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

Analysis of histopathology slides is a critical step for many diagnoses, and in particular in oncology where it defines the gold standard. In the case of digital histopathological analysis, highly trained pathologists must review vast…

Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that…

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…

Medical image annotation is a major hurdle for developing precise and robust machine learning models. Annotation is expensive, time-consuming, and often requires expert knowledge, particularly in the medical field. Here, we suggest using…

Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount…

The success of deep learning methods relies on the availability of well-labeled large-scale datasets. However, for medical images, annotating such abundant training data often requires experienced radiologists and consumes their limited…

In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose the problem of extended few-shot learning to study these…

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…

In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable…

Automatic cell segmentation in microscopy images works well with the support of deep neural networks trained with full supervision. Collecting and annotating images, though, is not a sustainable solution for every new microscopy database…

Supervised learning has proved effective for medical image analysis. However, it can utilize only the small labeled portion of data; it fails to leverage the large amounts of unlabeled data that is often available in medical image datasets.…

Methods for object detection and segmentation rely on large scale instance-level annotations for training, which are difficult and time-consuming to collect. Efforts to alleviate this look at varying degrees and quality of supervision.…

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…

Object detection has witnessed significant progress by relying on large, manually annotated datasets. Annotating such datasets is highly time consuming and expensive, which motivates the development of weakly supervised and few-shot object…

Predicting all applicable labels for a given image is known as multi-label classification. Compared to the standard multi-class case (where each image has only one label), it is considerably more challenging to annotate training data for…

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of…

The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of…

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…

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…

Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly…