Search Results for author:
Found 44 papers, 18 papers with code
Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN
The power and the potential of deep learning models attract many researchers to design advanced and sophisticated architectures.
Multi Label Text Classification
Multi-Label Text Classification
+1
CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference
We propose a novel statistical method for testing the results of anomaly detection (AD) under domain adaptation (DA), which we call CAD-DA -- controllable AD under DA.
From SMOTE to Mixup for Deep Imbalanced Classification
Traditionally, the well-known synthetic minority oversampling technique (SMOTE) for data augmentation, a data mining approach for imbalanced learning, has been used to improve this generalization.
Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
Score-based generative models (SGMs) are a popular family of deep generative models that achieve leading image generation quality.
Re-Benchmarking Pool-Based Active Learning for Binary Classification
Active learning is a paradigm that significantly enhances the performance of machine learning models when acquiring labeled data is expensive.
Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances.
Enhancing Label Sharing Efficiency in Complementary-Label Learning with Label Augmentation
Our analysis reveals that the efficiency of implicit label sharing is closely related to the performance of existing CLL models.
CLCIFAR: CIFAR-Derived Benchmark Datasets with Human Annotated Complementary Labels
Through extensive benchmark experiments, we discovered a notable decline in performance when transitioning from synthetic datasets to real-world datasets.
SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective
Researchers have proposed various methods for visually interpreting the Convolutional Neural Network (CNN) via saliency maps, which include Class-Activation-Map (CAM) based approaches as a leading family.
Semi-Supervised Domain Adaptation with Source Label Adaptation
Semi-Supervised Domain Adaptation (SSDA) involves learning to classify unseen target data with a few labeled and lots of unlabeled target data, along with many labeled source data from a related domain.
Reducing Training Sample Memorization in GANs by Training with Memorization Rejection
In this paper, we propose memorization rejection, a training scheme that rejects generated samples that are near-duplicates of training samples during training.
Reduction from Complementary-Label Learning to Probability Estimates
In this paper, we sidestep those limitations with a novel perspective--reduction to probability estimates of complementary classes.
Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration
To improve GAN in terms of model compatibility, we propose Boundary-Calibration GANs (BCGANs), which leverage the boundary information from a set of pre-trained classifiers using the original data.
A Unified View of cGANs with and without Classifiers
Conditional Generative Adversarial Networks (cGANs) are implicit generative models which allow to sample from class-conditional distributions.
Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts.
On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
Many recent developments on generative models for natural images have relied on heuristically-motivated metrics that can be easily gamed by memorizing a small sample from the true distribution or training a model directly to improve the metric.
Accurate and Clear Precipitation Nowcasting with Consecutive Attention and Rain-map Discrimination
We propose a new deep learning model for precipitation nowcasting that includes both the discrimination and attention techniques.
Adaptive and Generative Zero-Shot Learning
In addition, to break the limit of training with images only from seen classes, we design a generative scheme to simultaneously generate virtual class labels and their visual features by sampling and interpolating over seen counterparts.
A Large-scale Study on Training Sample Memorization in Generative Modeling
Many recent developments on generative models for natural images have relied on heuristically-motivated metrics that can be easily gamed by memorizing a small sample from the true distribution or training a model directly to improve the metric.
On the Role of Pre-training for Meta Few-Shot Learning
One is to (pre-)train a classifier with examples from known classes, and then transfer the pre-trained classifier to unknown classes using the new examples.
Cold-start Active Learning through Self-supervised Language Modeling
Typically, the active learning strategy is contingent on the classification model.
360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales
Technically, the gaze information can be inferred from two different magnification levels: face orientation and eye orientation.
Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels
In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions.
SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning
The results verify that the SERIL model can effectively adjust itself to new noise environments while overcoming the catastrophic forgetting issue.
Learning from Label Proportions with Consistency Regularization
The problem of learning from label proportions (LLP) involves training classifiers with weak labels on bags of instances, rather than strong labels on individual instances.
Learning Key Steps to Attack Deep Reinforcement Learning Agents
Deep reinforcement learning agents are known to be vulnerable to adversarial attacks.
Benchmarking Tropical Cyclone Rapid Intensification with Satellite Images and Attention-based Deep Models
In addition, the human-driven nature of such an approach makes it difficult to reproduce and benchmark prediction models.
A Pseudo-Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision
To address the need, we propose a special weakly supervised MLL problem that not only focuses on the situation of limited fine-grained supervision but also leverages the hierarchical relationship between the coarse concepts and the fine-grained ones.
Active Deep Q-learning with Demonstration
In this work, we propose Active Reinforcement Learning with Demonstration (ARLD), a new framework to streamline RL in terms of demonstration efforts by allowing the RL agent to query for demonstration actively during training.
REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis
This paper proposes REFUEL, a reinforcement learning method with two techniques: {\em reward shaping} and {\em feature rebuilding}, to improve the performance of online symptom checking for disease diagnosis.
Deep Learning with a Rethinking Structure for Multi-label Classification
Extracting the hidden correlation is generally a challenging task.
Compatibility Family Learning for Item Recommendation and Generation
In our learned space, we introduce a novel Projected Compatibility Distance (PCD) function which is differentiable and ensures diversity by aiming for at least one prototype to be close to a compatible item, whereas none of the prototypes are close to an incompatible item.
Dynamic Principal Projection for Cost-Sensitive Online Multi-Label Classification
The foundation of CS-DPP is an online LSDR framework derived from a leading LSDR algorithm.
Soft Methodology for Cost-and-error Sensitive Classification
Many real-world data mining applications need varying cost for different types of classification errors and thus call for cost-sensitive classification algorithms.
libact: Pool-based Active Learning in Python
libact is a Python package designed to make active learning easier for general users.
Active Sampling of Pairs and Points for Large-scale Linear Bipartite Ranking
In this paper, we develop a novel active sampling scheme within the pair-wise approach to conduct bipartite ranking efficiently.
Cost-Sensitive Reference Pair Encoding for Multi-Label Learning
Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing.
Cost-Sensitive Deep Learning with Layer-Wise Cost Estimation
While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms.
Can Active Learning Experience Be Transferred?
Empirical studies demonstrate that the learned experience not only is competitive with existing strategies on most single datasets, but also can be transferred across datasets to improve the performance on future learning tasks.
Automatic Bridge Bidding Using Deep Reinforcement Learning
Existing artificial intelligence systems for bridge bidding rely on and are thus restricted by human-designed bidding systems or features.
Cost-Sensitive Label Embedding for Multi-Label Classification
Furthermore, extensive experimental results demonstrate that CLEMS is significantly better than a wide spectrum of existing LE algorithms and state-of-the-art cost-sensitive algorithms across different cost functions.
Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning
Deep learning has been one of the most prominent machine learning techniques nowadays, being the state-of-the-art on a broad range of applications where automatic feature extraction is needed.
Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA
In this paper, we analyze the convergence rate of a representative algorithm with decayed learning rate (Oja and Karhunen, 1985) in the first family for the general $k>1$ case.
Feature-aware Label Space Dimension Reduction for Multi-label Classification
In addition, the approach can be extended to a kernelized version that allows the use of sophisticated feature combinations to assist LSDR.
