REVIEW 2 cited by
Universal representations:The missing link between faces, text, planktons, and cat breeds
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
With the advent of large labelled datasets and high-capacity models, the performance of machine vision systems has been improving rapidly. However, the technology has still major limitations, starting from the fact that different vision problems are still solved by different models, trained from scratch or fine-tuned on the target data. The human visual system, in stark contrast, learns a universal representation for vision in the early life of an individual. This representation works well for an enormous variety of vision problems, with little or no change, with the major advantage of requiring little training data to solve any of them. In this paper we investigate whether neural networks may work as universal representations by studying their capacity in relation to the “size†of a large combination of vision problems. We do so by showing that a single neural network can learn simultaneously several very different visual domains (from sketches to planktons and MNIST digits) as well as, or better than, a number of specialized networks. However, we also show that this requires to carefully normalize the information in the network, by using domain-specific scaling factors or, more generically, by using an instance normalization layer.
Forward citations
Cited by 2 Pith papers
-
Meta-Learning with Warped Gradient Descent
WarpGrad meta-learns interleaved warp layers that precondition gradients, delivering consistent accuracy gains in few-shot and multi-shot learning, plus promising results in reinforcement and continual learning.
-
3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation
A single separable-convolution 3D U-Net trained jointly on five segmentation datasets reaches mean Dice within about one point of per-task models while using around 1% of the parameters.
Discussion (0). Continue with ORCID to comment.