RONO: robust discriminative learning with noisy labels for 2D-3D cross-modal retrieval
Recently, with the advent of Metaverse and AI Generated Content, cross-modal retrieval
becomes popular with a burst of 2D and 3D data. However, this problem is challenging …
becomes popular with a burst of 2D and 3D data. However, this problem is challenging …
Adaptive integration of partial label learning and negative learning for enhanced noisy label learning
There has been significant attention devoted to the effectiveness of various domains, such
as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the …
as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the …
Joint semantic preserving sparse hashing for cross-modal retrieval
Supervised cross-modal hashing has received wide attention in recent years. However,
existing methods primarily rely on sample-wise semantic relationships to evaluate the …
existing methods primarily rely on sample-wise semantic relationships to evaluate the …
A survey of dataset refinement for problems in computer vision datasets
Large-scale datasets have played a crucial role in the advancement of computer vision.
However, they often suffer from problems such as class imbalance, noisy labels, dataset …
However, they often suffer from problems such as class imbalance, noisy labels, dataset …
Unsupervised hashing retrieval via efficient correlation distillation
Z Xi, X Wang, P Cheng - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
Deep hashing has been widely used in multimedia retrieval systems due to its storage and
computation efficiency. Unsupervised hashing has received a lot of attention in recent years …
computation efficiency. Unsupervised hashing has received a lot of attention in recent years …
Data-aware proxy hashing for cross-modal retrieval
Recently, numerous proxy hash code based methods, which sufficiently exploit the label
information of data to supervise the training of hashing models, have been proposed …
information of data to supervise the training of hashing models, have been proposed …
Paddles: Phase-amplitude spectrum disentangled early stopping for learning with noisy labels
Abstract Convolutional Neural Networks (CNNs) are powerful in learning patterns of different
vision tasks, but they are sensitive to label noise and may overfit to noisy labels during …
vision tasks, but they are sensitive to label noise and may overfit to noisy labels during …
Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection
Learning with noisy labels has gained increasing attention because the inevitable imperfect
labels in real-world scenarios can substantially hurt the deep model performance. Recent …
labels in real-world scenarios can substantially hurt the deep model performance. Recent …
Proxy-based graph convolutional hashing for cross-modal retrieval
Cross-modal hashing retrieval approaches have received extensive attention owing to their
storage superiority and retrieval efficiency. To achieve better retrieval performances …
storage superiority and retrieval efficiency. To achieve better retrieval performances …
Robust Noisy Correspondence Learning with Equivariant Similarity Consistency
Y Yang, L Wang, E Yang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
The surge in multi-modal data has propelled cross-modal matching to the forefront of
research interest. However the challenge lies in the laborious and expensive process of …
research interest. However the challenge lies in the laborious and expensive process of …