Menu

Post image 1
Post image 2
Post image 3
Post image 4
Post image 5
Post image 6
Post image 7
Post image 8
Post image 9
Post image 10
Post image 11
Post image 12
Post image 13
Post image 14
Post image 15
Post image 16
Post image 17
Post image 18
Post image 19
Post image 20
Post image 21
Post image 22
Post image 23
Post image 24
Post image 25
Post image 26
Post image 27
Post image 28
Post image 29
Post image 30
Post image 31
Post image 32
Post image 33
Post image 34
Post image 35
Post image 36
Post image 37
Post image 38
Post image 39
Post image 40
Post image 41
Post image 42
Post image 43
Post image 44
Post image 45
Post image 46
Post image 47
Post image 48
Post image 49
Post image 50
Post image 51
Post image 52
Post image 53
Post image 54
Post image 55
Post image 56
Post image 57
Post image 58
Post image 59
Post image 60
1 / 60
0

Playing with Vision Embeddings

Hacker News·Playing with Vision Embeddings·3 months ago
#23l9mXiN
Reading 0:00
15s threshold

Corn kernels + Triumphal Arch = Kernel Arch Embeddings are, in a sense, the native language of neural networks. They are how networks can encode a rich variety of semantically meaningful representations with just a list of numbers. However, those numbers are frustratingly opaque. You certainly won't be able to make sense of them by reading them one after another. In this post, we try to make sense of one neural network's embeddings. The Model The model we're going to be looking at in this post is DINOv3 ViT-S (Siméoni et al., 2025) . DINOv3 is interesting because it learns to map raw pixels to a rich feature space with very few priors. It doesn't know language, it can't describe what it sees, but it still learns to make sense of images. We won't go into full detail about how DINOv3 was trained, but two things matter for this post: it compresses any image into a single embedding (a list of 384 numbers) and it was trained so that different crops and augmentations of an image will have similar embeddings.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More