Search Results for author:
Found 69 papers, 31 papers with code
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
Multimodal contrastive learning models (e. g., CLIP) can learn high-quality representations from large-scale image-text datasets, yet they exhibit significant vulnerabilities to backdoor attacks, raising serious safety concerns.
Rethinking Chain-of-Thought from the Perspective of Self-Training
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in large language models (LLMs).
Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
Drawing from the theoretical analysis, we propose a novel method called dual-head knowledge distillation, which partitions the linear classifier into two classification heads responsible for different losses, thereby preserving the beneficial effects of both losses on the backbone while eliminating adverse influences on the classification head.
ELU-GCN: Effectively Label-Utilizing Graph Convolutional Network
In the first stage, ELU-GCN conducts graph learning to learn a new graph structure (\ie ELU-graph), which enables GCNs to effectively utilize label information.
Bayesian-guided Label Mapping for Visual Reprogramming
When adapting the output interface, label mapping methods transform the pretrained labels to downstream labels by establishing a gradient-free one-to-one correspondence between the two sets of labels.
Generative AI Enabled Matching for 6G Multiple Access
Then, we propose a framework based on generative diffusion models (GDMs) that iteratively denoises toward reward maximization to generate a matching strategy that meets specific requirements.
Prototype-based Optimal Transport for Out-of-Distribution Detection
In this paper, inspired by the inherent distribution shift between ID and OOD data, we propose a novel method that leverages optimal transport to measure the distribution discrepancy between test inputs and ID prototypes.
Artificial intelligence inspired freeform optics design: a review
Integrating artificial intelligence (AI) techniques such as machine learning and deep learning into freeform optics design has significantly enhanced design efficiency, expanded the design space, and led to innovative solutions.
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond
Furthermore, we design three benchmark datasets focused on label noise detection, label noise learning, and class-imbalanced learning.
AsyCo: An Asymmetric Dual-task Co-training Model for Partial-label Learning
Specifically, the disambiguation network is trained with self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence.
MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading
To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, \emph{a. k. a.}
Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
To alleviate this issue, we propose a Candidate Pseudolabel Learning method, termed CPL, to fine-tune VLMs with suitable candidate pseudolabels of unlabeled data in downstream tasks.
Revolutionizing Wireless Networks with Self-Supervised Learning: A Pathway to Intelligent Communications
With the rapid proliferation of mobile devices and data, next-generation wireless communication systems face stringent requirements for ultra-low latency, ultra-high reliability, and massive connectivity.
Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
The local visual areas are then cross-aligned with the finer descriptions by creating a similarity matrix using the pre-trained VLM.
Sample-specific Masks for Visual Reprogramming-based Prompting
Since we generate different masks for individual samples, SMM is theoretically shown to reduce approximation error for the target tasks compared with existing state-of-the-art VR methods.
BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detection
In this paper, we provide the first attempt at a computationally efficient backdoor detection method to defend against backdoored CLIP in the inference stage.
Improving Generalization of Deep Neural Networks by Optimum Shifting
Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima.
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
In this work, we propose a novel method -- Convex-Concave Loss, which enables a high variance of training loss distribution by gradient descent.
Does confidence calibration improve conformal prediction?
To address this issue, we propose Conformal Temperature Scaling (ConfTS), a variant of temperature scaling with a novel loss function designed to enhance the efficiency of prediction sets.
A General Framework for Learning from Weak Supervision
Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment.
Debiased Sample Selection for Combating Noisy Labels
To address this limitation, we propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection.
Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
To cope with this problem we propose a novel PU learning framework namely Latent Group-Aware Meta Disambiguation (LaGAM) which incorporates a hierarchical contrastive learning module to extract the underlying grouping semantics within PU data and produce compact representations.
Targeted Representation Alignment for Open-World Semi-Supervised Learning
Open-world Semi-Supervised Learning aims to classify unlabeled samples utilizing information from labeled data while unlabeled samples are not only from the labeled known categories but also from novel categories previously unseen.
keqing: knowledge-based question answering is a nature chain-of-thought mentor of LLM
Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, especially for question answering.
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.
Multi-Label Knowledge Distillation
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.
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.
Partial-label Learning with Mixed Closed-set and Open-set Out-of-candidate Examples
In this paper, we term the examples whose true label is outside the candidate label set OOC (out-of-candidate) examples, and pioneer a new PLL study to learn with OOC examples.
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.
Weakly Supervised Regression with Interval Targets
Third, we propose a statistically consistent limiting method for RIT to train the model by limiting the predictions to the interval.
Partial-Label Regression
Our proposed methods are theoretically grounded and can be compatible with any models, optimizers, and losses.
A Generalized Unbiased Risk Estimator for Learning with Augmented Classes
In this paper, we propose a generalized URE that can be equipped with arbitrary loss functions while maintaining the theoretical guarantees, given unlabeled data for LAC.
Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios
Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners.
CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning
In this paper, we propose a new method called CroSel, which leverages historical predictions from the model to identify true labels for most training examples.
Fine-Grained Classification with Noisy Labels
To this end, we propose a novel framework called stochastic noise-tolerated supervised contrastive learning (SNSCL) that confronts label noise by encouraging distinguishable representation.
xURLLC-Aware Service Provisioning in Vehicular Networks: A Semantic Communication Perspective
Semantic communication (SemCom), as an emerging paradigm focusing on meaning delivery, has recently been considered a promising solution for the inevitable crisis of scarce communication resources.
Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning
In this paper, we start with an empirical study of the dynamics of label disambiguation in both II-PLL and ID-PLL.
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks.
Generalized Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses
\emph{Classification with rejection} (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify.
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.
ProMix: Combating Label Noise via Maximizing Clean Sample Utility
To overcome the potential side effect of excessive clean set selection procedure, we further devise a novel SSL framework that is able to train balanced and unbiased classifiers on the separated clean and noisy samples.
Ranked #1 on
Learning with noisy labels
on CIFAR-10N-Worst
Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets
Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance.
Mitigating Neural Network Overconfidence with Logit Normalization
Our method is motivated by the analysis that the norm of the logit keeps increasing during training, leading to overconfident output.
Can Adversarial Training Be Manipulated By Non-Robust Features?
Under this threat, we show that adversarial training using a conventional defense budget $\epsilon$ provably fails to provide test robustness in a simple statistical setting, where the non-robust features of the training data can be reinforced by $\epsilon$-bounded perturbation.
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation
Although there have been a few studies on this problem, most of them only exploit unidirectional relationships from the source domain to the target domain.
Rethinking Calibration of Deep Neural Networks: Do Not Be Afraid of Overconfidence
Capturing accurate uncertainty quantification of the prediction from deep neural networks is important in many real-world decision-making applications.
Who Is Your Right Mixup Partner in Positive and Unlabeled Learning
In this paper, we propose a novel PU learning method, namely Positive and unlabeled learning with Partially Positive Mixup (P3Mix), which simultaneously benefits from data augmentation and supervision correction with a heuristic mixup technique.
Contrastive Label Disambiguation for Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
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.
Open-sampling: Re-balancing Long-tailed Datasets with Out-of-Distribution Data
Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance.
Multi-Class Classification from Single-Class Data with Confidences
We show that without any assumptions on the loss functions, models, and optimizers, we can successfully learn a multi-class classifier from only data of a single class with a rigorous consistency guarantee when confidences (i. e., the class-posterior probabilities for all the classes) are available.
On the Robustness of Average Losses for Partial-Label Learning
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL).
Learning from Similarity-Confidence Data
Weakly supervised learning has drawn considerable attention recently to reduce the expensive time and labor consumption of labeling massive data.
Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by slightly perturbing the features of correctly labeled training examples.
Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion
To this end, both the marginal distribution and the elements with high-confidence correlations are aligned over the common space of the query and key vectors which are computed from different modalities.
With False Friends Like These, Who Can Notice Mistakes?
In this paper, we unveil the threat of hypocritical examples -- inputs that are originally misclassified yet perturbed by a false friend to force correct predictions.
MetaInfoNet: Learning Task-Guided Information for Sample Reweighting
Deep neural networks have been shown to easily overfit to biased training data with label noise or class imbalance.
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
We also instantiate our framework with different combinations, which set the new state of the art on benchmark-simulated and real-world datasets with noisy labels.
Pointwise Binary Classification with Pairwise Confidence Comparisons
To alleviate the data requirement for training effective binary classifiers in binary classification, many weakly supervised learning settings have been proposed.
COMET: Convolutional Dimension Interaction for Collaborative Filtering
In this paper, we propose a novel representation learning-based model called COMET (COnvolutional diMEnsion inTeraction), which simultaneously models the high-order interaction patterns among historical interactions and embedding dimensions.
GLIMG: Global and Local Item Graphs for Top-N Recommender Systems
We argue that recommendation on global and local graphs outperforms that on a single global graph or multiple local graphs.
Provably Consistent Partial-Label Learning
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels.
Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning
Zero-Shot Learning (ZSL) learns models for recognizing new classes.
Combating noisy labels by agreement: A joint training method with co-regularization
The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning with noisy labels.
Ranked #10 on
Learning with noisy labels
on CIFAR-10N-Random3
Progressive Identification of True Labels for Partial-Label Learning
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label.
Learning with Multiple Complementary Labels
In this paper, we propose a novel problem setting to allow MCLs for each example and two ways for learning with MCLs.
Partial Label Learning with Self-Guided Retraining
We show that optimizing this convex-concave problem is equivalent to solving a set of quadratic programming (QP) problems.
Collaboration based Multi-Label Learning
It is well-known that exploiting label correlations is crucially important to multi-label learning.
