Related papers: Rethinking Annotation for Object Detection: Is Ann…
A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…
Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in economical ways, such as cloud sourcing. However, datasets…
Instance segmentation is a computer vision task where separate objects in an image are detected and segmented. State-of-the-art deep neural network models require large amounts of labeled data in order to perform well in this task. Making…
We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn…
Annotated datasets are an essential ingredient to train, evaluate, compare and productionalize supervised machine learning models. It is therefore imperative that annotations are of high quality. For their creation, good quality management…
Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…
Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing…
Performing data augmentation for learning deep neural networks is known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…
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…
Many open-world applications require the detection of novel objects, yet state-of-the-art object detection and instance segmentation networks do not excel at this task. The key issue lies in their assumption that regions without any…
Annotating tens or hundreds of tiny objects in a given image is laborious yet crucial for a multitude of Computer Vision tasks. Such imagery typically contains objects from various categories, yet the multi-class interactive annotation…
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…
Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training. However, collecting such large-scale densely-supervised datasets is notoriously costly. To reduce the…
Deep neural networks (DNNs) have demonstrated exceptional performance across various image segmentation tasks. However, the process of preparing datasets for training segmentation DNNs is both labor-intensive and costly, as it typically…
Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated…
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…
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…
Methods for object detection and segmentation often require abundant instance-level annotations for training, which are time-consuming and expensive to collect. To address this, the task of zero-shot object detection (or segmentation) aims…
Object detection models, a prominent class of machine learning algorithms, aim to identify and precisely locate objects in images or videos. However, this task might yield uneven performances sometimes caused by the objects sizes and the…
Object detection requires substantial labeling effort for learning robust models. Active learning can reduce this effort by intelligently selecting relevant examples to be annotated. However, selecting these examples properly without…