Search Results for author:
Found 217 papers, 97 papers with code
Sub-center ArcFace: Boosting Face Recognition by Large-scale Noisy Web Faces
In this paper, we relax the intra-class constraint of ArcFace to improve the robustness to label noise.
Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
Ranked #1 on
Face Recognition
on MFR
Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC
In each iteration, positive class centers and a random subset of negative class centers are selected to compute the margin-based softmax loss.
Domain Generalization via Conditional Invariant Representation
With the conditional invariant representation, the invariance of the joint distribution $\mathbb{P}(h(X), Y)$ can be guaranteed if the class prior $\mathbb{P}(Y)$ does not change across training and test domains.
Unicom: Universal and Compact Representation Learning for Image Retrieval
To further enhance the low-dimensional feature representation, we randomly select partial feature dimensions when calculating the similarities between embeddings and class-wise prototypes.
Ranked #1 on
Image Retrieval
on SOP
(using extra training data)
HumanMAC: Masked Motion Completion for Human Motion Prediction
In the training stage, we learn a motion diffusion model that generates motions from random noise.
CRIS: CLIP-Driven Referring Image Segmentation
In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances.
Contrastive Learning
Generalized Referring Expression Segmentation
+3
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously.
Ranked #1 on
Text Spotting
on Total-Text
(using extra training data)
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously.
Ranked #1 on
Text Spotting
on Inverse-Text
Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
Despite recent success in using the invariance principle for out-of-distribution (OOD) generalization on Euclidean data (e. g., images), studies on graph data are still limited.
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions.
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
Specifically, we design a novel method, termed Abnormal Adversarial Examples Regularization (AAER), which explicitly regularizes the variation of AAEs to hinder the classifier from becoming distorted.
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
To Smooth or Not? When Label Smoothing Meets Noisy Labels
We provide understandings for the properties of LS and NLS when learning with noisy labels.
Ranked #9 on
Learning with noisy labels
on CIFAR-10N-Random3
Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities
Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation.
DeepInception: Hypnotize Large Language Model to Be Jailbreaker
Despite remarkable success in various applications, large language models (LLMs) are vulnerable to adversarial jailbreaks that make the safety guardrails void.
Selective-Supervised Contrastive Learning with Noisy Labels
In the selection process, by measuring the agreement between learned representations and given labels, we first identify confident examples that are exploited to build confident pairs.
Ranked #11 on
Image Classification
on mini WebVision 1.0
A Survey of Label-noise Representation Learning: Past, Present and Future
Classical machine learning implicitly assumes that labels of the training data are sampled from a clean distribution, which can be too restrictive for real-world scenarios.
ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
However, the presence of intrinsic noise and unmatched image-text pairs in web data can potentially affect the performance of representation learning.
FedFed: Feature Distillation against Data Heterogeneity in Federated Learning
Comprehensive experiments demonstrate the efficacy of FedFed in promoting model performance.
Part-dependent Label Noise: Towards Instance-dependent Label Noise
Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise.
Domain Generalization via Entropy Regularization
To arrive at this, some methods introduce a domain discriminator through adversarial learning to match the feature distributions in multiple source domains.
Ranked #43 on
Domain Generalization
on PACS
Towards Label-free Scene Understanding by Vision Foundation Models
For nuImages and nuScenes datasets, the performance is 22. 1\% and 26. 8\% with improvements of 3. 5\% and 6. 0\%, respectively.
A Second-Order Approach to Learning with Instance-Dependent Label Noise
We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable.
Learning with Biased Complementary Labels
We therefore reason that the transition probabilities will be different.
Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision
With this unpaired mask-text supervision, we propose a new weakly-supervised open-vocabulary segmentation framework (Uni-OVSeg) that leverages confident pairs of mask predictions and entities in text descriptions.
One Shot Learning as Instruction Data Prospector for Large Language Models
Nuggets assesses the potential of individual instruction examples to act as effective one shot examples, thereby identifying those that can significantly enhance diverse task performance.
Semantic Structure-based Unsupervised Deep Hashing
Hashing is becoming increasingly popular for approximate nearest neighbor searching in massive databases due to its storage and search efficiency.
Point-Query Quadtree for Crowd Counting, Localization, and More
Such a querying process yields an intuitive, universal modeling of crowd as both the input and output are interpretable and steerable.
CausalAdv: Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning.
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability
Recently Graph Injection Attack (GIA) emerges as a practical attack scenario on Graph Neural Networks (GNNs), where the adversary can merely inject few malicious nodes instead of modifying existing nodes or edges, i. e., Graph Modification Attack (GMA).
Understanding and Improving Early Stopping for Learning with Noisy Labels
Instead of the early stopping, which trains a whole DNN all at once, we initially train former DNN layers by optimizing the DNN with a relatively large number of epochs.
Ranked #8 on
Learning with noisy labels
on CIFAR-10N-Aggregate
How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation
We further investigate its adaptability to controlled data perturbations and examine the efficacy of in-context learning as a tool to enhance its adaptation.
Combating Exacerbated Heterogeneity for Robust Models in Federated Learning
Privacy and security concerns in real-world applications have led to the development of adversarially robust federated models.
Reliable Adversarial Distillation with Unreliable Teachers
However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students.
SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
By exploiting computational geometry analysis and properties of segmentation, we design three complementary regularizers, i. e. volume regularization, anchor guidance, convex guarantee, to approximate the true SimT.
Out-of-distribution Detection with Implicit Outlier Transformation
It leads to a min-max learning scheme -- searching to synthesize OOD data that leads to worst judgments and learning from such OOD data for uniform performance in OOD detection.
Ranked #12 on
Out-of-Distribution Detection
on ImageNet-1k vs Textures
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space.
Confident Anchor-Induced Multi-Source Free Domain Adaptation
To address these challenges, we develop a novel Confident-Anchor-induced multi-source-free Domain Adaptation (CAiDA) model, which is a pioneer exploration of knowledge adaptation from multiple source domains to the unlabeled target domain without any source data, but with only pre-trained source models.
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
However, it has been shown that the MMD test is unaware of adversarial attacks -- the MMD test failed to detect the discrepancy between natural and adversarial data.
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
To defend against MI attacks, previous work utilizes a unilateral dependency optimization strategy, i. e., minimizing the dependency between inputs (i. e., features) and outputs (i. e., labels) during training the classifier.
ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance
To tackle this challenge and enhance the robustness of deep learning models against label noise in graph-based tasks, we propose a method called ERASE (Error-Resilient representation learning on graphs for lAbel noiSe tolerancE).
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
In this paper, we demystify assumptions behind NCD and find that high-level semantic features should be shared among the seen and unseen classes.
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
Instance-dependent Label-noise Learning under a Structural Causal Model
In particular, we show that properly modeling the instances will contribute to the identifiability of the label noise transition matrix and thus lead to a better classifier.
Continuous Dropout
On the one hand, continuous dropout is considerably closer to the activation characteristics of neurons in the human brain than traditional binary dropout.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Adversarial training (AT) with imperfect supervision is significant but receives limited attention.
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed.
Exploiting Class Activation Value for Partial-Label Learning
As the first contribution, we empirically show that the class activation map (CAM), a simple technique for discriminating the learning patterns of each class in images, is surprisingly better at making accurate predictions than the model itself on selecting the true label from candidate labels.
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.
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimate transition matrices.
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).
Provably End-to-end Label-Noise Learning without Anchor Points
In label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers.
Ranked #14 on
Learning with noisy labels
on CIFAR-100N
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.
Multi-Label Noise Transition Matrix Estimation with Label Correlations: Theory and Algorithm
However, estimating multi-label noise transition matrices remains a challenging task, as most existing estimators in noisy multi-class learning rely on anchor points and accurate fitting of noisy class posteriors, which is hard to satisfy in noisy multi-label learning.
Orthogonal Deep Neural Networks
To this end, we first prove that DNNs are of local isometry on data distributions of practical interest; by using a new covering of the sample space and introducing the local isometry property of DNNs into generalization analysis, we establish a new generalization error bound that is both scale- and range-sensitive to singular value spectrum of each of networks' weight matrices.
NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels
First, we thoroughly investigate noisy labels (NLs) injection into AT's inner maximization and outer minimization, respectively and obtain the observations on when NL injection benefits AT.
FedDAG: Federated DAG Structure Learning
To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server.
Dynamics-Aware Loss for Learning with Label Noise
Label noise poses a serious threat to deep neural networks (DNNs).
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.
Robust Angular Local Descriptor Learning
In recent years, the learned local descriptors have outperformed handcrafted ones by a large margin, due to the powerful deep convolutional neural network architectures such as L2-Net [1] and triplet based metric learning [2].
TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
To this end, we propose a target orientated hypothesis adaptation network (TOHAN) to solve the FHA problem, where we generate highly-compatible unlabeled data (i. e., an intermediate domain) to help train a target-domain classifier.
Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
The inheritance part is learned with a similarity loss to transfer the existing learned knowledge from the teacher model to the student model, while the exploration part is encouraged to learn representations different from the inherited ones with a dis-similarity loss.
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.
Robust Training of Federated Models with Extremely Label Deficiency
Federated semi-supervised learning (FSSL) has emerged as a powerful paradigm for collaboratively training machine learning models using distributed data with label deficiency.
Correcting the Triplet Selection Bias for Triplet Loss
Considering that the number of triplets grows cubically with the size of training data, triplet mining is thus indispensable for efficiently training with triplet loss.
Modeling Adversarial Noise for Adversarial Training
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
These hard samples are then employed to promote the quality of the ensemble model by adjusting the ensembling weights for each client model.
Trustable Co-label Learning from Multiple Noisy Annotators
This raises the following important question: how can we effectively use a small amount of trusted data to facilitate robust classifier learning from multiple annotators?
Improving Adversarial Robustness via Mutual Information Estimation
To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method.
Towards Lightweight Black-Box Attacks against Deep Neural Networks
As it is hard to mitigate the approximation error with few available samples, we propose Error TransFormer (ETF) for lightweight attacks.
Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability
Based on such insights, we propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data.
E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
In this work, we propose \textbf{E2HQV}, a novel E2V paradigm designed to produce high-quality video frames from events.
Adaptive Morphological Reconstruction for Seeded Image Segmentation
However, MR might mistakenly filter meaningful seeds that are required for generating accurate segmentation and it is also sensitive to the scale because a single-scale structuring element is employed.
Learning Diverse-Structured Networks for Adversarial Robustness
In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST).
Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data.
Detecting Out-of-distribution Data through In-distribution Class Prior
In this paper, we show that this assumption makes the above methods incapable when the ID model is trained with class-imbalanced data. Fortunately, by analyzing the causal relations between ID/OOD classes and features, we identify several common scenarios where the OOD-to-ID probabilities should be the ID-class-prior distribution and propose two strategies to modify existing inference-time detection methods: 1) replace the uniform distribution with the ID-class-prior distribution if they explicitly use the uniform distribution; 2) otherwise, reweight their scores according to the similarity between the ID-class-prior distribution and the softmax outputs of the pre-trained model.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
To this end, we suggest that generated data (with mistaken OOD generation) can be used to devise an auxiliary OOD detection task to facilitate real OOD detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+1
FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
Therefore, the label guidance on labeled data is hard to be propagated to unlabeled data.
Federated Causal Discovery from Heterogeneous Data
This discrepancy has motivated the development of federated causal discovery (FCD) approaches.
Experimental Quantum Generative Adversarial Networks for Image Generation
For the first time, we experimentally achieve the learning and generation of real-world hand-written digit images on a superconducting quantum processor.
MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models
In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.
Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds
In real-world crowd-sourcing scenarios, noise transition matrices are both annotator- and instance-dependent.
PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels.
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable.
Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight.
Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions
This paper bridges the gap by proposing a pairwise framework for noisy node classification on graphs, which relies on the PI as a primary learning proxy in addition to the pointwise learning from the noisy node class labels.
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.
Class-Dependent Label-Noise Learning with Cycle-Consistency Regularization Feature Space
We show that the cycle-consistency regularization helps to minimize the volume of the transition matrix T indirectly without exploiting the estimated noisy class posterior, which could further encourage the estimated transition matrix T to converge to its optimal solution.
Exploring Model Dynamics for Accumulative Poisoning Discovery
In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information.
On Exploring Node-feature and Graph-structure Diversities for Node Drop Graph Pooling
A pooling operation is essential for effective graph-level representation learning, where the node drop pooling has become one mainstream graph pooling technology.
Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks
The human visual system excels at detecting local blur of visual images, but the underlying mechanism is not well understood.
An Information-Theoretic View for Deep Learning
This upper bound shows that as the number of convolutional and pooling layers $L$ increases in the network, the expected generalization error will decrease exponentially to zero.
On the Rates of Convergence from Surrogate Risk Minimizers to the Bayes Optimal Classifier
We study the rates of convergence from empirical surrogate risk minimizers to the Bayes optimal classifier.
Learning with Bounded Instance- and Label-dependent Label Noise
Inspired by the idea of learning with distilled examples, we then propose a learning algorithm with theoretical guarantees for its robustness to BILN.
Algorithmic stability and hypothesis complexity
The bounds are based on martingale inequalities in the Banach space to which the hypotheses belong.
Transfer Learning with Label Noise
However, when learning this invariant knowledge, existing methods assume that the labels in source domain are uncontaminated, while in reality, we often have access to source data with noisy labels.
Dimensionality-Dependent Generalization Bounds for $k$-Dimensional Coding Schemes
Can we obtain dimensionality-dependent generalization bounds for $k$-dimensional coding schemes that are tighter than dimensionality-independent bounds when data is in a finite-dimensional feature space?
Elastic Net Hypergraph Learning for Image Clustering and Semi-supervised Classification
In the second step, hypergraph is used to represent the high order relationships between each datum and its prominent samples by regarding them as a hyperedge.
Classification with Noisy Labels by Importance Reweighting
In this scenario, there is an unobservable sample with noise-free labels.
Local Rademacher Complexity for Multi-label Learning
We analyze the local Rademacher complexity of empirical risk minimization (ERM)-based multi-label learning algorithms, and in doing so propose a new algorithm for multi-label learning.
Bayesian Quantum Circuit
Parameterized quantum circuits (PQCs), as one of the most promising schemes to realize quantum machine learning algorithms on near-term quantum computers, have been designed to solve machine earning tasks with quantum advantages.
Quantum Physics
Instance-Dependent PU Learning by Bayesian Optimal Relabeling
Specifically, by treating the unlabelled data as noisy negative examples, we could automatically label a group positive and negative examples whose labels are identical to the ones assigned by a Bayesian optimal classifier with a consistency guarantee.
A Grover-search Based Quantum Learning Scheme for Classification
Here we devise a Grover-search based quantum learning scheme (GBLS) to address the above two issues.
The Expressive Power of Parameterized Quantum Circuits
Parameterized quantum circuits (PQCs) have been broadly used as a hybrid quantum-classical machine learning scheme to accomplish generative tasks.
An Optimal Transport View on Generalization
We derive upper bounds on the generalization error of learning algorithms based on their \emph{algorithmic transport cost}: the expected Wasserstein distance between the output hypothesis and the output hypothesis conditioned on an input example.
An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
In this paper, we study the mixture proportion estimation (MPE) problem in a new setting: given samples from the mixture and the component distributions, we identify the proportions of the components in the mixture distribution.
Deep Domain Generalization via Conditional Invariant Adversarial Networks
Under the assumption that the conditional distribution $P(Y|X)$ remains unchanged across domains, earlier approaches to domain generalization learned the invariant representation $T(X)$ by minimizing the discrepancy of the marginal distribution $P(T(X))$.
Ranked #67 on
Domain Generalization
on PACS
On Compressing Deep Models by Low Rank and Sparse Decomposition
Deep compression refers to removing the redundancy of parameters and feature maps for deep learning models.
Why ResNet Works? Residuals Generalize
This paper studies the influence of residual connections on the hypothesis complexity of the neural network in terms of the covering number of its hypothesis space.
On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning
The objective of our proposed method is to transform the features from different tasks into a common feature space in which the tasks are closely related and the shared parameters can be better optimized.
Generative-Discriminative Complementary Learning
The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases.
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.
Transferring Knowledge Fragments for Learning Distance Metric from A Heterogeneous Domain
Some existing heterogeneous transfer learning (HTL) approaches can learn target distance metric by usually transforming the samples of source and target domain into a common subspace.
Multi-View Matrix Completion for Multi-Label Image Classification
Therefore, we propose to weightedly combine the MC outputs of different views, and present the multi-view matrix completion (MVMC) framework for transductive multi-label image classification.
Decomposition-Based Transfer Distance Metric Learning for Image Classification
In particular, DTDML learns a sparse combination of the base metrics to construct the target metric by forcing the target metric to be close to an integration of the source metrics.
Fast Supervised Discrete Hashing
Rather than adopting this method, FSDH uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm.
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs
One of the biggest challenges in learning BIQA models is the conflict between the gigantic image space (which is in the dimension of the number of image pixels) and the extremely limited reliable ground truth data for training.
DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs
To address this issue, we propose a novel deep unsupervised hashing model, dubbed DistillHash, which can learn a distilled data set consisted of data pairs, which have confidence similarity signals.
Truncated Cauchy Non-negative Matrix Factorization
Non-negative matrix factorization (NMF) minimizes the Euclidean distance between the data matrix and its low rank approximation, and it fails when applied to corrupted data because the loss function is sensitive to outliers.
A Quantum-inspired Algorithm for General Minimum Conical Hull Problems
In this paper, we propose a sublinear classical algorithm to tackle general minimum conical hull problems when the input has stored in a sample-based low-overhead data structure.
Towards Digital Retina in Smart Cities: A Model Generation, Utilization and Communication Paradigm
The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelligent sensing manner.
Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
Specifically, we prove a PAC-Bayes generalization bound for neural networks trained by SGD, which has a positive correlation with the ratio of batch size to learning rate.
Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples.
A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection
Alternatively, to access much more natural-looking pedestrians, we propose to augment pedestrian detection datasets by transforming real pedestrians from the same dataset into different shapes.
Confidence Scores Make Instance-dependent Label-noise Learning Possible
We find with the help of confidence scores, the transition distribution of each instance can be approximately estimated.
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
Hitherto, the distributional-assumption-free CPE methods rely on a critical assumption that the support of the positive data distribution cannot be contained in the support of the negative data distribution.
Multi-Class Classification from Noisy-Similarity-Labeled Data
We further estimate the transition matrix from only noisy data and build a novel learning system to learn a classifier which can assign noise-free class labels for instances.
Quantum noise protects quantum classifiers against adversaries
This robustness property is intimately connected with an important security concept called differential privacy which can be extended to quantum differential privacy.
Repulsive Mixture Models of Exponential Family PCA for Clustering
To alleviate this problem, in this paper, a repulsiveness-encouraging prior is introduced among mixing components and a diversified EPCA mixture (DEPCAM) model is developed in the Bayesian framework.
Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels
To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not.
Weakly Supervised Temporal Action Localization with Segment-Level Labels
Specifically, we devise a partial segment loss regarded as a loss sampling to learn integral action parts from labeled segments.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
Quantum Differentially Private Sparse Regression Learning
The eligibility of various advanced quantum algorithms will be questioned if they can not guarantee privacy.
LTF: A Label Transformation Framework for Correcting Label Shift
Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems.
Label-Noise Robust Domain Adaptation
Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains.
Dual-Path Distillation: A Unified Framework to Improve Black-Box Attacks
To obtain sufficient knowledge for crafting adversarial examples, previous methods query the target model with inputs that are perturbed with different searching directions.
ADD-Defense: Towards Defending Widespread Adversarial Examples via Perturbation-Invariant Representation
Motivated by this observation, we propose a defense framework ADD-Defense, which extracts the invariant information called \textit{perturbation-invariant representation} (PIR) to defend against widespread adversarial examples.
Improving robustness of softmax corss-entropy loss via inference information
Several state-of-the-arts start from improving the inter-class separability of training samples by modifying loss functions, where we argue that the adversarial samples are ignored and thus limited robustness to adversarial attacks is resulted.
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)
ME-MOMENTUM: EXTRACTING HARD CONFIDENT EXAMPLES FROM NOISILY LABELED DATA
To extract hard confident examples that contain non-simple patterns and are entangled with the inaccurately labeled examples, we borrow the idea of momentum from physics.
Score-based Causal Discovery from Heterogeneous Data
Most algorithms in causal discovery consider a single domain with a fixed distribution.
Extended T: Learning with Mixed Closed-set and Open-set Noisy Labels
The traditional transition matrix is limited to model closed-set label noise, where noisy training data has true class labels within the noisy label set.
COVID-MTL: Multitask Learning with Shift3D and Random-weighted Loss for Automated Diagnosis and Severity Assessment of COVID-19
In this paper, we present an end-to-end multitask learning (MTL) framework (COVID-MTL) that is capable of automated and simultaneous detection (against both radiology and NAT) and severity assessment of COVID-19.
Understanding the Interaction of Adversarial Training with Noisy Labels
A recent adversarial training (AT) study showed that the number of projected gradient descent (PGD) steps to successfully attack a point (i. e., find an adversarial example in its proximity) is an effective measure of the robustness of this point.
Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record.
A Machine Learning Approach for Predicting Human Preference for Graph Layouts
In this paper, we present the first machine learning approach for predicting human preference for graph layouts.
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.
Removing Adversarial Noise in Class Activation Feature Space
Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space.
Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
For example, there are estimated more than 40 different kinds of retinal diseases with variable morbidity, however with more than 30+ conditions are very rare from the global patient cohorts, which results in a typical long-tailed learning problem for deep learning-based screening models.
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Motivated by that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i. e., Bayes-label transition matrix (BLTM)) and learn a classifier to predict Bayes optimal labels.
Instance Correction for Learning with Open-set Noisy Labels
Lots of approaches, e. g., loss correction and label correction, cannot handle such open-set noisy labels well, since they need training data and test data to share the same label space, which does not hold for learning with open-set noisy labels.
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
In this way, we also give large-loss but less selected data a try; then, we can better distinguish between the cases (a) and (b) by seeing if the losses effectively decrease with the uncertainty after the try.
Ranked #26 on
Image Classification
on mini WebVision 1.0
Towards Defending against Adversarial Examples via Attack-Invariant Features
However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.
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.
Kernel Mean Estimation by Marginalized Corrupted Distributions
Estimating the kernel mean in a reproducing kernel Hilbert space is a critical component in many kernel learning algorithms.
Exploring Set Similarity for Dense Self-supervised Representation Learning
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks.
Can Label-Noise Transition Matrix Help to Improve Sample Selection and Label Correction?
Existing methods for learning with noisy labels can be generally divided into two categories: (1) sample selection and label correction based on the memorization effect of neural networks; (2) loss correction with the transition matrix.
Understanding Generalized Label Smoothing when Learning with Noisy Labels
It was shown that LS serves as a regularizer for training data with hard labels and therefore improves the generalization of the model.
Ranked #15 on
Learning with noisy labels
on CIFAR-10N-Worst
Modeling Adversarial Noise for Adversarial Defense
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
$\alpha$-Weighted Federated Adversarial Training
Federated Adversarial Training (FAT) helps us address the data privacy and governance issues, meanwhile maintains the model robustness to the adversarial attack.
Unleash the Potential of Adaptation Models via Dynamic Domain Labels
In this paper, we propose an embarrassing simple yet highly effective adversarial domain adaptation (ADA) method for effectively training models for alignment.
PI-GNN: Towards Robust Semi-Supervised Node Classification against Noisy Labels
Semi-supervised node classification on graphs is a fundamental problem in graph mining that uses a small set of labeled nodes and many unlabeled nodes for training, so that its performance is quite sensitive to the quality of the node labels.
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.
MANDERA: Malicious Node Detection in Federated Learning via Ranking
Although we know that the benign gradients and Byzantine attacked gradients are distributed differently, to detect the malicious gradients is challenging due to (1) the gradient is high-dimensional and each dimension has its unique distribution and (2) the benign gradients and the attacked gradients are always mixed (two-sample test methods cannot apply directly).
Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms.
Class2Simi: A New Perspective on Learning with Label Noise
It is worthwhile to perform the transformation: We prove that the noise rate for the noisy similarity labels is lower than that of the noisy class labels, because similarity labels themselves are robust to noise.
Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors
Conversational analysis systems are trained using noisy human labels and often require heavy preprocessing during multi-modal feature extraction.
Do We Need to Penalize Variance of Losses for Learning with Label Noise?
Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels.
Pluralistic Image Completion with Probabilistic Mixture-of-Experts
Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well.
Counterfactual Fairness with Partially Known Causal Graph
Interestingly, we find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided: the sensitive attributes do not have ancestors in the causal graph.
Mutual Quantization for Cross-Modal Search With Noisy Labels
More specifically, we propose a proxy-based contrastive (PC) loss to mitigate the gap between different modalities and train networks for different modalities jointly with small-loss samples that are selected with the PC loss and a mutual quantization loss.
MSR: Making Self-supervised learning Robust to Aggressive Augmentations
With the training going on, the model begins to overfit noisy pairs.
Recent Advances for Quantum Neural Networks in Generative Learning
Due to the intrinsic probabilistic nature of quantum mechanics, it is reasonable to postulate that quantum generative learning models (QGLMs) may surpass their classical counterparts.
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers.
Multi-scale Cooperative Multimodal Transformers for Multimodal Sentiment Analysis in Videos
On the whole, the "multi-scale" mechanism is capable of exploiting the different levels of semantic information of each modality which are used for fine-grained crossmodal interactions.
Symmetric Pruning in Quantum Neural Networks
To fill this knowledge gap, here we propose the effective quantum neural tangent kernel (EQNTK) and connect this concept with over-parameterization theory to quantify the convergence of QNNs towards the global optima.
Strength-Adaptive Adversarial Training
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations
This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
The early stopping strategy averts updating CNNs during the early training phase and is widely employed in the presence of noisy labels.
Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation
Motivated by this simple but effective learning pattern, we propose a General-Specific Learning Mechanism (GSLM) to explicitly drive a coarse-grained CAM to a fine-grained pseudo mask.
Fairness Improves Learning from Noisily Labeled Long-Tailed Data
Both long-tailed and noisily labeled data frequently appear in real-world applications and impose significant challenges for learning.
Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering
Our approach includes a density Mip-VoG for scene geometry and a feature Mip-VoG with a small MLP for view-dependent color.
Learning Differentially Private Probabilistic Models for Privacy-Preserving Image Generation
In particular, we first train a model to fit the distribution of the training data and make it satisfy differential privacy by performing a randomized response mechanism during training process.
Advancing Counterfactual Inference through Nonlinear Quantile Regression
Traditional counterfactual inference, under Pearls' counterfactual framework, typically depends on having access to or estimating a structural causal model.
Evolving Semantic Prototype Improves Generative Zero-Shot Learning
After alignment, synthesized sample features from unseen classes are closer to the real sample features and benefit DSP to improve existing generative ZSL methods by 8. 5\%, 8. 0\%, and 9. 7\% on the standard CUB, SUN AWA2 datasets, the significant performance improvement indicates that evolving semantic prototype explores a virgin field in ZSL.
Making Binary Classification from Multiple Unlabeled Datasets Almost Free of Supervision
Training a classifier exploiting a huge amount of supervised data is expensive or even prohibited in a situation, where the labeling cost is high.
A Universal Unbiased Method for Classification from Aggregate Observations
This motivates the study on classification from aggregate observations (CFAO), where the supervision is provided to groups of instances, instead of individual instances.
Why do CNNs excel at feature extraction? A mathematical explanation
Over the past decade deep learning has revolutionized the field of computer vision, with convolutional neural network models proving to be very effective for image classification benchmarks.
Unleashing the Potential of Regularization Strategies in Learning with Noisy Labels
In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data.
Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC).
Channel-Wise Contrastive Learning for Learning with Noisy Labels
In real-world datasets, noisy labels are pervasive.
ShadowNet for Data-Centric Quantum System Learning
Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality.
Late Stopping: Avoiding Confidently Learning from Mislabeled Examples
Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data.
Continual Learning From a Stream of APIs
Next, we train the CL model by minimizing the gap between the responses of the CL model and the black-box API on synthetic data, to transfer the API's knowledge to the CL model.
Gradient constrained sharpness-aware prompt learning for vision-language models
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i. e., improving the performance on unseen classes while maintaining the performance on seen classes.
Holistic Label Correction for Noisy Multi-Label Classification
The issues are, that we do not understand why label dependence is helpful in the problem, and how to learn and utilize label dependence only using training data with noisy multiple labels.
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.
