相关论文: Evaluating the Explainability of Vision Transforme…

Interpreting the decisions of deep learning models has been actively studied since the explosion of deep neural networks. One of the most convincing interpretation approaches is salience-based visual interpretation, such as Grad-CAM, where…

The quality of diabetic retinopathy (DR) screening relies on the ability to correctly grade severity; however, many deep-learning (DL) classifiers cannot be easily interpreted in the clinical context. This study presents a methodology that…

Vision Transformer (ViT) has achieved outstanding results in computer vision. Although there are many Transformer-based architectures derived from the original ViT, the dimension of patches are often the same with each other. This…

The emergence of Vision Transformers (ViTs) has revolutionized computer vision, yet their effectiveness compared to traditional Convolutional Neural Networks (CNNs) in medical imaging remains under-explored. This study presents a…

Intrigued by the inherent ability of the human visual system to identify salient regions in complex scenes, attention mechanisms have been seamlessly integrated into various Computer Vision (CV) tasks. Building upon this paradigm, Vision…

Although visual foundation models like DINOv2 provide state-of-the-art performance as feature extractors, their complex, high-dimensional representations create substantial hurdles for interpretability. This work proposes DINO-QPM, which…

For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs' output remains sensitive to small spatial shifts in the input, i.e.,…

Vision Transformers (ViTs) have recently become the state-of-the-art across many computer vision tasks. In contrast to convolutional networks (CNNs), ViTs enable global information sharing even within shallow layers of a network, i.e.,…

Manual Pap smear analysis for cervical cancer screening is limited by inter-observer variability, time constraints, and restricted expert availability. Although convolutional neural networks (CNNs) have automated cervical cell…

Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because information is propagated through complex interactions across layers and attention heads.…

Kidney stone classification from endoscopic images is critical for personalized treatment and recurrence prevention. While convolutional neural networks (CNNs) have shown promise in this task, their limited ability to capture long-range…

Face recognition systems are increasingly used in biometric security for convenience and effectiveness. However, they remain vulnerable to spoofing attacks, where attackers use photos, videos, or masks to impersonate legitimate users. This…

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions. The recent trend in automated medical image diagnostics leans…

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating…

Importance estimators are explainability methods that quantify feature importance for deep neural networks (DNN). In vision transformers (ViT), the self-attention mechanism naturally leads to attention maps, which are sometimes interpreted…

Medical image analysis often faces significant challenges due to limited expert-annotated data, hindering both model generalization and clinical adoption. We propose an expert-guided explainable few-shot learning framework that integrates…

Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the…

We investigate the problem of explainability for visual object detectors. Specifically, we demonstrate on the example of the YOLO object detector how to integrate Grad-CAM into the model architecture and analyze the results. We show how to…

In recent years, the integration of advanced imaging techniques and deep learning methods has significantly advanced computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Transformers, which have shown great…

Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating…