SOTAVerified

Robust Object Detection

A Benchmark for the: Robustness of Object Detection Models to Image Corruptions and Distortions

To allow fair comparison of robustness enhancing methods all models have to use a standard ResNet50 backbone because performance strongly scales with backbone capacity. If requested an unrestricted category can be added later.

Benchmark Homepage: https://github.com/bethgelab/robust-detection-benchmark

Metrics:

mPC [AP]: Mean Performance under Corruption [measured in AP]

rPC [%]: Relative Performance under Corruption [measured in %]

Test sets: Coco: val 2017; Pascal VOC: test 2007; Cityscapes: val;

( Image credit: Benchmarking Robustness in Object Detection )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 76–90 of 90 papers

TitleStatusHype
Learning Data Augmentation Strategies for Object DetectionCode1
Segmentation is All You Need—0
Switchable Whitening for Deep Representation LearningCode0
Iterative Normalization: Beyond Standardization towards Efficient WhiteningCode0
A Robust Learning Approach to Domain Adaptive Object DetectionCode0
Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments—0
Two at Once: Enhancing Learning and Generalization Capacities via IBN-NetCode1
Soft Sampling for Robust Object DetectionCode0
YOLOv3: An Incremental ImprovementCode1
Fusion of an Ensemble of Augmented Image Detectors for Robust Object Detection—0
Domain Adaptive Faster R-CNN for Object Detection in the WildCode1
Dropout Sampling for Robust Object Detection in Open-Set Conditions—0
Random Erasing Data AugmentationCode2
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksCode1
Modelling Observation Correlations for Active Exploration and Robust Object Detection—0
Show:102550
← PrevPage 4 of 4Next →

No leaderboard results yet.