Related papers: Sparse-shot Learning with Exclusive Cross-Entropy …

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

Annotating a large number of training images is very time-consuming. In this background, this paper focuses on learning from easy-to-acquire web data and utilizes the learned model for fine-grained image classification in labeled datasets.…

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection…

For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives. While in the few-shot setup we…

In recent years, data-driven methods have shown great success for extracting information about the infrastructure in urban areas. These algorithms are usually trained on large datasets consisting of thousands or millions of labeled training…

Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to…

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of…

As with other deep learning methods, label quality is important for learning modern convolutional object detectors. However, the potentially large number and wide diversity of object instances that can be found in complex image scenes makes…

While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes,…

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…

Polyp segmentation is a crucial step towards computer-aided diagnosis of colorectal cancer. However, most of the polyp segmentation methods require pixel-wise annotated datasets. Annotated datasets are tedious and time-consuming to produce,…

Recent advances in computer vision using deep learning with RGB imagery (e.g., object recognition and detection) have been made possible thanks to the development of large annotated RGB image datasets. In contrast, multispectral image (MSI)…

Semantic segmentation of microscopic cell images using deep learning is an important technique, however, it requires a large number of images and ground truth labels for training. To address the above problem, we consider an efficient…

Previous works on video object segmentation (VOS) are trained on densely annotated videos. Nevertheless, acquiring annotations in pixel level is expensive and time-consuming. In this work, we demonstrate the feasibility of training a…

Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a…

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…

Few-shot video object segmentation aims to reduce annotation costs; however, existing methods still require abundant dense frame annotations for training, which are scarce in the medical domain. We investigate an extremely low-data regime…

Accurate segmentation of tissue in histopathological images can be very beneficial for defining regions of interest (ROI) for streamline of diagnostic and prognostic tasks. Still, adapting to different domains is essential for…

High-quality data is necessary for modern machine learning. However, the acquisition of such data is difficult due to noisy and ambiguous annotations of humans. The aggregation of such annotations to determine the label of an image leads to…

Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world…