Learning from noisy labels with deep neural networks: A survey
Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …
amounts of big data. However, the quality of data labels is a concern because of the lack of …
Instance-dependent label-noise learning with manifold-regularized transition matrix estimation
In label-noise learning, estimating the transition matrix has attracted more and more
attention as the matrix plays an important role in building statistically consistent classifiers …
attention as the matrix plays an important role in building statistically consistent classifiers …
Sample selection with uncertainty of losses for learning with noisy labels
In learning with noisy labels, the sample selection approach is very popular, which regards
small-loss data as correctly labeled during training. However, losses are generated on-the …
small-loss data as correctly labeled during training. However, losses are generated on-the …
Dataset pruning: Reducing training data by examining generalization influence
The great success of deep learning heavily relies on increasingly larger training data, which
comes at a price of huge computational and infrastructural costs. This poses crucial …
comes at a price of huge computational and infrastructural costs. This poses crucial …
Bicro: Noisy correspondence rectification for multi-modality data via bi-directional cross-modal similarity consistency
As one of the most fundamental techniques in multimodal learning, cross-modal matching
aims to project various sensory modalities into a shared feature space. To achieve this …
aims to project various sensory modalities into a shared feature space. To achieve this …
Beyond images: Label noise transition matrix estimation for tasks with lower-quality features
The label noise transition matrix, denoting the transition probabilities from clean labels to
noisy labels, is crucial for designing statistically robust solutions. Existing estimators for …
noisy labels, is crucial for designing statistically robust solutions. Existing estimators for …
Mutual quantization for cross-modal search with noisy labels
Deep cross-modal hashing has become an essential tool for supervised multimodal search.
These models tend to be optimized with large, curated multimodal datasets, where most …
These models tend to be optimized with large, curated multimodal datasets, where most …
Optical remote sensing image understanding with weak supervision: Concepts, methods, and perspectives
In recent years, supervised learning has been widely used in various tasks of optical remote
sensing image (RSI) understanding, including RSI classification, pixel-wise segmentation …
sensing image (RSI) understanding, including RSI classification, pixel-wise segmentation …
Weak proxies are sufficient and preferable for fairness with missing sensitive attributes
Evaluating fairness can be challenging in practice because the sensitive attributes of data
are often inaccessible due to privacy constraints. The go-to approach that the industry …
are often inaccessible due to privacy constraints. The go-to approach that the industry …
Bridging the gap between few-shot and many-shot learning via distribution calibration
A major gap between few-shot and many-shot learning is the data distribution empirically
oserved by the model during training. In few-shot learning, the learned model can easily …
oserved by the model during training. In few-shot learning, the learned model can easily …