-
Hi Is there any ablation that use softmax ce using federeated loss?
CenterNet2 and Detic demonstrated that using federated loss is crucial for long tail distributed dataset like LVIS, and this sampl…
-
I don't manage to understand the difference between your few-shot and open-vocabulary models.
Your approach is based on image-only models and Open-vocabulary approach relies on a text based embedding…
-
Hello, thanks for the awesome collection of demos and code.
I wonder if you have benchmarks or comparisons of the text grounding segmentation capabilities of GroundingDino vs Florence-2? While I've b…
-
Hello mmlab,
It's great to see COCO and LVIS API merged into one repo.
However, the original python api still suffers from slow evaluation speed (~ minutes). AFAIK, NVIDIA has brought a C++ exte…
-
如图所示，YOLO-world-L在O365+GoldG的zero-shot on LVISmini 是 35.0 27.1 32.8 38.3，但是在下图消融中，同样的配置得到的结果为： 32.5 22.3 30.6 36.0。这是为什么？
-
Very wonderful work and amazing demos!
I am trying to use my own data to train the model for stage 1 and use your weights as pretrained model. The only changes include pretrained model path and tra…
-
I can successfully finetune on COCO dataset, and I can test weights for segmentations through:
`./tools/dist_test.sh /homedata/whcai/YOLO-World/configs/segmentation/yolo_world_seg_m_dual_vlpan_2e-4_8…
-
Hello,
I've been trying to qwen2 0.5B and tinyclip using the repository, but I'm running into CUDA OOM issues on the dense2dense distillation step. Im running on 4 80GB A100s, I was wondering if I …
-
Hi! I'm trying to reproduce the result of [Box-Supervised_DeformDETR_R50_2x](https://github.com/facebookresearch/Detic/blob/main/configs/BoxSup-DeformDETR_L_R50_4x.yaml), and I found that the actual s…
-
https://github.com/facebookresearch/Detic/blob/main/docs/MODEL_ZOO.md#real-time-model…