Search Results for author:
Found 60 papers, 23 papers with code
Knowledge Distillation from A Stronger Teacher
In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly.
Ranked #2 on
Knowledge Distillation
on ImageNet
(using extra training data)
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images
In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.
LightViT: Towards Light-Weight Convolution-Free Vision Transformers
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias.
LocalMamba: Visual State Space Model with Windowed Selective Scan
This paper posits that the key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling.
Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning
We showcase the improvement of our simulation environment with the designed new features, and validate effectiveness of incorporating human factors in embodied intelligence through the use of human demonstrations and reinforcement learning as a representative example.
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot
Task automation of surgical robot has the potentials to improve surgical efficiency.
TACO: Topics in Algorithmic COde generation dataset
Moreover, each TACO problem includes several fine-grained labels such as task topics, algorithms, programming skills, and difficulty levels, providing a more precise reference for the training and evaluation of code generation models.
Ranked #1 on
Code Generation
on TACO-Code
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
Inspired by this, this work proposes to explore the potential of visual state space models in light-weight model design and introduce a novel efficient model variant dubbed EfficientVMamba.
Masked Distillation with Receptive Tokens
To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks.
Knowledge Diffusion for Distillation
To address this, we propose to denoise student features using a diffusion model trained by teacher features.
Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
Different from existing GSM models using hand-crafted scale priors (e. g., the Jeffrey's prior), we propose to learn the scale prior through a deep convolutional neural network (DCNN).
DyRep: Bootstrapping Training with Dynamic Re-parameterization
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks.
Prioritized Architecture Sampling with Monto-Carlo Tree Search
One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once.
Relational Surrogate Loss Learning
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e. g., average precision and F1 score.
Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections
However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified.
GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles
The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry.
Quantum circuit architecture search for variational quantum algorithms
Variational quantum algorithms (VQAs) are expected to be a path to quantum advantages on noisy intermediate-scale quantum devices.
Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention
Deep learning-based LLIE methods focus on learning a mapping function between low-light images and normal-light images that outperforms conventional LLIE methods.
Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty
Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again.
Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot
Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task.
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
Strong adversarial examples are crucial for evaluating and enhancing the robustness of deep neural networks.
Positive Label Is All You Need for Multi-Label Classification
Our paper addresses label noise in MLC by introducing a positive and unlabeled multi-label classification (PU-MLC) method.
A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification
Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap of HSI classification models between pocket models and standard vision backbones.
MMD GAN with Random-Forest Kernels
In this paper, we propose a novel kind of kernel, random forest kernel, to enhance the empirical performance of MMD GAN.
Robust Data Preprocessing for Machine-Learning-Based Disk Failure Prediction in Cloud Production Environments
To provide proactive fault tolerance for modern cloud data centers, extensive studies have proposed machine learning (ML) approaches to predict imminent disk failures for early remedy and evaluated their approaches directly on public datasets (e. g., Backblaze SMART logs).
GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet
The training efficiency is thus boosted since the training space has been greedily shrunk from all paths to those potentially-good ones.
Ranked #72 on
Neural Architecture Search
on ImageNet
Wasserstein Distributionally Robust Optimization: A Three-Player Game Framework
Wasserstein distributionally robust optimization (DRO) has recently received significant attention in machine learning due to its connection to generalization, robustness and regularization.
Explicit Learning Topology for Differentiable Neural Architecture Search
Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types.
Data Agnostic Filter Gating for Efficient Deep Networks
To deploy a well-trained CNN model on low-end computation edge devices, it is usually supposed to compress or prune the model under certain computation budget (e. g., FLOPs).
Stretchable Cells Help DARTS Search Better
However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells.
MG-GCN: Fast and Effective Learning with Mix-grained Aggregators for Training Large Graph Convolutional Networks
To tackle the dilemma between accuracy and efficiency, we propose to use aggregators with different granularities to gather neighborhood information in different layers.
Locally Free Weight Sharing for Network Width Search
In this paper, to better evaluate each width, we propose a locally free weight sharing strategy (CafeNet) accordingly.
Gradient Boosted Binary Histogram Ensemble for Large-scale Regression
In this paper, we propose a gradient boosting algorithm for large-scale regression problems called \textit{Gradient Boosted Binary Histogram Ensemble} (GBBHE) based on binary histogram partition and ensemble learning.
Deep Instance Segmentation with Automotive Radar Detection Points
Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points.
Reinforcement Learning with Predictive Consistent Representations
Learning informative representations from image-based observations is a fundamental problem in deep Reinforcement Learning (RL).
Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy
To improve the privacy guarantee and efficiency, we combine a subsampling method with CGS and propose a novel LDA training algorithm with differential privacy, SUB-LDA.
GreedyNASv2: Greedier Search with a Greedy Path Filter
In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently.
Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning
Learning informative representations from image-based observations is of fundamental concern in deep Reinforcement Learning (RL).
Contrastive Learning for Automotive mmWave Radar Detection Points Based Instance Segmentation
Deep learning-based instance segmentation enables real-time object identification from the radar detection points.
Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation
However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.
Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning
Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.
RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systems
Recent state-of-the-art works reveal that the fusion of radar and LiDAR can lead to robust detection in adverse weather.
UNAEN: Unsupervised Abnormality Extraction Network for MRI Motion Artifact Reduction
Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies.
A step towards digital operations -- A novel grey-box approach for modelling the heat dynamics of Ultra-low temperature freezing chambers
In addition, the model for local evaporator temperature can effectively adapt to different operational patterns and provide insight into the local cooling supply status.
LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusion
They are sent to the core of LXL, called "radar occupancy-assisted depth-based sampling", to aid image view transformation.
Convex Optimal Power Flow Based on Power Injection-based Equations and Its Application in Bipolar DC Distribution Network
Optimal power flow (OPF) is a fundamental tool for analyzing the characteristics of bipolar DC distribution network (DCDN).
SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radar
Additionally, KDE helps alleviate point cloud sparsity by capturing density features.
LEGO: Learning and Graph-Optimized Modular Tracker for Online Multi-Object Tracking with Point Clouds
The state-of-the-art approaches usually employ a tracking-by-detection method, and data association plays a critical role.
Implicit Neural Representation for MRI Parallel Imaging Reconstruction
Our approach represents reconstructed fully-sampled images as functions of voxel coordinates and prior feature vectors from undersampled images, addressing the generalization challenges of INR.
Which Framework is Suitable for Online 3D Multi-Object Tracking for Autonomous Driving with Automotive 4D Imaging Radar?
These provide the first benchmark and important insights for the future development of 4D imaging radar-based online 3D MOT.
V2X Cooperative Perception for Autonomous Driving: Recent Advances and Challenges
To address this gap, this paper provides a comprehensive overview of the evolution of CP technologies, spanning from early explorations to recent developments, including advancements in V2X communication technologies.
Unpaired MRI Super Resolution with Contrastive Learning
To this end, we propose an unpaired MRI SR approach that employs contrastive learning to enhance SR performance with limited HR training data.
FreeKD: Knowledge Distillation via Semantic Frequency Prompt
(2) During the distillation period, a pixel-wise frequency mask is generated via Frequency Prompt, to localize those pixel of interests (PoIs) in various frequency bands.
Not All Steps are Equal: Efficient Generation with Progressive Diffusion Models
In the initial stage, a base denoising model is trained to encompass all timesteps.
Diffusion Reward: Learning Rewards via Conditional Video Diffusion
Learning rewards from expert videos offers an affordable and effective solution to specify the intended behaviors for reinforcement learning tasks.
Deterministic Computing Power Networking: Architecture, Technologies and Prospects
With the development of new Internet services such as computation-intensive and delay-sensitive tasks, the traditional "Best Effort" network transmission mode has been greatly challenged.
Empowering Computing and Networks Convergence System with Distributed Cooperative Routing
The cross-plane cooperative end-to-end routing schemes consider both computation efficiency of heterogeneous servers and the network congestion degrees while making routing plan, thereby determining where to execute requests and corresponding routing paths.
Active Generation for Image Classification
Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy.
LiDAR Point Cloud-based Multiple Vehicle Tracking with Probabilistic Measurement-Region Association
Simulation results illustrate the superior estimation accuracy of the proposed PMRA-PMBM filter in terms of both positions and extents of the vehicles comparing with PMBM filters using the gamma Gaussian inverse Wishart and DRA implementations.
Diverse and Tailored Image Generation for Zero-shot Multi-label Classification
Our approach introduces a novel image generation framework that produces multi-label synthetic images of unseen classes for classifier training.
