https://hackerpaper.kaipfister.de/p/1905.02244/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=30890744urn:hackerpapers:mention:1905.02244:30890744Sat, 02 Apr 2022 18:57:18 GMT<p>https://arxiv.org/abs/1905.02244v5</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.02244/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=24127929urn:hackerpapers:mention:1905.02244:24127929Wed, 12 Aug 2020 02:03:52 GMT<p>Yeah, so this work was done at Nvidia as part of a larger project that required semantic segmentation. But although MobileNetV3 has state-of-the-art performance on many image tasks like classification, detection, and segmentation - there are no public implementations of MobileNetV3 for semantic segmentation with good accuracy. Looking through implementations on GitHub, we saw accuracies of 40-50% mIoU, which is frankly unacceptable given that the paper claims 72.6% mIoU. So over the past few months at Nvidia, I worked with some researchers from ADLR (https://nv-adlr.github.io/) to implement…</p><p><a href="https://hackerpaper.kaipfister.de/p/1905.02244/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV