IAIS
by lancopku
[ACL 2021] Learning Relation Alignment for Calibrated Cross-modal Retrieval
AI summary
Attention calibrator
This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs.
- stars
- 30
- forks
- 4
- watching
- 4
Similar projects
Found by comparing what the projects do, not just their names.
Multimodal alignment model
Extending pretraining models to handle multiple modalities by aligning language and video representations
Multimodal model evaluator
Evaluating and improving large multimodal models through in-context learning
Model aligner
Aligns large multimodal models with human intentions and values using various algorithms and fine-tuning methods.
hekj/fda13
Navigation assistant
This project proposes a novel data augmentation technique to enhance visual-textual matching in vision-and-language navigation tasks.
aidc-ai/ovis575
Multimodal aligner
An MLLM architecture designed to align visual and textual embeddings through structural alignment
ML image recognition model
An implementation of a multimodal learning approach to improve language models' ability to recognize unseen images and understand novel concepts.
Calibration tool
Automated calibration tool for robotic vision systems
Multimodal model evaluator
An open-source benchmark and evaluation tool for assessing multimodal large language models' performance in embodied decision-making tasks
Attention transfer
Improves performance of convolutional neural networks by transferring knowledge from teacher models to student models using attention mechanisms.
Image-language detector
This implementation provides a framework for phrase localization and visual relationship detection using comprehensive image-language cues.
Image Captioning Model
Adaptive attention mechanism for image captioning using visual sentinels
Vision Language Integrator
Improves performance of vision language tasks by integrating computer vision capabilities into large language models
Retrieval model trainer
Trains and evaluates a universal multimodal retrieval model to perform various information retrieval tasks.
mop/bier39
Metric learner
This project implements a deep metric learning framework using an adversarial auxiliary loss to improve robustness.
Localizer
Improves image restoration performance by converting global operations to local ones during inference
