Example the bias of CNNs to exploit high-frequency components in image might be good for CV benchmark performance, if you feed the same representations to a robotic policy then it is clearly sub-optimal, shape is more important here ....
Comments
Log in with your Bluesky account to leave a comment
Fine-tuning is a fine game when you know the test-distribution and I believe that active fine-tuning at test time will be on the cards. But none can truly generalize out-of-distribution. You either collect a hell lot of data or stumble upon an architecture that truly generalizes of OOD for your task
Comments