Browse SoTA > Computer Vision > Object Detection > Robust Object Detection

Robust Object Detection

6 papers with code · Computer Vision
Subtask of 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 )

Leaderboards

Greatest papers with code

Domain Adaptive Faster R-CNN for Object Detection in the Wild

CVPR 2018 yuhuayc/da-faster-rcnn

The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.

REGION PROPOSAL ROBUST OBJECT DETECTION UNSUPERVISED DOMAIN ADAPTATION

Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming

ICLR 2020 bethgelab/imagecorruptions

The ability to detect objects regardless of image distortions or weather conditions is crucial for real-world applications of deep learning like autonomous driving.

AUTONOMOUS DRIVING DATA AUGMENTATION INSTANCE SEGMENTATION ROBUST OBJECT DETECTION

Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approach

ICCV 2019 TAMU-VITA/UAV-NDFT

Object detection from images captured by Unmanned Aerial Vehicles (UAVs) is becoming increasingly useful.

ROBUST OBJECT DETECTION

A Robust Learning Approach to Domain Adaptive Object Detection

ICCV 2019 mkhodabandeh/robust_domain_adaptation

To adapt to the domain shift, the model is trained on the target domain using a set of noisy object bounding boxes that are obtained by a detection model trained only in the source domain.

DOMAIN ADAPTATION ROBUST OBJECT DETECTION SELF-DRIVING CARS

Soft Sampling for Robust Object Detection

18 Jun 2018starimpact/arm_SNIPER

Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset.

ROBUST OBJECT DETECTION

TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems

9 Apr 2020git-disl/TOG

The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems.

AUTONOMOUS DRIVING OBJECT RECOGNITION REAL-TIME OBJECT DETECTION ROBUST OBJECT DETECTION