RavenK/TAC-ViT-base-rgb

TAC RGB encoder

<!-- Provide a quick summary of what the model is/does. -->

This model is used for encoding RGB image into a dense feature.

Caution, the model does not contain the last FC layer. So, the output features are not aligned with depth.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

The model is pre-trained with RGB-D contrastive objectives, named TAC. Different from InfoNCE-based loss fuctions, TAC leverages the similarity between videos frames and estimate a similarity matrix as soft labels. The backbone of this version is ViT-B/32. The pre-training is conducted on a new unified RGB-D database, UniRGBD. The main purpose of this work is depth representation. So, the RGB encoder is just a side model.

Model Sources

<!-- Provide the basic links for the model. -->

• —Repository: TAC
• —Paper: Learning Depth Representation from RGB-D Videos by Time-Aware Contrastive Pre-training

Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

@ARTICLE{10288539,
  author={He, Zongtao and Wang, Liuyi and Dang, Ronghao and Li, Shu and Yan, Qingqing and Liu, Chengju and Chen, Qijun},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={Learning Depth Representation From RGB-D Videos by Time-Aware Contrastive Pre-Training}, 
  year={2024},
  volume={34},
  number={6},
  pages={4143-4158},
  doi={10.1109/TCSVT.2023.3326373}}