Search Results for author:
Found 12 papers, 3 papers with code
Two-Way Multi-Label Loss
In contrast to the softmax loss, the BCE loss involves issues regarding imbalance as multiple classes are decomposed into a bunch of binary classifications; recent works improve the BCE loss to cope with the issue by means of weighting.
Grassmannian learning mutual subspace method for image set recognition
The image set is represented by a low-dimensional input subspace; and this input subspace is matched with reference subspaces by a similarity of their canonical angles, an interpretable and easy to compute metric.
T-vMF Similarity for Regularizing Intra-Class Feature Distribution
By focusing on the angle between a feature and a classifier which is embedded in cosine similarity at the classification layer, we formulate a novel similarity beyond the cosine based on von Mises-Fisher distribution of directional statistics.
Gaussian-Based Pooling for Convolutional Neural Networks
Convolutional neural networks (CNNs) contain local pooling to effectively downsize feature maps for increasing computation efficiency as well as robustness to input variations.
Discriminant analysis based on projection onto generalized difference subspace
To avoid the difficulty, we first introduce geometrical Fisher discriminant analysis (gFDA) based on a simplified Fisher criterion.
Global Feature Guided Local Pooling
In the proposed method, the parameterized pooling form is derived from a probabilistic perspective to flexibly represent various types of pooling and then the parameters are estimated by means of global statistics in the input feature map.
Analyzing Filters Toward Efficient ConvNet
Deep convolutional neural network (ConvNet) is a promising approach for high-performance image classification.
Flip-Invariant Motion Representation
In action recognition, local motion descriptors contribute to effectively representing video sequences where target actions appear in localized spatio-temporal regions.
Structured Feature Similarity With Explicit Feature Map
Unlike the previous methods, the proposed method is built on not a histogram form but a tensor structure of a feature array extracted such as on spatial grids, in order to construct effective SSIM-based similarity measure of high robustness which is a key requirement in feature matching.
Three Viewpoints Toward Exemplar SVM
In contrast to category-level or cluster-level classifiers, exemplar SVM is successfully applied to classifying (or detecting) a target object as well as transferring instance-level annotations.
Dirichlet-based Histogram Feature Transform for Image Classification
On the other hand, in the bag-of-feature (BoF) framework, the Dirichlet mixture model can be extended to Gaussian mixture by transforming histogram-based local descriptors, e. g., SIFT, and thereby we propose the method of Dirichlet-derived GMM Fisher kernel.
BFO Meets HOG: Feature Extraction Based on Histograms of Oriented p.d.f. Gradients for Image Classification
Since the p. d. f essentially represents the image, we extract the features from the p. d. f by means of the gradients on the p. d. f.
