TrajGazeMerge β€” checkpoints

Stage-1 trajectory encoder + Stage-2 LoRA-finetuned Qwen2.5-VL-7B-Instruct checkpoints for the TrajGazeMerge project β€” a trajectory-aware visual token selection method that compresses egocentric visual tokens 10Γ— (merge_ratio = 0.9) while keeping the kept tokens task-relevant.

Code: https://github.com/Jaewoo97/trajgaze (branch cf-mask-augmented-training). Paper draft: docs/NeurIPS_2026_Gaze_hand_Trajectory_Merging_for_Efficient_Egocentric_Video_Understanding.pdf in the source repo.


Best result (one sentence)

TAS-only is best in both 2-dataset (StreamGaze + EgoGazeVQA) and 3-dataset (+ HD-EPIC) setups. Adding ATR / CGM losses hurts mean accuracy; counterfactual-mask diagnosis (see eval_results/) shows these extensions do not change LLM language-prior usage on EgoGazeVQA. See the code repo's docs/paper_narrative_v3.md for the mechanism-by-role reading.

Setup Method StreamGaze EgoGazeVQA HD-EPIC mean
A (2 ds) TAS-only β˜… 67.49 57.77 β€” 62.63
A TAS+ATR+CGM (FULL) 61.98 59.40 β€” 60.69
A CGM-only 62.74 55.92 β€” 59.33
B (3 ds) TAS-only-hdepic β˜… 63.69 55.92 50.12 56.57
B TAS+ATR-hdepic 60.65 54.76 50.66 55.35
B CF-1 (cf-mask aug, early-stopped) β€” β€” β€” ~54.5
B CF-3 (cf-mask + shuf aug, early-stopped) β€” β€” β€” ~50.0

Files

stage1/ β€” Trajectory encoder (Stage-1 pretrained)

File Size Role
stage1/E1_combined_AB_TAS.pth 142 MB A + B + TAS encoder (Stage-1 supervised). Required as --stage1-ckpt for every Stage-2 / cf-mask run.

stage2/ β€” LoRA-finetuned Stage-2 (Qwen-VL + TAS encoder fine-tune)

LoRA: r=16, Ξ±=32, target_modules=[q_proj, k_proj, v_proj, o_proj]. Each .pth contains lora_state, encoder_state, and (when applicable) atr_state.

File Size Stage-2 loss Setup Notes
stage2/E1_combined_TAS_only.pth β˜… 16 GB CE only A Headline (Setup A best).
stage2/E1_combined_TAS_ATR.pth 16 GB CE + ATR A Ablation.
stage2/E1_combined_TAS_ATR_CGM.pth (FULL) 16 GB CE + ATR + CGM A Ablation; EgoGazeVQA mask_kept sign-flip but StreamGaze regress.
stage2/E1_combined_CGM_only.pth 16 GB CE + CGM A Ablation; trained from earlier non-TAS Stage-1.
stage2/E1_combined_TASonly_hdepic.pth β˜… 16 GB CE only B Setup B best (+ HD-EPIC).
stage2/E1_combined_TAS_ATR_hdepic.pth 16 GB CE + ATR B Setup B ablation row.
stage2/E1_combined_cf1_hdepic.pth 16 GB CE + cf-mask margin B Direction A (CF-1). Training stopped early at step ~6500.
stage2/E1_combined_cf3_hdepic.pth 16 GB CE + cf-mask + shuf margins B Direction A (CF-3). Training stopped early at step ~6500.

eval_results/ β€” counterfactual-mask summaries + per-sample parquets

Used to reproduce the 4Γ—2 cf-mask matrix in docs/visual_grounding_diagnosis_v2.md. Each ckpt has per-variant *_mask_summary.json + *_per_sample.parquet for {streamgaze, egovqa}.


How to use

  1. Clone the code: git clone https://github.com/Jaewoo97/trajgaze && cd trajgaze && git checkout cf-mask-augmented-training.
  2. Place the Stage-1 ckpt at TrajGaze_v2/checkpoints/E1_combined_AB_TAS/best.pth.
  3. Place each Stage-2 ckpt at TrajGazeMerge/checkpoints/<run-name>/best.pth matching the file name above (drop the .pth suffix in the dir name; the file inside is always best.pth).
  4. Run cf-mask diagnostic (no training needed for inference):
    PYTHONPATH=. python -m TrajGazeMerge.eval.counterfactual_mask_eval \
        --stage1-ckpt TrajGaze_v2/checkpoints/E1_combined_AB_TAS/best.pth \
        --lora-ckpt   TrajGazeMerge/checkpoints/E1_combined_TAS_only/best.pth \
        --val-dataset streamgaze --tag my_run
    

See repo README.md for full training commands (including CF-1, CF-3 reproduce commands in Β§4d).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support