Search Results for author:
Found 20 papers, 8 papers with code
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
Existing vision-language models exhibit strong generalization on a variety of visual domains and tasks.
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
In this paper, we introduce LiDAR (Linear Discriminant Analysis Rank), a metric designed to measure the quality of representations within JE architectures.
Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals
To achieve effective pretraining in the presence of potential distributional shifts, we propose a frequency-aware masked autoencoder ($\texttt{bio}$FAME) that learns to parameterize the representation of biosignals in the frequency space.
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
We do so by Masked Augmentation Subspace Training (or MAST) to encode in the single feature space the priors from different data augmentations in a factorized way.
MAEEG: Masked Auto-encoder for EEG Representation Learning
We propose a reconstruction-based self-supervised learning model, the masked auto-encoder for EEG (MAEEG), for learning EEG representations by learning to reconstruct the masked EEG features using a transformer architecture.
Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc.
GAUDI: A Neural Architect for Immersive 3D Scene Generation
We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera.
Ranked #1 on
Image Generation
on ARKitScenes
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.
A Dot Product Attention Free Transformer
We introduce Dot Product Attention Free Transformer (DAFT), an efficient variant of Transformers \citep{transformer} that eliminates the query-key dot product in self attention.
Ranked #588 on
Image Classification
on ImageNet
(Number of params metric)
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
We analyze the learning dynamics of infinitely wide neural networks with a finite sized bottle-neck.
An Attention Free Transformer
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention.
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
Uncertainty Weighted Offline Reinforcement Learning
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration.
Subject-Aware Contrastive Learning for Biosignals
Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100).
Capsules with Inverted Dot-Product Attention Routing
We introduce a new routing algorithm for capsule networks, in which a child capsule is routed to a parent based only on agreement between the parent's state and the child's vote.
Geometric Capsule Autoencoders for 3D Point Clouds
The pose encodes where the entity is, while the feature encodes what it is.
A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
The second part of the study focuses on the impact of geometrical transformations such as rotations and scale changes.
Co-Regularized Deep Representations for Video Summarization
A comprehensive user study is conducted comparing our proposed method to a variety of schemes, including the summarization currently in use by one of the most popular video sharing websites.
DeepHash: Getting Regularization, Depth and Fine-Tuning Right
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval.
Top-Down Regularization of Deep Belief Networks
We suggest a deep learning strategy that bridges the gap between the two phases, resulting in a three-phase learning procedure.
