Corpus ID: 67856078

Predictive Inequity in Object Detection

@article{Wilson2019PredictiveII,
  title={Predictive Inequity in Object Detection},
  author={Benjamin Wilson and Judy Hoffman and Jamie H. Morgenstern},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.11097}
}
In this work, we investigate whether state-of-the-art object detection systems have equitable predictive performance on pedestrians with different skin tones. This work is motivated by many recent examples of ML and vision systems displaying higher error rates for certain demographic groups than others. We annotate an existing large scale dataset which contains pedestrians, BDD100K, with Fitzpatrick skin tones in ranges [1-3] or [4-6]. We then provide an in-depth comparative analysis of… Expand
A Survey on Bias in Visual Datasets
TLDR
There is no such thing as a bias-free dataset, so scientists and practitioners must become aware of the biases in their datasets and make them explicit, and a checklist that can be used to spot different types of bias during visual dataset collection is proposed. Expand
L ARGE DATASETS : A P YRRHIC WIN FOR COMPUTER VISION ?
In this paper we investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as specific concernsExpand
Understanding and Evaluating Racial Biases in Image Captioning
TLDR
Differences in caption performance, sentiment, and word choice between images of lighter versus darker-skinned people are found to be greater in modern captioning systems compared to older ones, thus leading to concerns that without proper consideration and mitigation these differences will only become increasingly prevalent. Expand
Adversarial Removal of Gender from Deep Image Representations
TLDR
This work provides convincing interpretable visual evidence through an autoencoder-augmented model showing that this approach is performing semantically meaningful removal of gender features, and thus can also be used to remove gender attributes directly from images. Expand
Age and gender bias in pedestrian detection algorithms
TLDR
The age and gender bias in the performance of state-of-the-art pedestrian detection algorithms is characterized and it is shown that all of the 24 top-performing methods of the Caltech Pedestrian Detection Benchmark have higher miss rates on children. Expand
Machines Learn Appearance Bias in Face Recognition
TLDR
A transfer learning model trained on human subjects' first impressions of personality traits in other faces is better at judging a person's dominance based on their face than other traits like trustworthiness or likeability, even for emotionally neutral faces. Expand
Multimodal Machine Learning for Pedestrian Detection
TLDR
This experiment attempts to explore different techniques that can be used to detect pedestrians while minimizing bias, and uses both a YOLO v3 convolutional neural network and K-Means clustering for classifying skin-tones. Expand
Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
TLDR
It is shown that trained models significantly amplify the association of target labels with gender beyond what one would expect from biased datasets, and an adversarial approach is adopted to remove unwanted features corresponding to protected variables from intermediate representations in a deep neural network. Expand
Characterizing Bias in Classifiers using Generative Models
TLDR
This work incorporates a progressive conditional generative model for synthesizing photo-realistic facial images and Bayesian Optimization for an efficient interrogation of independent facial image classification systems and shows how this approach can be used to efficiently characterize racial and gender biases in commercial systems. Expand
Person, Human, Neither: The Dehumanization Potential of Automated Image Tagging
TLDR
This work audits six proprietary image tagging algorithms for their potential to perpetuate dehumanization and highlights the subtle ways in which ITAs may inflict widespread, disparate harm, and emphasizes the importance of considering the social context of the resulting application. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 33 REFERENCES
Pedestrian Detection: An Evaluation of the State of the Art
TLDR
An extensive evaluation of the state of the art in a unified framework of monocular pedestrian detection using sixteen pretrained state-of-the-art detectors across six data sets and proposes a refined per-frame evaluation methodology. Expand
Occluded Pedestrian Detection Through Guided Attention in CNNs
TLDR
A simple and compact method based on the FasterRCNN architecture for occluded pedestrian detection with significant improvement on the heavy occlusion subset, and on CityPersons and on Caltech it outperform the state-of-the-art method by 4pp. Expand
Scale-Aware Fast R-CNN for Pedestrian Detection
TLDR
This paper argues that the issue of large variance in instance scales, which results in undesirable large intracategory variance in features, may severely hurt the performance of modern object instance detection methods, can be substantially alleviated by the divide-and-conquer philosophy. Expand
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of sceneExpand
Is Faster R-CNN Doing Well for Pedestrian Detection?
TLDR
A very simple but effective baseline for pedestrian detection, using an RPN followed by boosted forests on shared, high-resolution convolutional feature maps, presenting competitive accuracy and good speed. Expand
The Pascal Visual Object Classes (VOC) Challenge
TLDR
The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse. Expand
Are we ready for autonomous driving? The KITTI vision benchmark suite
TLDR
The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
The Cityscapes Dataset for Semantic Urban Scene Understanding
TLDR
This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Expand
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
...
1
2
3
4
...