Search Results for author:
Found 43 papers, 17 papers with code
UAV-Rain1k: A Benchmark for Raindrop Removal from UAV Aerial Imagery
Raindrops adhering to the lens of UAVs can obstruct visibility of the background scene and degrade image quality.
Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months.
Search Optimization with Query Likelihood Boosting and Two-Level Approximate Search for Edge Devices
We present a novel search optimization solution for approximate nearest neighbor (ANN) search on resource-constrained edge devices.
Boosting Segment Anything Model Towards Open-Vocabulary Learning
The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting.
Multiplayer Homicidal Chauffeur Reach-Avoid Games: A Pursuit Enclosure Function Approach
We propose a cooperative strategy for the pursuers based on subgames for multiple pursuers against one evader and optimal task allocation.
SemanticBoost: Elevating Motion Generation with Augmented Textual Cues
Our framework comprises a Semantic Enhancement module and a Context-Attuned Motion Denoiser (CAMD).
Minimax Optimal Transfer Learning for Kernel-based Nonparametric Regression
This paper focuses on investigating the transfer learning problem within the context of nonparametric regression over a reproducing kernel Hilbert space.
Structural transfer learning of non-Gaussian DAG
Directed acyclic graph (DAG) has been widely employed to represent directional relationships among a set of collected nodes.
Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift
Two types of covariate shift problems are the focus of this paper and the sharp convergence rates are established for a general loss function to provide a unified theoretical analysis, which concurs with the optimal results in literature where the squared loss is used.
Efficient Post-training Quantization with FP8 Formats
Recent advances in deep learning methods such as LLMs and Diffusion models have created a need for improved quantization methods that can meet the computational demands of these modern architectures while maintaining accuracy.
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
As the number of bits decreases, the quantization grid broadens, thus emphasizing the importance of up and down rounding.
FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs
The rapid growth of memory and computation requirements of large language models (LLMs) has outpaced the development of hardware, hindering people who lack large-scale high-end GPUs from training or deploying LLMs.
NeuralMatrix: Compute the Entire Neural Networks with Linear Matrix Operations for Efficient Inference
The inherent diversity of computation types within individual Deep Neural Network (DNN) models imposes a corresponding need for a varied set of computation units within hardware processors.
BS-GAT Behavior Similarity Based Graph Attention Network for Network Intrusion Detection
To address the above issue, this paper proposes a graph neural network algorithm based on behavior similarity (BS-GAT) using graph attention network.
Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding
To better accelerate the generative transformers while keeping good generation quality, we propose Lformer, a semi-autoregressive text-to-image generation model.
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension
One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i. e., subnet).
GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks
Based on the pre-trained model, we propose the graph prompting function to modify the standalone node into a token pair, and reformulate the downstream node classification looking the same as edge prediction.
Fine-Grained Semantically Aligned Vision-Language Pre-Training
Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks.
Virtual Homogeneity Learning: Defending against Data Heterogeneity in Federated Learning
In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift.
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training.
Ranked #10 on
Image Generation
on STL-10
Learning linear non-Gaussian directed acyclic graph with diverging number of nodes
The proposed method leverages a novel concept of topological layer to facilitate the DAG learning.
Efficient Learning of Quadratic Variance Function Directed Acyclic Graphs via Topological Layers
Directed acyclic graph (DAG) models are widely used to represent causal relationships among random variables in many application domains.
Kernel-based estimation for partially functional linear model: Minimax rates and randomized sketches
This paper considers the partially functional linear model (PFLM) where all predictive features consist of a functional covariate and a high dimensional scalar vector.
Maximize the Exploration of Congeneric Semantics for Weakly Supervised Semantic Segmentation
The graph network that is established with patches as the nodes can maximize the mutual learning of similar objects.
DeceFL: A Principled Decentralized Federated Learning Framework
Although there has been a joint effort in tackling such a critical issue by proposing privacy-preserving machine learning frameworks, such as federated learning, most state-of-the-art frameworks are built still in a centralized way, in which a central client is needed for collecting and distributing model information (instead of data itself) from every other client, leading to high communication pressure and high vulnerability when there exists a failure at or attack on the central client.
Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved.
A Competitive Method to VIPriors Object Detection Challenge
In this report, we introduce the technical details of our submission to the VIPriors object detection challenge.
Evolutionary Multi-objective Architecture Search Framework: Application to COVID-19 3D CT Classification
We propose a new objective, namely potential, which can help exploit promising models to indirectly reduce the number of models involved in weights training, thus alleviating search instability.
Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans
The experimental results show that our automatically searched models (CovidNet3D) outperform the baseline human-designed models on the three datasets with tens of times smaller model size and higher accuracy.
Alpha-DAG: a reinforcement learning based algorithm to learn Directed Acyclic Graphs
Directed acyclic graphs (DAGs) are widely used to model the casual relationships among random variables in many disciplines.
Design of Double Auction Mechanism Based on Social Network
The goal of this paper is to propose mechanisms such that they can encourage buyers already in the market to invite other potential buyers to join the auction through social networks, and achieve an effective allocation of merchandises and increase profits for sellers, which cannot be achieved under the existing double auction mechanism.
Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models
Our results show that object detection can help improve the accuracy of some skin disease classes.
Attacking Vision-based Perception in End-to-End Autonomous Driving Models
One such example is autonomous driving, which often relies on deep learning for perception.
Benchmarking the Performance and Energy Efficiency of AI Accelerators for AI Training
Different from the existing end-to-end benchmarks which only present the training time, We try to investigate the impact of hardware, vendor's software library, and deep learning framework on the performance and energy consumption of AI training.
Symmetry-constrained Rectification Network for Scene Text Recognition
Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes.
AutoML: A Survey of the State-of-the-Art
Deep learning (DL) techniques have penetrated all aspects of our lives and brought us great convenience.
Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models
Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception.
Structure learning via unstructured kernel-based M-regression
In statistical learning, identifying underlying structures of true target functions based on observed data plays a crucial role to facilitate subsequent modeling and analysis.
Scene Text Detection and Recognition: The Deep Learning Era
As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning.
TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks.
Ranked #2 on
Curved Text Detection
on SCUT-CTW1500
AxTrain: Hardware-Oriented Neural Network Training for Approximate Inference
The intrinsic error tolerance of neural network (NN) makes approximate computing a promising technique to improve the energy efficiency of NN inference.
Efficient kernel-based variable selection with sparsistency
Variable selection is central to high-dimensional data analysis, and various algorithms have been developed.
Wilcoxon Rank-Based Tests for Clustered Data with R Package clusrank
For independent data, they are available in several R packages such as stats and coin.
Computation
