Search Results for author:
Found 34 papers, 19 papers with code
Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
We innovatively introduce analytic learning into TTA, using the Analytic Classifiers (ACs) to prevent model forgetting.
ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
While previous works have introduced several benchmarks to evaluate the safety risk of LLMs, the community still has a limited understanding of current LLMs' capability to recognize illegal and unsafe content in Chinese contexts.
C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets
Conformal prediction, as an emerging uncertainty quantification technique, typically functions as post-hoc processing for the outputs of trained classifiers.
Fine-tuning can Help Detect Pretraining Data from Large Language Models
In light of this, we introduce a novel and effective method termed Fine-tuned Score Deviation (FSD), which improves the performance of current scoring functions for pretraining data detection.
Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning
Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model.
Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models
In this work, we demonstrate that existing prompt tuning methods usually lead to a trade-off of calibration between base and new classes: the cross-entropy loss in CoOp causes overconfidence in new classes by increasing textual label divergence, whereas the regularization of KgCoOp maintains the confidence level but results in underconfidence in base classes due to the improved accuracy.
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.
On the Noise Robustness of In-Context Learning for Text Generation
In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning.
GACL: Exemplar-Free Generalized Analytic Continual Learning
The GACL adopts analytic learning (a gradient-free training technique) and delivers an analytical (i. e., closed-form) solution to the GCIL scenario.
Learning with Noisy Foundation Models
Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning.
TorchCP: A Python Library for Conformal Prediction
Conformal Prediction (CP) has attracted great attention from the research community due to its strict theoretical guarantees.
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.
Exploring Learning Complexity for Efficient Downstream Dataset Pruning
In this paper, we propose a straightforward, novel, and training-free hardness score named Distorting-based Learning Complexity (DLC), to identify informative images and instructions from the downstream dataset efficiently.
Open-Vocabulary Calibration for Fine-tuned CLIP
Vision-language models (VLMs) have emerged as formidable tools, showing their strong capability in handling various open-vocabulary tasks in image recognition, text-driven visual content generation, and visual chatbots, to name a few.
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.
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.
Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition
However, the high computational cost of optimization-based TTA algorithms makes it intractable to run on resource-constrained edge devices.
Conformal Prediction for Deep Classifier via Label Ranking
Conformal prediction is a statistical framework that generates prediction sets containing ground-truth labels with a desired coverage guarantee.
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks.
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.
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
Modern neural networks are known to give overconfident prediction for out-of-distribution inputs when deployed in the open world.
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.
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.
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.
ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively.
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.
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.
Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix
The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value than the easy cases.
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.
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
Learning with noisy labels is a practically challenging problem in weakly supervised learning.
Deep Stock Trading: A Hierarchical Reinforcement Learning Framework for Portfolio Optimization and Order Execution
Portfolio management via reinforcement learning is at the forefront of fintech research, which explores how to optimally reallocate a fund into different financial assets over the long term by trial-and-error.
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.
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 #11 on
Learning with noisy labels
on CIFAR-10N-Random3
