ImageNet, every mention

mentionsepisodesper episode tap a year for its mentions

Verbatim, from the transcripts: the passages where ImageNet comes up

loading…

▶ 12:12 Francois Chaubard If I take a batch of like ImageNet or CIFR-Ten, and I forward pass through the model,

▶ 8:13 Diana Hu Is it fair to say that the data set that was created from embodiment X is similar to the scale of an impact that ImageNet did for Vision because it was huge and it was the first large data set across multiple hardware, huge collaboration. 3 times in the scene

▶ 15:32 François Chollet And, uh, my, my mental model for that was ImageNet. 2 times in the scene

▶ 0:53 Diana Hu One of the first projects that you created was ImageNet in 2009, 16 years ago. 3 times in the scene
▶ 4:27 Dr. Fei-Fei Li And that was why ImageNet was conceived and, uh, came to life.
▶ 5:45 Dr. Fei-Fei Li So that was what we call the ImageNet challenge. 4 times in the scene
▶ 8:36 Diana Hu ImageNet was really the seat to solve the concept of object recognition. 2 times in the scene
▶ 13:29 Dr. Fei-Fei Li While computer vision, as a computer vision scientist, we're seeing this incredible growth, you know, from image net to image captioning to image generation using some of the diffusion techniques.
▶ 29:35 Diana Hu Like, Andrew Kaparthi, Jim Phan, who's at NVIDIA, Jia Deng, who's your, uh, co-author for ImageNet, they all went on to have these incredible careers.
▶ 39:12 unnamed speaker You mentioned that open sourcing was a big part of the growth from ImageNet.
▶ 41:06 unnamed speaker So you called very well the, um, shift in machine learning towards data-driven methods with ImageNet.

▶ 14:10 Craig Cannon Well, it was like the image net thing from like almost 10 years ago.

▶ 32:05 Wojciech Zaremba So I would say the most stunning, um, were so-called, um, image net, uh, results. 4 times in the scene

Turn any episode into a week of clips.