Search Results for author:
Found 16 papers, 2 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.
Inkorrect: Online Handwriting Spelling Correction
We show that Inkorrect's Pareto frontier dominates the points that correspond to prior work.
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.
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 #4 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.
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.
Ranking architectures using meta-learning
However, it requires a large amount of computing resources and in order to alleviate this, a performance prediction network has been recently proposed that enables efficient architecture search by forecasting the performance of candidate architectures, instead of relying on actual model training.
Flexible Multi-task Networks by Learning Parameter Allocation
The binary allocation variables are learned jointly with the model parameters by standard back-propagation thanks to the Gumbel-Softmax reparametrization method.
Ranked #1 on
Multi-Task Learning
on OMNIGLOT
Gumbel-Matrix Routing for Flexible Multi-task Learning
We propose the Gumbel-Matrix routing, a novel multi-task routing method based on the Gumbel-Softmax, that is designed to learn fine-grained parameter sharing.
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision.
Fast Task-Aware Architecture Inference
At the core of our framework lies a deep value network that can predict the performance of input architectures on a task by utilizing task meta-features and the previous model training experiments performed on related tasks.
Learning to discover and localize visual objects with open vocabulary
To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels.
WebVision Challenge: Visual Learning and Understanding With Web Data
The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.
