77 citations · 298 across the 18 of their papers we have counts for
18 papers
Label-Efficient Sleep Staging Using Transformers Pre-trained with Position Prediction
Sayeri Lala, Hanlin Goh, Christopher Sandino
Sleep staging is a clinically important task for diagnosing various sleep disorders, but remains challenging to deploy at scale because it because it is both labor-intensive and ti…
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
Yuhang Zang, Hanlin Goh, Josh Susskind +1
Existing vision-language models exhibit strong generalization on a variety of visual domains and tasks. However, such models mainly perform zero-shot recognition in a closed-set ma…
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
Vimal Thilak, Chen Huang, Omid Saremi +5
Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent…
Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals
Ran Liu, Ellen L. Zippi, Hadi Pouransari +5
Leveraging multimodal information from biosignals is vital for building a comprehensive representation of people's physical and mental states. However, multimodal biosignals often…
MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors
Chen Huang, Hanlin Goh, Jiatao Gu +1
Recent Self-Supervised Learning (SSL) methods are able to learn feature representations that are invariant to different data augmentations, which can then be transferred to downstr…
MAEEG: Masked Auto-encoder for EEG Representation Learning
Hsiang-Yun Sherry Chien, Hanlin Goh, Christopher M. Sandino +1
Decoding information from bio-signals such as EEG, using machine learning has been a challenge due to the small data-sets and difficulty to obtain labels. We propose a reconstructi…
Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents
Yao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi +1
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human…
GAUDI: A Neural Architect for Immersive 3D Scene Generation
Miguel Angel Bautista, Pengsheng Guo, Samira Abnar +9
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. We tackle thi…
Position Prediction as an Effective Pretraining Strategy
Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram +7
Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of thei…
Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
Etai Littwin, Omid Saremi, Shuangfei Zhai +4
We analyze the learning dynamics of infinitely wide neural networks with a finite sized bottle-neck. Unlike the neural tangent kernel limit, a bottleneck in an otherwise infinite w…
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning
Yue Wu, Shuangfei Zhai, Nitish Srivastava +4
Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and ac…
An Attention Free Transformer
Shuangfei Zhai, Walter Talbott, Nitish Srivastava +4
We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are…
Subject-Aware Contrastive Learning for Biosignals
Joseph Y. Cheng, Hanlin Goh, Kaan Dogrusoz +2
Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100). To handle these challen…
Capsules with Inverted Dot-Product Attention Routing
Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh +1
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. T…
Geometric Capsule Autoencoders for 3D Point Clouds
Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov
We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric…
A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
Vijay Chandrasekhar, Jie Lin, Olivier Morère +2
With deep learning becoming the dominant approach in computer vision, the use of representations extracted from Convolutional Neural Nets (CNNs) is quickly gaining ground on Fisher…
Co-Regularized Deep Representations for Video Summarization
Olivier Morère, Hanlin Goh, Antoine Veillard +2
Compact keyframe-based video summaries are a popular way of generating viewership on video sharing platforms. Yet, creating relevant and compelling summaries for arbitrarily long v…
DeepHash: Getting Regularization, Depth and Fine-Tuning Right
Jie Lin, Olivier Morere, Vijay Chandrasekhar +2
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing…