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 )

Libraries

Use these libraries to find Robust Object Detection models and implementations

ConstScene: Dataset and Model for Advancing Robust Semantic Segmentation in Construction Environments

robustinsight/constscene 27 Dec 2023

The increasing demand for autonomous machines in construction environments necessitates the development of robust object detection algorithms that can perform effectively across various weather and environmental conditions.

3
27 Dec 2023

Object-Aware Domain Generalization for Object Detection

WoojuLee24/OA-DG 19 Dec 2023

To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection.

33
19 Dec 2023

DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors

daeunfullgrace/dyra 28 Nov 2023

This paper introduces DyRA, a dynamic resolution adjustment network providing an image-specific scale factor for existing detectors.

5
28 Nov 2023

On the Robustness of Object Detection Models in Aerial Images

hehaodong530/dota-c 29 Aug 2023

The robustness of object detection models is a major concern when applied to real-world scenarios.

20
29 Aug 2023

Improved Region Proposal Network for Enhanced Few-Shot Object Detection

zshanggu/htrpn 15 Aug 2023

Specifically, we develop a hierarchical ternary classification region proposal network (HTRPN) to localize the potential unlabeled novel objects and assign them new objectness labels to distinguish these objects from the base training dataset classes.

16
15 Aug 2023

COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts

alibaba/easyrobust ICCV 2023

To give a more comprehensive robustness assessment, we introduce COCO-O(ut-of-distribution), a test dataset based on COCO with 6 types of natural distribution shifts.

302
24 Jul 2023

Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

visionlearninggroup/mind_back 26 Mar 2023

We propose to use Relative Gradient Norm (RGN) as a way to measure the vulnerability of a backbone to feature distortion, and show that high RGN is indeed correlated with lower OOD performance.

3
26 Mar 2023

Identification of Novel Classes for Improving Few-Shot Object Detection

zshanggu/htrpn 18 Mar 2023

Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception ability of the object detection model for large objects.

16
18 Mar 2023

Towards Scene Understanding for Autonomous Operations on Airport Aprons

apronai/apron-dataset Asian Conference on Computer Vision (ACCV) Workshops 2022

The results are quite promising for future applications and provide essential insights regarding the selection of aggregation strategies as well as current potentials and limitations of similar approaches in this research domain.

8
04 Dec 2022

Robust Object Detection in Remote Sensing Imagery with Noisy and Sparse Geo-Annotations (Full Version)

mxbh/robust_object_detection 24 Oct 2022

In order to create the necessary training annotations for object detectors, imagery can be georeferenced and combined with data from other sources, such as points of interest localized by GPS sensors.

28
24 Oct 2022