Add ViTMatte (#25843) - SemanticDiff

Commit

2 years ago

Add ViTMatte (#25843) * First draft * Simplify image processor * Fix rebase * Address comments * Address more comments * Address more comments * Address more comments * Address more comments * Improve pad_image * Add tests * Update integration test * Fix image processor tests * Fix model tests * Convert checkpoints * Fix doc tests * Remove file * Apply suggestions * Address comments * Fix typing hint * Add batch_norm_eps * Address comments * Fix style

References

#25843 - Add ViTMatte

#56 - Add udop

#27720 - Add common processor tests

#29969 - [SigLIP] Add fast tokenizer

#32831 - [Docs] Update resources

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#39821 - Support MetaCLIP 2

#58 - Add EoMT DINOv3 model

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#41212 - Add EoMT with DINOv3 backbone