Search Results for author:
Found 38 papers, 18 papers with code
Peeking Behind the Curtains of Residual Learning
The utilization of residual learning has become widespread in deep and scalable neural nets.
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network.
Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM).
Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering Approach
The dynamic tier scheduler assigns clients to suitable tiers to minimize the overall training time in each round.
Ranked #1 on
Image Classification
on CIFAR-10
(training time (s) metric)
DistDNAS: Search Efficient Feature Interactions within 2 Hours
To optimize search efficiency, DistDNAS distributes the search and aggregates the choice of optimal interaction modules on varying data dates, achieving over 25x speed-up and reducing search cost from 2 days to 2 hours.
Farthest Greedy Path Sampling for Two-shot Recommender Search
FGPS enhances path diversity to facilitate more comprehensive supernet exploration, while emphasizing path quality to ensure the effective identification and utilization of promising architectures.
CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation
To address these issues, we propose a transformer network with multi-stage CNN (Convolutional Neural Network) feature injection for surface defect segmentation, which is a UNet-like structure named CINFormer.
Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects
To this end, we develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
ZeRO++: Extremely Efficient Collective Communication for Giant Model Training
Zero Redundancy Optimizer (ZeRO) has been used to train a wide range of large language models on massive GPUs clusters due to its ease of use, efficiency, and good scalability.
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods.
Ranked #1 on
Video Object Tracking
on SoccerNet-v2
Multiple Object Tracking Challenge Technical Report for Team MT_IoT
This is a brief technical report of our proposed method for Multiple-Object Tracking (MOT) Challenge in Complex Environments.
Ranked #8 on
Multi-Object Tracking
on DanceTrack
(using extra training data)
PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
In this work, we establish PIDS, a novel paradigm to jointly explore point interactions and point dimensions to serve semantic segmentation on point cloud data.
Ranked #6 on
Robust 3D Semantic Segmentation
on SemanticKITTI-C
Neural Architecture Search
Robust 3D Semantic Segmentation
+1
Energy Efficiency Optimization of Intelligent Reflective Surface-assisted Terahertz-RSMA System
This paper examines the energy efficiency optimization problem of intelligent reflective surface (IRS)-assisted multi-user rate division multiple access (RSMA) downlink systems under terahertz propagation.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
BiFeat: Supercharge GNN Training via Graph Feature Quantization
We identify the main accuracy impact factors in graph feature quantization and theoretically prove that BiFeat training converges to a network where the loss is within $\epsilon$ of the optimal loss of uncompressed network.
NASRec: Weight Sharing Neural Architecture Search for Recommender Systems
To overcome the data multi-modality and architecture heterogeneity challenges in the recommendation domain, NASRec establishes a large supernet (i. e., search space) to search the full architectures.
SMLT: A Serverless Framework for Scalable and Adaptive Machine Learning Design and Training
In addition, by providing an end-to-end design, SMLT solves the intrinsic problems in serverless platforms such as the communication overhead, limited function execution duration, need for repeated initialization, and also provides explicit fault tolerance for ML training.
SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training using Gradient Similarity Measurement
In this paper, we propose a fully automated and lightweight adaptive batching methodology to enable fine-grained batch size adaption (e. g., at a mini-batch level) that can achieve state-of-the-art performance with record breaking batch sizes.
Demystifying Hyperparameter Optimization in Federated Learning
Such data heterogeneity and privacy requirements bring unique challenges for learning hyperparameter optimization as the training dynamics change across clients even within the same training round and they are difficult to measure due to privacy constraints.
Automated Mobile Attention KPConv Networks via A Wide & Deep Predictor
MAKPConv employs a depthwise kernel to reduce resource consumption and re-calibrates the contribution of kernel points towards each neighbor point via Neighbor-Kernel attention to improve representation power.
Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX
This paper presents Citadel, a scalable collaborative ML system that protects the privacy of both data owner and model owner in untrusted infrastructures with the help of Intel SGX.
The Age of Correlated Features in Supervised Learning based Forecasting
In these applications, a neural network is trained to predict a time-varying target (e. g., solar power), based on multiple correlated features (e. g., temperature, humidity, and cloud coverage).
Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning
Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks.
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
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.
Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
In this work, we propose SVD training, the first method to explicitly achieve low-rank DNNs during training without applying SVD on every step.
TiFL: A Tier-based Federated Learning System
To this end, we propose TiFL, a Tier-based Federated Learning System, which divides clients into tiers based on their training performance and selects clients from the same tier in each training round to mitigate the straggler problem caused by heterogeneity in resource and data quantity.
AutoShrink: A Topology-aware NAS for Discovering Efficient Neural Architecture
Specifically, both ShrinkCNN and ShrinkRNN are crafted within 1. 5 GPU hours, which is 7. 2x and 6. 7x faster than the crafting time of SOTA CNN and RNN models, respectively.
EPNAS: Efficient Progressive Neural Architecture Search
In this paper, we propose Efficient Progressive Neural Architecture Search (EPNAS), a neural architecture search (NAS) that efficiently handles large search space through a novel progressive search policy with performance prediction based on REINFORCE~\cite{Williams. 1992. PG}.
SwiftNet: Using Graph Propagation as Meta-knowledge to Search Highly Representative Neural Architectures
Designing neural architectures for edge devices is subject to constraints of accuracy, inference latency, and computational cost.
LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
Distributed learning systems have enabled training large-scale models over large amount of data in significantly shorter time.
Differentiable Fine-grained Quantization for Deep Neural Network Compression
Thus judiciously selecting different precision for different layers/structures can potentially produce more efficient models compared to traditional quantization methods by striking a better balance between accuracy and compression rate.
SmoothOut: Smoothing Out Sharp Minima to Improve Generalization in Deep Learning
It becomes an open question whether escaping sharp minima can improve the generalization.
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
We mathematically prove the convergence of TernGrad under the assumption of a bound on gradients.
EigenNet: A Bayesian hybrid of generative and conditional models for sparse learning
To overcome this limitation, we present a novel hybrid model, EigenNet, that uses the eigenstructures of data to guide variable selection.
Parallel Inference for Latent Dirichlet Allocation on Graphics Processing Units
Extensive experiments showed that our parallel inference methods consistently produced LDA models with the same predictive power as sequential training methods did but with 26x speedup for CGS and 196x speedup for CVB on a GPU with 30 multiprocessors; actually the speedup is almost linearly scalable with the number of multiprocessors available.
