Related papers: Exploiting Web Images for Dataset Construction: A …

A recurring focus of the deep learning community is towards reducing the labeling effort. Data gathering and annotation using a search engine is a simple alternative to generating a fully human-annotated and human-gathered dataset. Although…

Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is…

Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension, offering a significant leap forward. These breakthroughs have proven particularly instrumental in addressing…

Training data are critical in face recognition systems. However, labeling a large scale face data for a particular domain is very tedious. In this paper, we propose a method to automatically and incrementally construct datasets from massive…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

Aesthetic image captioning (AIC) refers to the multi-modal task of generating critical textual feedbacks for photographs. While in natural image captioning (NIC), deep models are trained in an end-to-end manner using large curated datasets…

Current wisdom suggests more labeled image data is always better, and obtaining labels is the bottleneck. Yet curating a pool of sufficiently diverse and informative images is itself a challenge. In particular, training image curation is…

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention.…

Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as…

One of the prevalent learning tasks involving images is content-based image classification. This is a difficult task especially because the low-level features used to digitally describe images usually capture little information about the…

Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include…

While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…

One of the key challenges of detecting AI-generated images is spotting images that have been created by previously unseen generative models. We argue that the limited diversity of the training data is a major obstacle to addressing this…

Although the availability of a large amount of data is usually given for granted, there are relevant scenarios where this is not the case; for instance, in the biomedical/healthcare domain, some applications require to build huge datasets…

Dataset bias remains a significant barrier towards solving real world computer vision tasks. Though deep convolutional networks have proven to be a competitive approach for image classification, a question remains: have these models have…

In this paper, we present a characteristic extraction algorithm and the Multi-domain Image Characteristics Dataset of characteristic-tagged images to simulate the way a human brain classifies cross-domain information and generates insight.…

Active learning enables the efficient construction of a labeled dataset by labeling informative samples from an unlabeled dataset. In a real-world active learning scenario, considering the diversity of the selected samples is crucial…

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled raw from the Internet by using text queries, without any human annotation. We develop a…

Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless,…

Convolutional neural networks (CNNs) have been successfully applied to many recognition and learning tasks using a universal recipe; training a deep model on a very large dataset of supervised examples. However, this approach is rather…