The cost of labeling data often limits the performance of machine learni...
Pre-trained large text-to-image models synthesize impressive images with...
We study domain-adaptive image synthesis, the problem of teaching pretra...
Despite the remarkable progress in deep generative models, synthesizing
...
Recent conditional image generation methods produce images of remarkable...
In Composed Image Retrieval (CIR), a user combines a query image with te...
Semi-supervised anomaly detection is a common problem, as often the data...
Transferring knowledge from an image synthesis model trained on a large
...
Vision-language contrastive learning suggests a new learning paradigm by...
With the increasing computing power of edge devices, Federated Learning ...
Learning invariant representations is an important requirement when trai...
We introduce anomaly clustering, whose goal is to group data into
semant...
Contrastive self-supervised learning has shown impressive results in lea...
We propose a novel training method to integrate rules into deep learning...
Anomaly detection (AD), separating anomalies from normal data, has vario...
We extend semi-supervised learning to the problem of domain adaptation t...
We aim at constructing a high performance model for defect detection tha...
Semi-supervised learning on class-imbalanced data, although a realistic
...
We present a two-stage framework for deep one-class classification. We f...
Contrastive representation learning has shown to be an effective way of
...
While deep face recognition has benefited significantly from large-scale...
Semi-supervised learning (SSL) has promising potential for improving the...
Recognizing wild faces is extremely hard as they appear with all kinds o...
Semi-supervised learning (SSL) provides an effective means of leveraging...
Data privacy has emerged as an important issue as data-driven deep learn...
We improve the recently-proposed "MixMatch" semi-supervised learning
alg...
We tackle an unsupervised domain adaptation problem for which the domain...
We propose an active learning approach for transferring representations
...
Predicting structured outputs such as semantic segmentation relies on
ex...
Predicting structured outputs such as semantic segmentation relies on
ex...
Real-world face recognition datasets exhibit long-tail characteristics, ...
Recent developments in deep domain adaptation have allowed knowledge tra...
Convolutional neural network-based approaches for semantic segmentation ...
Despite rapid advances in face recognition, there remains a clear gap be...
Variational Autoencoder (VAE) is an efficient framework in modeling natu...
Deep neural networks (DNNs) trained on large-scale datasets have recentl...
Recently, convolutional neural networks (CNNs) have been used as a power...
This paper investigates a novel problem of generating images from visual...
Object detection systems based on the deep convolutional neural network ...
Learning invariant representations is an important problem in machine
le...