相关论文: Avoiding Leakage Poisoning: Concept Interventions …

Concept-based models are an emerging paradigm in deep learning that constrains the inference process to operate through human-interpretable variables, facilitating explainability and human interaction. However, these architectures, on par…

Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This…

Recent years have witnessed significant progress in the development of machine learning models across a wide range of fields, fueled by increased computational resources, large-scale datasets, and the rise of deep learning architectures.…

Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate representations through explicit concept activations. However, this interpretability…

Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world. To improve out-of-distribution (OOD) detection for…

Despite their remarkable performance on a wide range of visual tasks, machine learning technologies often succumb to data distribution shifts. Consequently, a range of recent work explores techniques for detecting these shifts.…

For a group of autonomous communicating agents, the ability to distinguish a meaningful input from disturbance, and come to collective agreement or disagreement in response to that input, is paramount for carrying out coordinated…

In this paper, we tackle the detection of out-of-distribution (OOD) objects in semantic segmentation. By analyzing the literature, we found that current methods are either accurate or fast but not both which limits their usability in real…

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how…

Interpretability and explainability of neural networks is continuously increasing in importance, especially within safety-critical domains and to provide the social right to explanation. Concept based explanations align well with how humans…

Data-driven molecular discovery leverages artificial intelligence/machine learning (AI/ML) and generative modeling to filter and design novel molecules. Discovering novel molecules requires accurate out-of-distribution (OOD) predictions,…

Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-trained vision-language model (i.e. CLIP). However, there exist two key limitations in concept…

Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We introduce OCCAM, a framework for open-set causal concept explanation and ontology…

Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or from OoD. Diffusion Models (DMs) are recently utilized in OoD…

We introduce Class Distribution Monitoring (CDM), an effective concept-drift detection scheme that monitors the class-conditional distributions of a datastream. In particular, our solution leverages multiple instances of an online and…

Concept Bottleneck Models (CBMs) map the black-box visual representations extracted by deep neural networks onto a set of interpretable concepts and use the concepts to make predictions, enhancing the transparency of the decision-making…

Interventions in language models (LMs) are applied strategically to steer model behavior during the forward pass. Learnable interventions, also known as representation fine-tuning, aim to apply pointwise control within the concept subspace…

In safety-critical Cyber-Physical Systems (CPS), accurate trajectory prediction provides vital guidance for downstream planning and control, yet although deep learning models achieve high-fidelity forecasts on validation data, their…

With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this…

In the realm of task-oriented dialogue systems, a robust intent detection mechanism must effectively handle malformed utterances encountered in real-world scenarios. This study presents a novel fine-tuning framework for large language…