AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following

Qiaomu Miao, Alexandros Graikos, Jingwei Zhang, Sounak Mondal, Minh Hoai, Dimitris Samaras

ECCV 2024 · Vision-language and multimodal › Visual question answering · approach: Vision-language model VQA evaluation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
refine Grad-CAM heatmaps with a diffusion model instead of using them raw as pseudo labels (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.237 -> 0.179Improved
use Grad-CAM VQA prior as the starting point of diffusion refinement (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.191 -> 0.179Improved
use diffusion refinement instead of a Gaussian placed at the Grad-CAM argmax (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.207 -> 0.179Improved
use diffusion model instead of a direct U-Net mapping from Grad-CAM to ground truth (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.190 -> 0.179Improved
start refinement from intermediate noise step 250 rather than 200 or 300 (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.184 (t=200), 0.186 (t=300) -> 0.179 (t=250)Improved
use 5 inference steps instead of 2 in diffusion refinement (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.179 -> 0.180No clear effect
train the diffusion model with Mean Teacher on unlabeled data (GCDR-MT) (ablation)GCDR · GazeFollow (10% labels)Avg. Dist.: 0.179 -> 0.172Improved
feed Grad-CAM heatmaps as direct input to the gaze model (ablation)VAT · GazeFollow (10% labels)Avg. Dist.: 0.202 -> 0.188Improved
refine Grad-CAM pseudo labels with diffusion instead of VAT teacher pseudo labels (GCDR vs Semi-VAT)VAT student · GazeFollow (5% labels)Avg. Dist.: 0.222 -> 0.201Improved
increase amount of unlabeled data from 10% to 90% of GazeFollow (ablation)GCDR-MT · GazeFollow (10% labels)Avg. Dist.: 0.183 -> 0.172Improved
apply Mean Teacher directly to the Miao et al. modelMiao et al. model · GazeFollow (10% labels)Avg. Dist.: 0.190 -> 0.217Hurt
adapt GCDR to the Lian et al. base model with 10% labelsGCDR-MT · GazeFollow (10% labels, Lian base model)Avg. Dist.: 0.216 -> 0.171Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy