Related papers: Diagnosing Medical Datasets with Training Dynamics
It is well known that the quality and quantity of training data are significant factors which affect the development and performance of machine intelligence algorithms. Without representative data, neither scientists nor algorithms would be…
One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…
Recent diagnostic datasets on compositional generalization, such as SCAN (Lake and Baroni, 2018) and COGS (Kim and Linzen, 2020), expose severe problems in models trained from scratch on these datasets. However, in contrast to this poor…
The impressive advances and applications of large language and joint language-and-visual understanding models has led to an increased need for methods of probing their potential reasoning capabilities. However, the difficulty of gather…
Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the…
In a world where new domains are constantly discovered and machine learning (ML) is applied to automate new tasks every day, challenges arise with the number of samples available to train ML models. While the traditional ML training relies…
Robot learning holds the promise of learning policies that generalize broadly. However, such generalization requires sufficiently diverse datasets of the task of interest, which can be prohibitively expensive to collect. In other fields,…
The success of automated driving deployment is highly depending on the ability to develop an efficient and safe driving policy. The problem is well formulated under the framework of optimal control as a cost optimization problem. Model…
During the past decade, several areas of speech and language understanding have witnessed substantial breakthroughs from the use of data-driven models. In the area of dialogue systems, the trend is less obvious, and most practical systems…
Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…
Mislabeled, duplicated, or biased data in real-world scenarios can lead to prolonged training and even hinder model convergence. Traditional solutions prioritizing easy or hard samples lack the flexibility to handle such a variety…
Embodied foundation models are increasingly performant in real-world domains such as robotics or autonomous driving. These models are often deployed in interactive or assistive settings, where it is important that these assistive models…
Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…
We explore semantic segmentation beyond the conventional, single-dataset homogeneous training and bring forward the problem of Heterogeneous Training of Semantic Segmentation (HTSS). HTSS involves simultaneous training on multiple…
Compared to current AI or robotic systems, humans navigate their environment with ease, making tasks such as data collection trivial. However, humans find it harder to model complex relationships hidden in the data. AI systems, especially…
Annotation scarcity is a long-standing problem in medical image analysis area. To efficiently leverage limited annotations, abundant unlabeled data are additionally exploited in semi-supervised learning, while well-established…
To realize the full potential of deep learning for medical imaging, large annotated datasets are required for training. Such datasets are difficult to acquire because labeled medical images are not usually available due to privacy issues,…
Autonomous driving algorithms rely heavily on learning-based models, which require large datasets for training. However, there is often a large amount of redundant information in these datasets, while collecting and processing these…
Synthetic data sets are used across linguistic domains and NLP tasks, particularly in scenarios where authentic data is limited (or even non-existent). One such domain is that of clinical (healthcare) contexts, where there exist significant…
Creating a dataset for training supervised machine learning algorithms can be a demanding task. This is especially true for medical image segmentation since one or more specialists are usually required for image annotation, and creating…