Statements (31)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:object_detection_model
|
| gptkbp:application |
object detection
instance segmentation |
| gptkbp:arXivID |
2102.05702
|
| gptkbp:author |
gptkb:Yue_Zhang
gptkb:Jingdong_Wang Shoufa Chen Xiaokang Chen Yue Cao Yue Chen Zhiqiang Shen |
| gptkbp:basedOn |
gptkb:DETR
|
| gptkbp:citation |
1000+
|
| gptkbp:contribution |
faster convergence
conditional cross-attention mechanism improved object detection performance |
| gptkbp:developedBy |
gptkb:Facebook_AI_Research
|
| gptkbp:improves |
gptkb:DETR
|
| gptkbp:input |
images
|
| gptkbp:introducedIn |
2021
|
| gptkbp:notableFeature |
conditional attention mechanism
faster training than DETR |
| gptkbp:notablePublication |
Conditional DETR for Fast Training Convergence
|
| gptkbp:openSource |
yes
|
| gptkbp:output |
class labels
bounding boxes |
| gptkbp:repository |
https://github.com/Atten4Vis/ConditionalDETR
|
| gptkbp:uses |
transformer architecture
|
| gptkbp:bfsParent |
gptkb:DETR
|
| gptkbp:bfsLayer |
8
|
| https://www.w3.org/2000/01/rdf-schema#label |
Conditional DETR
|