Search Results for author:
Found 10 papers, 6 papers with code
GIVT: Generative Infinite-Vocabulary Transformers
We introduce generative infinite-vocabulary transformers (GIVT) which generate vector sequences with real-valued entries, instead of discrete tokens from a finite vocabulary.
Ranked #13 on
Image Generation
on ImageNet 256x256
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data.
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose relationship with the label changes across domains.
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation.
Probable Domain Generalization via Quantile Risk Minimization
By minimizing the $\alpha$-quantile of predictor's risk distribution over domains, QRM seeks predictors that perform well with probability $\alpha$.
Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences
Given two object images, how can we explain their differences in terms of the underlying object properties?
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views
In order to sidestep the main technical difficulty of the multi-object-multi-view scenario -- maintaining object correspondences across views -- MulMON iteratively updates the latent object representations for a scene over multiple views.
Unit-level surprise in neural networks
To adapt to changes in real-world data distributions, neural networks must update their parameters.
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
Existing methods for SFDA leverage entropy-minimization techniques which: (i) apply only to classification; (ii) destroy model calibration; and (iii) rely on the source model achieving a good level of feature-space class-separation in the target domain.
A Framework for the Quantitative Evaluation of Disentangled Representations
Recent AI research has emphasised the importance of learning disentangled representations of the explanatory factors behind data.
