AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Unsupervised Domain Adaptation for Semantic Segmentation of NIR Images through Generative Latent Search

Prashant Pandey, Aayush Kumar Tyagi, Sameer Ambekar, Prathosh AP

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 20 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 Sobel edge concatenation to decoder (ablation)GLSS (perceptual loss + latent search) · SNV (DeepLabv3+)IoU: 0.182 -> 0.385Improved
add Sobel edge concatenation to decoder (ablation)GLSS (perceptual loss + latent search) · Hand Gesture (DeepLabv3+)IoU: 0.300 -> 0.698Improved
add perceptual loss (ablation)GLSS (edge + latent search) · SNV (DeepLabv3+)IoU: 0.223 -> 0.385Improved
add perceptual loss (ablation)GLSS (edge + latent search) · Hand Gesture (DeepLabv3+)IoU: 0.58 -> 0.698Improved
add latent search (ablation)GLSS (edge + perceptual loss) · SNV (DeepLabv3+)IoU: 0.330 -> 0.385Improved
add latent search (ablation)GLSS (edge + perceptual loss) · Hand Gesture (DeepLabv3+)IoU: 0.615 -> 0.698Improved
add edge concatenation alone to baseline (ablation)GLSS baseline · Hand Gesture (DeepLabv3+)IoU: 0.227 -> 0.560Improved
add latent search alone (ablation)GLSS baseline · SNV (DeepLabv3+)IoU: 0.112 -> 0.128Improved
use VAE instead of BigGAN as generative model (ablation)GLSS · SNV (DeepLabv3+)IoU: 0.09 -> 0.38Improved
use VAE instead of BigGAN as generative model (ablation)GLSS · Hand Gesture (DeepLabv3+)IoU: 0.21 -> 0.69Improved
reduce target data used for VAE training from 60% to 20%GLSS · SNV target-independenceIoU: 0.37 -> 0.38No clear effect
reduce target data used from 60% to 20%DADA · SNV target-independenceIoU: 0.31 -> 0.23Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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