Related papers: Contrastive Monotonic Pixel-Level Modulation
Unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain has attracted much attention in recent years. While many domain adaptation techniques have been proposed…
Learning high-quality, robust, efficient, and disentangled representations is a central challenge in artificial intelligence (AI). Deep metric learning frameworks tackle this challenge primarily using architectural and optimization…
Unsupervised multi-domain image-to-image translation aims to synthesis images among multiple domains without labeled data, which is more general and complicated than one-to-one image mapping. However, existing methods mainly focus on…
Multimodal models are becoming increasingly effective, in part due to unified components, such as the Transformer architecture. However, multimodal models still often consist of many task- and modality-specific pieces and training…
Biological brains learn continually from a stream of unlabeled data, while integrating specialized information from sparsely labeled examples without compromising their ability to generalize. Meanwhile, machine learning methods are…
Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…
Image-to-image translation models transfer images from input domain to output domain in an endeavor to retain the original content of the image. Contrastive Unpaired Translation is one of the existing methods for solving such problems.…
Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images. Recent studies have shown remarkable success for multiple domains but they suffer from two main…
Image-to-image translation aims to learn a mapping between different groups of visually distinguishable images. While recent methods have shown impressive ability to change even intricate appearance of images, they still rely on domain…
Unsupervised image-to-image translation aims at learning the relationship between samples from two image domains without supervised pair information. The relationship between two domain images can be one-to-one, one-to-many or many-to-many.…
In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text)…
Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…
We pilot a family of stable contrastive losses for learning pixel-level representations that jointly capture semantic and geometric information. Our approach maps each pixel of an image to an overcomplete descriptor that is both…
With the development of computational intelligence algorithms, unsupervised monocular depth and pose estimation framework, which is driven by warped photometric consistency, has shown great performance in the daytime scenario. While in some…
In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the…
We tackle the problem of monocular 3D object detection across different sensors, environments, and camera setups. In this paper, we introduce a novel unsupervised domain adaptation approach, MonoCT, that generates highly accurate pseudo…
Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation. However, the existing methods only consider one of the two perspectives, which…
We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…
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…
Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing…