Related papers: DiffAug: A Diffuse-and-Denoise Augmentation for Tr…

The challenge in fine-grained visual categorization lies in how to explore the subtle differences between different subclasses and achieve accurate discrimination. Previous research has relied on large-scale annotated data and pre-trained…

Text-to-image diffusion models are a class of deep generative models that have demonstrated an impressive capacity for high-quality image generation. However, these models are susceptible to implicit biases that arise from web-scale…

Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, bypassing the traditional localization-mapping-planning…

Detectors often suffer from performance drop due to domain gap between training and testing data. Recent methods explore diffusion models applied to domain generalization (DG) and adaptation (DA) tasks, but still struggle with large…

Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc. However, due to the inherent complexity and non-uniqueness of…

Generative adversarial networks (GANs) are challenging to train stably, and a promising remedy of injecting instance noise into the discriminator input has not been very effective in practice. In this paper, we propose Diffusion-GAN, a…

Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and eddy current, leading to detail loss in reconstructing the DTI-derived parametric…

Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from…

Learning models with categorical variables requires optimizing expectations over discrete distributions, a setting in which stochastic gradient-based optimization is challenging due to the non-differentiability of categorical sampling. A…

While Diffusion Models (DM) exhibit remarkable performance across various image generative tasks, they nonetheless reflect the inherent bias presented in the training set. As DMs are now widely used in real-world applications, these biases…

The slow inference process of image diffusion models significantly degrades interactive user experiences. To address this, we introduce Diffusion Preview, a novel paradigm employing rapid, low-step sampling to generate preliminary outputs…

Image restoration tasks like deblurring, denoising, and dehazing usually need distinct models for each degradation type, restricting their generalization in real-world scenarios with mixed or unknown degradations. In this work, we propose…

Recent research finds CNN models for image classification demonstrate overlapped adversarial vulnerabilities: adversarial attacks can mislead CNN models with small perturbations, which can effectively transfer between different models…

Diffusion models have demonstrated their powerful generative capability in many tasks, with great potential to serve as a paradigm for offline reinforcement learning. However, the quality of the diffusion model is limited by the…

The depth-of-field (DoF) effect, which introduces aesthetically pleasing blur, enhances photographic quality but is fixed and difficult to modify once the image has been created. This becomes problematic when the applied blur is…

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

Currently, methods for single-image deblurring based on CNNs and transformers have demonstrated promising performance. However, these methods often suffer from perceptual limitations, poor generalization ability, and struggle with heavy or…

Diffusion policies trained via offline behavioral cloning have recently gained traction in robotic motion generation. While effective, these policies typically require a large number of trainable parameters. This model size affords powerful…

Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the stability-plasticity dilemma and data scarcity. Current…

This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility…