}$, a perception-enhanced framework with a data simulation pipeline and a self-distillation strategy that jointly address data scarcity and feature degradation in underwater stereo matching.
arXiv:2507.08375v2 Announce Type: replace
Abstract: Video restoration and enhancement are critical not only for improving visual quality, but also as essential pre-processing steps to boost the perfo...
By Alexandra Malyugina, Yini Li, Joanne Lin, Nantheera Anantrasirichai
arXiv:2608. 08965v1 Announce Type: new Abstract: Underwater images often suffer from diverse and coexisting degradations, including color distortion, scattering haze, texture attenuation, and uneven illumination.
By Weifeng Kong, Chenghao Xu, Lin Chen, Ziheng Cao, Guanying Huo
arXiv:2608.23215v1 Announce Type: cross
Abstract: Automated perception in side-scan sonar (SSS) imagery is severely hindered by physical acoustic artifacts, resulting in representations that inextric...
By Taqi Hamoda, Hayat Rajani, Nuno Gracias
arXiv:2609.18069v1 Announce Type: new
Abstract: Underwater semantic segmentation is essential for marine ecosystem monitoring, yet remains challenging due to severe visual degradation. Light absorpti...
By Xian Wu, Xinjin Li, Yiliu Xu, Yining Liu, Yong Jiang
arXiv:2608. 03218v1 Announce Type: cross Abstract: Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility.
By Mingzhuo Li, Guang Li, Linfeng Ye, Jiafeng Mao, Takahiro Ogawa, Konstantinos N. Plataniotis, Miki Haseyama
arXiv:2601.14180v5 Announce Type: replace
Abstract: Self-supervised learning has been increasingly investigated for low-dose computed tomography (LDCT) image denoising, as it alleviates the dependenc...
By Yichao Liu, Zongru Shao, Rui Wen, Yueyang Teng, Junwen Guo
arXiv:2606. 11695v1 Announce Type: cross Abstract: High-quality labeled data is essential for training reliable ML/DL models.
By Ha-Linh Nguyen, Hong-Anh Nguyen, Minh-Duc La, Phong Lam, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo
arXiv:2607. 05319v1 Announce Type: cross Abstract: We study why diffusion autoencoders can achieve similar image quality while learning substantially different latent structures.
By Rajat Rasal, Avinash Kori, Tian Xia, Ben Glocker
arXiv:2606. 07086v1 Announce Type: cross Abstract: Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets.
By Chen-Hsuan Fang, Wei-Hsinag Chen, Pin-Hsuan Yu, Jung-Hua Wang, Tsung-Wei Pan