AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Controlling Style and Semantics in Weakly-Supervised Image Generation

Dario Pavllo, Aurelien Lucchi, Thomas Hofmann

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 39 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 sparse detector masks instead of dense semantic segmentation masks (ablation)1-step weakly-supervised model · COCO-valFID: 23.97 -> 20.02Improved
use sparse detector masks instead of ground-truth masks (SPADE) (ablation)1-step model · COCO-valFID: 22.64 -> 20.02Improved
train on extra unlabeled images (VG+ augmented) (ablation)1-step sparse mask model · COCO-valFID: 20.02 -> 18.93Improved
add stuff classes to the mask classes (vs COCO things only) (ablation)SPADE ground-truth masks · COCO-valFID: 32.31 (+9.67)Improved
add ground-truth attributes to the discriminator (ablation)text-conditioned 1-step model · COCO-valFID: 20.63 -> 20.44 (-0.19)No clear effect
draw BERT embeddings from second-to-last layer (ablation)text-conditioned 1-step model · COCO-valFID: 20.63 -> 19.77 (-0.86)Improved
use 6 attention heads instead of 12 with second-to-last layer (ablation)text-conditioned 1-step model · COCO-valFID: 19.77 -> 19.65Improved
feed foreground information to S_avg block of G1 (ablation)2-step attribute model · COCO-valFID: 25.16 -> 20.83 (+4.33 when removed)Improved
randomize style attributes at inference (ablation)2-step attribute model · COCO-valFID: 20.83 -> 20.64 (-0.19)No clear effect
two-step background/foreground decomposition instead of one step (ablation)text-conditioned model · COCO-valFID: 20.63 -> 20.64No clear effect
two-step decomposition instead of one step (ablation)attribute-conditioned model · COCO-val / VG-valFID: 21.13 -> 20.83 (COCO), 15.12 -> 14.88 (VG)Improved
add text style input (6h, L_{n-1}) to sparse mask model (ablation)1-step sparse model · COCO-valFID: 20.02 -> 19.65No clear effect

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