AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation

Zanlin Ni, Yulin Wang, Renping Zhou, Rui Lu, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Yuan Yao, Gao Huang

ECCV 2024 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters · 4 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
make the generation policy learnable (policy network instead of manual schedules) (ablation)AdaNAT-S (T=4) · ImageNet 256x256FID-50K: 7.65 -> 5.40Improved
make the learned policy adaptive to each sample (ablation)AdaNAT-S (T=4) · ImageNet 256x256FID-50K: 5.40 -> 4.54Improved
use FID as the reward with an adaptive policy (ablation)AdaNAT-L (T=8) · ImageNet 256x256FID-50K: 55.4 (Fail)Hurt
use FID as the reward with a non-adaptive policy (ablation)AdaNAT-L (T=8) · ImageNet 256x256FID-50K vs visual quality: 2.86 -> 2.56 FID (adversarial vs FID-reward)Mixed
use a pre-trained image reward model as reward (ablation)AdaNAT · ImageNet 256x256sample diversityHurt
use adversarial discriminator reward instead of FID or pretrained reward model (ablation)AdaNAT · ImageNet 256x256fidelity/diversity balanceImproved
apply AdaNAT policy to Muse on CC3MMuse · CC3MFID-30K: 7.67 -> 6.83Improved
use adversarial reward instead of FID reward vs AutoNAT (ablation)AdaNAT-L · ImageNet 256x256 (T=8)FID-50K: 2.56 -> 2.86 (FID-based vs Adv-based); AutoNAT-L 2.68Hurt

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