Search Results for author:
Found 21 papers, 13 papers with code
EAT: Towards Long-Tailed Out-of-Distribution Detection
The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes.
Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning
In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data.
Novel Class Discovery
Open-World Semi-Supervised Learning
+1
Robust Representation Learning for Unreliable Partial Label Learning
This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels, often resulting in a sub-optimal performance with existing methods.
Partial-Label Regression
Our proposed methods are theoretically grounded and can be compatible with any models, optimizers, and losses.
Complementary Classifier Induced Partial Label Learning
complementary labels), which accurately indicates a set of labels that do not belong to a sample.
Rethinking the Value of Labels for Instance-Dependent Label Noise Learning
Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms.
Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection
However, since such approaches only utilize the highest score proposal and discard the potentially useful information from other proposals, their independent MIL backbone often limits models to salient parts of an object or causes them to detect only one object per class.
Complementary to Multiple Labels: A Correlation-Aware Correction Approach
Moreover, theoretical findings reveal that calculating a transition matrix from label correlations in \textit{multi-labeled CLL} (ML-CLL) needs multi-labeled data, while this is unavailable for ML-CLL.
On the Pitfall of Mixup for Uncertainty Calibration
It has been recently found that models trained with mixup also perform well on uncertainty calibration.
Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision
MIPLGP first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes.
A Survey on Extreme Multi-label Learning
Multi-label learning has attracted significant attention from both academic and industry field in recent decades.
Multi-label Classification with High-rank and High-order Label Correlations
Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization.
One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement
To cope with the challenge, we investigate single-positive multi-label learning (SPMLL) where each example is annotated with only one relevant label, and show that one can successfully learn a theoretically grounded multi-label classifier for the problem.
Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization
Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision.
Multiple Instance Learning
Out-of-Distribution Generalization
+1
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.
Instance-Dependent Partial Label Learning
In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature.
Prototypical Classifier for Robust Class-Imbalanced Learning
Deep neural networks have been shown to be very powerful methods for many supervised learning tasks.
Learning from Noisy Labels via Dynamic Loss Thresholding
During the training process, DLT records the loss value of each sample and calculates dynamic loss thresholds.
Semi-Supervised Partial Label Learning via Confidence-Rated Margin Maximization
After that, maximum margin formulation is introduced to jointly enable the induction of predictive model and the estimation of labeling confidence over unlabeled data.
Towards Mitigating the Class-Imbalance Problem for Partial Label Learning
Partial label (PL) learning aims to induce a multi-class classifier from training examples where each of them is associated with a set of candidate labels, among which only one is valid.
LIFT : Multi-Label Learning with Label-Specific Features
Existing approaches learn from multi-label data by manipulating with identical feature set, i. e. the very instance representation of each example is employed in the discrimination processes of all class labels.
