AI Paper Atlas

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

Seeking Similarities Over Differences: Similarity-Based Domain Alignment for Adaptive Object Detection

Farzaneh Rezaeianaran, Rakshith Shetty, Rahaf Aljundi, Daniel Olmeda Reino, Shanshan Zhang, Bernt Schiele

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 88 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 adversarial training instead of contrastive loss (single group) (ablation)Faster R-CNN UDA · Sim2Realcar AP: 33.2 -> 40.8Improved
use adversarial training instead of contrastive loss (multiple groups) (ablation)Faster R-CNN UDA · Sim2Realcar AP: 36.9 -> 43.1Improved
use adversarial training instead of contrastive loss (MG+CA) (ablation)Faster R-CNN UDA · Sim2Realcar AP: 42.6 -> 45.6Improved
add image-level alignment (multiple groups, class-agnostic) (ablation)ViSGA · Sim2Realcar AP: 45.6 -> 49.3Improved
add image-level alignment (single group) (ablation)ViSGA single group · Sim2Realcar AP: 40.8 -> 39.5Hurt
use multiple visually similar groups instead of no grouping (ablation)ViSGA · Sim2Realcar AP: 39.0 -> 44.9Improved
use multiple visually similar groups instead of no grouping (ablation)ViSGA · FoggymAP: 38.5 -> 41.8Improved
aggregate into a single group instead of no grouping (ablation)ViSGA · FoggymAP: 38.5 -> 33.7Hurt
ignore predicted class label in grouping (class-agnostic) (ablation)ViSGA · Sim2Realcar AP: 44.9 -> 49.3Improved
ignore predicted class label in grouping (class-agnostic) (ablation)ViSGA · FoggymAP: 41.8 -> 43.3Improved
use adaptive number of clusters instead of fixed (ablation)ViSGA · FoggymAP: 42.5 -> 43.3Improved
use cosine similarity instead of IoU for grouping (ablation)ViSGA · Sim2Realcar AP: 44.8 -> 49.3Improved

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