Search Results for author:
Found 29 papers, 9 papers with code
SCD: Self-Contrastive Decorrelation of Sentence Embeddings
In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach.
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models
Optimizing the training objective entails aligning text perplexities in a contrastive fashion.
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings
This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods for sentence embedding.
Mixture-of-experts VAEs can disregard variation in surjective multimodal data
Machine learning systems are often deployed in domains that entail data from multiple modalities, for example, phenotypic and genotypic characteristics describe patients in healthcare.
SCD: Self-Contrastive Decorrelation for Sentence Embeddings
In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach.
Hierarchical Multimodal Variational Autoencoders
Humans find structure in natural phenomena by absorbing stimuli from multiple input sources such as vision, text, and speech.
Attention-based Contrastive Learning for Winograd Schemas
Self-supervised learning has recently attracted considerable attention in the NLP community for its ability to learn discriminative features using a contrastive objective.
Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models
Can we get existing language models and refine them for zero-shot commonsense reasoning?
Learning Private Representations with Focal Entropy
Specifically, we propose focal entropy - a variant of entropy embedded in an adversarial representation learning setting to leverage privacy sanitization.
Multimodal Prototypical Networks for Few-shot Learning
Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios.
Learning Graph-Based Priors for Generalized Zero-Shot Learning
The task of zero-shot learning (ZSL) requires correctly predicting the label of samples from classes which were unseen at training time.
Contrastive Self-Supervised Learning for Commonsense Reasoning
We achieve such commonsense reasoning by constructing pair-wise contrastive auxiliary predictions.
Multimodal Self-Supervised Learning for Medical Image Analysis
We introduce the multimodal puzzle task, which facilitates rich representation learning from multiple image modalities.
Pruning at a Glance: Global Neural Pruning for Model Compression
We prove the viability of our method by producing highly compressed models, namely VGG-16, ResNet-56, and ResNet-110 respectively on CIFAR10 without losing any performance compared to the baseline, as well as ResNet-34 and ResNet-50 on ImageNet without a significant loss of accuracy.
Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds
In this work, we propose a variant of the self-attention Transformer network architectures model to generate meaningful and diverse questions.
Privacy-preserving Representation Learning by Disentanglement
The proposed approach deals with the setting where the private features are not explicit, and is estimated though the course of learning.
Attention Is (not) All You Need for Commonsense Reasoning
The recently introduced BERT model exhibits strong performance on several language understanding benchmarks.
Ranked #7 on
Natural Language Understanding
on PDP60
Budget-Aware Adapters for Multi-Domain Learning
To implement this idea we derive specialized deep models for each domain by adapting a pre-trained architecture but, differently from other methods, we propose a novel strategy to automatically adjust the computational complexity of the network.
Learning to remember: Dynamic Generative Memory for Continual Learning
Continuously trainable models should be able to learn from a stream of data over an undefined period of time.
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
In order to tackle these challenges, we introduce Dynamic Generative Memory (DGM) - a synaptic plasticity driven framework for continual learning.
Ranked #4 on
Continual Learning
on ImageNet-50 (5 tasks)
Low-Shot Learning from Imaginary 3D Model
Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits.
Self Paced Adversarial Training for Multimodal Few-shot Learning
State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks.
Pruning at a Glance: A Structured Class-Blind Pruning Technique for Model Compression
High performance of deep learning models typically comes at cost of considerable model size and computation time.
The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA
We show that our metric is effective in providing a more fine-grained evaluation both on the quantitative and qualitative level.
Cross-modal Hallucination for Few-shot Fine-grained Recognition
State-of-the-art deep learning algorithms generally require large amounts of data for model training.
Gaussian Process Uncertainty in Age Estimation as a Measure of Brain Abnormality
Finally, we illustrate differences in the disease pattern to normal aging, supporting the application of uncertainty as a measure of neuropathology.
Differentially Private Federated Learning: A Client Level Perspective
In such an attack, a client's contribution during training and information about their data set is revealed through analyzing the distributed model.
A Multi-Armed Bandit to Smartly Select a Training Set from Big Medical Data
With the availability of big medical image data, the selection of an adequate training set is becoming more important to address the heterogeneity of different datasets.
DeepNAT: Deep Convolutional Neural Network for Segmenting Neuroanatomy
We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1-weighted magnetic resonance images.
