Search Results for author:
Found 23 papers, 14 papers with code
Image Retrieval And Classification Using Local Feature Vectors
We also propose a Two-Step Matching process for reducing the response time of the CBIR systems.
Deep Semi-Random Features for Nonlinear Function Approximation
For deep models, with no unrealistic assumptions, we prove universal approximation ability, a lower bound on approximation error, a partial optimization guarantee, and a generalization bound.
Residual Connections Encourage Iterative Inference
In general, a Resnet block tends to concentrate representation learning behavior in the first few layers while higher layers perform iterative refinement of features.
Generalization in Machine Learning via Analytical Learning Theory
This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions.
Manifold Mixup: Better Representations by Interpolating Hidden States
Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples.
Ranked #18 on
Image Classification
on OmniBenchmark
Modularity Matters: Learning Invariant Relational Reasoning Tasks
We focus on two supervised visual reasoning tasks whose labels encode a semantic relational rule between two or more objects in an image: the MNIST Parity task and the colorized Pentomino task.
On Adversarial Mixup Resynthesis
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders.
Interpolation Consistency Training for Semi-Supervised Learning
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.
Adversarial Mixup Resynthesizers
In this paper, we explore new approaches to combining information encoded within the learned representations of autoencoders.
Manifold Mixup: Learning Better Representations by Interpolating Hidden States
Because the hidden states are learned, this has an important effect of encouraging the hidden states for a class to be concentrated in such a way so that interpolations within the same class or between two different classes do not intersect with the real data points from other classes.
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice.
Towards Understanding Generalization in Gradient-Based Meta-Learning
We also show that coherence of meta-test gradients, measured by the average inner product between the task-specific gradient vectors evaluated at meta-train solution, is also correlated with generalization.
InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
There are also some recent methods based on language models (e. g. graph2vec) but they tend to only consider certain substructures (e. g. subtrees) as graph representatives.
Ranked #24 on
Graph Classification
on IMDb-B
GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning
We present GraphMix, a regularization technique for Graph Neural Network based semi-supervised object classification, leveraging the recent advances in the regularization of classical deep neural networks.
GraphMix: Improved Training of GNNs for Semi-Supervised Learning
We present GraphMix, a regularization method for Graph Neural Network based semi-supervised object classification, whereby we propose to train a fully-connected network jointly with the graph neural network via parameter sharing and interpolation-based regularization.
Ranked #1 on
Node Classification
on Pubmed random partition
SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks
In this work we focus on their ability to have invariance towards the presence or absence of details.
Interpolation-based semi-supervised learning for object detection
Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much.
PatchUp: A Feature-Space Block-Level Regularization Technique for Convolutional Neural Networks
Our approach improves the robustness of CNN models against the manifold intrusion problem that may occur in other state-of-the-art mixing approaches.
Towards an Unsupervised Method for Model Selection in Few-Shot Learning
The study of generalization of neural networks in gradient-based meta-learning has recently great research interest.
Towards Domain-Agnostic Contrastive Learning
Despite recent success, most contrastive self-supervised learning methods are domain-specific, relying heavily on data augmentation techniques that require knowledge about a particular domain, such as image cropping and rotation.
CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback
We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT).
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective
Mixup is a popular data augmentation technique for training deep neural networks where additional samples are generated by linearly interpolating pairs of inputs and their labels.
DPOD: Domain-Specific Prompt Tuning for Multimodal Fake News Detection
In this work, we explore whether out-of-domain data can help to improve out-of-context misinformation detection (termed here as multi-modal fake news detection) of a desired domain, to address this challenging problem.
