OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1312.6229/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks — mentioned by karpathyhttps://news.ycombinator.com/item?id=8525597urn:hackerpapers:mention:1312.6229:8525597Wed, 29 Oct 2014 04:45:11 GMT<p>The fact that RCNN does a wasteful and naive feature re-computation for every object-like region in the image is well-known in the community, and there are several papers addressing the shortcoming in very similar ways (i.e. precomputing pool-5 features for the entire image once, instead of recomputing from scratch for each individual box). The Overfeat detecion paper [0] was among the first ones, for example, and it achieved similar speedups as discussed in the article, but the accuracy is not as great for various other reasons. This article makes it sound like Spatial Pyramid Pooling is…</p><p><a href="https://hackerpaper.kaipfister.de/p/1312.6229/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV