Search Results for author:
Found 16 papers, 7 papers with code
Poly-View Contrastive Learning
Contrastive learning typically matches pairs of related views among a number of unrelated negative views.
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
In online F-TTA, a pre-trained model is adapted using a stream of test samples by minimizing a self-supervised objective, such as entropy minimization.
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
We consider a different lower bound on the MI consisting of an entropy and a reconstruction term (ER), and analyze the main MVSSL families through its lens.
DUET: 2D Structured and Approximately Equivariant Representations
We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data.
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
We show that $\sigma$Reparam provides stability and robustness with respect to the choice of hyperparameters, going so far as enabling training (a) a Vision Transformer {to competitive performance} without warmup, weight decay, layer normalization or adaptive optimizers; (b) deep architectures in machine translation and (c) speech recognition to competitive performance without warmup and adaptive optimizers.
Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer
Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks.
Position Prediction as an Effective Pretraining Strategy
This pretraining strategy which has been used in BERT models in NLP, Wav2Vec models in Speech and, recently, in MAE models in Vision, forces the model to learn about relationships between the content in different parts of the input using autoencoding related objectives.
Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?
Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned.
Stochastic Contrastive Learning
While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables.
Evaluating the fairness of fine-tuning strategies in self-supervised learning
In this work we examine how fine-tuning impacts the fairness of contrastive Self-Supervised Learning (SSL) models.
Neural Temporal Point Processes For Modelling Electronic Health Records
The modelling of Electronic Health Records (EHRs) has the potential to drive more efficient allocation of healthcare resources, enabling early intervention strategies and advancing personalised healthcare.
Learning medical triage from clinicians using Deep Q-Learning
We show that this approach is on a par with human performance, yielding safe triage decisions in 94% of cases, and matching expert decisions in 85% of cases.
Neural Language Priors
The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words.
Relational Graph Attention Networks
We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems.
Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks.
