Search Results for author:
Found 44 papers, 33 papers with code
DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model
Text-to-image (T2I) generative models have attracted significant attention and found extensive applications within and beyond academic research.
Break-for-Make: Modular Low-Rank Adaptations for Composable Content-Style Customization
Based on the adapters broken apart for separate training content and style, we then make the entity parameter space by reconstructing the content and style PLPs matrices, followed by fine-tuning the combined adapter to generate the target object with the desired appearance.
FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data
Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity in federated learning (FL) by grouping similar clients for cluster-wise model training.
Ultrasound Imaging based on the Variance of a Diffusion Restoration Model
Despite today's prevalence of ultrasound imaging in medicine, ultrasound signal-to-noise ratio is still affected by several sources of noise and artefacts.
Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models
Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a combination of low- and high-resolution visual features can effectively mitigate this shortcoming.
Ranked #57 on
Visual Question Answering
on MM-Vet
CreativeSynth: Creative Blending and Synthesis of Visual Arts based on Multimodal Diffusion
Large-scale text-to-image generative models have made impressive strides, showcasing their ability to synthesize a vast array of high-quality images.
Learning Image Demoireing from Unpaired Real Data
The proposed method, referred to as Unpaired Demoireing (UnDeM), synthesizes pseudo moire images from unpaired datasets, generating pairs with clean images for training demoireing models.
Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study
The poor cross-architecture generalization of dataset distillation greatly weakens its practical significance.
MotionCrafter: One-Shot Motion Customization of Diffusion Models
The essence of a video lies in its dynamic motions, including character actions, object movements, and camera movements.
Diffusion Reconstruction of Ultrasound Images with Informative Uncertainty
Bringing the best from both worlds, we propose a hybrid approach leveraging advances in diffusion models.
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs, in the fashion of performing iterative weight pruning-and-growing on top of sparse LLMs.
Ultrasound Image Reconstruction with Denoising Diffusion Restoration Models
Ultrasound image reconstruction can be approximately cast as a linear inverse problem that has traditionally been solved with penalized optimization using the $l_1$ or $l_2$ norm, or wavelet-based terms.
Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation
PLMs can perform well in schema alignment but struggle to achieve complex reasoning, while LLMs is superior in complex reasoning tasks but cannot achieve precise schema alignment.
Spatial Re-parameterization for N:M Sparsity
This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity in CNNs.
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
We apply ProSpect in various personalized attribute-aware image generation applications, such as image-guided or text-driven manipulations of materials, style, and layout, achieving previously unattainable results from a single image input without fine-tuning the diffusion models.
MultiQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization
However, in this paper, we investigate existing methods and observe a significant accumulation of quantization errors caused by frequent bit-width switching of weights and activations, leading to limited performance.
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
Compared to the common iterative exhaustive search algorithm, our strategy avoids the enumeration of all possible combinations in the universal set, reducing the time complexity from exponential to linear.
Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer
Large-scale text-to-video diffusion models have demonstrated an exceptional ability to synthesize diverse videos.
A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning
Our framework consists of three key components, i. e., a parallel contrastive learning scheme for style representation and style transfer, a domain enhancement module for effective learning of style distribution, and a generative network for style transfer.
Bi-directional Masks for Efficient N:M Sparse Training
We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves practical speedups supported by the N:M sparse tensor core.
Real-Time Image Demoireing on Mobile Devices
In this paper, we launch the first study on accelerating demoireing networks and propose a dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices.
SMMix: Self-Motivated Image Mixing for Vision Transformers
Due to the subtle designs of the self-motivated paradigm, our SMMix is significant in its smaller training overhead and better performance than other CutMix variants.
Shadow Removal by High-Quality Shadow Synthesis
Specifically, the encoder extracts the shadow feature of a region identity which is then paired with another region identity to serve as the generator input to synthesize a pseudo image.
Inversion-Based Style Transfer with Diffusion Models
Our key idea is to learn artistic style directly from a single painting and then guide the synthesis without providing complex textual descriptions.
DiffStyler: Controllable Dual Diffusion for Text-Driven Image Stylization
Despite the impressive results of arbitrary image-guided style transfer methods, text-driven image stylization has recently been proposed for transferring a natural image into a stylized one according to textual descriptions of the target style provided by the user.
Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training
In QAT, the contemporary experience is that all quantized weights are updated for an entire training process.
Learning Best Combination for Efficient N:M Sparsity
In this paper, we show that the N:M learning can be naturally characterized as a combinatorial problem which searches for the best combination candidate within a finite collection.
Super Vision Transformer
Experimental results on ImageNet demonstrate that our SuperViT can considerably reduce the computational costs of ViT models with even performance increase.
Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning
Our framework consists of three key components, i. e., a multi-layer style projector for style code encoding, a domain enhancement module for effective learning of style distribution, and a generative network for image style transfer.
A Survey of Deep Learning Models for Structural Code Understanding
In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights.
Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters
Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its closest filters.
OptG: Optimizing Gradient-driven Criteria in Network Sparsity
We prove that supermask training is to accumulate the criteria of gradient-driven sparsity for both removed and preserved weights, and it can partly solve the independence paradox.
Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection
In this paper, we propose a novel approach called Adaptive Memory Network with Self-supervised Learning (AMSL) to address these challenges and enhance the generalization ability in unsupervised anomaly detection.
End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction
Deep learning techniques have emerged as a promising approach to highly accelerated MRI.
fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Data
Improving speed and image quality of Magnetic Resonance Imaging (MRI) via novel reconstruction approaches remains one of the highest impact applications for deep learning in medical imaging.
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
We empirically compare the proposed approach with several state-of-the-art anomaly detection methods on HAR and HC datasets.
1xN Pattern for Pruning Convolutional Neural Networks
We also provide a workflow of filter rearrangement that first rearranges the weight matrix in the output channel dimension to derive more influential blocks for accuracy improvements and then applies similar rearrangement to the next-layer weights in the input channel dimension to ensure correct convolutional operations.
Carrying out CNN Channel Pruning in a White Box
Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w. r. t.
Lottery Jackpots Exist in Pre-trained Models
Existing studies achieve the sparsity of neural networks via time-consuming weight training or complex searching on networks with expanded width, which greatly limits the applications of network pruning.
OUTCOMES: Rapid Under-sampling Optimization achieves up to 50% improvements in reconstruction accuracy for multi-contrast MRI sequences
Multi-contrast Magnetic Resonance Imaging (MRI) acquisitions from a single scan have tremendous potential to streamline exams and reduce imaging time.
Super Resolution Using Segmentation-Prior Self-Attention Generative Adversarial Network
Convolutional Neural Network (CNN) is intensively implemented to solve super resolution (SR) tasks because of its superior performance.
Channel Pruning via Automatic Structure Search
In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i. e., channel number in each layer, rather than selecting "important" channels as previous works did.
RGTI:Response generation via templates integration for End to End dialog
End-to-end models have achieved considerable success in task-oriented dialogue area, but suffer from the challenges of (a) poor semantic control, and (b) little interaction with auxiliary information.
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method
Despite enjoying extensive applications in video analysis, three-dimensional convolutional neural networks (3D CNNs)are restricted by their massive computation and storage consumption.
