Search Results for author:
Found 27 papers, 5 papers with code
Edgeworth Expansion for Semi-hard Triplet Loss
We develop a higher-order asymptotic analysis for the semi-hard triplet loss using the Edgeworth expansion.
Theoretical and Practical Analysis of Fréchet Regression via Comparison Geometry
Fr\'echet regression extends classical regression methods to non-Euclidean metric spaces, enabling the analysis of data relationships on complex structures such as manifolds and graphs.
Heteroscedastic Double Bayesian Elastic Net
In many practical applications, regression models are employed to uncover relationships between predictors and a response variable, yet the common assumption of constant error variance is frequently violated.
Test-Time Augmentation Meets Variational Bayes
Test-Time Augmentation (TTA) is a technique that instead leverages these data augmentations during the testing phase to achieve robust predictions.
A Fashion Item Recommendation Model in Hyperbolic Space
In this work, we propose a fashion item recommendation model that incorporates hyperbolic geometry into user and item representations.
Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds
One approach to address this problem is density ratio estimation using incremental mixtures of the two distributions.
Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
In this paper, we propose a model-agnostic local explanation method that effectively exploits the nested structure of the input to estimate the two-level feature attributions simultaneously.
Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
One of the simplest techniques to tackle this task is focal loss, a generalization of cross-entropy by introducing one positive parameter.
On permutation-invariant neural networks
From these observations, we show that Deep Sets, one of the well-known permutation-invariant neural networks, can be generalized in the sense of a quasi-arithmetic mean.
A Short Survey on Importance Weighting for Machine Learning
Importance weighting is a fundamental procedure in statistics and machine learning that weights the objective function or probability distribution based on the importance of the instance in some sense.
Understanding Test-Time Augmentation
Test-Time Augmentation (TTA) is a very powerful heuristic that takes advantage of data augmentation during testing to produce averaged output.
Information Geometrically Generalized Covariate Shift Adaptation
In particular, the phenomenon that the marginal distribution of the data changes is called covariate shift, one of the most important research topics in machine learning.
Generalization Bounds for Set-to-Set Matching with Negative Sampling
The problem of matching two sets of multiple elements, namely set-to-set matching, has received a great deal of attention in recent years.
Fashion-Specific Attributes Interpretation via Dual Gaussian Visual-Semantic Embedding
Several techniques to map various types of components, such as words, attributes, and images, into the embedded space have been studied.
Information Geometry of Dropout Training
Dropout is one of the most popular regularization techniques in neural network training.
GRASP EARTH: Intuitive Software for Discovering Changes on the Planet
Detecting changes on the Earth, such as urban development, deforestation, or natural disaster, is one of the research fields that is attracting a great deal of attention.
SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts
This paper addresses the problem of set-to-set matching, which involves matching two different sets of items based on some criteria, especially in the case of high-dimensional items like images.
$α$-Geodesical Skew Divergence
The asymmetric skew divergence smooths one of the distributions by mixing it, to a degree determined by the parameter $\lambda$, with the other distribution.
Density Fixing: Simple yet Effective Regularization Method based on the Class Prior
Machine learning models suffer from overfitting, which is caused by a lack of labeled data.
Why Mixup Improves the Model Performance
Machine learning techniques are used in a wide range of domains.
Large-Scale Landslides Detection from Satellite Images with Incomplete Labels
Earthquakes and tropical cyclones cause the suffering of millions of people around the world every year.
New Perspective of Interpretability of Deep Neural Networks
Improving the interpretability of DNNs is one of the hot research topics.
PNUNet: Anomaly Detection using Positive-and-Negative Noise based on Self-Training Procedure
We propose the novel framework for anomaly detection in images.
Intentional Attention Mask Transformation for Robust CNN Classification
To tackle this problem, we exploit a multi-channel attention mechanism in feature space.
Interpretation of Feature Space using Multi-Channel Attentional Sub-Networks
To tackle this problem, we exploit a multi-channel attention mechanism in feature space.
Anomaly Detection Using GANs for Visual Inspection in Noisy Training Data
The proposed method detects pixel-level micro anomalies with a high accuracy from 1024x1024 high resolution images which are actually used in an industrial scene.
Node Centralities and Classification Performance for Characterizing Node Embedding Algorithms
Embedding graph nodes into a vector space can allow the use of machine learning to e. g. predict node classes, but the study of node embedding algorithms is immature compared to the natural language processing field because of a diverse nature of graphs.
