metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0932)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | val |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 932 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5533 |
| Val Accuracy | 0.4117 |
| Test Accuracy | 0.4346 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, sweet_pepper, can, camel, plain, keyboard, castle, possum, television, shrew, wardrobe, train, snake, girl, rocket, skyscraper, cockroach, squirrel, beetle, bus, turtle, trout, telephone, ray, tulip, clock, willow_tree, raccoon, mushroom, sea, pickup_truck, chair, wolf, mountain, seal, road, shark, boy, baby, tractor, snail, table, orchid, spider, cloud, pear, crab, oak_tree, chimpanzee, couch