DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1907.11503/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients — mentioned by cmahttps://news.ycombinator.com/item?id=43375324urn:hackerpapers:mention:1907.11503:43375324Sat, 15 Mar 2025 21:38:28 GMT<p>There is definitely work out there that deals directly in dct blocks from jpeg: https://arxiv.org/abs/1907.11503 https://arxiv.org/abs/2308.09110 With generative ai they tend to have a learned compressed representation instead (VAE)</p><p><a href="https://hackerpaper.kaipfister.de/p/1907.11503/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV