Using Deep Learning to Improve Eye-Tracking Performance in Virtual Reality
Applying state-of-the-art deep learning models for eye feature detection can significantly improve the dropout rate, accuracy, and precision of gaze estimation in virtual reality compared to traditional computer vision techniques.
Demographic Disparities in TikTok's and Instagram's Local Machine Learning Models
TikTok's and Instagram's local machine learning models exhibit significant demographic disparities in their performance, particularly for age and gender prediction, as well as extraction of visual concepts from images.
MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck for Minimal Sufficient Representation
The core message of this work is to propose the Multi-View Entropy Bottleneck (MVEB) objective to effectively learn the minimal sufficient representation in the unsupervised multi-view setting. MVEB simplifies the learning of the minimal sufficient representation to maximizing both the agreement between the embeddings of two views and the differential entropy of the embedding distribution.
Generating Realistic Training Data for Robust 2D and 3D Object Reconstruction under Occlusion using Time-Lapse Imagery
Our method automatically generates a large, realistic dataset of dynamic objects under occlusions using freely available time-lapse imagery, enabling efficient training of object reconstruction methods that are robust to occlusions.
Automated Expansion of Pre-trained Vision Transformers for Continual Learning
A novel continual learning approach that automatically expands pre-trained vision transformers by adding modular adapters and representation descriptors to accommodate distribution shifts in incoming tasks, without the need for memory rehearsal.
Neural Histogram Layers for Extracting Informative "Engineered" Features
The core message of this work is that neural network layers can be designed to learn histogram-based "engineered" features, such as local binary patterns and edge histogram descriptors, which can improve feature representation and performance on image classification tasks.
Task2Box: Modeling Asymmetric Relationships Between Datasets Using Box Embeddings
TASK2BOX is a method that uses box embeddings to effectively model and visualize asymmetric relationships between datasets, such as hierarchical structures and task affinities.
© 2024 by Linnk AI