Search Results for author:
Found 56 papers, 18 papers with code
Dynamically Anchored Prompting for Task-Imbalanced Continual Learning
We find that imbalanced tasks significantly challenge the capability of models to control the trade-off between stability and plasticity from the perspective of recent prompt-based continual learning methods.
AI-Empowered RIS-Assisted Networks: CV-Enabled RIS Selection and DNN-Enabled Transmission
This paper investigates artificial intelligence (AI) empowered schemes for reconfigurable intelligent surface (RIS) assisted networks from the perspective of fast implementation.
Graph Neural Networks for Wireless Networks: Graph Representation, Architecture and Evaluation
Graph neural networks (GNNs) have been regarded as the basic model to facilitate deep learning (DL) to revolutionize resource allocation in wireless networks.
SEMRes-DDPM: Residual Network Based Diffusion Modelling Applied to Imbalanced Data
In the current oversampling methods based on generative networks, the methods based on GANs can capture the true distribution of data, but there is the problem of pattern collapse and training instability in training; in the oversampling methods based on denoising diffusion probability models, the neural network of the inverse diffusion process using the U-Net is not applicable to tabular data, and although the MLP can be used to replace the U-Net, the problem exists due to the simplicity of the structure and the poor effect of removing noise.
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.
Energy Consumption Analysis for Continuous Phase Modulation in Smart-Grid Internet of Things of beyond 5G
Wireless sensor network (WSN) underpinning the smart-grid Internet of Things (SG-IoT) has been a popular research topic in recent years due to its great potential for enabling a wide range of important applications.
Frequency Domain Nuances Mining for Visible-Infrared Person Re-identification
Specifically, we propose a novel Frequency Domain Nuances Mining (FDNM) method to explore the cross-modality frequency domain information, which mainly includes an amplitude guided phase (AGP) module and an amplitude nuances mining (ANM) module.
Illuminating the Black Box: A Psychometric Investigation into the Multifaceted Nature of Large Language Models
This study explores the idea of AI Personality or AInality suggesting that Large Language Models (LLMs) exhibit patterns similar to human personalities.
Federated Learning with Extremely Noisy Clients via Negative Distillation
The model trained on noisy labels serves as a `bad teacher' in knowledge distillation, aiming to decrease the risk of providing incorrect information.
Generate E-commerce Product Background by Integrating Category Commonality and Personalized Style
Furthermore, for products with specific and fine-grained requirements in layout, elements, etc, a Personality-Wise Generator is devised to learn such personalized style directly from a reference image to resolve textual ambiguities, and is trained in a self-supervised manner for more efficient training data usage.
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model.
FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning
A typical way of pFL focuses on label distribution skew, and they adopt a decoupling scheme where the model is split into a common feature extractor and two prediction heads (generic and personalized).
GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks
This paper studies the GNN-based learning approach for the sum-rate maximization in multiple-user multiple-input single-output (MU-MISO) networks subject to the users' individual data rate requirements and the power budget of the base station.
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.
Decision Fusion Network with Perception Fine-tuning for Defect Classification
In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage.
Feature Fusion from Head to Tail for Long-Tailed Visual Recognition
To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T).
Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment
It is unfavorable for training on balanced data, but can be utilized to adjust the validity of the samples in long-tailed data, thereby solving the distorted embedding space of long-tailed problems.
Ranked #13 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition
Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead.
PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition
Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis.
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution.
Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation
Personalized Federated Learning (PFL) aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner.
Federated Semi-Supervised Learning with Annotation Heterogeneity
Federated Semi-Supervised Learning (FSSL) aims to learn a global model from different clients in an environment with both labeled and unlabeled data.
Retrieved Sequence Augmentation for Protein Representation Learning
RSA links query protein sequences to a set of sequences with similar structures or properties in the database and combines these sequences for downstream prediction.
IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks
In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricting the input information and recovering the feature information, including: 1) information restriction: for a BNN, by evaluating the learning ability on the input information, discarding some of the information it cannot focus on, and limiting the amount of input information to match its learning ability; 2) information recovery: due to the information loss in forward propagation, the output feature information of the network is not enough to support accurate classification.
Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph
Establishing how a set of learners can provide privacy-preserving federated learning in a fully decentralized (peer-to-peer, no coordinator) manner is an open problem.
Vector-valued Privacy-Preserving Average Consensus
We show that the vector-valued PPAC problem can be solved via associated matrix-weighted networks with the higher-dimensional agent state.
Pricing Stocks with Trading Volumes
The new framework can be easily adopted to local volume and stochastic volume models for the option pricing problem, which will point out a new possible direction for this central problem in quantitative finance.
Label-Noise Learning with Intrinsically Long-Tailed Data
In this case, it is hard to distinguish clean samples from noisy samples on the intrinsic tail classes with the unknown intrinsic class distribution.
The 1st Data Science for Pavements Challenge
The Data Science for Pavement Challenge (DSPC) seeks to accelerate the research and development of automated vision systems for pavement condition monitoring and evaluation by providing a platform with benchmarked datasets and codes for teams to innovate and develop machine learning algorithms that are practice-ready for use by industry.
FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation
Federated learning provides a privacy guarantee for generating good deep learning models on distributed clients with different kinds of data.
Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features
Experiments on several benchmark datasets show that the proposed CReFF is an effective solution to obtain a promising FL model under heterogeneous and long-tailed data.
A Deep Learning Approach for Repairing Missing Activity Labels in Event Logs for Process Mining
The performance of existing process discovery algorithms can be affected when there are missing activity labels in event logs.
AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks
We propose a novel adversarial iterative pruning method (AIP) for CNNs based on knowledge transfer.
A Novel Approach to Discover Switch Behaviours in Process Mining
Process mining is a relatively new subject which builds a bridge between process modelling and data mining.
A Multi-View Framework to Detect Redundant Activity Labels for More Representative Event Logs in Process Mining
Such inconsistency would then lead to redundancy in activity labels, which refer to labels that have different syntax but share the same behaviours.
Discovering Redundant Activities in Event Logs for the Simplification of Process Models
The key to process mining is to discovery understandable process models.
Detecting and Understanding Branching Frequency Changes in Process Models
In this paper, we propose a method which takes both event logs and process models as input and generates a choice sequence for each exclusive choice in the process model.
Self-Distribution Binary Neural Networks
In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i. e., 1-bit representation).
ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN
While the accuracy loss after pruning based on the structure sensitivity is relatively slight, the process is time-consuming and the algorithm complexity is notable.
Placement in Integrated Circuits using Cyclic Reinforcement Learning and Simulated Annealing
Physical design and production of Integrated Circuits (IC) is becoming increasingly more challenging as the sophistication in IC technology is steadily increasing.
UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration
For ResNet with bottlenecks, we use the pruning method with traditional CNN to trim the 3x3 convolutional layer in the middle of the blocks.
DANCE: Enhancing saliency maps using decoys
Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier.
Multi-Scale Dual-Branch Fully Convolutional Network for Hand Parsing
In this paper, we propose a novel parsing framework, Multi-Scale Dual-Branch Fully Convolutional Network (MSDB-FCN), for hand parsing tasks.
ProductNet: a Collection of High-Quality Datasets for Product Representation Learning
ProductNet is a collection of high-quality product datasets for better product understanding.
Low-Power Computer Vision: Status, Challenges, Opportunities
In addition to mobile phones, many autonomous systems rely on visual data for making decisions and some of these systems have limited energy (such as unmanned aerial vehicles also called drones and mobile robots).
Bayes Imbalance Impact Index: A Measure of Class Imbalanced Dataset for Classification Problem
To the best of our knowledge, there is no any measurement about the extent of influence of class imbalance on the classification performance of imbalanced data.
Large-Scale Object Detection of Images from Network Cameras in Variable Ambient Lighting Conditions
However, the images found in those datasets, are independent of one another and cannot be used to test YOLO's consistency at detecting the same object as its environment (e. g. ambient lighting) changes.
2018 Low-Power Image Recognition Challenge
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing. ieee. org/lpirc) is an annual competition started in 2015.
Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling
Within each iteration of our learning algorithm, for each observed training image, we generate synthesized images at multiple grids by initializing the finite-step MCMC sampling from a minimal 1 x 1 version of the training image.
Cooperative Training of Descriptor and Generator Networks
Specifically, within each iteration of the cooperative learning algorithm, the generator model generates initial synthesized examples to initialize a finite-step MCMC that samples and trains the energy-based descriptor model.
Alternating Back-Propagation for Generator Network
This paper proposes an alternating back-propagation algorithm for learning the generator network model.
A Theory of Generative ConvNet
If we further assume that the non-linearity in the ConvNet is Rectified Linear Unit (ReLU) and the reference distribution is Gaussian white noise, then we obtain a generative ConvNet model that is unique among energy-based models: The model is piecewise Gaussian, and the means of the Gaussian pieces are defined by an auto-encoder, where the filters in the bottom-up encoding become the basis functions in the top-down decoding, and the binary activation variables detected by the filters in the bottom-up convolution process become the coefficients of the basis functions in the top-down deconvolution process.
Learning FRAME Models Using CNN Filters
We explain that each learned model corresponds to a new CNN unit at a layer above the layer of filters employed by the model.
Online Object Tracking, Learning and Parsing with And-Or Graphs
In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network.
Generative Modeling of Convolutional Neural Networks
(2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, which is fundamentally different from the commonly used discriminative gradient, and yet has the same computational architecture and cost as the latter.
