Related papers: Learn to Accumulate Evidence from All Training Sam…
Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches…
Although evidence integration to the boundary model has successfully explained a wide range of behavioral and neural data in decision making under uncertainty, how animals learn and optimize the boundary remains unresolved. Here, we propose…
Fine-tuned large language models (LLMs) often exhibit overconfidence, particularly when trained on small datasets, resulting in poor calibration and inaccurate uncertainty estimates. Evidential Deep Learning (EDL), an uncertainty-aware…
Although the existing uncertainty-based semi-supervised medical segmentation methods have achieved excellent performance, they usually only consider a single uncertainty evaluation, which often fails to solve the problem related to…
Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…
In this work, we examine the effectiveness of an uncertainty quantification framework known as Evidential Deep Learning applied in the context of biomedical image segmentation. This class of models involves assigning Dirichlet distributions…
The combination of deep neural nets and theory-driven models, which we call deep grey-box modeling, can be inherently interpretable to some extent thanks to the theory backbone. Deep grey-box models are usually learned with a regularized…
There are two major types of uncertainty one can model. Aleatoric uncertainty captures noise inherent in the observations. On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained…
A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…
In real-world scenarios, typical visual recognition systems could fail under two major causes, i.e., the misclassification between known classes and the excusable misbehavior on unknown-class images. To tackle these deficiencies, flexible…
Understanding the process of learning in neural networks is crucial for improving their performance and interpreting their behavior. This can be approximately understood by asking how a model's output is influenced when we fine-tune on a…
We investigate active learning in the context of deep neural network models for change detection and map updating. Active learning is a natural choice for a number of remote sensing tasks, including the detection of local surface changes:…
Contrastive approaches to representation learning have recently shown great promise. In contrast to generative approaches, these contrastive models learn a deterministic encoder with no notion of uncertainty or confidence. In this paper, we…
Deep learning achieves remarkable generalization capability with overwhelming number of model parameters. Theoretical understanding of deep learning generalization receives recent attention yet remains not fully explored. This paper…
Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…
Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimization of norms may…
Scientists need to compare the support for models based on observed phenomena. The main goal of the evidential paradigm is to quantify the strength of evidence in the data for a reference model relative to an alternative model. This is done…
Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization --…
Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate…
Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…