Related papers: Dataset Augmentation in Feature Space
Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in…
Deep learning techniques are often criticized to heavily depend on a large quantity of labeled data. This problem is even more challenging in medical image analysis where the annotator expertise is often scarce. We propose a novel…
Data Augmentation (DA) -- enriching training data by adding synthetic samples -- is a technique widely adopted in Computer Vision (CV) and Natural Language Processing (NLP) tasks to improve models performance. Yet, DA has struggled to gain…
Data augmentation is commonly used for generating additional data from the available training data to achieve a robust estimation of the parameters of complex models like the one for speaker verification (SV), especially for under-resourced…
Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and…
It has been demonstrated that the amount of data is crucial in data-driven machine learning methods. Data is always valuable, but in some tasks, it is almost like gold. This occurs in engineering areas where data is scarce or very expensive…
Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample…
Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which search augmentation maximizing task loss, show significant…
Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra…
With promising empirical performance across a wide range of applications, synthetic data augmentation appears a viable solution to data scarcity and the demands of increasingly data-intensive models. Its effectiveness lies in expanding the…
Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…
The deployment of autonomous agents in real-world scenarios is challenged by "unknown unknowns", i.e. novel unexpected environments not encountered during training, such as degraded signs. While existing research focuses on anomaly…
Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…
Data Augmentation (DA) is frequently used to provide additional training data without extra human annotation automatically. However, data augmentation may introduce noisy data that impairs training. To guarantee the quality of augmented…
Data augmentation is widely used to enhance generalization in visual classification tasks. However, traditional methods struggle when source and target domains differ, as in domain adaptation, due to their inability to address domain gaps.…
Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…
The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the…
Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…
Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant…
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…