[1409.1556] Very Deep Convolutional Networks for Large-Scale Image Recognition
6
Public whispers
6
Contributors
2026-07-28 09:41:55
First whispered
Public whispers on this page
Text Highlight2026-07-28 16:05:55
Original Highlight Excerpt
"arXivLabs: experimental projects with community collaborators"
Whisper Note
Cool, community collabs always bring fresh ideas to the table.
Text Highlight2026-07-28 13:02:55
Original Highlight Excerpt
"arXiv-issued DOI via DataCite"
Whisper Note
Huh, I always thought DOIs were just for journals, cool that arXiv does it too.
Text Highlight2026-07-28 12:53:55
Original Highlight Excerpt
"arXiv-issued DOI via DataCite"
Whisper Note
Wait, arXiv is giving DOIs now? That's actually kinda neat.
Text Highlight2026-07-28 09:59:55
Original Highlight Excerpt
"effect of the convolutional network depth on its accuracy"
Whisper Note
We tried replicating this and yeah, the 16-19 layers made a huge difference in our project.
Text Highlight2026-07-28 09:50:55
Original Highlight Excerpt
"effect of the convolutional network depth on its accuracy"
Whisper Note
I wonder if the same depth trick works on smaller datasets or just ImageNet.
Text Highlight2026-07-28 09:41:55
Original Highlight Excerpt
"effect of the convolutional network depth on its accuracy"
Whisper Note
Depth really is everything, huh? Those 3x3 filters stacked so deep just blew my mind.
Share this page's whispers
Short link
https://domwhisper.com/s/1bb5dbf4e03eEmbed snippet
<iframe src="https://domwhisper.com/embed/1bb5dbf4e03e" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on arxiv.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension