相关论文: A Unified Analysis of Mixed Sample Data Augmentati…

Data augmentation is an important technique in training deep neural networks as it enhances their ability to generalize and remain robust. While data augmentation is commonly used to expand the sample size and act as a consistency…

Size of the training dataset is an important factor in the performance of a machine learning algorithms and tools used in medical image processing are not exceptions. Machine learning tools normally require a decent amount of training data…

Unsupervised domain adaptation (UDA) addresses the problem of distribution shift between the unlabelled target domain and labelled source domain. While the single target domain adaptation (STDA) is well studied in the literature for both 2D…

In modern large-scale machine learning applications, the training data are often partitioned and stored on multiple machines. It is customary to employ the "data parallelism" approach, where the aggregated training loss is minimized without…

We investigate how pair-wise data augmentation techniques like Mixup affect the sample complexity of finding optimal decision boundaries in a binary linear classification problem. For a family of data distributions with a separability…

Synthetically augmenting training datasets with diffusion models has become an effective strategy for improving the generalization of image classifiers. However, existing approaches typically increase dataset size by 10-30x and struggle to…

Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on…

Recently, a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques, two or more randomly selected natural images are mixed together to generate an…

Automated data augmentation, which aims at engineering augmentation policy automatically, recently draw a growing research interest. Many previous auto-augmentation methods utilized a Density Matching strategy by evaluating policies in…

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…

Meta-learning methods typically follow a two-loop framework, where each loop potentially suffers from notorious overfitting, hindering rapid adaptation and generalization to new tasks. Existing schemes solve it by enhancing the…

Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often hampers accuracy. Mixed Precision (MP) mitigates this…

Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit…

For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…

The computational resources required to train a model have been increasing since the inception of deep networks. Training neural networks on massive datasets have become a challenging and time-consuming task. So, there arises a need to…

Data augmentation is one of the most effective techniques to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability in medical image analysis, it is frequently underutilized. This…

Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of…

Data augmentation has become a de facto component of deep learning-based medical image segmentation methods. Most data augmentation techniques used in medical imaging focus on spatial and intensity transformations to improve the diversity…

Existing detectors are often trained on biased datasets, leading to the possibility of overfitting on non-causal image attributes that are spuriously correlated with real/synthetic labels. While these biased features enhance performance on…

Motion recognition is a promising direction in computer vision, but the training of video classification models is much harder than images due to insufficient data and considerable parameters. To get around this, some works strive to…