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

Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional…

Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between…

In computer vision, a prevailing method for quantifying dataset bias is to train a model to distinguish between datasets. High classification accuracy is then interpreted as evidence of meaningful semantic differences. This approach assumes…

Some complex problems, such as image tagging and natural language processing, are very challenging for computers, where even state-of-the-art technology is yet able to provide satisfactory accuracy. Therefore, rather than relying solely on…

Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose two methods for selecting the most relevant data with weak…

The major challenge in today's computer vision scenario is the availability of good quality labeled data. In a field of study like image classification, where data is of utmost importance, we need to find more reliable methods which can…

Some of the most severe bottlenecks preventing widespread development of machine learning models for human behavior include a dearth of labeled training data and difficulty of acquiring high quality labels. Active learning is a paradigm for…

We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. This setting is similar to semi-supervised learning, but significantly harder because there are no labelled examples for the…

Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses…

What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing methods are (i) offline, i.e. they produce a static dataset from…

In order to handle the challenges of autonomous driving, deep learning has proven to be crucial in tackling increasingly complex tasks, such as 3D detection or instance segmentation. State-of-the-art approaches for image-based detection…

Efficient and easy segmentation of images and volumes is of great practical importance. Segmentation problems that motivate our approach originate from microscopy imaging commonly used in materials science, medicine, and biology. We…

Numerous fake images spread on social media today and can severely jeopardize the credibility of online content to public. In this paper, we employ deep networks to learn distinct fake image related features. In contrast to authentic…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…

The rapid proliferation of AI-generated images, powered by generative adversarial networks (GANs), diffusion models, and other synthesis techniques, has raised serious concerns about misinformation, copyright violations, and digital…

The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word…

The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading…

In the deep-learning community new algorithms are published at an incredible pace. Therefore, solving an image classification problem for new datasets becomes a challenging task, as it requires to re-evaluate published algorithms and their…

The problem of image-base person identification/recognition is to provide an identity to the image of an individual based on learned models that describe his/her appearance. Most traditional person identification systems rely on learning a…

We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…