Related papers: Delta-Adapter: Scalable Exemplar-Based Image Editi…

Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additional parameters are introduced to excavate the task-specific…

We present an approach to example-based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real-time semantically…

Text-to-Image Diffusion models have enabled a wide array of image editing applications. However, capturing all types of edits through text alone can be challenging and cumbersome. The ambiguous nature of certain image edits is better…

Semi-supervised domain adaptation (SSDA) is to adapt a learner to a new domain with only a small set of labeled samples when a large labeled dataset is given on a source domain. In this paper, we propose a pair-based SSDA method that adapts…

Inspired by the in-context learning mechanism of large language models (LLMs), a new paradigm of generalizable visual prompt-based image editing is emerging. Existing single-reference methods typically focus on style or appearance…

Text-guided image editing faces significant challenges when considering training and inference flexibility. Much literature collects large amounts of annotated image-text pairs to train text-conditioned generative models from scratch, which…

Fine-tuning advanced diffusion models for high-quality image stylization usually requires large training datasets and substantial computational resources, hindering their practical applicability. We propose Ada-Adapter, a novel framework…

Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot image classification performance. However, due to their…

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framework based on…

Recently proposed DNN-based stereo matching methods that learn priors directly from data are known to suffer a drastic drop in accuracy in new environments. Although supervised approaches with ground truth disparity maps often work well,…

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…

Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time. This process necessitates storing copies of the model over time for each task that the pre-trained model is…

Recently, unsupervised exemplar-based image-to-image translation, conditioned on a given exemplar without the paired data, has accomplished substantial advancements. In order to transfer the information from an exemplar to an input image,…

Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine-tuning based task adaptation strategy becomes…

Semi-supervised domain adaptation (SSDA) adapts a learner to a new domain by effectively utilizing source domain data and a few labeled target samples. It is a practical yet under-investigated research topic. In this paper, we analyze the…

Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. We challenge this paradigm by demonstrating that powerful pre-trained text-conditioned image editing models can…

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic…

Recent studies have shown remarkable success in unsupervised image-to-image translation. However, if there has no access to enough images in target classes, learning a mapping from source classes to the target classes always suffers from…

Recent studies on face attribute editing by exemplars have achieved promising results due to the increasing power of deep convolutional networks and generative adversarial networks. These methods encode attribute-related information in…

Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of few-shot action…