Search Results for author:
Found 79 papers, 29 papers with code
Asymmetric Two-Stream Architecture for Accurate RGB-D Saliency Detection
In this paper, we propose an asymmetric two-stream architecture taking account of the inherent differences between RGB and depth data for saliency detection.
Ranked #19 on
Thermal Image Segmentation
on RGB-T-Glass-Segmentation
Fully Automated Correlated Time Series Forecasting in Minutes
Given a forecasting task, which includes a dataset and a forecasting horizon, automated design methods automatically search for an optimal forecasting model for the task in a manually designed search space, and then train the identified model using the dataset to enable the forecasting.
OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement
Decentralized Federated Learning (DFL) surpasses Centralized Federated Learning (CFL) in terms of faster training, privacy preservation, and light communication, making it a promising alternative in the field of federated learning.
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
In decentralized communication, the server aggregation phase in Centralized Federated Learning shifts to the client side, which means that clients connect with each other in a peer-to-peer manner.
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
To address this gap, this work delves deeply into the benign overfitting perspective of transformers in vision.
DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
Furthermore, considering that the source data is either unaccessible or too enormous to store for current generative models, we introduce a new paradigm for their distillation without source data, termed Data-Free Knowledge Distillation for Diffusion Models (DKDM).
DiVE: DiT-based Video Generation with Enhanced Control
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e. g. problematic maneuvers in corner cases.
CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation
We also propose a class-aware feature-wise collaborative learning (CFCL) strategy to achieve effective knowledge transfer between CNN-based and Transformer-based models in the feature space by granting their intermediate features the similar capability of category perception.
Exploring Domain Shift on Radar-Based 3D Object Detection Amidst Diverse Environmental Conditions
The rapid evolution of deep learning and its integration with autonomous driving systems have led to substantial advancements in 3D perception using multimodal sensors.
MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models
As Large Language Models (LLMs) grow dramatically in size, there is an increasing trend in compressing and speeding up these models.
CriDiff: Criss-cross Injection Diffusion Framework via Generative Pre-train for Prostate Segmentation
Additionally, the domain gap between the images features and the diffusion model features poses a great challenge to prostate segmentation.
Disentangling Heterogeneous Knowledge Concept Embedding for Cognitive Diagnosis on Untested Knowledge
Finally, the embeddings will be applied to multiple existing cognitive diagnosis models to infer students' proficiency on UKCs.
QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Version
The first difficulty in enabling continual calibration on the edge is that the full training data may be too large and thus not always available on edge devices.
Voltage Regulation in Polymer Electrolyte Fuel Cell Systems Using Gaussian Process Model Predictive Control
This study introduces a novel approach utilizing Gaussian process model predictive control (MPC) to stabilize the output voltage of a polymer electrolyte fuel cell (PEFC) system by simultaneously regulating hydrogen and airflow rates.
GAgent: An Adaptive Rigid-Soft Gripping Agent with Vision Language Models for Complex Lighting Environments
This paper introduces GAgent: an Gripping Agent designed for open-world environments that provides advanced cognitive abilities via VLM agents and flexible grasping abilities with variable stiffness soft grippers.
Leveraging vision-language models for fair facial attribute classification
Performance disparities of image recognition across different demographic populations are known to exist in deep learning-based models, but previous work has largely addressed such fairness problems assuming knowledge of sensitive attribute labels.
Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking
We found that by introducing a small number of specific Chinese rich semantic structures, LLMs achieve better performance than the BERT-based model on few-shot CSC task.
Impact on Public Health Decision Making by Utilizing Big Data Without Domain Knowledge
Relevant to such uses, important examples of bias in the use of AI are evident when decision-making based on data fails to account for the robustness of the data, or predictions are based on spurious correlations.
Unsupervised Generation of Pseudo Normal PET from MRI with Diffusion Model for Epileptic Focus Localization
In this study, we investigated unsupervised learning methods for unpaired MRI to PET translation for generating pseudo normal FDG PET for epileptic focus localization.
The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness
To tackle the scarcity and privacy issues associated with domain-specific datasets, the integration of federated learning in conjunction with fine-tuning has emerged as a practical solution.
Common-Sense Bias Discovery and Mitigation for Classification Tasks
Machine learning model bias can arise from dataset composition: sensitive features correlated to the learning target disturb the model decision rule and lead to performance differences along the features.
FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning
Federated learning (FL) is a powerful technology that enables collaborative training of machine learning models without sharing private data among clients.
Generalized Neural Networks for Real-Time Earthquake Early Warning
Deep learning enhances earthquake monitoring capabilities by mining seismic waveforms directly.
Perception of Misalignment States for Sky Survey Telescopes with the Digital Twin and the Deep Neural Networks
To address this, we need a method to obtain misalignment states, aiding in the reconstruction of accurate point spread functions for data processing methods or facilitating adjustments of optical components for improved image quality.
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions.
Asymmetrically Decentralized Federated Learning
To further improve algorithm performance and alleviate local heterogeneous overfitting in Federated Learning (FL), our algorithm combines the Sharpness Aware Minimization (SAM) optimizer and local momentum.
Deep Model Fusion: A Survey
Specifically, we categorize existing deep model fusion methods as four-fold: (1) "Mode connectivity", which connects the solutions in weight space via a path of non-increasing loss, in order to obtain better initialization for model fusion; (2) "Alignment" matches units between neural networks to create better conditions for fusion; (3) "Weight average", a classical model fusion method, averages the weights of multiple models to obtain more accurate results closer to the optimal solution; (4) "Ensemble learning" combines the outputs of diverse models, which is a foundational technique for improving the accuracy and robustness of the final model.
ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration
The high-accuracy and resource-intensive deep neural networks (DNNs) have been widely adopted by live video analytics (VA), where camera videos are streamed over the network to resource-rich edge/cloud servers for DNN inference.
A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.
Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining
It motivates us to develop a technique to evaluate true loss changes without retraining, with which channels to prune can be selected more reliably and confidently.
Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data
Specifically, SFGC contains two collaborative components: (1) a training trajectory meta-matching scheme for effectively synthesizing small-scale graph-free data; (2) a graph neural feature score metric for dynamically evaluating the quality of the condensed data.
Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet
The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock.
SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistency
Images captured under low-light conditions are often plagued by several challenges, including diminished contrast, increased noise, loss of fine details, and unnatural color reproduction.
Knowledge-embedded meta-learning model for lift coefficient prediction of airfoils
In the proposed model, a primary network is responsible for representing the relationship between the lift and angle of attack, while the geometry information is encoded into a hyper network to predict the unknown parameters involved in the primary network.
LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version
First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model.
Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs
Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities.
AutoPINN: When AutoML Meets Physics-Informed Neural Networks
We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.
Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting
To overcome these limitations, we propose SEARCH, a joint, scalable framework, to automatically devise effective CTS forecasting models.
Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery
We propose fair dense representation with contrastive learning (FairDCL) as a method for de-biasing the multi-level latent space of convolution neural network models.
SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters
Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tuning.
Shale oil production prediction and fracturing optimization based on machine learning
The results reveal that DNN exhibit best production prediction accuracy compared to RF and SVM.
FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity
As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects.
Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils
In contrast, the hard-constrained scheme produces airfoils with a wider range of geometric diversity while strictly adhering to the geometric constraints.
Segmenting across places: The need for fair transfer learning with satellite imagery
This work highlights the need to conduct fairness analysis for satellite imagery segmentation models and motivates the development of methods for fair transfer learning in order not to introduce disparities between places, particularly urban and rural locations.
Graph Neural Networks for Graphs with Heterophily: A Survey
In the end, we point out the potential directions to advance and stimulate more future research and applications on heterophilic graph learning with GNNs.
MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection
The multiple accurate cues from multiple DFs are then simultaneously propagated to the saliency network with a multi-guidance loss.
Joint Semantic Mining for Weakly Supervised RGB-D Salient Object Detection
As a by-product, a CapS dataset is constructed by augmenting existing benchmark training set with additional image tags and captions.
BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule
Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.
MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning
Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image.
Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation
For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments.
To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection
Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate.
SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging
In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning.
Handling Data Heterogeneity with Generative Replay in Collaborative Learning for Medical Imaging
Specifically, instead of directly training a model for task performance, we develop a novel dual model architecture: a primary model learns the desired task, and an auxiliary "generative replay model" allows aggregating knowledge from the heterogenous clients.
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis
We investigate this question through the lens of edge connectivity, and provide an affirmative answer by defining a connectivity concept, ZERo-cost Operation Sensitivity (ZEROS), to score the importance of candidate operations in DARTS at initialization.
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation.
Ranked #23 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Calibrated RGB-D Salient Object Detection
Complex backgrounds and similar appearances between objects and their surroundings are generally recognized as challenging scenarios in Salient Object Detection (SOD).
Ranked #3 on
Object Detection
on PKU-DDD17-Car
Learning Multi-modal Information for Robust Light Field Depth Estimation
We first excavate the internal spatial correlation by designing a context reasoning unit which separately extracts comprehensive contextual information from the focal stack and RGB images.
Dynamic Fusion Network For Light Field Depth Estimation
Focus based methods have shown promising results for the task of depth estimation.
A Unified Framework for IRS Enabled Wireless Powered Sensor Networks
To evaluate the performance of this IRS assisted WPSN, we are interested in maximizing its system sum throughput to jointly optimize the energy beamforming of the PS, the transmission time allocation, as well as the phase shifts of the WET and WIT phases.
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.
Dynamic Context-Sensitive Filtering Network for Video Salient Object Detection
Our bidirectional dynamic fusion strategy encourages the interaction of spatial and temporal information in a dynamic manner.
Ranked #15 on
Video Polyp Segmentation
on SUN-SEG-Easy (Unseen)
DUT-LFSaliency: Versatile Dataset and Light Field-to-RGB Saliency Detection
The success of learning-based light field saliency detection is heavily dependent on how a comprehensive dataset can be constructed for higher generalizability of models, how high dimensional light field data can be effectively exploited, and how a flexible model can be designed to achieve versatility for desktop computers and mobile devices.
Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement
A probabilistic exploration enhancement method is accordingly devised to encourage intelligent exploration during the architecture search in the latent space, to avoid local optimal in architecture search.
The Detection of Thoracic Abnormalities ChestX-Det10 Challenge Results
The detection of thoracic abnormalities challenge is organized by the Deepwise AI Lab.
Federated Learning for Breast Density Classification: A Real-World Implementation
Building robust deep learning-based models requires large quantities of diverse training data.
Accurate RGB-D Salient Object Detection via Collaborative Learning
The explicitly extracted edge information goes together with saliency to give more emphasis to the salient regions and object boundaries.
Ranked #20 on
RGB-D Salient Object Detection
on NJU2K
Real-time Earthquake Early Warning with Deep Learning: Application to the 2016 Central Apennines, Italy Earthquake Sequence
Earthquake early warning systems are required to report earthquake locations and magnitudes as quickly as possible before the damaging S wave arrival to mitigate seismic hazards.
Select, Supplement and Focus for RGB-D Saliency Detection
Depth data containing a preponderance of discriminative power in location have been proven beneficial for accurate saliency prediction.
Ranked #16 on
RGB-D Salient Object Detection
on NJU2K
(using extra training data)
Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization
In this paper, we formulate the supernet training in the One-Shot NAS as a constrained optimization problem of continual learning that the learning of current architecture should not degrade the performance of previous architectures during the supernet training.
Multi-Domain Learning and Identity Mining for Vehicle Re-Identification
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
Memory-oriented Decoder for Light Field Salient Object Detection
In this paper, we present a deep-learning-based method where a novel memory-oriented decoder is tailored for light field saliency detection.
Efficient Novelty-Driven Neural Architecture Search
The best architecture obtained by our algorithm with the same search space achieves the state-of-the-art test error rate of 2. 51\% on CIFAR-10 with only 7. 5 hours search time in a single GPU, and a validation perplexity of 60. 02 and a test perplexity of 57. 36 on PTB.
High Dimensional Bayesian Optimization via Supervised Dimension Reduction
Furthermore, a kernel trick is developed to reduce computational complexity and learn nonlinear subset of the unknowing function when applying SIR to extremely high dimensional BO.
Ancient Painting to Natural Image: A New Solution for Painting Processing
By doing so, the ancient painting processing problems become natural image processing problems and models trained on natural images can be directly applied to the transferred paintings.
Multi-level CNN for lung nodule classification with Gaussian Process assisted hyperparameter optimization
In this paper, a non-stationary kernel is proposed which allows the surrogate model to adapt to functions whose smoothness varies with the spatial location of inputs, and a multi-level convolutional neural network (ML-CNN) is built for lung nodule classification whose hyperparameter configuration is optimized by using the proposed non-stationary kernel based Gaussian surrogate model.
Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method
In this paper, we first test the state of the art semantic segmentation deep learning classifiers for LUCC mapping with 7 categories in the TGRA area with rapideye 5m resolution data.
Human and Machine Speaker Recognition Based on Short Trivial Events
Trivial events are ubiquitous in human to human conversations, e. g., cough, laugh and sniff.
Authorship attribution of source code by using back propagation neural network based on particle swarm optimization
Then these metrics are input to neural network for supervised learning, the weights of which are output by PSO and BP hybrid algorithm.
Speaker Recognition with Cough, Laugh and "Wei"
This paper proposes a speaker recognition (SRE) task with trivial speech events, such as cough and laugh.
