Related papers: Industrial Synthetic Segment Pre-training

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Automatic visual inspection using machine learning plays a key role in achieving zero-defect policies in industry. Research on anomaly detection is constrained by the availability of datasets that capture complex defect appearances and…

Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target dataset distribution. As a result, they capture only the…

Current research workflows for precise video segmentation are often forced into a compromise between labor-intensive manual curation, costly commercial platforms, and/or privacy-compromising cloud-based services. The demand for…

Simulation offers a scalable and efficient alternative to real-world data collection for learning visuomotor robotic policies. However, the simulation-to-reality, or Sim2Real distribution shift -- introduced by employing simulation-trained…

The growing scale of datasets in deep learning has introduced significant computational challenges. Dataset pruning addresses this challenge by constructing a compact but informative coreset from the full dataset with comparable…

While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and…

Incompletely-Supervised Concealed Object Segmentation (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments, utilizing incompletely annotated data, such as weak and semi-annotations, for model…

Producing manual, pixel-accurate, image segmentation labels is tedious and time-consuming. This is often a rate-limiting factor when large amounts of labeled images are required, such as for training deep convolutional networks for…

Formula-driven supervised learning (FDSL) is a pre-training method that relies on synthetic images generated from mathematical formulae such as fractals. Prior work on FDSL has shown that pre-training vision transformers on such synthetic…

Current semantic segmentation models typically require a substantial amount of manually annotated data, a process that is both time-consuming and resource-intensive. Alternatively, leveraging advanced text-to-image models such as Midjourney…

We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images. To this end, we collected the first large-scale DIS dataset, called DIS5K, which…

Recent advances in appearance-based models have shown improved eye tracking performance in difficult scenarios like occlusion due to eyelashes, eyelids or camera placement, and environmental reflections on the cornea and glasses. The key…

Interactive Medical Image Segmentation (IMIS) has long been constrained by the limited availability of large-scale, diverse, and densely annotated datasets, which hinders model generalization and consistent evaluation across different…

Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent…

Improved surgical skill is generally associated with improved patient outcomes, although assessment is subjective; labour-intensive; and requires domain specific expertise. Automated data driven metrics can alleviate these difficulties, as…

Formula-driven supervised learning (FDSL) has been shown to be an effective method for pre-training vision transformers, where ExFractalDB-21k was shown to exceed the pre-training effect of ImageNet-21k. These studies also indicate that…

In computer-assisted surgery, automatically recognizing anatomical organs is crucial for understanding the surgical scene and providing intraoperative assistance. While machine learning models can identify such structures, their deployment…

Automatic surgical instrument segmentation of endoscopic images is a crucial building block of many computer-assistance applications for minimally invasive surgery. So far, state-of-the-art approaches completely rely on the availability of…

Existing dataset pruning techniques primarily focus on classification tasks, limiting their applicability to more complex and practical tasks like instance segmentation. Instance segmentation presents three key challenges: pixel-level…