Search Results for author:
Found 27 papers, 9 papers with code
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference
To this end, we explore few-shot learning from the perspective of neural network architecture, as well as a three stage pipeline of network updates under different data supplies, where unsupervised external data is considered for pre-training, base categories are used to simulate few-shot tasks for meta-training, and the scarcely labelled data of an novel task is taken for fine-tuning.
Ranked #1 on
Few-Shot Image Classification
on Meta-Dataset
BayesDLL: Bayesian Deep Learning Library
We release a new Bayesian neural network library for PyTorch for large-scale deep networks.
Online Multi-Object Tracking with Dual Matching Attention Networks
In this paper, we propose an online Multi-Object Tracking (MOT) approach which integrates the merits of single object tracking and data association methods in a unified framework to handle noisy detections and frequent interactions between targets.
Ranked #5 on
Online Multi-Object Tracking
on MOT16
On PyTorch Implementation of Density Estimators for von Mises-Fisher and Its Mixture
The von Mises-Fisher (vMF) is a well-known density model for directional random variables.
Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
The latter can be achieved by minimizing the maximum discrepancy of predictors (classifiers).
Ranked #3 on
Synthetic-to-Real Translation
on Syn2Real-C
Efficient Deep Gaussian Process Models for Variable-Sized Input
The key advantage is that the combination of GP and DRF leads to a tractable model that can both handle a variable-sized input as well as learn deep long-range dependency structures of the data.
Relevance Factor VAE: Learning and Identifying Disentangled Factors
We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all meaningful sources of variation and their cardinality.
Similarity Mapping with Enhanced Siamese Network for Multi-Object Tracking
Multi-object tracking has recently become an important area of computer vision, especially for Advanced Driver Assistance Systems (ADAS).
Deep Clustered Convolutional Kernels
Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting.
Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data
The Cox process is a flexible event model that can account for uncertainty of the intensity function in the Poisson process.
Probabilistic Approximate Logic and its Implementation in the Logical Imagination Engine
In spite of the rapidly increasing number of applications of machine learning in various domains, a principled and systematic approach to the incorporation of domain knowledge in the engineering process is still lacking and ad hoc solutions that are difficult to validate are still the norm in practice, which is of growing concern not only in mission-critical applications.
Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data.
Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation
In this paper, we improve the performance of DA by introducing a discriminative discrepancy measure which takes advantage of auxiliary information available in the source and the target domains to better align the source and target distributions.
Ordinal-Content VAE: Isolating Ordinal-Valued Content Factors in Deep Latent Variable Models
In deep representational learning, it is often desired to isolate a particular factor (termed {\em content}) from other factors (referred to as {\em style}).
Recursive Inference for Variational Autoencoders
Using the functional gradient approach, we devise an intuitive learning criteria for selecting a new mixture component: the new component has to improve the data likelihood (lower bound) and, at the same time, be as divergent from the current mixture distribution as possible, thus increasing representational diversity.
Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach
We deal with the problem of learning the underlying disentangled latent factors that are shared between the paired bi-modal data in cross-modal retrieval.
Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
In this paper, we address the problem in a completely different way by considering a random inference model, where we model the mean and variance functions of the variational posterior as random Gaussian processes (GP).
Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)
First, we factorize the latent space of the whole face to the subspace indicating different parts of the face.
Differentiable Expectation-Maximization for Set Representation Learning
The elements of an input set are considered as i. i. d.~samples from a mixture distribution, and we define our set embedding feed-forward network as the maximum-a-posterior (MAP) estimate of the mixture which is approximately attained by a few Expectation-Maximization (EM) steps.
Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximation
In essence, the MAP solution is approximated by the LDA estimate, but to take the GP prior into account, we adopt the prior-norm adjustment to estimate LDA's shared variance parameters, which ensures that the adjusted estimate is consistent with the GP prior.
SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval
Specifically, we aim to predict class labels of the data instances in each modality, and assign those labels to the corresponding instances in the other modality (i. e., swapping the pseudo labels).
Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders
Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass.
Fisher SAM: Information Geometry and Sharpness Aware Minimisation
Recent sharpness-aware minimisation (SAM) is known to find flat minima which is beneficial for better generalisation with improved robustness.
Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach
We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's robustness.
FedHB: Hierarchical Bayesian Federated Learning
We propose a novel hierarchical Bayesian approach to Federated Learning (FL), where our model reasonably describes the generative process of clients' local data via hierarchical Bayesian modeling: constituting random variables of local models for clients that are governed by a higher-level global variate.
A Hierarchical Bayesian Model for Deep Few-Shot Meta Learning
We propose a novel hierarchical Bayesian model for learning with a large (possibly infinite) number of tasks/episodes, which suits well the few-shot meta learning problem.
Vulnerability Clustering and other Machine Learning Applications of Semantic Vulnerability Embeddings
Cyber-security vulnerabilities are usually published in form of short natural language descriptions (e. g., in form of MITRE's CVE list) that over time are further manually enriched with labels such as those defined by the Common Vulnerability Scoring System (CVSS).
