AI Paper Atlas

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

Vector-Decomposed Disentanglement for Domain-Invariant Object Detection

Aming Wu, Rui Liu, Yahong Han, Linchao Zhu, Yi Yang

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 154 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
plug in vector-decomposed disentanglementSW · Cityscapes to FoggyCityscapesmAP (%): 34.3 -> 37.9Improved
plug in vector-decomposed disentanglementICCR · Cityscapes to FoggyCityscapesmAP (%): 37.4 -> 40.0Improved
plug in vector-decomposed disentanglementSW · Daytime-sunny to Dusk-rainymAP (%): 31.5 -> 36.9Improved
plug in vector-decomposed disentanglementICCR · Daytime-sunny to Dusk-rainymAP (%): 34.9 -> 37.8Improved
plug in vector-decomposed disentanglementSW · Daytime-sunny to Night-rainymAP (%): 17.4 -> 23.1Improved
plug in vector-decomposed disentanglementICCR · Daytime-sunny to Night-rainymAP (%): 20.6 -> 23.7Improved
plug in vector-decomposed disentanglementSW · Daytime-sunny to compound target (Dusk+Night rainy)mAP (%): 27.3 -> 32.6Improved
use two-step training instead of one-step training (ablation)SW-VDD · Cityscapes to FoggyCityscapesmAP (%): 34.5 -> 37.9Improved
use two-step training instead of one-step training (ablation)SW-VDD · PASCAL to WatercolormAP (%): 54.5 -> 56.6Improved
add orthogonal loss with two-step training (ablation)SW-VDD · Cityscapes to FoggyCityscapesmAP (%): 36.5 -> 37.9Improved
add orthogonal loss with two-step training (ablation)SW-VDD · PASCAL to WatercolormAP (%): 54.9 -> 56.6Improved
add orthogonal loss with one-step training (ablation)SW-VDD · Cityscapes to FoggyCityscapesmAP (%): 33.2 -> 34.5Improved

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