Related papers: BIRL: Benchmark on Image Registration methods with…
Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. However, existing CL benchmarks, e.g. Permuted-MNIST and Split-CIFAR, make use of artificial temporal variation and do not align with or generalize to the…
Image matching approaches have been widely used in computer vision applications in which the image-level matching performance of matchers is critical. However, it has not been well investigated by previous works which place more emphases on…
We introduce RoLA, a framework that transforms any in-the-wild image into an interactive, physics-enabled robotic environment. Unlike previous methods, RoLA operates directly on a single image without requiring additional hardware or…
Highly automated driving functions currently often rely on a-priori knowledge from maps for planning and prediction in complex scenarios like cities. This makes map-relative localization an essential skill. In this paper, we address the…
Medical image classification is a challenging task due to the scarcity of labeled samples and class imbalance caused by the high variance in disease prevalence. Semi-supervised learning (SSL) methods can mitigate these challenges by…
High-fidelity registration of histopathological whole slide images (WSIs), such as hematoxylin & eosin (H&E) and immunohistochemistry (IHC), is vital for integrated molecular analysis but challenging to evaluate without ground-truth (GT)…
We introduce a scalable witness-based persistent homology pipeline for full-brain MRI volumes that couples density-aware landmark selection with a GPU-ready witness filtration. Candidates are scored by a hybrid metric that balances…
Topological and geometrical analysis of retinal blood vessel is a cost-effective way for early detection of many common diseases. Meanwhile, automated vessel segmentation and vascular tree analysis are still lacking in terms of…
This paper introduces the MERIT Dataset, a multimodal (text + image + layout) fully labeled dataset within the context of school reports. Comprising over 400 labels and 33k samples, the MERIT Dataset is a valuable resource for training…
Unsupervised medical anomaly detection is severely limited by the scarcity of normal training samples. Existing methods typically train dedicated models for each dataset or disease, requiring hundreds of normal images per task and lacking…
Although some existing image manipulation localization (IML) methods incorporate authenticity-related supervision, this information is typically utilized merely as an auxiliary training signal to enhance the model's sensitivity to…
Image classification benchmark datasets such as CIFAR, MNIST, and ImageNet serve as critical tools for model evaluation. However, despite the cleaning efforts, these datasets still suffer from pervasive noisy labels and often contain…
Medical imaging is key in modern medicine. From magnetic resonance imaging (MRI) to microscopic imaging for blood cell detection, diagnostic medical imaging reveals vital insights into patient health. To predict diseases or provide…
Real-world tasks such as garment manipulation and table rearrangement demand robots to perform generalizable, highly precise, and long-horizon actions. Although imitation learning has proven to be an effective approach for teaching robots…
Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images. Current methods adopt either global-level or pixel-level feature matching.…
Due to the nature of enhancement--the absence of paired ground-truth information, high-level vision tasks have been recently employed to evaluate the performance of low-light image enhancement. A widely-used manner is to see how accurately…
Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels. Furthermore, modeling the relationships between input and some (dull) classes further…
Accurate fetal growth assessment from ultrasound (US) relies on precise biometry measured by manually identifying anatomical landmarks in standard planes. Manual landmarking is time-consuming, operator-dependent, and sensitive to…
Single-cell datasets often lack individual cell labels, making it challenging to identify cells associated with disease. To address this, we introduce Mixture Modeling for Multiple Instance Learning (MMIL), an expectation maximization…
Obtaining large-scale labeled object detection dataset can be costly and time-consuming, as it involves annotating images with bounding boxes and class labels. Thus, some specialized active learning methods have been proposed to reduce the…