Related papers: Synthesizing Artifact Dataset for Pixel-level Dete…
Deep-learning-based pipelines have shown the potential to revolutionalize microscopy image diagnostics by providing visual augmentations to a trained pathology expert. However, to match human performance, the methods rely on the…
An increasing number of public datasets have shown a transformative impact on automated medical segmentation. However, these datasets are often with varying label quality, ranging from manual expert annotations to AI-generated…
Collecting fine-grained labels usually requires expert-level domain knowledge and is prohibitive to scale up. In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples. The…
The segmentation of histological images is critical for various biomedical applications, yet the lack of annotated data presents a significant challenge. We propose a microscopy pseudo labeling pipeline utilizing unsupervised image…
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing…
Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets. These dataset generation methods often require new annotations of synthetic images, which forces practitioners to…
The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…
Fully annotated large-scale medical image datasets are highly valuable. However, because labeling medical images is tedious and requires specialized knowledge, the large-scale datasets available often have missing annotation issues. For…
Deep learning methods require massive of annotated data for optimizing parameters. For example, datasets attached with accurate bounding box annotations are essential for modern object detection tasks. However, labeling with such pixel-wise…
In the proposed study, we describe the possibility of automated dataset collection using an articulated robot. The proposed technology reduces the number of pixel errors on a polygonal dataset and the time spent on manual labeling of 2D…
Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vision exploit deep Convolutional Neural Networks (CNN) to…
Recent advances in deep generative models have led to significant progress in video generation, yet the fidelity of AI-generated videos remains limited. Synthesized content often exhibits visual artifacts such as temporally inconsistent…
While image segmentation is crucial in various computer vision applications, such as autonomous driving, grasping, and robot navigation, annotating all objects at the pixel-level for training is nearly impossible. Therefore, the study of…
Supervised learning-based segmentation methods typically require a large number of annotated training data to generalize well at test time. In medical applications, curating such datasets is not a favourable option because acquiring a large…
Semantic human matting aims to estimate the per-pixel opacity of the foreground human regions. It is quite challenging and usually requires user interactive trimaps and plenty of high quality annotated data. Annotating such kind of data is…
Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…
Labeling datasets for supervised object detection is a dull and time-consuming task. Errors can be easily introduced during annotation and overlooked during review, yielding inaccurate benchmarks and performance degradation of deep neural…
State of the art methods for semantic image segmentation are trained in a supervised fashion using a large corpus of fully labeled training images. However, gathering such a corpus is expensive, due to human annotation effort, in contrast…
This paper proposes a training data augmentation pipeline that combines synthetic image data with neural style transfer in order to address the vulnerability of deep vision models to common corruptions. We show that although applying style…
One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation,…