Search Results for author:
Found 41 papers, 21 papers with code
Towards Modality Generalization: A Benchmark and Prospective Analysis
Multi-modal learning has achieved remarkable success by integrating information from various modalities, achieving superior performance in tasks like recognition and retrieval compared to uni-modal approaches.
LaVin-DiT: Large Vision Diffusion Transformer
Second, for generative modeling, we develop a joint diffusion transformer that progressively produces vision outputs.
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
This framework iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities.
Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detection
Therefore, we appeal for more attention to incremental effectiveness on likelihood, i. e., whether a method could always surpass or at least match the performance of likelihood in U-OOD detection.
Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs
We applied the HCP strategy in experiments with six Repo-Code LLMs, and the results demonstrate that our proposed method can significantly enhance completion accuracy while substantially reducing the length of input.
DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception
The development of large language models (LLMs) has significantly advanced the emergence of large multimodal models (LMMs).
Few-Shot Adversarial Prompt Learning on Vision-Language Models
The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention.
Tackling Noisy Labels with Network Parameter Additive Decomposition
Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization.
Mitigating Label Noise on Graph via Topological Sample Selection
Despite the success of the carefully-annotated benchmarks, the effectiveness of existing graph neural networks (GNNs) can be considerably impaired in practice when the real-world graph data is noisily labeled.
Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision
While existing weakly-supervised approaches leverage image-text pairs to reduce the expansive annotation cost, the lack of mask supervision makes it difficult for the model to locate multiple instances and accurately group pixels with similar semantics, significantly hampering versatility and performance.
One-Shot Learning as Instruction Data Prospector for Large Language Models
Contemporary practices in instruction tuning often hinge on enlarging data scaling without a clear strategy for ensuring data quality, inadvertently introducing noise that may compromise model performance.
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).
Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms.
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
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
However, since the prompts need to be sampled from a large volume of annotated examples, finding the right prompt may result in high annotation costs.
VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence
To be commensurate with this capacity, in addition to the real data used for pre-training, we also generated and leveraged synthetic ophthalmic imaging data.
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.
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.
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.
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.
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.
Dynamics-Aware Loss for Learning with Label Noise
Label noise poses a serious threat to deep neural networks (DNNs).
Robust Generalization against Corruptions via Worst-Case Sharp ness Minimization
Robust generalization aims to deal with the most challenging data distributions which are rarely presented in training set and contain severe noise corruptions.
HumanMAC: Masked Motion Completion for Human Motion Prediction
In the training stage, we learn a motion diffusion model that generates motions from random noise.
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.
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.
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.
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
Objects in Semantic Topology
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
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.
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.
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 #28 on
Image Classification
on mini WebVision 1.0
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.
Robust early-learning: Hindering the memorization of noisy labels
The \textit{early stopping} method therefore can be exploited for learning with noisy labels.
Ranked #34 on
Image Classification
on mini WebVision 1.0
(ImageNet Top-1 Accuracy metric)
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.
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.
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.
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.
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.
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 #19 on
Learning with noisy labels
on CIFAR-10N-Random3
