jianzongwu / awesome-open-vocabulary Goto Github PK

Please consider adding the following related papers:

1. CLIPSelf (arxiv link: https://arxiv.org/abs/2310.01403, code link: https://github.com/wusize/CLIPSelf)
2. CLIM (AAAI'2024, arxiv link: https://arxiv.org/abs/2312.11376, code link: https://github.com/wusize/CLIM)

Thanks.

In my opinion, the survey found at https://arxiv.org/pdf/2307.09220.pdf appears to closely align with the subject matter of your work and might contribute valuable context or insights to your readers 😁

Hello! Thanks for your great work! Please consider adding the following paper: SegPrompt(ICCV2023) https://arxiv.org/pdf/2308.06531.pdf in Class-agnostic Segmentation.

Hi, thanks for your great and helpful survey for open-vocabulary learning. However, I find an incorrect ciation in the survey. Could you update the survey and revise the ciation? The incorrect ciation is [254] of SCAN in the Table 13 and [334] of SCAN in the section "Results under the Cross-evaluation Setting" on 16th page. Many Thanks!

Hi! Guys. Please comment the missing paper in this issue. We will check and add them accordingly.

I am very interested in your summary work on open vocabulary learning. Could you please consider adding the corresponding GitHub repositoriy star count of different open vocabulary algorithm at the readme file in the subsequent updates if the GitHub repositoriy exist, similar to https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/blob/main/README.md ?

Thanks for this great repo! One question: do you consider incorporating works in the interactive segmentation domain? In my opinion, interactive segmentation models are trained in a class-agnostic manner and can naturally generalize to data distributions beyond those seen in training. For example, in the 2D image domain, models trained on COCO can also segment satellite/medical images. In the 3D domain, models trained on ScanNet can also segment objects in outdoor scenarios, e.g., KITTI.

This paper，（GLIP）“Grounded Language-Image Pre-training” has been misclassified; it should be under "Open Vocabulary Object Detection" instead of "Semantic Segmentation" in "Open Vocabulary Segmentation."

Hi, thank you for this repo. I notice that the newest updated date is 2023/7/20. I would like to ask whether you will regularly update this pape list in this git.