MIC
Context-aware adaptor
An unsupervised domain adaptation method that uses contextual information to improve performance on visual recognition tasks
[CVPR23] Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
269 stars
3 watching
40 forks
Language: Python
last commit: 3 months ago Related projects:
| Repository | Description | Stars |
|---|---|---|
| lhoyer/hrda | A framework for unsupervised domain adaptation in semantic segmentation using multi-resolution training and learned scale attention. | 235 |
 shi-labs/vcoder | An adapter for improving large language models at object-level perception tasks with auxiliary perception modalities | 261 |
 srijith-rkr/kaust-whisper-adapter | A tool for fine-tuning the OpenAI Whisper speech recognition model using residual adapters and parameter-efficient learning methods. | 32 |
 chrisallenming/ltc-msda | An implementation of a knowledge aggregation method for adapting to multiple domains using a graph-based framework. | 68 |
 wasidennis/adaptsegnet | This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another. | 849 |
 haozhezhao/mic | Develops a multimodal vision-language model to enable machines to understand complex relationships between instructions and images in various tasks. | 334 |
 lancopku/iais | This project proposes a novel method for calibrating attention distributions in multimodal models to improve contextualized representations of image-text pairs. | 30 |
 naoto0804/cross-domain-detection | Develops object detection algorithms to adapt to new domains with limited supervision | 422 |
 bupt-ai-cz/meta-selflearning | Develops a method to improve performance of computer vision tasks by adapting models to new domains and data sources through meta-learning and self-learning techniques. | 199 |
 yknzhu/segdeepm | A tool for fine-tuning deep neural networks to improve object detection and segmentation capabilities by incorporating contextual information. | 27 |
 canjie-luo/moran_v2 | A deep learning framework for scene text recognition with rectification and attention mechanisms. | 636 |
 mop/bier | This project implements a deep metric learning framework using an adversarial auxiliary loss to improve robustness. | 39 |
 pathak22/context-encoder | Unsupervised feature learning by image inpainting using Generative Adversarial Networks (GANs) | 885 |
 reedscot/cvpr2016 | A system for learning deep representations of fine-grained visual descriptions from images | 334 |
 easezyc/deep-transfer-learning | A collection of implementations of algorithms to adapt deep learning models from one domain to another | 892 |