Predictive Inequity in Object Detection · HackerPapers discussions

Predictive Inequity in Object Detection — mentioned by klyrs

Fri, 30 Aug 2019 16:21:52 GMT

That progress is not made all at once. It's a problem with a known fix; but just like buffer overflows, a known fix doesn't always get implemented everywhere. For example, this 2019 paper: https://arxiv.org/pdf/1902.11097.pdf

Paper and discussion history. A mention is not an endorsement.

Predictive Inequity in Object Detection — mentioned by js2

Sun, 14 Apr 2019 21:15:10 GMT

The story doesn’t cite the specific paper. But I think I submitted the paper last month: “Predictive Inequality in Object Detection” https://news.ycombinator.com/item?id=19379827 https://arxiv.org/abs/1902.11097 I’m not denying the conclusion of the paper, but it does have a lot of limitations. Also, Tesla notwithstanding, isn’t object detection primarily done via lidar?

Paper and discussion history. A mention is not an endorsement.

Predictive Inequity in Object Detection — HN submission

Wed, 13 Mar 2019 15:48:23 GMT

Predictive Inequity in Object Detection

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Predictive Inequity in Object Detection — mentioned by uberman

Thu, 07 Mar 2019 21:01:34 GMT

The article is very thin on details. It serves mostly to point to an abstract for a research paper : https://arxiv.org/abs/1902.11097 The abstract is unfortunately also very light on detail. It appears as though the researchers trained a number of classification systems using static images of pedestrians noting skin color and observed that darker skin tones resulted in mis-classification more often than for lighter skin tones. The original article then sensationalizes this suggesting that means self driving cars are more likely to kill darker skinned people. I believe there are a number of…

Paper and discussion history. A mention is not an endorsement.

Predictive Inequity in Object Detection — mentioned by czr

Thu, 07 Mar 2019 01:18:24 GMT

The headline here is not a good description of the actual paper (https://arxiv.org/pdf/1902.11097.pdf). The difference in average precision in bounding boxes between the LS (light skin) and DS (dark skin) observed by the researchers was around 1-10%. Not "can't recognize". Notably, people with dark skin were underrepresented in the dataset that the researchers used. When they compensated for the dataset imbalance by reweighting examples, the issue was resolved. Notably, the research itself is on publicly-available object detection systems, not any actual autonomous vehicles. Any company…

Paper and discussion history. A mention is not an endorsement.