Search Results for author:
Found 33 papers, 22 papers with code
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
Score identity Distillation (SiD) is a data-free method that has achieved SOTA performance in image generation by leveraging only a pretrained diffusion model, without requiring any training data.
What If We Recaption Billions of Web Images with LLaMA-3?
For discriminative models like CLIP, we observe enhanced zero-shot performance in cross-modal retrieval tasks.
Ranked #96 on
Visual Question Answering
on MM-Vet
Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation
Specifically, its data-free distillation of Stable Diffusion 1. 5 achieves a record low FID of 8. 15 on the COCO-2014 validation set, with a CLIP score of 0. 304 at an LSG scale of 1. 5, and an FID of 9. 56 with a CLIP score of 0. 313 at an LSG scale of 2.
Ranked #22 on
Text-to-Image Generation
on MS COCO
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
This achievement not only redefines the benchmarks for efficiency and effectiveness in diffusion distillation but also in the broader field of diffusion-based generation.
Ranked #9 on
Image Generation
on CIFAR-10
InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models
To mitigate this issue, we manually curate a benchmark dataset specifically designed for MLLMs, with a focus on complex reasoning tasks.
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling.
Ranked #13 on
Image Generation
on CelebA 64x64
Beta Diffusion
We introduce beta diffusion, a novel generative modeling method that integrates demasking and denoising to generate data within bounded ranges.
Class-Balancing Diffusion Models
To tackle this problem, we set from the hypothesis that the data distribution is not class-balanced, and propose Class-Balancing Diffusion Models (CBDM) that are trained with a distribution adjustment regularizer as a solution.
POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models
Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years.
Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
Patch Diffusion meanwhile improves the performance of diffusion models trained on relatively small datasets, $e. g.$, as few as 5, 000 images to train from scratch.
Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyond
Although text-to-image diffusion models have made significant strides in generating images from text, they are sometimes more inclined to generate images like the data on which the model was trained rather than the provided text.
DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration
However, it is expensive and infeasible to include every type of degradation to cover real-world cases in the training data.
CARD: Classification and Regression Diffusion Models
In this paper, we introduce classification and regression diffusion (CARD) models, which combine a denoising diffusion-based conditional generative model and a pre-trained conditional mean estimator, to accurately predict the distribution of $\boldsymbol y$ given $\boldsymbol x$.
Diffusion-GAN: Training GANs with Diffusion
Both the observed and generated data are diffused by the same adaptive diffusion process.
Ranked #1 on
Image Generation
on LSUN Bedroom 256 x 256
Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
This paper introduces a new topic-modeling framework where each document is viewed as a set of word embedding vectors and each topic is modeled as an embedding vector in the same embedding space.
Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
Employing a forward diffusion chain to gradually map the data to a noise distribution, diffusion-based generative models learn how to generate the data by inferring a reverse diffusion chain.
Ranked #2 on
Text-to-Image Generation
on CUB
A Behavior Regularized Implicit Policy for Offline Reinforcement Learning
For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy.
Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPs
In this paper, to exploit both global and local dependencies without self-attention, we present Mix-Shift-MLP (MS-MLP) which makes the size of the local receptive field used for mixing increase with respect to the amount of spatial shifting.
Alignment Attention by Matching Key and Query Distributions
The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains.
A Prototype-Oriented Framework for Unsupervised Domain Adaptation
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.
Crossformer: Transformer with Alternated Cross-Layer Guidance
Crossformer with states sharing not only provides the desired cross-layer guidance and regularization but also reduces the memory requirement.
State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning
For training more effective agents, we propose a framework that supports learning a flexible and well-regularized policy, which consists of a fully implicit policy and a regularization through the state-action visitation frequency induced by the current policy and that induced by the data-collecting behavior policy.
Contrastive Attraction and Contrastive Repulsion for Representation Learning
We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.
Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
The forward CT is the expected cost of moving a source data point to a target one, with their joint distribution defined by the product of the source probability density function (PDF) and a source-dependent conditional distribution, which is related to the target PDF via Bayes' theorem.
Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework
Based on this object function we introduce a novel information theoretic framework for unsupervised image anomaly detection.
Ranked #9 on
Anomaly Detection
on One-class CIFAR-100
Learning on Attribute-Missing Graphs
Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community.
MCMC-Interactive Variational Inference
Leveraging well-established MCMC strategies, we propose MCMC-interactive variational inference (MIVI) to not only estimate the posterior in a time constrained manner, but also facilitate the design of MCMC transitions.
ACT: Asymptotic Conditional Transport
We propose conditional transport (CT) as a new divergence to measure the difference between two probability distributions.
Node Attribute Generation on Graphs
NANG learns a unifying latent representation which is shared by both node attributes and graph structures and can be translated to different modalities.
Elastic Boundary Projection for 3D Medical Image Segmentation
The key observation is that, although the object is a 3D volume, what we really need in segmentation is to find its boundary which is a 2D surface.
Phase Collaborative Network for Two-Phase Medical Image Segmentation
However, in medical image analysis, fusing prediction from two phases is often difficult, because (i) there is a domain gap between two phases, and (ii) the semantic labels are not pixel-wise corresponded even for images scanned from the same patient.
Understanding VAEs in Fisher-Shannon Plane
In information theory, Fisher information and Shannon information (entropy) are respectively used to quantify the uncertainty associated with the distribution modeling and the uncertainty in specifying the outcome of given variables.
Degeneration in VAE: in the Light of Fisher Information Loss
While enormous progress has been made to Variational Autoencoder (VAE) in recent years, similar to other deep networks, VAE with deep networks suffers from the problem of degeneration, which seriously weakens the correlation between the input and the corresponding latent codes, deviating from the goal of the representation learning.
