FDA
by hekj
Official Implementation of Frequency-enhanced Data Augmentation for Vision-and-Language Navigation (NeurIPS2023)
AI summary
Navigation assistant
This project proposes a novel data augmentation technique to enhance visual-textual matching in vision-and-language navigation tasks.
- stars
- 13
- forks
- 0
- watching
- 3
Similar projects
Found by comparing what the projects do, not just their names.
Attention calibrator
This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs.
Vision Language Integrator
Improves performance of vision language tasks by integrating computer vision capabilities into large language models
Navigation data generator
Generates data for CARLA's visual navigation system using raw camera images and instructions.
Navigation Aid
An AR navigation aid for visually impaired individuals.
Multimodal alignment model
Extending pretraining models to handle multiple modalities by aligning language and video representations
Biomedicine assistant
A research project aimed at building large language and vision models for biomedical applications with capabilities comparable to GPT-4.
Localizer
Improves image restoration performance by converting global operations to local ones during inference
Annotator
A tool for annotating and labeling data for autonomous driving applications using semi-supervised machine learning
Hallucination fixer
Improves the performance of large language models by intervening in their internal workings to reduce hallucinations
Data augmentation framework
Provides a framework for learning with noisy labels using data augmentation strategies.
Language embeddings
Provides pre-trained ELMo representations for multiple languages to improve NLP tasks.
Robot Navigation
Develops robot navigation policies in crowded spaces using reinforcement learning and attention mechanisms.
Conversational AI assistant
An AI-powered conversational assistant built on top of a Raspberry Pi.
Region-of-Interest Training
Training and deploying large language models on computer vision tasks using region-of-interest inputs
Arabic embedder
Provides sentence embeddings for Arabic languages using pre-trained word embeddings and Smooth Inverse Frequency algorithm
