AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis

Patrick Esser, Johannes Haux, Bjorn Ommer

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-centric learning theory and video · 31 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
add adaptive KL weight controlled by second classifier T' to adversarial disentanglement (ablation)adversarial disentangling · Table 1 MI constraint 0.125I_T' (entanglement): 0.8727 -> 0.1201Improved
add adaptive KL weight instead of fixed gamma=1 (ablation)our method · Table 1 MI constraint 0.125I_T' (entanglement): 0.4096 -> 0.1201Improved
add adaptive weighting instead of only variational regularization (ablation)our method · Table 1 MI constraint 0.125reconstruction loss: 3.9350 -> 3.5279Improved
add KL term to adversarial approach (reconstruction cost) (ablation)adversarial only · Table 1 MI constraint 0.125reconstruction loss: 2.9818 -> 3.5279Hurt
combine KL and MI with equal weights rather than adaptive (ablation)our method · Table 1 MI constraint 0.125reconstruction loss: 3.9615 -> 3.5279Improved
add KL term (L_vb) to adversarial model on Market-1501 transfer (ablation)adversarial · Market-1501 (transfer)reID mAP (%): 6.6 -> 25.4Improved
add KL term (L_vb) to adversarial model on DeepFashion transfer (ablation)adversarial · DeepFashion (transfer)reID mAP (%): 10.5 -> 47.1Improved
add KL term to adversarial model, Market-1501 reconstruction (ablation)adversarial · Market-1501 (reconstruction)reID mAP (%): 34.8 -> 30.2Hurt
add KL term to adversarial model, DeepFashion pose error (ablation)adversarial · DeepFashion (transfer)pose error (% of image width): 7.4 +- 8.1 -> 6.8 +- 7.6Improved
use unsupervised method instead of supervised VUNet, DeepFashion transfer appearanceVUNet · DeepFashion (transfer)reID mAP (%): 14.6 -> 47.1Improved
use unsupervised method instead of keypoint-supervised VUNet, pose error on Market-1501 transferVUNet · Market-1501 (transfer)pose error (% of image width): 17.5 +- 9.4 -> 24.7 +- 9.9Hurt

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