Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TokenFusion

TokenFusion

Reported on 24 benchmarks across 6 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology16 results

3DonSUN-RGBD val
mAP@0.25· 2022-04-19
64.9
best: 69.7 (Point-GCC+TR3D+FF)
SOTA
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D ClassificationonSUN-RGBD val
mAP@0.25· 2022-04-19
64.9
best: 69.7 (Point-GCC+TR3D+FF)
SOTA
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D Object DetectiononSUN-RGBD val
mAP@0.25· 2022-04-19
64.9
best: 69.7 (Point-GCC+TR3D+FF)
SOTA
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
16konSUN-RGBD val
mAP@0.25· 2022-04-19
64.9
best: 69.7 (Point-GCC+TR3D+FF)
SOTA
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3DonSUN-RGBD val
mAP@0.5· 2022-04-19
48.3
best: 54 (Point-GCC+TR3D+FF)
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3DonScanNetV2
mAP@0.25· 2022-04-19
70.8
best: 78.8 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3DonScanNetV2
mAP@0.5· 2022-04-19
54.2
best: 67.9 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D ClassificationonSUN-RGBD val
mAP@0.5· 2022-04-19
48.3
best: 54 (Point-GCC+TR3D+FF)
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D ClassificationonScanNetV2
mAP@0.25· 2022-04-19
70.8
best: 78.8 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D ClassificationonScanNetV2
mAP@0.5· 2022-04-19
54.2
best: 67.9 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D Object DetectiononSUN-RGBD val
mAP@0.5· 2022-04-19
48.3
best: 54 (Point-GCC+TR3D+FF)
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D Object DetectiononScanNetV2
mAP@0.25· 2022-04-19
70.8
best: 78.8 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
2D Object DetectiononScanNetV2
mAP@0.5· 2022-04-19
54.2
best: 67.9 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
16konSUN-RGBD val
mAP@0.5· 2022-04-19
48.3
best: 54 (Point-GCC+TR3D+FF)
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
16konScanNetV2
mAP@0.25· 2022-04-19
70.8
best: 78.8 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
16konScanNetV2
mAP@0.5· 2022-04-19
54.2
best: 67.9 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721

Computer Vision8 results

Object DetectiononSUN-RGBD val
mAP@0.25· 2022-04-19
64.9
best: 69.7 (Point-GCC+TR3D+FF)
SOTA
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3D Object DetectiononSUN-RGBD val
mAP@0.25· 2022-04-19
64.9
best: 69.7 (Point-GCC+TR3D+FF)
SOTA
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
Object DetectiononSUN-RGBD val
mAP@0.5· 2022-04-19
48.3
best: 54 (Point-GCC+TR3D+FF)
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
Object DetectiononScanNetV2
mAP@0.25· 2022-04-19
70.8
best: 78.8 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
Object DetectiononScanNetV2
mAP@0.5· 2022-04-19
54.2
best: 67.9 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3D Object DetectiononSUN-RGBD val
mAP@0.5· 2022-04-19
48.3
best: 54 (Point-GCC+TR3D+FF)
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3D Object DetectiononScanNetV2
mAP@0.25· 2022-04-19
70.8
best: 78.8 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721
3D Object DetectiononScanNetV2
mAP@0.5· 2022-04-19
54.2
best: 67.9 (DEST (based on V-DETR) (TTA))
Multimodal Token Fusion for Vision Transformers arXiv:2204.08721