Related papers: Webly-Supervised Image Manipulation Localization v…

Background and Objectives: Cardiovascular magnetic resonance (CMR) imaging is a powerful modality in functional and anatomical assessment for various cardiovascular diseases. Sufficient image quality is essential to achieve proper diagnosis…

As artificial intelligence advances rapidly, particularly with the advent of GANs and diffusion models, the accuracy of Image Inpainting Localization (IIL) has become increasingly challenging. Current IIL methods face two main challenges: a…

Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed name-only continual learning where…

Data augmentations are widely used in training medical image deep learning models to increase the diversity and size of sparse datasets. However, commonly used augmentation techniques can result in loss of clinically relevant information…

Image labeling is a critical bottleneck in the development of computer vision technologies, often constraining machine learning performance due to the time-intensive nature of manual annotations. This work introduces a novel approach that…

Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels, i.e., a…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

Data quality is critical for multimedia tasks, while various types of systematic flaws are found in image benchmark datasets, as discussed in recent work. In particular, the existence of the semantic gap problem leads to a many-to-many…

Real-world image matting is essential for applications in content creation and augmented reality. However, it remains challenging due to the complex nature of scenes and the scarcity of high-quality datasets. To address these limitations,…

Semantic segmentation is one of the basic, yet essential scene understanding tasks for an autonomous agent. The recent developments in supervised machine learning and neural networks have enjoyed great success in enhancing the performance…

The increasing realism of AI-generated imagery poses challenges for verifying visual authenticity. We present an explainable image authenticity detection system that combines a lightweight convolutional classifier ("Faster-Than-Lies") with…

The advancement of text-to-image synthesis has introduced powerful generative models capable of creating realistic images from textual prompts. However, precise control over image attributes remains challenging, especially at the instance…

Recent research in the field of computer vision strongly focuses on deep learning architectures to tackle image processing problems. Deep neural networks are often considered in complex image processing scenarios since traditional computer…

Existing camouflaged object detection (COD) methods rely heavily on large-scale datasets with pixel-wise annotations. However, due to the ambiguous boundary, annotating camouflage objects pixel-wisely is very time-consuming and…

Large-scale datasets for single-label multi-class classification, such as \emph{ImageNet-1k}, have been instrumental in advancing deep learning and computer vision. However, a critical and often understudied aspect is the comprehensive…

In Active Domain Adaptation (ADA), one uses Active Learning (AL) to select a subset of images from the target domain, which are then annotated and used for supervised domain adaptation (DA). Given the large performance gap between…

Active learning (AL) is a label-efficient machine learning paradigm that focuses on selectively annotating high-value instances to maximize learning efficiency. Its effectiveness can be further enhanced by incorporating weak supervision,…

Cancer detection and classification from gigapixel whole slide images of stained tissue specimens has recently experienced enormous progress in computational histopathology. The limitation of available pixel-wise annotated scans shifted the…

With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limitation of current training datasets is their reliance on…

Surgical scenes convey crucial information about the quality of surgery. Pixel-wise localization of tools and anatomical structures is the first task towards deeper surgical analysis for microscopic or endoscopic surgical views. This is…