GLIPv2: Unifying Localization and Vision-Language Understanding · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2206.05836/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTGLIPv2: Unifying Localization and Vision-Language Understanding — mentioned by drothlishttps://news.ycombinator.com/item?id=35230200urn:hackerpapers:mention:2206.05836:35230200Mon, 20 Mar 2023 11:50:19 GMT<p>According to the ViperGPT paper their &quot;ImagePatch.find()&quot; uses GLIP. According to the GLIP paper,† accuracy on a test-set not seen during training is around 60% so... neat demos but whether it&#x27;ll be reliable enough depends on your application. † https://arxiv.org/abs/2206.05836</p><p><a href="https://hackerpaper.kaipfister.de/p/2206.05836/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV