Related papers: Rashomon Sets for Prototypical-Part Networks: Edit…
While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming.…
Few-shot segmentation targets to segment new classes with few annotated images provided. It is more challenging than traditional semantic segmentation tasks that segment known classes with abundant annotated images. In this paper, we…
Predictive multiplicity refers to the phenomenon in which classification tasks may admit multiple competing models that achieve almost-equally-optimal performance, yet generate conflicting outputs for individual samples. This presents…
To meet the demands of applications like robotics and autonomous driving that require real-time responses to dynamic environments, efficient continual learning methods suitable for edge devices have attracted increasing attention. In this…
Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…
Interpretation and visualization of the behavior of detection transformers tends to highlight the locations in the image that the model attends to, but it provides limited insight into the \emph{semantics} that the model is focusing on.…
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering RNN-based approaches is improving their explainability and interpretability. In this work we present MEME: a model…
Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called…
Prototype-based methods are of the particular interest for domain specialists and practitioners as they summarize a dataset by a small set of representatives. Therefore, in a classification setting, interpretability of the prototypes is as…
Open-set few-shot image classification aims to train models using a small amount of labeled data, enabling them to achieve good generalization when confronted with unknown environments. Existing methods mainly use visual information from a…
The ability to interpret machine learning model decisions is critical in such domains as healthcare, where trust in model predictions is as important as their accuracy. Inspired by the development of prototype parts-based deep neural…
The Rashomon Effect describes the following phenomenon: for a given dataset there may exist many models with equally good performance but with different solution strategies. The Rashomon Effect has implications for Explainable Machine…
Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g.,…
The Rashomon effect presents a significant challenge in model selection. It occurs when multiple models achieve similar performance on a dataset but produce different predictions, resulting in predictive multiplicity. This is especially…
Concept bottleneck models (CBMs) are a class of interpretable neural network models that predict the target response of a given input based on its high-level concepts. Unlike the standard end-to-end models, CBMs enable domain experts to…
In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks.…
Robust model predictive control algorithms are essential for addressing unavoidable errors due to the uncertainty in predicting real-world systems. However, the formulation of such algorithms typically results in a trade-off between…
Deep learning models have achieved high performance in medical applications, however, their adoption in clinical practice is hindered due to their black-box nature. Self-explainable models, like prototype-based models, can be especially…
Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points. However, the limited interpretability of these systems…
Molecular property prediction is essential in a variety of contemporary scientific fields, such as drug development and designing energy storage materials. Although there are many machine learning models available for this purpose, those…