Related papers: MARIO: A Mixed Annotation Framework For Polyp Segm…

Accurate segmentation of organelle instances from electron microscopy (EM) images plays an essential role in many neuroscience researches. However, practical scenarios usually suffer from high annotation costs, label scarcity, and large…

Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for…

Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint is to implement weakly-supervised pipelines trained with…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

With the increasing multimedia information, multimodal recommendation has received extensive attention. It utilizes multimodal information to alleviate the data sparsity problem in recommendation systems, thus improving recommendation…

Precise delineation of multiple organs or abnormal regions in the human body from medical images plays an essential role in computer-aided diagnosis, surgical simulation, image-guided interventions, and especially in radiotherapy treatment…

Facial analysis models are increasingly applied in real-world applications that have significant impact on peoples' lives. However, as literature has shown, models that automatically classify facial attributes might exhibit algorithmic…

The medical imaging literature has witnessed remarkable progress in high-performing segmentation models based on convolutional neural networks. Despite the new performance highs, the recent advanced segmentation models still require large,…

This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to…

Obtaining large-scale medical data, annotated or unannotated, is challenging due to stringent privacy regulations and data protection policies. In addition, annotating medical images requires that domain experts manually delineate…

Image collections, if critical aspects of image content are exposed, can spur research and practical applications in many domains. Supervised machine learning may be the only feasible way to annotate very large collections, but leading…

Recent temporal action segmentation approaches need frame annotations during training to be effective. These annotations are very expensive and time-consuming to obtain. This limits their performances when only limited annotated data is…

Weak supervision learning on classification labels has demonstrated high performance in various tasks, while a few pixel-level fine annotations are also affordable. Naturally a question comes to us that whether the combination of…

Scribble-based weakly supervised segmentation methods have shown promising results in medical image segmentation, significantly reducing annotation costs. However, existing approaches often rely on auxiliary tasks to enforce semantic…

Face anti-spoofing plays a critical role in safeguarding facial recognition systems against presentation attacks. While existing deep learning methods show promising results, they still suffer from the lack of fine-grained annotations,…

This technical report describes a modular and extensible architecture for computing visual statistics in RoboCup SPL (MARIO), presented during the SPL Open Research Challenge at RoboCup 2022, held in Bangkok (Thailand). MARIO is an…

Tabular data inherently exhibits significant feature heterogeneity, but existing transformer-based methods lack specialized mechanisms to handle this property. To bridge the gap, we propose MAYA, an encoder-decoder transformer-based…

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision,…

Annotated images are required for both supervised model training and evaluation in image classification. Manually annotating images is arduous and expensive, especially for multi-labeled images. A recent trend for conducting such laboursome…