Related papers: Museum Exhibit Identification Challenge for Domain…

The emergent ecosystems of intelligent edge devices in diverse Internet of Things (IoT) applications, from automatic surveillance to precision agriculture, increasingly rely on recording and processing variety of image data. Due to resource…

AI-generated images have become increasingly realistic and have garnered significant public attention. While synthetic images are intriguing due to their realism, they also pose an important misinformation threat. To address this new…

As we deploy machine learning systems in the real world, a core challenge is to maintain a model that is performant even as the data shifts. Such shifts can take many forms: new classes may emerge that were absent during training, a problem…

Multi-Label Image Classification (MLIC) aims to predict a set of labels that present in an image. The key to deal with such problem is to mine the associations between image contents and labels, and further obtain the correct assignments…

Despite recent advances in object detection using deep learning neural networks, these neural networks still struggle to identify objects in art images such as paintings and drawings. This challenge is known as the cross depiction problem…

As we enter into the big data age and an avalanche of images have become readily available, recognition systems face the need to move from close, lab settings where the number of classes and training data are fixed, to dynamic scenarios…

The massive digitization of artworks during the last decades created the need for categorization, analysis, and management of huge amounts of data related to abstract concepts, highlighting a challenging problem in the field of computer…

Real-world scenarios pose several challenges to deep learning based computer vision techniques despite their tremendous success in research. Deeper models provide better performance, but are challenging to deploy and knowledge distillation…

Multi-label image classification is a foundational topic in various domains. Multimodal learning approaches have recently achieved outstanding results in image representation and single-label image classification. For instance, Contrastive…

Current progress in out-of-distribution (OOD) detection is limited by the lack of large, high-quality datasets with clearly defined OOD categories across varying difficulty levels (near- to far-OOD) that support both fine- and…

Open-set face recognition describes a scenario where unknown subjects, unseen during the training stage, appear on test time. Not only it requires methods that accurately identify individuals of interest, but also demands approaches that…

During the diagnostic process, doctors incorporate multimodal information including imaging and the medical history - and similarly medical AI development has increasingly become multimodal. In this paper we tackle a more subtle challenge:…

Domain adaptation for visual recognition has undergone great progress in the past few years. Nevertheless, most existing methods work in the so-called closed-set scenario, assuming that the classes depicted by the target images are exactly…

Person re-identification (re-ID) requires densely distributed cameras. In practice, the person of interest may not be captured by cameras and, therefore, needs to be retrieved using subjective information (e.g., sketches from witnesses).…

Recognizing materials in real-world images is a challenging task. Real-world materials have rich surface texture, geometry, lighting conditions, and clutter, which combine to make the problem particularly difficult. In this paper, we…

Labelled image datasets have played a critical role in high-level image understanding. However, the process of manual labelling is both time-consuming and labor intensive. To reduce the cost of manual labelling, there has been increased…

We present Open Images V4, a dataset of 9.2M images with unified annotations for image classification, object detection and visual relationship detection. The images have a Creative Commons Attribution license that allows to share and adapt…

Cross-domain mapping has been a very active topic in recent years. Given one image, its main purpose is to translate it to the desired target domain, or multiple domains in the case of multiple labels. This problem is highly challenging due…

We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images. To this end, we collected the first large-scale DIS dataset, called DIS5K, which…

Deep learning has paved the way for strong recognition systems which are often both trained on and applied to natural images. In this paper, we examine the give-and-take relationship between such visual recognition systems and the rich…