DropMAE

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

Object TrackingonGOT-10k
Success Rate 0.5· 2023-04-02
86.8
best: 92.2 (SAMURAI-L)
SOTA
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks arXiv:2304.00571
Visual Object TrackingonGOT-10k
Success Rate 0.5· 2023-04-02
86.8
best: 92.2 (SAMURAI-L)
SOTA
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks arXiv:2304.00571
Object TrackingonGOT-10k
Average Overlap· 2023-04-02
75.9
best: 81.7 (SAMURAI-L)
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks arXiv:2304.00571
Object TrackingonGOT-10k
Success Rate 0.75· 2023-04-02
72
best: 82.3 (SPMTrack-G)
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks arXiv:2304.00571
Visual Object TrackingonGOT-10k
Average Overlap· 2023-04-02
75.9
best: 81.7 (SAMURAI-L)
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks arXiv:2304.00571
Visual Object TrackingonGOT-10k
Success Rate 0.75· 2023-04-02
72
best: 82.3 (SPMTrack-G)
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks arXiv:2304.00571