相关论文: Learn 3D VQA Better with Active Selection and Rean…

Learning-based solutions for vision tasks require a large amount of labeled training data to ensure their performance and reliability. In single-task vision-based settings, inconsistency-based active learning has proven to be effective in…

Active learning (AL) is a widely-used training strategy for maximizing predictive performance subject to a fixed annotation budget. In AL one iteratively selects training examples for annotation, often those for which the current model is…

Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods. To surmount the constraint of…

Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs.…

In the era of data-driven intelligence, the paradox of data abundance and annotation scarcity has emerged as a critical bottleneck in the advancement of machine learning. This paper gives a detailed overview of Active Learning (AL), which…

Visual Question Answering (VQA) has witnessed tremendous progress in recent years. However, most efforts only focus on the 2D image question answering tasks. In this paper, we present the first attempt at extending VQA to the 3D domain,…

Visual Question Answering (VQA) presents a unique challenge as it requires the ability to understand and encode the multi-modal inputs - in terms of image processing and natural language processing. The algorithm further needs to learn how…

The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet. In consequence, we need curious and continuously learning algorithms that actively acquire knowledge…

Active learning (AL) is a training paradigm for selecting unlabeled samples for annotation to improve model performance on a test set, which is useful when only a limited number of samples can be annotated. These algorithms often work by…

Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance…

Label aggregation such as majority voting is commonly used to resolve annotator disagreement in dataset creation. However, this may disregard minority values and opinions. Recent studies indicate that learning from individual annotations…

Active learning aims to train a classifier as fast as possible with as few labels as possible. The core element in virtually any active learning strategy is the criterion that measures the usefulness of the unlabeled data based on which new…

High accuracy medical image classification can be limited by the costs of acquiring more data as well as the time and expertise needed to label existing images. In this paper, we apply active learning to medical image classification, a…

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these…

Recently, several studies have investigated active learning (AL) for natural language processing tasks to alleviate data dependency. However, for query selection, most of these studies mainly rely on uncertainty-based sampling, which…

Active Learning (AL) allows models to learn interactively from user feedback. This paper introduces a counterfactual data augmentation approach to AL, particularly addressing the selection of datapoints for user querying, a pivotal concern…

One of the most intriguing features of the Visual Question Answering (VQA) challenge is the unpredictability of the questions. Extracting the information required to answer them demands a variety of image operations from detection and…

Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to…

In 3D Visual Question Answering (3D VQA), the scarcity of fully annotated data and limited visual content diversity hampers the generalization to novel scenes and 3D concepts (e.g., only around 800 scenes are utilized in ScanQA and SQA…

Annotating datasets for question answering (QA) tasks is very costly, as it requires intensive manual labor and often domain-specific knowledge. Yet strategies for annotating QA datasets in a cost-effective manner are scarce. To provide a…