Related papers: Dual-Domain CLIP-Assisted Residual Optimization Pe…

We propose DiffCLIP, a novel vision-language model that extends the differential attention mechanism to CLIP architectures. Differential attention was originally developed for large language models to amplify relevant context while…

Zero-shot 3D object classification is crucial for real-world applications like autonomous driving, however it is often hindered by a significant domain gap between the synthetic data used for training and the sparse, noisy LiDAR scans…

We propose approaches based on deep learning to localize objects in images when only a small training dataset is available and the images have low quality. That applies to many problems in medical image processing, and in particular to the…

Undersampled MRI reconstruction is crucial for accelerating clinical scanning. Dual-domain reconstruction network is performant among SoTA deep learning methods. In this paper, we rethink dual-domain model design from the perspective of the…

Few-shot Generalist Anomaly Detection requires models to generalize to novel categories without retraining, posing significant challenges in real-world scenarios with scarce samples and rapidly changing categories. Existing CLIP-based…

Metal artifacts is a major challenge in computed tomography (CT) imaging, significantly degrading image quality and making accurate diagnosis difficult. However, previous methods either require prior knowledge of the location of metal…

Semi-supervised object detection methods are widely used in autonomous driving systems, where only a fraction of objects are labeled. To propagate information from the labeled objects to the unlabeled ones, pseudo-labels for unlabeled…

In computed tomography imaging, metal implants frequently generate severe artifacts that compromise image quality and hinder diagnostic accuracy. There are three main challenges in the existing methods: the deterioration of organ and tissue…

In medical imaging, most of the image registration methods implicitly assume a one-to-one correspondence between the source and target images (i.e., diffeomorphism). However, this is not necessarily the case when dealing with pathological…

Foundation models have recently gained tremendous popularity in medical image analysis. State-of-the-art methods leverage either paired image-text data via vision-language pre-training or unpaired image data via self-supervised pre-training…

In total hip arthroplasty, analysis of postoperative medical images is important to evaluate surgical outcome. Since Computed Tomography (CT) is most prevalent modality in orthopedic surgery, we aimed at the analysis of CT image. In this…

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically leverages Class Activation Maps (CAMs) to achieve pixel-level predictions. Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced to…

Diffusion-weighted MRI is nowadays performed routinely due to its prognostic ability, yet the quality of the scans are often unsatisfactory which can subsequently hamper the clinical utility. To overcome the limitations, here we propose a…

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…

Signal models based on sparse representations have received considerable attention in recent years. On the other hand, deep models consisting of a cascade of functional layers, commonly known as deep neural networks, have been highly…

Image colorization is a challenging problem due to multi-modal uncertainty and high ill-posedness. Directly training a deep neural network usually leads to incorrect semantic colors and low color richness. While transformer-based methods…

In the field of design patent analysis, traditional tasks such as patent classification and patent image retrieval heavily depend on the image data. However, patent images -- typically consisting of sketches with abstract and structural…

High performance materials, from natural bone over ancient damascene steel to modern superalloys, typically possess a complex structure at the microscale. Their properties exceed those of the individual components and their knowledge-based…

Identifying multiple novel classes in an image, known as open-vocabulary multi-label recognition, is a challenging task in computer vision. Recent studies explore the transfer of powerful vision-language models such as CLIP. However, these…

Dual energy computed tomography (DECT) imaging plays an important role in advanced imaging applications due to its material decomposition capability. Image-domain decomposition operates directly on CT images using linear matrix inversion,…