Search Results for author:
Found 45 papers, 13 papers with code
Lower Layer Matters: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused
Large Language Models (LLMs) have demonstrated exceptional performance across various natural language processing tasks, yet they occasionally tend to yield content that factually inaccurate or discordant with the expected output, a phenomenon empirically referred to as "hallucination".
Resource Allocation and Workload Scheduling for Large-Scale Distributed Deep Learning: A Survey
The large-scale environment with large volumes of datasets, models, and computational and communication resources raises various unique challenges for resource allocation and workload scheduling in distributed deep learning, such as scheduling complexity, resource and workload heterogeneity, and fault tolerance.
Looking Backward: Streaming Video-to-Video Translation with Feature Banks
This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts.
Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey
Due to intensive synchronization of models and sharing of data across GPUs and computing nodes during distributed training and inference processes, communication efficiency becomes the bottleneck for achieving high performance at a large scale.
S2LIC: Learned Image Compression with the SwinV2 Block, Adaptive Channel-wise and Global-inter Attention Context
In this paper, we propose an Adaptive Channel-wise and Global-inter attention Context (ACGC) entropy model, which can efficiently achieve dual feature aggregation in both inter-slice and intraslice contexts.
Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
As a consequence, this yields an $\widetilde{O}\left(n^{-1/2} t^{-\frac{d}{4}}\right)$ upper bound for the total variation error of the distribution of the sample generated by the diffusion model under a mere sub-Gaussian assumption.
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
This enables our model for video synthesis by editing the first frame with any prevalent I2I models and then propagating edits to successive frames.
Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis
In this paper, we introduce Fairy, a minimalist yet robust adaptation of image-editing diffusion models, enhancing them for video editing applications.
Fast and High-Performance Learned Image Compression With Improved Checkerboard Context Model, Deformable Residual Module, and Knowledge Distillation
Then we only encode non-zero channels in the encoding and decoding process, which can greatly reduce the encoding and decoding time.
Enhanced Residual SwinV2 Transformer for Learned Image Compression
In particular, our method achieves comparable results while reducing model complexity by 56% compared to these recent methods.
Mask Hierarchical Features For Self-Supervised Learning
We mask part of patches in the representation space and then utilize sparse visible patches to reconstruct high semantic image representation.
Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
Our Fast-BEV consists of five parts, We novelly propose (1) a lightweight deployment-friendly view transformation which fast transfers 2D image feature to 3D voxel space, (2) an multi-scale image encoder which leverages multi-scale information for better performance, (3) an efficient BEV encoder which is particularly designed to speed up on-vehicle inference.
Fast-BEV: Towards Real-time On-vehicle Bird's-Eye View Perception
Recently, the pure camera-based Bird's-Eye-View (BEV) perception removes expensive Lidar sensors, making it a feasible solution for economical autonomous driving.
MobileTL: On-device Transfer Learning with Inverted Residual Blocks
MobileTL trains the shifts for internal normalization layers to avoid storing activation maps for the backward pass.
Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions.
Ranked #4 on
Semantic Segmentation
on Replica
Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation
In addition, these methods based on the context-adaptive entropy model cannot be accelerated in the decoding process by parallel computing devices, e. g. FPGA or GPU.
Play It Cool: Dynamic Shifting Prevents Thermal Throttling
Machine learning (ML) has entered the mobile era where an enormous number of ML models are deployed on edge devices.
Asymmetric Learned Image Compression with Multi-Scale Residual Block, Importance Map, and Post-Quantization Filtering
Based on this observation, we design an asymmetric paradigm, in which the encoder employs three stages of MSRBs to improve the learning capacity, whereas the decoder only needs one stage of MSRB to yield satisfactory reconstruction, thereby reducing the decoding complexity without sacrifcing performance.
SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
The proposed Supervised MAE (SupMAE) only exploits a visible subset of image patches for classification, unlike the standard supervised pre-training where all image patches are used.
Differentiable Electron Microscopy Simulation: Methods and Applications for Visualization
We propose a new microscopy simulation system that can depict atomistic models in a micrograph visual style, similar to results of physical electron microscopy imaging.
Personalized Execution Time Optimization for the Scheduled Jobs
Scheduled batch jobs have been widely used on the asynchronous computing platforms to execute various enterprise applications, including the scheduled notifications and the candidate pre-computation for the modern recommender systems.
Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision
This is because researchers do not choose consistent training recipes and even use different data, hampering the fair comparison between different methods.
RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training
Recently, self-supervised vision transformers have attracted unprecedented attention for their impressive representation learning ability.
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks.
Learning Topic Models: Identifiability and Finite-Sample Analysis
Our theory introduces a new set of geometric conditions for topic model identifiability, conditions that are weaker than conventional separability conditions, which typically rely on the existence of pure topic documents or of anchor words.
Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules
However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image.
Inception Convolution with Efficient Dilation Search
To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.
Reinforcement Learning-based Product Delivery Frequency Control
We demonstrate statistically significant improvement in daily metrics and resource efficiency by our method in several notification applications at a scale of billions of users.
ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
We use ScaleNAS to create high-resolution models for two different tasks, ScaleNet-P for human pose estimation and ScaleNet-S for semantic segmentation.
Ranked #5 on
Multi-Person Pose Estimation
on COCO test-dev
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
Therefore, we propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides.
Once Quantized for All: Progressively Searching for Quantized Compact Models
Automatic search of Quantized Neural Networks (QNN) has attracted a lot of attention.
NASGEM: Neural Architecture Search via Graph Embedding Method
To preserve graph correlation information in encoding, we propose NASGEM which stands for Neural Architecture Search via Graph Embedding Method.
Computation Reallocation for Object Detection
However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal.
Bayesian Joint Estimation of Multiple Graphical Models
In this paper, we propose a novel Bayesian group regularization method based on the spike and slab Lasso priors for jointly estimating multiple graphical models.
Improved Hybrid Layered Image Compression using Deep Learning and Traditional Codecs
Recently deep learning-based methods have been applied in image compression and achieved many promising results.
A Deep Image Compression Framework for Face Recognition
In this paper, we propose a deep convolutional autoencoder compression network for face recognition tasks.
Bayesian Regularization for Graphical Models with Unequal Shrinkage
We consider a Bayesian framework for estimating a high-dimensional sparse precision matrix, in which adaptive shrinkage and sparsity are induced by a mixture of Laplace priors.
Discriminative Similarity for Clustering and Semi-Supervised Learning
By generalization analysis via Rademacher complexity, the generalization error bound for the kernel classifier learned from hypothetical labeling is expressed as the sum of pairwise similarity between the data from different classes, parameterized by the weights of the kernel classifier.
An Empirical Bayes Approach for High Dimensional Classification
We propose an empirical Bayes estimator based on Dirichlet process mixture model for estimating the sparse normalized mean difference, which could be directly applied to the high dimensional linear classification.
Clustering With Side Information: From a Probabilistic Model to a Deterministic Algorithm
Empirical studies have been carried out to compare our work with many constrained clustering algorithms from the literature on both a variety of data sets and under a variety of conditions such as using noisy side information and erroneous k values.
On a Theory of Nonparametric Pairwise Similarity for Clustering: Connecting Clustering to Classification
Modeling the underlying data distribution by nonparametric kernel density estimation, the generalization error bounds for both unsupervised nonparametric classifiers are the sum of nonparametric pairwise similarity terms between the data points for the purpose of clustering.
PAC-Bayesian AUC classification and scoring
We also extend our method to a class of non-linear score functions, essentially leading to a nonparametric procedure, by considering a Gaussian process prior.
Learning Locally-Adaptive Decision Functions for Person Verification
This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule.
Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models
First, we can boost the diversity of classification ensemble by incorporating multiple clustering outputs, each of which provides grouping constraints for the joint label predictions of a set of related objects.
Localized Sliced Inverse Regression
We developed localized sliced inverse regression for supervised dimension reduction.
