Search Results for author:
Found 15 papers, 6 papers with code
GUMBEL-NERF: Representing Unseen Objects as Part-Compositional Neural Radiance Fields
We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects.
Fixed-Weight Difference Target Propagation
Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work?
Informative Sample-Aware Proxy for Deep Metric Learning
Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies.
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution.
PoF: Post-Training of Feature Extractor for Improving Generalization
We developed a training algorithm called PoF: Post-Training of Feature Extractor that updates the feature extractor part of an already-trained deep model to search a flatter minimum.
Feature Space Particle Inference for Neural Network Ensembles
Ensembles of deep neural networks demonstrate improved performance over single models.
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
Generalization measures are intensively studied in the machine learning community for better modeling generalization gaps.
Adversarial Transformations for Semi-Supervised Learning
We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning.
Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network.
Generating Easy-to-Understand Referring Expressions for Target Identifications
Moreover, we regard that sentences that are easily understood are those that are comprehended correctly and quickly by humans.
Canonical and Compact Point Cloud Representation for Shape Classification
We present a novel compact point cloud representation that is inherently invariant to scale, coordinate change and point permutation.
Binary-decomposed DCNN for accelerating computation and compressing model without retraining
Our method replaces real-valued inner-product computations with binary inner-product computations in existing network models to accelerate computation of inference and decrease model size without the need for retraining.
APAC: Augmented PAttern Classification with Neural Networks
Our method is named as APAC: the Augmented PAttern Classification, which is a way of classification using the optimal decision rule for augmented data learning.
Ranked #7 on
Image Classification
on MNIST
Pairwise Rotation Hashing for High-dimensional Features
Binary Hashing is widely used for effective approximate nearest neighbors search.
