mmaaz60/mvits_for_class_agnostic_od
[ECCV'22] Official repository of paper titled "Class-agnostic Object Detection with Multi-modal Transformer".
PythonMIT
Issues
- 1
Error: Unexpected key(s) in state_dict: "transformer.text_encoder.embeddings.position_ids"
#35 opened by bernard0047 - 0
Table 1
#34 opened by geek-APTX4869 - 1
class-specific object detection
#33 opened by fushh - 1
Could you provide the checkpoint used to generate class-agnostic proposals in Object Centric OVD?
#32 opened by fushh - 7
Not getting results
#31 opened by charul15 - 1
Possibility to Change the Text Encoder?
#27 opened by mcairlangga2 - 1
clarification: what does language structure in the ablation study in the paper mean?
#29 opened by Edwardmark - 2
fail to download pretrained model
#30 opened by 22wei22 - 3
Pre-trained model files
#13 opened by ma-siddiqui - 6
Loading checkpoints for inference
#14 opened by KaleemW - 2
- 1
- 1
how to generate 'tokens_positive' ann from detector dataset like object365?
#17 opened by zhouxingguang - 1
Questions about your pretrained model
#18 opened by slcheng97 - 1
Questions about your training procedure?
#19 opened by GYslchen - 1
How to generate the class-agnostic segmentation results (0-1 mask) based on the pre-trained model?
#23 opened by cjfcsjt - 2
Confusion about the number of ORE test dataset
#25 opened by dengyuhai - 2
How long the training takes?
#21 opened by lxtGH - 3
Issue about the training code
#24 opened by HarborYuan - 2
- 2
one of the variables needed for gradient computation has been modified by an inplace operation
#20 opened by xushilin1 - 0
- 2
using my own custom dataset
#8 opened by nikky4D - 1
pretrain data download
#16 opened by zhouxingguang - 2
Loading the Faster RCNN checkpoint
#11 opened by MartinPedersenpp - 0
- 1
CPU only implementation
#9 opened by cattendu - 6
aligning image text pairs
#7 opened by nikky4D - 5
- 2
Need to understand how to import weights
#4 opened by abhi-vellala - 4
Is EMA used in this work?
#5 opened by JacobYuan7