experiment:
  id: exp_clip_dino_gnn_v1
  description: CLIP+DINO fusion with bipartite GNN and BCE+InfoNCE.
  tags:
    - baseline_c_plus_gnn
    - adjective_embedding
    - visual_genome

defaults:
  dataset: configs/dataset.yaml
  model: configs/model.yaml
  train: configs/train.yaml
  eval: configs/eval.yaml

baseline_runs:
  - name: baseline_a_clip_only_mlp
    overrides:
      encoders.clip.enabled: true
      encoders.dino.enabled: false
      graph.variant: none
      gnn.type: none
  - name: baseline_b_dino_only_mlp
    overrides:
      encoders.clip.enabled: false
      encoders.dino.enabled: true
      graph.variant: none
      gnn.type: none
  - name: baseline_c_clip_dino_mlp
    overrides:
      encoders.clip.enabled: true
      encoders.dino.enabled: true
      graph.variant: none
      gnn.type: none

main_run:
  name: proposed_clip_dino_gnn
  overrides:
    graph.variant: bipartite
    gnn.type: gat
    attribute_nodes.init_type: clip_text

ablation_runs:
  - name: graph_enriched_with_attribute_priors
    overrides:
      graph.variant: enriched
      graph.include_attribute_priors: true
  - name: trainable_attribute_nodes
    overrides:
      attribute_nodes.init_type: trainable
  - name: bce_only
    overrides:
      loss.contrastive.enabled: false
  - name: partial_encoder_finetune
    overrides:
      training.stage2.enabled: true
      training.stage2.unfreeze_top_n_layers: 4