Related papers: Towards Concept-based Interpretability of Skin Les…

Advancements in audio neural networks have established state-of-the-art results on downstream audio tasks. However, the black-box structure of these models makes it difficult to interpret the information encoded in their internal audio…

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…

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward-align these models with carefully annotated abstract,…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

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…

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these…

Accurate diagnosis of skin diseases remains a significant challenge due to the complex and diverse visual features present in dermatoscopic images, often compounded by a lack of interpretability in existing purely visual diagnostic models.…

Distributional semantic models capture word-level meaning that is useful in many natural language processing tasks and have even been shown to capture cognitive aspects of word meaning. The majority of these models are purely text based,…

Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the…

Medical image retrieval aims to identify clinically relevant lesion cases to support diagnostic decision making, education, and quality control. In practice, retrieval queries often combine a reference lesion image with textual descriptors…

The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior. While the former need is…

In clinical practice, segmenting specific lesions based on the needs of physicians can significantly enhance diagnostic accuracy and treatment efficiency. However, conventional lesion segmentation models lack the flexibility to distinguish…

A lot of deep learning (DL) research these days is mainly focused on improving quantitative metrics regardless of other factors. In human-centered applications, like skin lesion classification in dermatology, DL-driven clinical decision…

Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechanisms that translate their broad knowledge into clinically…

Advances in multi-modal embeddings, and in particular CLIP, have recently driven several breakthroughs in Computer Vision (CV). CLIP has shown impressive performance on a variety of tasks, yet, its inherently opaque architecture may hinder…

Vision models with high overall accuracy often exhibit systematic errors in specific scenarios, posing potential serious safety concerns. Diagnosing bugs of vision models is gaining increased attention, however traditional diagnostic…

Interpretability is crucial to enhance trust in machine learning models for medical diagnostics. However, most state-of-the-art image classifiers based on neural networks are not interpretable. As a result, clinicians often resort to known…

Deep learning implemented with convolutional network architectures can exceed specialists' diagnostic accuracy. However, whole-image deep learning trained on a given dataset may not generalize to other datasets. The problem arises because…

The development of vision-language models (VLMs) for histo-pathology has shown promising new usages and zero-shot performances. However, current approaches, which decompose large slides into smaller patches, focus solely on inductive…

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one…