AI Paper Atlas

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

Robust Object Detection via Instance-Level Temporal Cycle Confusion

Xin Wang, Thomas E. Huang, Benlin Liu, Fisher Yu, Xiaolong Wang, Joseph E. Gonzalez, Trevor Darrell

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 28 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 CycConf auxiliary taskFaster R-CNN · BDD100K Daytime->NightAP50: 31.35 -> 33.58Improved
add CycConf auxiliary taskFaster R-CNN · BDD100K Night->DaytimeAP50: 33.04 -> 34.34Improved
add CycConf auxiliary taskFaster R-CNN · Waymo Front Left->BDD100K NightAP50: 19.62 -> 26.01Improved
add CycConf auxiliary taskFaster R-CNN · Waymo Front Right->BDD100K NightAP50: 17.26 -> 20.58Improved
use cycle confusion (match most different instance) instead of cycle consistency (nearest neighbour) (ablation)Faster R-CNN + CycConf · BDD100K Daytime->NightAP50: 32.44 -> 33.58Improved
use cycle confusion instead of cycle consistency (ablation)Faster R-CNN + CycConf · Waymo Front Left->BDD100K NightAP50: 23.44 -> 26.01Improved
use cycle confusion instead of cycle consistency (ablation)Faster R-CNN + CycConf · Waymo Front Right->BDD100K NightAP50: 17.92 -> 20.58Improved
add image-level rotation taskFaster R-CNN · BDD100K Daytime->NightAP50: 31.35 -> 32.95Improved
add Jigsaw taskFaster R-CNN · BDD100K Daytime->NightAP50: 31.35 -> 31.22No clear effect
add Jigsaw taskFaster R-CNN · Waymo Front Right->BDD100K NightAP50: 17.26 -> 16.58Hurt
add image rotation task with target-domain unlabeled data (UDA)Faster R-CNN ResNet-101 · Cityscapes->Foggy CityscapesmAP50: 25.6 -> 41.5Improved
add image rotation task with target-domain unlabeled data (UDA)Faster R-CNN VGG-16 · Cityscapes->Foggy CityscapesmAP50: 18.8 -> 37.8Improved

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