Related papers: Identifying Reliable Annotations for Large Scale I…

Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in the presence of limited amount of labeled data. In this…

Automatic annotation of images with descriptive words is a challenging problem with vast applications in the areas of image search and retrieval. This problem can be viewed as a label-assignment problem by a classifier dealing with a very…

Recently deep neural networks, which require a large amount of annotated samples, have been widely applied in nuclei instance segmentation of H\&E stained pathology images. However, it is inefficient and unnecessary to label all pixels for…

In this paper, we categorize fine-grained images without using any object / part annotation neither in the training nor in the testing stage, a step towards making it suitable for deployments. Fine-grained image categorization aims to…

We present a comparison between Gaussian processes (GPs) and artificial neural networks (ANNs) as methods for determining photometric redshifts for galaxies, given training set data. In particular, we compare their degradation in…

Inference in Gaussian process (GP) models is computationally challenging for large data, and often difficult to approximate with a small number of inducing points. We explore an alternative approximation that employs stochastic inference…

Present-day deep neural networks for video semantic segmentation require a large number of fine-grained pixel-level annotations to achieve the best possible results. Obtaining such annotations, however, is very expensive. On the other hand,…

The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for segmenting bioimages that can contain numerous object instances with thin separations. In this paper, we introduce a…

Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…

3D image segmentation is one of the most important and ubiquitous problems in medical image processing. It provides detailed quantitative analysis for accurate disease diagnosis, abnormal detection, and classification. Currently deep…

Deep learning has achieved great success in recognizing video actions, but the collection and annotation of training data are still quite laborious, which mainly lies in two aspects: (1) the amount of required annotated data is large; (2)…

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…

There has been a lot of recent research on improving the efficiency of fine-tuning foundation models. In this paper, we propose a novel efficient fine-tuning method that allows the input image size of Segment Anything Model (SAM) to be…

Training Convolutional Neural Networks (CNNs) for very high resolution images requires a large quantity of high-quality pixel-level annotations, which is extremely labor- and time-consuming to produce. Moreover, professional photo…

When one wants to train a neural network to perform semantic segmentation, creating pixel-level annotations for each of the images in the database is a tedious task. If he works with aerial or satellite images, which are usually very large,…

This paper proposes a novel framework for implicit multi-camera system calibration utilizing Gaussian Process (GP) regression. Conventional explicit calibration methods are constrained by rigid mathematical models and struggle with complex,…

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

Pixel-wise segmentation is one of the most data and annotation hungry tasks in our field. Providing representative and accurate annotations is often mission-critical especially for challenging medical applications. In this paper, we propose…

Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper we try to overcome this difficulty by presenting a…

Two of the most common tasks in medical imaging are classification and segmentation. Either task requires labeled data annotated by experts, which is scarce and expensive to collect. Annotating data for segmentation is generally considered…