Related papers: Studying How to Efficiently and Effectively Guide …

Predictive coding networks are neural models that perform inference through an iterative energy minimization process, whose operations are local in space and time. While effective in shallow architectures, they suffer significant…

The success of deep neural networks (DNNs) is attributable to three factors: increased compute capacity, more complex models, and more data. These factors, however, are not always present, especially for edge applications such as autonomous…

Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a…

Deep neural networks (DNNs) have demonstrated exceptional performance across various image segmentation tasks. However, the process of preparing datasets for training segmentation DNNs is both labor-intensive and costly, as it typically…

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a…

Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text…

Explanation-guided learning (EGL) has shown promise in aligning model predictions with interpretable reasoning, particularly in computer vision tasks. However, most approaches rely on external annotations or heuristic-based segmentation to…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Deep neural networks can be unreliable in the real world when the training set does not adequately cover all the settings where they are deployed. Focusing on image classification, we consider the setting where we have an error distribution…

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Regression problems assume every instance is annotated (labeled) with a real value, a form of annotation we call \emph{strong guidance}. In order for these annotations to be accurate, they must be the result of a precise experiment or…

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…

Current foundation models have shown impressive performance across various tasks. However, several studies have revealed that these models are not effective for everyone due to the imbalanced geographical and economic representation of the…

Fine-grained annotations---e.g. dense image labels, image segmentation and text tagging---are useful in many ML applications but they are labor-intensive to generate. Moreover there are often systematic, structured errors in these…

Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world applications to justify their reliability. Many example-based…

Deep Neural Networks (DNNs) tend to accrue technical debt and suffer from significant retraining costs when adapting to evolving requirements. Modularizing DNNs offers the promise of improving their reusability. Previous work has proposed…

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…

Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…