configs/segmentation/README.md

Fine-tuning YOLO-World for Instance Segmentation

Models

We fine-tune YOLO-World on LVIS (LVIS-Base) with mask annotations for open-vocabulary (zero-shot) instance segmentation.

We provide two fine-tuning strategies YOLO-World towards open-vocabulary instance segmentation:

• fine-tuning all modules: leads to better LVIS segmentation accuracy but affects the zero-shot performance.

• fine-tuning the segmentation head: maintains the zero-shot performanc but lowers LVIS segmentation accuracy.

Model	Fine-tuning Data	Fine-tuning Modules	APmask	APr	APc	APf	Weights
YOLO-World-Seg-M	LVIS-Base	all modules	25.9	13.4	24.9	32.6	HF Checkpoints 🤗
YOLO-World-v2-Seg-M	LVIS-Base	all modules	25.9	13.4	24.9	32.6	HF Checkpoints 🤗
YOLO-World-Seg-L	LVIS-Base	all modules	28.7	15.0	28.3	35.2	HF Checkpoints 🤗
YOLO-World-v2-Seg-L	LVIS-Base	all modules	28.7	15.0	28.3	35.2	HF Checkpoints 🤗
YOLO-World-Seg-M	LVIS-Base	seg head	16.7	12.6	14.6	20.8	HF Checkpoints 🤗
YOLO-World-v2-Seg-M	LVIS-Base	seg head	17.8	13.9	15.5	22.0	HF Checkpoints 🤗
YOLO-World-Seg-L	LVIS-Base	seg head	19.1	14.2	17.2	23.5	HF Checkpoints 🤗
YOLO-World-v2-Seg-L	LVIS-Base	seg head	19.8	17.2	17.5	23.6	HF Checkpoints 🤗
NOTE:

1. The mask AP are evaluated on the LVIS val 1.0.
2. All models are fine-tuned for 80 epochs on LVIS-Base (866 categories, common + frequent).
3. The YOLO-World-Seg with only seg head fine-tuned maintains the original zero-shot detection capability and segments objects.