相关论文: Active Image Synthesis for Efficient Labeling

While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge. Dataset distillation addresses these challenges by synthesizing…

Retinal vessel segmentation from retinal images is an essential task for developing the computer-aided diagnosis system for retinal diseases. Efforts have been made on high-performance deep learning-based approaches to segment the retinal…

Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active graph learning focuses on selecting the most qualitative…

Modern deep learning has achieved great success in various fields. However, it requires the labeling of huge amounts of data, which is expensive and labor-intensive. Active learning (AL), which identifies the most informative samples to be…

Active learning (AL) aims to minimize labeling efforts for data-demanding deep neural networks (DNNs) by selecting the most representative data points for annotation. However, currently used methods are ill-equipped to deal with biased…

Recently deep learning - namely convolutional neural networks (CNNs) - have yielded impressive performance for the task of building segmentation on large overhead (e.g., satellite) imagery benchmarks. However, these benchmark datasets only…

Modern AI algorithms require labeled data. In real world, majority of data are unlabeled. Labeling the data are costly. this is particularly true for some areas requiring special skills, such as reading radiology images by physicians. To…

Active learning is able to reduce the amount of labelling effort by using a machine learning model to query the user for specific inputs. While there are many papers on new active learning techniques, these techniques rarely satisfy the…

In this paper, we propose a novel way to interpret text information by extracting visual feature presentation from multiple high-resolution and photo-realistic synthetic images generated by Text-to-image Generative Adversarial Network (GAN)…

Learning segmentation from noisy labels is an important task for medical image analysis due to the difficulty in acquiring highquality annotations. Most existing methods neglect the pixel correlation and structural prior in segmentation,…

Supervised object detection has been proven to be successful in many benchmark datasets achieving human-level performances. However, acquiring a large amount of labeled image samples for supervised detection training is tedious,…

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…

Recent advances in machine learning have led to increased deployment of black-box classifiers across a wide variety of applications. In many such situations there is a critical need to both reliably assess the performance of these…

In image classification tasks, the ability of deep CNNs to deal with complex image data has proven to be unrivalled. However, they require large amounts of labeled training data to reach their full potential. In specialised domains such as…

Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We…

New deep-learning architectures are created every year, achieving state-of-the-art results in image recognition and leading to the belief that, in a few years, complex tasks such as sign language translation will be considerably easier,…

Deep learning is currently reaching outstanding performances on different tasks, including image classification, especially when using large neural networks. The success of these models is tributary to the availability of large collections…

The development of deep learning based image representation learning (IRL) methods has attracted great attention for various image understanding problems. Most of these methods require the availability of a high quantity and quality of…

Sketch recognition allows natural and efficient interaction in pen-based interfaces. A key obstacle to building accurate sketch recognizers has been the difficulty of creating large amounts of annotated training data. Several authors have…

In many real-world datasets, like WebVision, the performance of DNN based classifier is often limited by the noisy labeled data. To tackle this problem, some image related side information, such as captions and tags, often reveal underlying…