Related papers: Weakly Supervised Concept Learning with Class-Leve…

Deep learning models have gained increasing adoption in medical image analysis. However, these models often produce overconfident predictions, which can compromise clinical accuracy and reliability. Bridging the gap between high-performance…

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…

Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these…

Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage…

To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

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…

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is…

As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often…

Objective: Semantic indexing of biomedical literature is usually done at the level of MeSH descriptors with several related but distinct biomedical concepts often grouped together and treated as a single topic. This study proposes a new…

Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve…

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…

The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…

Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints. Existing methods only rely on the features extracted at support keypoints to predict or refine the…

Black-box deep learning approaches have showcased significant potential in the realm of medical image analysis. However, the stringent trustworthiness requirements intrinsic to the medical field have catalyzed research into the utilization…

High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignment in medical VLMs…

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained attention for its cost-effectiveness. Most existing methods emphasize inter-class separation, often neglecting the shared semantics among related categories…

Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs struggle to verify whether predicted concepts correspond to…

Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate model predictions with…