refactor(compressors): migrate pipeline to OWLv2-based detection with text labels

- Replace bbox-prompted segmentation with OWLv2 text-guided object detection
- Refactor HashPipeline from nn.Module to plain class with modular stage methods
- Add detect_batch, segment_batch, filter_batch for explicit pipeline stages
- Rename forward to forward_batch with text_labels API instead of bboxes
- Add mask_scoring_config, score_threshold, postprocess_threshold configuration
- Update model_loader to expose Dinov2Model type annotation

mini-nav/compressors/model_loader.py

@@ -6,6 +6,7 @@ import torch
 from transformers import (
     AutoImageProcessor,
     AutoModel,
+    Dinov2Model,
     Owlv2ForObjectDetection,
     Owlv2Processor,
     Sam2Model,
@@ -34,7 +35,7 @@ def load_sam_model(
 
 def load_dino_model(
     model_name: str = "facebook/dinov2-large",
-) -> tuple[AutoImageProcessor, AutoModel]:
+) -> tuple[AutoImageProcessor, Dinov2Model]:
     device = get_device()
 
     processor = AutoImageProcessor.from_pretrained(model_name)