Few-Shot Partial-Label Learning

Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label. A basic promise of existing PLL solutions is that there are sufficient partial-label (PL) samples for training. However, it is more common than not to have just few PL samples at hand when dealing with new tasks. Furthermore, existing few-shot learning algorithms assume precise labels of the support set; as such, irrelevant labels may seriously mislead the meta-learner and thus lead to a compromised performance. How to enable PLL under a few-shot learning setting is an important problem, but not yet well studied. In this paper, we introduce an approach called FsPLL (Few-shot PLL). FsPLL first performs adaptive distance metric learning by an embedding network and rectifying prototypes on the tasks previously encountered. Next, it calculates the prototype of each class of a new task in the embedding network. An unseen example can then be classified via its distance to each prototype. Experimental results on widely-used few-shot datasets demonstrate that our FsPLL can achieve a superior performance than the state-of-the-art methods, and it needs fewer samples for quickly adapting to new tasks.

Download Full-text

Chi-Squared Distance Metric Learning for Histogram Data

Mathematical Problems in Engineering ◽

10.1155/2015/352849 ◽

2015 ◽

Vol 2015 ◽

pp. 1-12 ◽

Cited By ~ 2

Author(s):

Wei Yang ◽

Luhui Xu ◽

Xiaopan Chen ◽

Fengbin Zheng ◽

Yang Liu

Keyword(s):

Nearest Neighbor ◽

State Of The Art ◽

Metric Learning ◽

Nearest Neighbors ◽

Distance Metric Learning ◽

Distance Metric ◽

Projected Gradient Method ◽

Proper Distance ◽

Chi Squared ◽

Real World Datasets

Learning a proper distance metric for histogram data plays a crucial role in many computer vision tasks. The chi-squared distance is a nonlinear metric and is widely used to compare histograms. In this paper, we show how to learn a general form of chi-squared distance based on the nearest neighbor model. In our method, the margin of sample is first defined with respect to the nearest hits (nearest neighbors from the same class) and the nearest misses (nearest neighbors from the different classes), and then the simplex-preserving linear transformation is trained by maximizing the margin while minimizing the distance between each sample and its nearest hits. With the iterative projected gradient method for optimization, we naturally introduce thel2,1norm regularization into the proposed method for sparse metric learning. Comparative studies with the state-of-the-art approaches on five real-world datasets verify the effectiveness of the proposed method.

Download Full-text

Accuracy of distance metric learning algorithms

Proceedings of the 2nd Workshop on Data Mining using Matrices and Tensors - DMMT '09 ◽

10.1145/1581114.1581115 ◽

2009 ◽

Cited By ~ 1

Author(s):

Frank Nielsen ◽

Aurélien Sérandour

Keyword(s):

Learning Algorithms ◽

Metric Learning ◽

Distance Metric Learning ◽

Distance Metric

Download Full-text

Distance metric learning for graph structured data

Machine Learning ◽

10.1007/s10994-021-06009-3 ◽

2021 ◽

Author(s):

Tomoki Yoshida ◽

Ichiro Takeuchi ◽

Masayuki Karasuyama

Keyword(s):

Metric Learning ◽

Structured Data ◽

Distance Metric Learning ◽

Distance Metric

Download Full-text

Ensemble-Based Out-of-Distribution Detection

Electronics ◽

10.3390/electronics10050567 ◽

2021 ◽

Vol 10 (5) ◽

pp. 567

Author(s):

Donghun Yang ◽

Kien Mai Mai Ngoc ◽

Iksoo Shin ◽

Kyong-Ha Lee ◽

Myunggwon Hwang

Keyword(s):

Detection Method ◽

State Of The Art ◽

Metric Learning ◽

Feature Space ◽

Confidence Score ◽

Distance Metric Learning ◽

Current State ◽

Overall Performance ◽

Deep Learning Model

To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a confidence score based on the Mahalanobis distance in a feature space. Although it outperformed the previous approaches, the results were sensitive to the quality of the trained model and the dataset complexity. Herein, we propose a novel OOD detection method that can train more efficient feature space for OOD detection. The proposed method uses an ensemble of the features trained using the softmax-based classifier and the network based on distance metric learning (DML). Through the complementary interaction of these two networks, the trained feature space has a more clumped distribution and can fit well on the Gaussian distribution by class. Therefore, OOD data can be efficiently detected by setting a threshold in the trained feature space. To evaluate the proposed method, we applied our method to various combinations of image datasets. The results show that the overall performance of the proposed approach is superior to those of other methods, including the state-of-the-art approach, on any combination of datasets.

Download Full-text