Related papers: Discovering Fine-Grained Visual-Concept Relations …

Vision-and-language (V-L) tasks require the system to understand both vision content and natural language, thus learning fine-grained joint representations of vision and language (a.k.a. V-L representations) is of paramount importance.…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…

Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning algorithms extract a transferable embedding from seen classes…

The network trained for domain adaptation is prone to bias toward the easy-to-transfer classes. Since the ground truth label on the target domain is unavailable during training, the bias problem leads to skewed predictions, forgetting to…

Concept Bottleneck Models (CBMs) aim to enhance interpretability by structuring predictions around human-understandable concepts. However, unintended information leakage, where predictive signals bypass the concept bottleneck, compromises…

In this paper, we introduce an explainable algorithm designed from a multi-modal foundation model, that performs fast and explainable image classification. Drawing inspiration from CLIP-based Concept Bottleneck Models (CBMs), our method…

Spectral clustering is a leading clustering method. Two of its major shortcomings are the disjoint optimization process and the limited representation capacity. To address these issues, we propose a deep spectral clustering model (named…

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…

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain…

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar…

We are concerned with the challenge of reliably classifying and assessing intracranial aneurysms using deep learning without compromising clinical transparency. While traditional black-box models achieve high predictive accuracy, their lack…

Intelligent vehicular communication with vehicle road collaboration capability is a key technology enabled by 6G, and the integration of various visual sensors on vehicles and infrastructures plays a crucial role. Moreover, accurate channel…

Although multi-view learning has made signifificant progress over the past few decades, it is still challenging due to the diffificulty in modeling complex correlations among different views, especially under the context of view missing. To…

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to…

Semantic image and video segmentation stand among the most important tasks in computer vision nowadays, since they provide a complete and meaningful representation of the environment by means of a dense classification of the pixels in a…

Although saliency maps can highlight important regions to explain the reasoning behind image classification in artificial intelligence (AI), the meaning of these regions is left to the user's interpretation. In contrast, conceptbased…

Cone-beam computed tomography (CBCT) is an important tool facilitating computer aided interventions, despite often suffering from artifacts that pose challenges for accurate interpretation. While the degraded image quality can affect…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…