Related papers: Shortcut Invariance: Targeted Jacobian Regularizat…
Although deep learning models in medical imaging often achieve excellent classification performance, they can rely on shortcut learning, exploiting spurious correlations or confounding factors that are not causally related to the target…
Deep neural networks often exploit shortcuts. These are spurious cues which are associated with output labels in the training data but are unrelated to task semantics. When the shortcut features are associated with sensitive attributes,…
Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…
Out-of-Distribution (OOD) generalization has become a primary metric for evaluating image analysis systems. Since deep learning models tend to capture domain-specific context, they often develop shortcut dependencies on these non-causal…
Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD)…
Labeled data is a fundamental component in training supervised deep learning models for computer vision tasks. However, the labeling process, especially for ordinal image classification where class boundaries are often ambiguous, is prone…
Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training targets, their last-layer features, together with the…
Despite that deep learning has achieved state-of-the-art performance for medical image segmentation, its success relies on a large set of manually annotated images for training that are expensive to acquire. In this paper, we propose an…
Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often…
Obtaining pixel-level annotations in the medical domain is both expensive and time-consuming, often requiring close collaboration between clinical experts and developers. Semi-supervised medical image segmentation aims to leverage limited…
Modern neural network architectures often generalize well despite containing many more parameters than the size of the training dataset. This paper explores the generalization capabilities of neural networks trained via gradient descent. We…
This work tackles a central machine learning problem of performance degradation on out-of-distribution (OOD) test sets. The problem is particularly salient in medical imaging based diagnosis system that appears to be accurate but fails when…
In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…
A critical vulnerability of supervised deep learning in high-dimensional tabular domains is "generalization collapse": models form precise decision boundaries around known training distributions but fail catastrophically when encountering…
Deep learning models are prone to learning shortcut solutions to problems using spuriously correlated yet irrelevant features of their training data. In high-risk applications such as medical image analysis, this phenomenon may prevent…
Deep neural networks often fail to generalize outside of their training distribution, in particular when only a single data domain is available during training. While test-time adaptation has yielded encouraging results in this setting, we…
Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the…
In the era of foundation models, Out-of- Distribution (OOD) problems, i.e., the data discrepancy between the training environments and testing environments, hinder AI generalization. Further, relational data like graphs disobeying the…
Noisy labels can significantly affect the performance of deep neural networks (DNNs). In medical image segmentation tasks, annotations are error-prone due to the high demand in annotation time and in the annotators' expertise. Existing…
We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…