相关论文: Interpretable Failure Detection with Human-Level C…

Deep neural networks have recently advanced the state-of-the-art in image compression and surpassed many traditional compression algorithms. The training of such networks involves carefully trading off entropy of the latent representation…

While significant advances exist in pseudo-label generation for semi-supervised semantic segmentation, pseudo-label selection remains understudied. Existing methods typically use fixed confidence thresholds to retain high-confidence…

Deepfake detection remains a formidable challenge due to the complex and evolving nature of fake content in real-world scenarios. However, existing academic benchmarks suffer from severe discrepancies from industrial practice, typically…

Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model…

We study the problem of troubleshooting machine learning systems that rely on analytical pipelines of distinct components. Understanding and fixing errors that arise in such integrative systems is difficult as failures can occur at multiple…

In object detection with deep neural networks, the box-wise objectness score tends to be overconfident, sometimes even indicating high confidence in presence of inaccurate predictions. Hence, the reliability of the prediction and therefore…

We present a practical framework for detecting errors in LLM-generated SQL by estimating uncertainty at the level of individual nodes in the query's abstract syntax tree (AST). Our approach proceeds in two stages. First, we introduce a…

Machine Learning (ML) models are widely used in high-stakes domains such as healthcare, where the reliability of predictions is critical. However, these models often fail to account for uncertainty, providing predictions even with low…

Explainability of Deep Neural Networks (DNNs) has been garnering increasing attention in recent years. Of the various explainability approaches, concept-based techniques stand out for their ability to utilize human-meaningful concepts…

While advanced classifiers have been increasingly used in real-world safety-critical applications, how to properly evaluate the black-box models given specific human values remains a concern in the community. Such human values include…

Embedding is a common technique for analyzing multi-dimensional data. However, the embedding projection cannot always form significant and interpretable visual structures that foreshadow underlying data patterns. We propose an approach that…

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…

Concept probing has recently garnered increasing interest as a way to help interpret artificial neural networks, dealing both with their typically large size and their subsymbolic nature, which ultimately renders them unfeasible for direct…

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…

Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses serious challenges in applications where reliable uncertainty…

Object detection in autonomous driving applications implies that the detection and tracking of semantic objects are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art…

Fake news detection has become a major task to solve as there has been an increasing number of fake news on the internet in recent years. Although many classification models have been proposed based on statistical learning methods showing…

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial intelligence. Two-stage approaches explicitly decouple DNN based perception from…

Purpose: Our study presents an enhanced approach to medical image caption generation by integrating concept detection into attention mechanisms. Method: This method utilizes sophisticated models to identify critical concepts within medical…