AI Paper Atlas

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

Learning Good Features to Transfer Across Tasks and Domains

Pierluigi Zama Ramirez, Adriano Cardace, Luca De Luigi, Alessio Tonioni, Samuele Salti, Luigi Di Stefano

TPAMI 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 10 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 edge detection auxiliary task (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 50.16Improved
add NDA loss (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 50.30Improved
add both edge auxiliary task and NDA loss (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 51.28Improved
use autoencoder instead of edge detection as auxiliary task (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 48.07No clear effect
use edge detection instead of depth as source task (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 20.38Hurt
add edge decoder while training N1 only (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 48.69Improved
use two separate edge decoders for N1 and N2 (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 49.99Improved
train N1, N2 and a shared edge decoder simultaneously (ablation)separate edge decoders · Carla to Cityscapes, depth to semanticsmIoU (%): 49.99 -> 50.16Improved
add adversarial alignment of E1 features (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 48.19No clear effect
add asymmetric adversarial alignment of E1 features (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 44.00Hurt
add LargerNorm with norm 500 (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 35.08Hurt
add NDA loss on E2 features (ablation)base AT/DT · Carla to Cityscapes, depth to semanticsmIoU (%): 48.04 -> 27.18Hurt

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