AI Paper Atlas

Research map / Benchmarks / Cityscapes to Foggy Cityscapes

Cityscapes to Foggy Cityscapes leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Cityscapes to Foggy Cityscapes. Best mAP: 47.9 (MGA, TPAMI 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Cityscapes to Foggy Cityscapes · mAP

16 papers, each with its best reported number for its own method; higher is better.

#mAP ↑MethodPaperTopic
147.9MGA
FCOS VGG-16
Robust Domain Adaptive Object Detection With Unified Multi-Granularity Alignment
TPAMI 2024 · Table 1
Open-set and few-shot detection
247.1Ours (SFOD)
Deformable DETR
Beyond Boundaries: Leveraging Vision Foundation Models for Source-Free Object Detection
AAAI 2026 · Table 1
Open-set and few-shot detection
345.8CSDA
FCOS+VGG16
CSDA: Learning Category-Scale Joint Feature for Domain Adaptive Object Detection
ICCV 2023 · Table 1
Open-set and few-shot detection
445.2Ours (with GPA)
ResNet50
Self-Adversarial Disentangling for Specific Domain Adaptation
TPAMI 2023 · Table 1(a)
Domain adaptation and generalization
544.3MGADA
Faster R-CNN, VGG-16
Multi-Granularity Alignment Domain Adaptation for Object Detection
CVPR 2022 · Table 1
Open-set and few-shot detection
643D-adapt*
Faster R-CNN, ResNet-101
Decoupled Adaptation for Cross-Domain Object Detection
ICLR 2022 · Table: Results from Cityscapes
Open-set and few-shot detection
742.3CDG-UDA
VGG16
Category Dictionary Guided Unsupervised Domain Adaptation for Object Detection
AAAI 2021 · Table 1
Domain adaptation and generalization
840.9KTNet
VGG-16
Knowledge Mining and Transferring for Domain Adaptive Object Detection
ICCV 2021 · Table 1
Open-set and few-shot detection
940.8FGRR (Ours)
Faster-RCNN VGG-16
Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
TPAMI 2022 · Table 2
Open-set and few-shot detection
1040ICCR-VDD
VGG16
Vector-Decomposed Disentanglement for Domain-Invariant Object Detection
ICCV 2021 · Table 1
Open-set and few-shot detection
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.