Related papers: Text-Anchored Score Composition: Tackling Conditio…
Language-Assisted Image Clustering (LAIC) augments the input images with additional texts with the help of vision-language models (VLMs) to promote clustering performance. Despite recent progress, existing LAIC methods often overlook two…
Text-to-image models are known to struggle with generating images that perfectly align with textual prompts. Several previous studies have focused on evaluating image-text alignment in text-to-image generation. However, these evaluations…
Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation. However, even state-of-the-art MM-DiT models like FLUX struggle with achieving precise alignment between text prompts and…
Recently, the multimedia community has witnessed the rise of diffusion models trained on large-scale multi-modal data for visual content creation, particularly in the field of text-to-image generation. In this paper, we propose a new task…
Recent text-to-image diffusion models have reached an unprecedented level in generating high-quality images. However, their exclusive reliance on textual prompts often falls short in precise control of image compositions. In this paper, we…
Text-to-image generation has witnessed significant advancements with the integration of Large Vision-Language Models (LVLMs), yet challenges remain in aligning complex textual descriptions with high-quality, visually coherent images. This…
Textual representations based on pre-trained language models are key, especially in few-shot learning scenarios. What makes a representation good for text classification? Is it due to the geometric properties of the space or because it is…
Text-to-image synthesis has made encouraging progress and attracted lots of public attention recently. However, popular evaluation metrics in this area, like the Inception Score and Fr'echet Inception Distance, incur several issues. First…
Score-based diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific training of a conditional model or classifier guidance, which…
We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, including inpainting and super-resolution. In these problems, the observation determines only part of the unknown signal. The remaining…
Class imbalance poses a major challenge for machine learning as most supervised learning models might exhibit bias towards the majority class and under-perform in the minority class. Cost-sensitive learning tackles this problem by treating…
Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin…
Inversion methods, such as Textual Inversion, generate personalized images by incorporating concepts of interest provided by user images. However, existing methods often suffer from overfitting issues, where the dominant presence of…
Unifying Image Quality Assessment (IQA) and Image Aesthetic Assessment (IAA) in a single multimodal large language model is appealing, yet existing methods adopt a task-agnostic recipe that applies the same reasoning strategy and reward to…
This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary features to alter a classifier's prediction for a given image. Our proposed method,…
This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme…
Inverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have…
Layout-guided text-to-image models offer greater control over the generation process by explicitly conditioning image synthesis on the spatial arrangement of elements. As a result, their adoption has increased in many computer vision…
Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…
Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional understanding. In contrast, recent generative text-to-image…