Related papers: Continuous Adversarial Flow Models
We propose a gradient flow procedure for generative modeling by transporting particles from an initial source distribution to a target distribution, where the gradient field on the particles is given by a noise-adaptive Wasserstein Gradient…
Age progression and regression aim to synthesize photorealistic appearance of a given face image with aging and rejuvenation effects, respectively. Existing generative adversarial networks (GANs) based methods suffer from the following…
Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…
Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training efficiency. Moreover, as new adversarial attacks and training…
Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest,…
We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This…
Video recognition models remain vulnerable to adversarial attacks, while existing diffusion-based purification methods suffer from inefficient sampling and curved trajectories. Directly regressing clean videos from adversarial inputs often…
Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high quality image samples but can be difficult to optimize as…
Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution…
This paper proposes the TrafficFlowGAN, a physics-informed flow based generative adversarial network (GAN), for uncertainty quantification (UQ) of dynamical systems. TrafficFlowGAN adopts a normalizing flow model as the generator to…
Time-unconditional generative models learn time-independent denoising vector fields. But without time conditioning, the same noisy input may correspond to multiple noise levels and different denoising directions, which interferes with the…
Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also…
With the advent of generative adversarial networks, synthesizing images from textual descriptions has recently become an active research area. It is a flexible and intuitive way for conditional image generation with significant progress in…
Future frame prediction in videos is a promising avenue for unsupervised video representation learning. Video frames are naturally generated by the inherent pixel flows from preceding frames based on the appearance and motion dynamics in…
Continual learning in robotics seeks systems that can constantly adapt to changing environments and tasks, mirroring human adaptability. A key challenge is refining dynamics models, essential for planning and control, while addressing…
The proposed method, Discriminator Guidance, aims to improve sample generation of pre-trained diffusion models. The approach introduces a discriminator that gives explicit supervision to a denoising sample path whether it is realistic or…
Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…
While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test data might not be…
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a novel explanation.…
Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…