-
尊敬的徐学长，你好！一个小小的问题。您肯定有做过attention机制的消融实验吧！额，请问下您的attention机制能带来多少的精度提升呢？
-
Hi @xing0047 , thanks for open-sourcing your work!
Is the current TPS codebase compatible with higher CUDA versions (for newer PyTorch versions), for example, 11.3?
The current configuration req…
-
- [x] OpenImages (#274)
- [x] VoTT (#573)
- [x] CelebA (#484)
- [x] SYNTHIA (#532)
- [ ] Veri776 (re-indefication)
- [x] CIFAR (#225)
- [x] MNIST (#234)
- [x] Fashion-MNIST (#234)
- [x] Kineti…
-
## タイトル: C^2DA：対照学習と文脈認識に基づくドメイン適応型セマンティックセグメンテーション
## リンク: https://arxiv.org/abs/2410.19748
## 概要:
教師なしドメイン適応セマンティックセグメンテーション（UDA-SS）は、ソースドメインデータ（例：合成データ）でモデルをトレーニングし、ターゲットドメインデータ（例：実世界データ）のアノテーシ…
-
Hi,
It seems that you have not results of SSD? Also, you only have segmentation results on Camvid?
The rest seems ok for me. Congratulations!
-
ChatGPT proposed the following lists of datasets:
(50/50)
KITTI
Waymo Open Dataset
BDD100K
ApolloScape
nuScenes
Cityscapes
Mapillary Vistas
BOSCH Small Traffic Lights
Oxford RobotCar
Argo…
-
Hello! Thanks for the great work! @AlessioTonioni
I'm at it again and have questions about the results of "Learning to adapt".
I used 12 Synthia video sequences as dataset and meta-trained the ne…
-
@gheinrich
Hello,
in your segmentation tutorial, you used fixed dimensional PNG labels (single-channel 8-bit paletted image), but in the new DIGITS, we can also specify RGB values if we have RG…
-
hello! thanks for the great work!
When I tried to run your code on my pc, I cannot run it directly and I have 3 questions about your work.
1. How do you organize your ' adaptation_list.csv '?
2.…
-
hi, I meet some problem in warmup_at stage (the second stage). The miou of the model didn't increase compare to the source only model. The value of miou decreased and increased once and once and the …