Gender Classification on Zappos50k in-domain (test)
85.98Top-1 AccuracyMSCon
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MSConLoss=Multi-Similarity Contrastive, Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 85.98 | 0.56 | |
| SupCon GenLoss=SupCon (Gender), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 85.11 | 0.58 | |
| XEnt MTLoss=Cross-Entropy (Multi-task), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 85.07 | 0.55 | |
| XEnt GendLoss=Cross-Entropy (Gender), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 83.09 | 0.6 | |
| CSNLoss=Conditional Similarity Network, Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 69.21 | 0.6 | |
| SimCLRLoss=SimCLR, Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 69.1 | 0.84 | |
| XEnt CloLoss=Cross-Entropy (Closure), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 66.59 | 0.57 | |
| SupCon CloLoss=SupCon (Closure), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 65.9 | 0.6 | |
| XEnt CatLoss=Cross-Entropy (Category), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 63.78 | 0.59 | |
| SupCon CatLoss=SupCon (Category), Evaluation Protocol=Fine-tune classification layer on frozen embedding2023.07 | 61.24 | 0.62 |