Search Results for author:
Found 32 papers, 19 papers with code
OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs
Specifically, we force the predictions from our one-step student model for same input to lie on the same sampling ODE trajectory of the teacher model.
Accelerating Video Diffusion Models via Distribution Matching
Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets.
Aria: An Open Multimodal Native Mixture-of-Experts Model
Information comes in diverse modalities.
Ranked #5 on
Video Question Answering
on TVBench
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
In this paper, we aim to incorporate the sub-quadratic modeling capability of Gated Linear Attention (GLA) into the 2D diffusion backbone.
ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
Recent text-to-image customization works have been proven successful in generating images of given concepts by fine-tuning the diffusion models on a few examples.
LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
Accuracy and speed are critical in image editing tasks.
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models.
MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation
The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field.
Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method
However, since the off-the-shelf pre-trained networks are trained on clean images, the one-step estimation procedure of the clean image may be inaccurate, especially in the early stages of the generation process in diffusion models.
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion.
MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation
The flexibility of these techniques enables the editing of arbitrary regions within the frame.
MagicEdit: High-Fidelity and Temporally Coherent Video Editing
In this report, we present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task.
MagicAvatar: Multimodal Avatar Generation and Animation
This report presents MagicAvatar, a framework for multimodal video generation and animation of human avatars.
AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts.
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
In this work, we extend this editing framework to diffusion models and propose a novel approach DragDiffusion.
Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
In this paper, we study two types of bad positive pairs that can impair the quality of time series representation learned through contrastive learning: the noisy positive pair and the faulty positive pair.
MagicVideo: Efficient Video Generation With Latent Diffusion Models
In specific, unlike existing works that directly train video models in the RGB space, we use a pre-trained VAE to map video clips into a low-dimensional latent space and learn the distribution of videos' latent codes via a diffusion model.
Ranked #10 on
Text-to-Video Generation
on UCF-101
Towards Adversarial Robustness of Deep Vision Algorithms
However, deep neural networks have been shown to be vulnerable to adversarial perturbations in input data.
MagicMix: Semantic Mixing with Diffusion Models
Unlike style transfer, where an image is stylized according to the reference style without changing the image content, semantic blending mixes two different concepts in a semantic manner to synthesize a novel concept while preserving the spatial layout and geometry.
Towards Adversarially Robust Deep Image Denoising
Secondly, to robustify DIDs, we propose an adversarial training strategy, hybrid adversarial training ({\sc HAT}), that jointly trains DIDs with adversarial and non-adversarial noisy data to ensure that the reconstruction quality is high and the denoisers around non-adversarial data are locally smooth.
Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond
Specifically, we prove that lookahead using SGD as its inner-loop optimizer can better balance the optimization error and generalization error to achieve smaller excess risk error than vanilla SGD on (strongly) convex problems and nonconvex problems with Polyak-{\L}ojasiewicz condition which has been observed/proved in neural networks.
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
Recently, the relation between the sharpness of the loss landscape and the generalization error has been established by Foret et al. (2020), in which the Sharpness Aware Minimizer (SAM) was proposed to mitigate the degradation of the generalization.
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning
Using information-theoretic principles, we consider the generalization error (gen-error) of iterative semi-supervised learning (SSL) algorithms that iteratively generate pseudo-labels for a large amount of unlabelled data to progressively refine the model parameters.
Information-Theoretic Generalization Bounds for Iterative Semi-Supervised Learning
We consider iterative semi-supervised learning (SSL) algorithms that iteratively generate pseudo-labels for a large amount unlabelled data to progressively refine the model parameters.
Recovering the Unbiased Scene Graphs from the Biased Ones
Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.
Ranked #3 on
Unbiased Scene Graph Generation
on Visual Genome
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise activations of adversarial data with those of their natural counterparts.
RAIN: A Simple Approach for Robust and Accurate Image Classification Networks
However, similar to existing preprocessing-based methods, the randomized process will degrade the prediction accuracy.
Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation
To successfully align the multi-modal data structures across domains, the following works exploit discriminative information in the adversarial training process, e. g., using multiple class-wise discriminators and introducing conditional information in input or output of the domain discriminator.
On Robustness of Neural Ordinary Differential Equations
We then provide an insightful understanding of this phenomenon by exploiting a certain desirable property of the flow of a continuous-time ODE, namely that integral curves are non-intersecting.
PROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
Previous adversarial learning methods condition domain alignment only on pseudo labels, but noisy and inaccurate pseudo labels may perturb the multi-class distribution embedded in probabilistic predictions, hence bringing insufficient alleviation to the latent mismatch problem.
Unsupervised Image Noise Modeling with Self-Consistent GAN
They jointly facilitate unsupervised learning of a noise model for various noise types.
Interpreting Deep Classification Models With Bayesian Inference
The results demonstrate that the proposed interpreter successfully finds the core hidden units most responsible for prediction making.
