3D on DSEC

Metric: mAP (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	mAP▼	Augmentations	Paper	Date↕	Code
1	CAFR	38	No	Embracing Events and Frames with Hierarchical Fe...	2024-07-17	Code
2	EFNet	30	No	Event-Based Fusion for Motion Deblurring with Cr...	2021-11-30	Code
3	RENet	29.4	No	RGB-Event Fusion for Moving Object Detection in ...	2022-09-17	Code
4	CMX	29.1	No	CMX: Cross-Modal Fusion for RGB-X Semantic Segme...	2022-03-09	Code
5	SPNet	27.7	No	Specificity-preserving RGB-D Saliency Detection	2021-08-18	Code
6	SENet	26.2	No	Squeeze-and-Excitation Networks	2017-09-05	Code
7	CBAM	26.1	No	CBAM: Convolutional Block Attention Module	2018-07-17	Code
8	DCF	25.7	No	-	-	Code
9	ECANet	25.7	No	ECA-Net: Efficient Channel Attention for Deep Co...	2019-10-08	Code
10	FPN-Fusion	24.4	No	-	-	Code
11	SAGate	19.6	No	Bi-directional Cross-Modality Feature Propagatio...	2020-07-17	Code
12	RAMNet	17.6	No	Combining Events and Frames using Recurrent Asyn...	2021-02-18	Code

#1CAFRSOTA
38
mAP· 2024-07-17
Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection Code
#2EFNetSOTA
30
mAP· 2021-11-30
Event-Based Fusion for Motion Deblurring with Cross-modal Attention Code
#3RENet
29.4
mAP· 2022-09-17
RGB-Event Fusion for Moving Object Detection in Autonomous Driving Code
#4CMX
29.1
mAP· 2022-03-09
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformers Code
#5SPNetSOTA
27.7
mAP· 2021-08-18
Specificity-preserving RGB-D Saliency Detection Code
#6SENetSOTA
26.2
mAP· 2017-09-05
Squeeze-and-Excitation Networks Code
#7CBAM
26.1
mAP· 2018-07-17
CBAM: Convolutional Block Attention Module Code
#8DCF
25.7
mAP
No paperCode
#9ECANet
25.7
mAP· 2019-10-08
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks Code
#10FPN-Fusion
24.4
mAP
No paperCode
#11SAGate
19.6
mAP· 2020-07-17
Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation Code
#12RAMNet
17.6
mAP· 2021-02-18
Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction Code