AI Paper Atlas

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

LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation

Koutilya PNVR, Bharat Singh, Pallabi Ghosh, Behjat Siddiquie, David Jacobs

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 33 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
use LDM latent z as input instead of RGB image (ZNet vs RGBNet) (ablation)text-based segmentation network · PhraseCut testmIoU: 46.7 -> 51.3Improved
add LDM internal diffusion features via cross-attention (LD-ZNet vs ZNet) (ablation)ZNet · PhraseCut testmIoU: 51.3 -> 52.7Improved
use z-space input instead of RGB (ablation)ZNet · AIGImIoU: 63.4 -> 68.4Improved
add LDM diffusion features on top of ZNet (ablation)ZNet · AIGImIoU: 68.4 -> 74.1Improved
inject LDM features via cross-attention instead of concatenation (ablation)LD-ZNet · PhraseCut testmIoU: 50.2 -> 52.7Improved
use z input and LDM features (ablation)LD-ZNet · RefCOCO (zero-shot from PhraseCut)IoU: 36.3 -> 41.0Improved
use LDM-initialized UNet segmentation network (RGBNet) vs CLIPSeg/MDETR/SEEMRGBNet · AIGImIoU: 63.4 vs 57.4 (SEEM)Improved
use LDM features from middle blocks 6-10 at timesteps 300-500 (ablation)LD-ZNet feature selection · PhraseCut small validation subsetAPImproved

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