Search Results for author:
Found 93 papers, 32 papers with code
Are Anchor Points Really Indispensable in Label-Noise Learning?
Existing theories have shown that the transition matrix can be learned by exploiting \textit{anchor points} (i. e., data points that belong to a specific class almost surely).
Ranked #18 on
Learning with noisy labels
on CIFAR-10N-Random3
Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification
To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information.
Can SAM Segment Polyps?
Recently, Meta AI Research releases a general Segment Anything Model (SAM), which has demonstrated promising performance in several segmentation tasks.
Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure in an unsupervised way.
Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i. e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples.
Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
To overcome this problem, inspired by the recent success of graph contrastive learning and Siamese networks in visual representation learning, we propose a novel self-supervised approach in this paper to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning.
Unifying Graph Contrastive Learning with Flexible Contextual Scopes
To address aforementioned problems, we present a simple self-supervised learning method termed Unifying Graph Contrastive Learning with Flexible Contextual Scopes (UGCL for short).
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
Our experiments conducted on four tasks and four offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms is immune to such a backdoor attack.
ControlCap: Controllable Region-level Captioning
The multimodal model is constrained to generate captions within a few sub-spaces containing the control words, which increases the opportunity of hitting less frequent captions, alleviating the caption degeneration issue.
Ranked #1 on
Dense Captioning
on Visual Genome
Watermarking for Out-of-distribution Detection
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models.
Ranked #20 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
Feature Aggregation and Propagation Network for Camouflaged Object Detection
In this paper, we propose a novel Feature Aggregation and Propagation Network (FAP-Net) for camouflaged object detection.
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML
These solutions, referred to as TEE-Shielded DNN Partition (TSDP), partition a DNN model into two parts, offloading the privacy-insensitive part to the GPU while shielding the privacy-sensitive part within the TEE.
An In-depth Study on Internal Structure of Chinese Words
Several previous works on syntactic parsing propose to annotate shallow word-internal structures for better utilizing character-level information.
Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach
Previous methods are limited to transductive scenarios, where entities exist in the knowledge graphs, so they are unable to handle unseen entities.
Understanding Robust Overfitting of Adversarial Training and Beyond
Here, we explore the causes of robust overfitting by comparing the data distribution of \emph{non-overfit} (weak adversary) and \emph{overfitted} (strong adversary) adversarial training, and observe that the distribution of the adversarial data generated by weak adversary mainly contain small-loss data.
SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation
In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?"
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs).
Probabilistic Margins for Instance Reweighting in Adversarial Training
Reweighting adversarial data during training has been recently shown to improve adversarial robustness, where data closer to the current decision boundaries are regarded as more critical and given larger weights.
Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.
Regularly Truncated M-estimators for Learning with Noisy Labels
However, such a procedure is arguably debatable from two folds: (a) it does not consider the bad influence of noisy labels in selected small-loss examples; (b) it does not make good use of the discarded large-loss examples, which may be clean or have meaningful information for generalization.
Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards.
PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining
Then, this function assists in querying the semantic distribution of the sensitive dataset, facilitating the selection of data from the public dataset with analogous semantics for pre-training.
MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset
1) Based on a frame-free annotation methodology, we avoid writing complex frames for new predicates.
Centralized Cooperative Exploration Policy for Continuous Control Tasks
To explicitly encourage exploration in continuous control tasks, we propose CCEP (Centralized Cooperative Exploration Policy), which utilizes underestimation and overestimation of value functions to maintain the capacity of exploration.
Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
Machine learning models are vulnerable to Out-Of-Distribution (OOD) examples, and such a problem has drawn much attention.
SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification
The "splice" in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias; 2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together.
A prognostic dynamic model applicable to infectious diseases providing easily visualized guides -- A case study of COVID-19 in the UK
A reasonable prediction of infectious diseases transmission process under different disease control strategies is an important reference point for policy makers.
Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning
This paper proposes the Recovery Triggered States (RTS) method, a novel approach that effectively protects the victim agents from backdoor attacks.
Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch
Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised Learning (SSL), where the classes of labeled data are assumed to be only a subset of the classes of unlabeled data.
Adversarial Metric Learning
In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs.
Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
Unsupervised Image-to-Image Translation achieves spectacularly advanced developments nowadays.
Indefinite Kernel Logistic Regression with Concave-inexact-convex Procedure
Since the concave-convex procedure has to solve a sub-problem in each iteration, we propose a concave-inexact-convex procedure (CCICP) algorithm with an inexact solving scheme to accelerate the solving process.
Learning Data-adaptive Nonparametric Kernels
Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility.
RetinaMatch: Efficient Template Matching of Retina Images for Teleophthalmology
To the best of our knowledge, this is the first template matching algorithm for retina images with small template images from unconstrained retinal areas.
Multi-Grained Chinese Word Segmentation
Traditionally, word segmentation (WS) adopts the single-grained formalism, where a sentence corresponds to a single word sequence.
A Survey on Multi-output Learning
Multi-output learning aims to simultaneously predict multiple outputs given an input.
Saliency Propagation From Simple to Difficult
In the teaching-to-learn step, a teacher is designed to arrange the regions from simple to difficult and then assign the simplest regions to the learner.
Learning with Inadequate and Incorrect Supervision
To address label insufficiency, we use a graph to bridge the data points so that the label information can be propagated from the scarce labeled examples to unlabeled examples along the graph edges.
A Regularization Approach for Instance-Based Superset Label Learning
As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms.
Ensemble Teaching for Hybrid Label Propagation
More importantly, HyDEnT conducts propagation under the guidance of an ensemble of teachers.
Robust Visual Tracking Revisited: From Correlation Filter to Template Matching
In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs).
An Approach to Efficient Fitting of Univariate and Multivariate Stochastic Volatility Models
The model is a nonlinear and non-Gaussian state space model, and consequently is difficult to fit.
Methodology Computation
Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network
In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance.
Curvilinear Distance Metric Learning
To address this issue, we first reveal that the traditional linear distance metric is equivalent to the cumulative arc length between the data pair's nearest points on the learned straight measurer lines.
Network Cooperation with Progressive Disambiguation for Partial Label Learning
Partial Label Learning (PLL) aims to train a classifier when each training instance is associated with a set of candidate labels, among which only one is correct but is not accessible during the training phase.
Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph.
Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification
Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification.
Robust early-learning: Hindering the memorization of noisy labels
The \textit{early stopping} method therefore can be exploited for learning with noisy labels.
Ranked #32 on
Image Classification
on mini WebVision 1.0
(ImageNet Top-1 Accuracy metric)
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning
Semi-Supervised Learning (SSL) with mismatched classes deals with the problem that the classes-of-interests in the limited labeled data is only a subset of the classes in massive unlabeled data.
Wireless Communication Based on Microwave Photon-Level Detection With Superconducting Devices: Achievable Rate Prediction
Future wireless communication system embraces physical-layer signal detection with high sensitivity, especially in the microwave photon level.
Quantumized Microwave Detection Based on $Λ$-Type Three-level Superconducting System: HMM Modeling and Performance Prediction
Based on the state transition principles of the three-level system, we propose a statistical model for microwave signal detection.
Learning with Group Noise
Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels.
Channel Modeling and Signal Processing for Array-based Visible Light Communication System in Misalignment
In this way the light emitted by different LED can be separated well from each other then minimize signal interference.
Weak Radio Frequency Signal Detection Based on Piezo-Opto-Electro-Mechanical System: Architecture Design and Sensitivity Prediction
We propose a novel radio-frequency (RF) receiving architecture based on micro-electro-mechanical system (MEMS) and optical coherent detection module.
Parkinsonian Chinese Speech Analysis towards Automatic Classification of Parkinson's Disease
Speech disorders often occur at the early stage of Parkinson's disease (PD).
KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation
However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images.
Multi-grained Chinese Word Segmentation with Weakly Labeled Data
Detailed evaluation shows that our proposed model with weakly labeled data significantly outperforms the state-of-the-art MWS model by 1. 12 and 5. 97 on NEWS and BAIKE data in F1.
LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders
Variational autoencoders (VAEs), as an important aspect of generative models, have received a lot of research interests and reached many successful applications.
MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning
During the training of a reinforcement learning (RL) agent, the distribution of training data is non-stationary as the agent's behavior changes over time.
The $f$-Divergence Reinforcement Learning Framework
In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards.
Co-variance: Tackling Noisy Labels with Sample Selection by Emphasizing High-variance Examples
The sample selection approach is popular in learning with noisy labels, which tends to select potentially clean data out of noisy data for robust training.
Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding
In this paper, we decompose the video into several segments and intuitively model the task of complex event detection as a multiple instance learning problem by representing each video as a "bag" of segments in which each segment is referred to as an instance.
数据标注方法比较研究:以依存句法树标注为例(Comparison Study on Data Annotation Approaches: Dependency Tree Annotation as Case Study)
“数据标注最重要的考虑因素是数据的质量和标注代价。我们调研发现自然语言处理领域的数据标注工作通常采用机标人校的标注方法以降低代价;同时, 很少有工作严格对比不同标注方法, 以探讨标注方法对标注质量和代价的影响。该文借助一个成熟的标注团队, 以依存句法数据标注为案例, 实验对比了机标人校、双人独立标注、及本文通过融合前两种方法所新提出的人机独立标注方法, 得到了一些初步的结论。”
Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels
Essentially, our CGPN can enhance the learning performance of GNNs under extremely limited labels by contrastively propagating the limited labels to the entire graph.
Universal Semi-Supervised Learning
Universal Semi-Supervised Learning (UniSSL) aims to solve the open-set problem where both the class distribution (i. e., class set) and feature distribution (i. e., feature domain) are different between labeled dataset and unlabeled dataset.
Consistency and Diversity induced Human Motion Segmentation
Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance.
Synergistic Network Learning and Label Correction for Noise-robust Image Classification
Taking the expertise of DNNs to learn meaningful patterns before fitting noise, our framework first trains two networks over the current dataset with small loss selection.
Adaptive Discriminative Regularization for Visual Classification
Regarding this hypothesis, we propose a novel regularization to improve discriminative learning.
Multi-class Label Noise Learning via Loss Decomposition and Centroid Estimation
Further, by defining a new form of data centroid, we transform the recovery problem of a label-dependent part to a centroid estimation problem.
Indoor 3-Dimensional Visible Light Positioning: Error Metric and LED Layout Optimization
We consider 3-dimensional (3D) visible light positioning (VLP) based on smartphone camera in an indoor scenario.
Hyperspectral Image Classification With Contrastive Graph Convolutional Network
To enhance the feature representation ability, in this paper, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations, which is termed Contrastive Graph Convolutional Network (ConGCN), for HSI classification.
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels
To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy labels.
The design and optimization of synchronization sequence for Ultraviolet communication
Compared with equilong random sequence, the synchronization accuracy of the optimized synchronization sequence is significantly improved.
To Store or Not? Online Data Selection for Federated Learning with Limited Storage
We first define a new data valuation metric for data evaluation and selection in FL with theoretical guarantees for speeding up model convergence and enhancing final model accuracy, simultaneously.
Discourse-Aware Emotion Cause Extraction in Conversations
In this paper, we investigate the importance of discourse structures in handling utterance interactions and conversationspecific features for ECEC.
Ranked #5 on
Causal Emotion Entailment
on RECCON
Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data
Inspired by early research on exploring naturally annotated data for Chinese word segmentation (CWS), and also by recent research on integration of speech and text processing, this work for the first time proposes to mine word boundaries from parallel speech/text data.
Unsupervised Domain Adaptation GAN Inversion for Image Editing
In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing.
Automatic Sleep Stage Classification with Cross-modal Self-supervised Features from Deep Brain Signals
This sleep stage classification model could be adapted to chronic and continuous monitor sleep for Parkinson's patients in daily life, and potentially utilized for more precise treatment in deep brain-machine interfaces, such as closed-loop deep brain stimulation.
A Hierarchical Approach to Population Training for Human-AI Collaboration
A major challenge for deep reinforcement learning (DRL) agents is to collaborate with novel partners that were not encountered by them during the training phase.
Theoretical Analysis of Heterodyne Rydberg Atomic Receiver Sensitivity Based on Transit Relaxation Effect and Frequency Detuning
We conduct a theoretical investigation into the impacts of local microwave electric field frequency detuning, laser frequency detuning, and transit relaxation rate on enhancing heterodyne Rydberg atomic receiver sensitivity.
Exploiting Counter-Examples for Active Learning with Partial labels
In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process.
Distribution Shift Matters for Knowledge Distillation with Webly Collected Images
Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network.
Aligning Speakers: Evaluating and Visualizing Text-based Diarization Using Efficient Multiple Sequence Alignment (Extended Version)
This paper presents a novel evaluation approach to text-based speaker diarization (SD), tackling the limitations of traditional metrics that do not account for any contextual information in text.
Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples
As selected data have high discrepancies in probabilities, the divergence of two networks can be maintained by training on such data.
Atom-Motif Contrastive Transformer for Molecular Property Prediction
As motifs in a molecule are significant patterns that are of great importance for determining molecular properties (e. g., toxicity and solubility), overlooking motif interactions inevitably hinders the effectiveness of MPP.
Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization
By fully exploring both variant and invariant parameters, our EVIL can effectively identify a robust subnetwork to improve OOD generalization.
Beacon-enabled TDMA Ultraviolet Communication Network System Design and Realization
Nonline of sight (NLOS) ultraviolet (UV) scattering communication can serve as a good candidate for outdoor optical wireless communication (OWC) in the cases of non-perfect transmitter-receiver alignment and radio silence.
Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling
The emergence of on-demand ride pooling services allows each vehicle to serve multiple passengers at a time, thus increasing drivers' income and enabling passengers to travel at lower prices than taxi/car on-demand services (only one passenger can be assigned to a car at a time like UberX and Lyft).
Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Polyp Segmentation
To address scale variation, we present a scale-enhanced consistency constraint, which ensures consistency in the segmentation maps generated from the same input image at different scales.
Direct Distillation between Different Domains
Then, we build a fusion-activation mechanism to transfer the valuable domain-invariant knowledge to the student network, while simultaneously encouraging the adapter within the teacher network to learn the domain-specific knowledge of the target data.
Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning
The experimental results on popular LLMs, such as GPT-3. 5-turbo and Gemini-pro, show that our IR method enhances the overall accuracy of factual reasoning by 27. 33% and mathematical proof by 31. 43%, when compared with traditional DR methods.
Ultraviolet Positioning via TDOA: Error Analysis and System Prototype
The theoretical average error matches well with the simulation results, which indicates that theoretical fitting can provide reliable guidance and prediction for hardware experiments.
