Related papers: ASemConsist: Adaptive Semantic Feature Control for…
Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…
Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often…
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and…
Recently, learning-based semantic communication (SemCom) has emerged as a promising approach in the upcoming 6G network and researchers have made remarkable efforts in this field. However, existing works have yet to fully explore the…
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…
Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed set of candidates. A natural idea is to embed these opinions in a vector space so that the…
Generating an image from a given text description has two goals: visual realism and semantic consistency. Although significant progress has been made in generating high-quality and visually realistic images using generative adversarial…
Given a text and an image of a specific subject, text-to-image customization aims to generate new images that align with both the text and the subject's appearance. Existing works follow the pseudo-word paradigm, which represents the…
Accurate color alignment in text-to-image (T2I) generation is critical for applications such as fashion, product visualization, and interior design, yet current diffusion models struggle with nuanced and compound color terms (e.g., Tiffany…
In the quest for fairness in artificial intelligence, novel approaches to enhance it in facial image based gender classification algorithms using text guided methodologies are presented. The core methodology involves leveraging semantic…
We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target domain, as the images…
Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from textual descriptions. However, these approaches have faced challenges in precisely aligning the generated…
Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers…
Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…
We propose CatVersion, an inversion-based method that learns the personalized concept through a handful of examples. Subsequently, users can utilize text prompts to generate images that embody the personalized concept, thereby achieving…
Current learning-based subject customization approaches, predominantly relying on U-Net architectures, suffer from limited generalization ability and compromised image quality. Meanwhile, optimization-based methods require subject-specific…
Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…
Representation learning plays a central role in structuring internal embeddings to capture the statistical properties of language, influencing the coherence and contextual consistency of generated text. Statistical Coherence Alignment is…
Recent studies extend the autoregression paradigm to text-to-image generation, achieving performance comparable to diffusion models. However, our new PairComp benchmark -- featuring test cases of paired prompts with similar syntax but…
Diffusion-based video motion customization facilitates the acquisition of human motion representations from a few video samples, while achieving arbitrary subjects transfer through precise textual conditioning. Existing approaches often…