Search Results for author:
Found 16 papers, 7 papers with code
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
With 3T, we propose a more flexible strategy that allows the image tower to benefit from both pretrained embeddings and contrastive training.
When does Privileged Information Explain Away Label Noise?
Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise.
Massively Scaling Heteroscedastic Classifiers
Heteroscedastic classifiers, which learn a multivariate Gaussian distribution over prediction logits, have been shown to perform well on image classification problems with hundreds to thousands of classes.
Plex: Towards Reliability using Pretrained Large Model Extensions
A recent trend in artificial intelligence is the use of pretrained models for language and vision tasks, which have achieved extraordinary performance but also puzzling failures.
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information
Supervised learning datasets often have privileged information, in the form of features which are available at training time but are not available at test time e. g. the ID of the annotator that provided the label.
Deep Classifiers with Label Noise Modeling and Distance Awareness
Uncertainty estimation in deep learning has recently emerged as a crucial area of interest to advance reliability and robustness in safety-critical applications.
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
In this paper we introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks.
Correlated Input-Dependent Label Noise in Large-Scale Image Classification
We place a multivariate Normal distributed latent variable on the final hidden layer of a neural network classifier.
Ranked #5 on
Image Classification
on WebVision-1000
Routing Networks with Co-training for Continual Learning
We propose the use of sparse routing networks for continual learning.
VAEs in the Presence of Missing Data
Real world datasets often contain entries with missing elements e. g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests.
A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
By tuning the softmax temperature, we improve accuracy, log-likelihood and calibration on both image classification benchmarks with controlled label noise as well as Imagenet-21k which has naturally occurring label noise.
Scalable Deep Unsupervised Clustering with Concrete GMVAEs
By applying a continuous relaxation to the discrete variables in these methods we can achieve a reduction in the training time complexity to be constant in the number of clusters used.
Memory-Augmented Neural Networks for Machine Translation
Memory-augmented neural networks (MANNs) have been shown to outperform other recurrent neural network architectures on a series of artificial sequence learning tasks, yet they have had limited application to real-world tasks.
An Empirical Comparison of Syllabuses for Curriculum Learning
Our experimental results provide an empirical basis for the choice of syllabus on a new problem that could benefit from curriculum learning.
Deep Contextual Multi-armed Bandits
Contextual multi-armed bandit problems arise frequently in important industrial applications.
Implementing Neural Turing Machines
Our implementation learns to solve three sequential learning tasks from the original NTM paper.
