Search Results for author: Hanshu Yan

Found 26 papers, 14 papers with code

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

1 code implementation13 May 2024 Hanshu Yan, Xingchao Liu, Jiachun Pan, Jun Hao Liew, Qiang Liu, Jiashi Feng

We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models.

MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation

no code implementations9 Jan 2024 Weimin WANG, Jiawei Liu, Zhijie Lin, Jiangqiao Yan, Shuo Chen, Chetwin Low, Tuyen Hoang, Jie Wu, Jun Hao Liew, Hanshu Yan, Daquan Zhou, Jiashi Feng

The growing demand for high-fidelity video generation from textual descriptions has catalyzed significant research in this field.

MORPH Video Generation

Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method

1 code implementation19 Dec 2023 Jiachun Pan, Hanshu Yan, Jun Hao Liew, Jiashi Feng, Vincent Y. F. Tan

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.

Video Generation

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

2 code implementations27 Nov 2023 Zhongcong Xu, Jianfeng Zhang, Jun Hao Liew, Hanshu Yan, Jia-Wei Liu, Chenxu Zhang, Jiashi Feng, Mike Zheng Shou

Existing animation works typically employ the frame-warping technique to animate the reference image towards the target motion.

Image Animation

MagicEdit: High-Fidelity and Temporally Coherent Video Editing

no code implementations28 Aug 2023 Jun Hao Liew, Hanshu Yan, Jianfeng Zhang, Zhongcong Xu, Jiashi Feng

In this report, we present MagicEdit, a surprisingly simple yet effective solution to the text-guided video editing task.

Translation Video Editing

MagicAvatar: Multimodal Avatar Generation and Animation

no code implementations28 Aug 2023 Jianfeng Zhang, Hanshu Yan, Zhongcong Xu, Jiashi Feng, Jun Hao Liew

This report presents MagicAvatar, a framework for multimodal video generation and animation of human avatars.

Video Generation

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models

1 code implementation20 Jul 2023 Jiachun Pan, Jun Hao Liew, Vincent Y. F. Tan, Jiashi Feng, Hanshu Yan

Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts.

Denoising

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

3 code implementations26 Jun 2023 Yujun Shi, Chuhui Xue, Jun Hao Liew, Jiachun Pan, Hanshu Yan, Wenqing Zhang, Vincent Y. F. Tan, Song Bai

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

1 code implementation7 Feb 2023 Xiang Lan, Hanshu Yan, Shenda Hong, Mengling Feng

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.

Contrastive Learning Representation Learning +2

MagicVideo: Efficient Video Generation With Latent Diffusion Models

no code implementations20 Nov 2022 Daquan Zhou, Weimin WANG, Hanshu Yan, Weiwei Lv, Yizhe Zhu, Jiashi Feng

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.

Text-to-Video Generation Video Generation

Towards Adversarial Robustness of Deep Vision Algorithms

no code implementations19 Nov 2022 Hanshu Yan

However, deep neural networks have been shown to be vulnerable to adversarial perturbations in input data.

Adversarial Robustness Image Classification

MagicMix: Semantic Mixing with Diffusion Models

2 code implementations28 Oct 2022 Jun Hao Liew, Hanshu Yan, Daquan Zhou, Jiashi Feng

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.

Denoising Style Transfer

Towards Adversarially Robust Deep Image Denoising

no code implementations12 Jan 2022 Hanshu Yan, Jingfeng Zhang, Jiashi Feng, Masashi Sugiyama, Vincent Y. F. Tan

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.

Adversarial Attack Adversarial Robustness +1

Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond

1 code implementation NeurIPS 2021 Pan Zhou, Hanshu Yan, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan

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

1 code implementation ICLR 2022 Jiawei Du, Hanshu Yan, Jiashi Feng, Joey Tianyi Zhou, Liangli Zhen, Rick Siow Mong Goh, Vincent Y. F. Tan

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

1 code implementation3 Oct 2021 Haiyun He, Hanshu Yan, Vincent Y. F. Tan

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.

Generalization Bounds

Information-Theoretic Generalization Bounds for Iterative Semi-Supervised Learning

no code implementations29 Sep 2021 Haiyun He, Hanshu Yan, Vincent Tan

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.

Generalization Bounds

Recovering the Unbiased Scene Graphs from the Biased Ones

1 code implementation5 Jul 2021 Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng

Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.

Missing Labels Scene Graph Classification +4

CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection

2 code implementations10 Feb 2021 Hanshu Yan, Jingfeng Zhang, Gang Niu, Jiashi Feng, Vincent Y. F. Tan, Masashi Sugiyama

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.

Adversarial Robustness feature selection

Semantic Domain Adversarial Networks for Unsupervised Domain Adaptation

no code implementations30 Mar 2020 Dapeng Hu, Jian Liang, Qibin Hou, Hanshu Yan, Yunpeng Chen, Shuicheng Yan, Jiashi Feng

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.

Object Recognition Semantic Segmentation +1

On Robustness of Neural Ordinary Differential Equations

2 code implementations ICLR 2020 Hanshu Yan, Jiawei Du, Vincent Y. F. Tan, Jiashi Feng

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.

Adversarial Attack

PROTOTYPE-ASSISTED ADVERSARIAL LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION

no code implementations25 Sep 2019 Dapeng Hu, Jian Liang*, Qibin Hou, Hanshu Yan, Jiashi Feng

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.

Object Recognition Semantic Segmentation +1

Interpreting Deep Classification Models With Bayesian Inference

no code implementations ICLR 2018 Hanshu Yan, Jiashi Feng

The results demonstrate that the proposed interpreter successfully finds the core hidden units most responsible for prediction making.

Bayesian Inference Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.