Related papers: FeatDistill: A Feature Distillation Enhanced Multi…
Artificial intelligence (AI) in media has advanced rapidly over the last decade. The introduction of Generative Adversarial Networks (GANs) improved the quality of photorealistic image generation. Diffusion models later brought a new era of…
Diffusion-based generative models have demonstrated their powerful performance across various tasks, but this comes at a cost of the slow sampling speed. To achieve both efficient and high-quality synthesis, various distillation-based…
The tremendous recent advances in generative artificial intelligence techniques have led to significant successes and promise in a wide range of different applications ranging from conversational agents and textual content generation to…
Dataset distillation has emerged as a technique aiming to condense informative features from large, natural datasets into a compact and synthetic form. While recent advancements have refined this technique, its performance is bottlenecked…
Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on…
Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining diffusion, a novel framework that enhances image generation…
Synthetic image generation has opened up new opportunities but has also created threats in regard to privacy, authenticity, and security. Detecting fake images is of paramount importance to prevent illegal activities, and previous research…
Recent generative models show impressive performance in generating photographic images. Humans can hardly distinguish such incredibly realistic-looking AI-generated images from real ones. AI-generated images may lead to ubiquitous…
Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance. Although distilling precise 3D…
Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…
Modern multimodal generators can now produce scientific figures at near-publishable quality, creating a new challenge for visual forensics and research integrity. Unlike conventional AI-generated natural images, scientific figures are…
This article identifies and addresses a fundamental bottleneck in data-driven 360-degree image quality assessment (IQA): the lack of intelligent, sample-level data selection. Hence, we propose a novel framework that introduces a critical…
AI-generated image (AIGI) detection and source model attribution remain central challenges in combating deepfake abuses, primarily due to the structural diversity of generative models. Current detection methods are prone to overfitting…
Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels,…
Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing…
Fine-grained image retrieval (FGIR) is to learn visual representations that distinguish visually similar objects while maintaining generalization. Existing methods propose to generate discriminative features, but rarely consider the…
Facial expressions are the most common universal forms of body language. In the past few years, automatic facial expression recognition (FER) has been an active field of research. However, it is still a challenging task due to different…
Dataset distillation seeks to synthesize a highly compact dataset that achieves performance comparable to the original dataset on downstream tasks. For the classification task that use pre-trained self-supervised models as backbones,…
Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent…
Recent advances in large-scale text-to-image generation models have led to a surge in subject-driven text-to-image generation, which aims to produce customized images that align with textual descriptions while preserving the identity of…