Robust Object Detection
42 papers with code • 5 benchmarks • 9 datasets
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 )
Benchmarks
These leaderboards are used to track progress in Robust Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Robust Object Detection models and implementationsDatasets
MS COCO
Cityscapes
PASCAL VOC 2007
DWD
RF100
Separated COCO
Aircraft Context Dataset
Occluded COCO
Apron Dataset
Most implemented papers
TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems
git-disl/TOG
•
•
The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems.
RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
shachoi/RobustNet
•
•
CVPR 2021
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving.
SimROD: A Simple Adaptation Method for Robust Object Detection
This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD).
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
helioszhao/shade
•
•
Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning.
DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors
This paper introduces DyRA, a dynamic resolution adjustment network providing an image-specific scale factor for existing detectors.
Soft Sampling for Robust Object Detection
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.
A Robust Learning Approach to Domain Adaptive Object Detection
Gabriel-Macias/robust_frcnn
•
•
ICCV 2019
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.
Switchable Whitening for Deep Representation Learning
XingangPan/Switchable-Whitening
•
•
ICCV 2019
Unlike existing works that design normalization techniques for specific tasks, we propose Switchable Whitening (SW), which provides a general form unifying different whitening methods as well as standardization methods.
Refined Plane Segmentation for Cuboid-Shaped Objects by Leveraging Edge Detection
Our approach is motivated by logistics, where this assumption is valid and refined planes can be used to perform robust object detection without the need for supervised learning.
Vehicle Position Estimation with Aerial Imagery from Unmanned Aerial Vehicles
fkthi/OpenTrafficMonitoringPlus
•
•
A robust object detection is crucial for reliable results, hence the state-of-the-art deep neural network Mask-RCNN is applied for that purpose.
