.png){kind=icon}
Return
Bel: Batch Equalization Loss for scene graph generation
.png){kind=icon}
PRE
AI
DOI：10.1007/s10044-023-01199-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Since scene graph can be used as the basis of many high-level vision semantic tasks, scene graph generation has attracted more and more attention of researchers, but most works are limited by the long-tail distribution of dataset, tend to predict those frequent but uninformative predicates such as on and of. From a novel perspective, we found that in the training process, the model would promote the categories included in the batch, while suppressing the categories not in the batch. The long-tailed distribution of the data leads to the continuous suppression of tail categories, thus results in the model bias. In order to solve the problem above, we propose a novel simple and effective method named Batch Equalization Loss, which can be applied to most of the existing models and can bring effective improvement with only a few changes. It is worth noting that our method can achieve a more significant improvement on small batches than on big batches. Extensive experiments on the VG150 dataset show that our work can bring significant improvement on the basis of existing works. Code will be available at GitHub in the near future.
Keywords:
Scene graph generation
Long-tailed data
Training batch
Equalization loss function
Journal
IF:
2
Papers:
2.0K
Citations:
1.9K
Organization
Cited Papers
ShareSaveShareSaveShareSaveThermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons.png)
Indoor Air
OAAI
Indoor AirIF0
OAAIShareSaveSynthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source
PREAI
ShareSaveArsenic removal from aqueous solutions by adsorption using novel MIL-53(Fe) as a highly efficient adsorbentRSC Advances
RSC AdvancesIF0
PREAI
ShareSave
View more