Deep Learning
Achieving Rotational Invariance with Bessel-Convolutional Neural Networks
As of today, Convolutional Neural Networks (CNN) are one of the most powerful tools for image analysis. They achieve, thanks to convolutions, an invariance with respect to translations.
perform in-context learning, it is unclear what the relationship is between tasks on which this succeeds and what is present in the training data. To make progress
In-context learning refers to the ability of a model to condition on a prompt sequence consisting of in-context examples (input-output pairs from some task) along with a new query input, and generate the corresponding output.
DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations Ximeng Sun 1 Ping Hu1 Kate Saenko 1,2 1 Boston University, 2
Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task that has many real-world applications.
Your head is there to move you around: Goal-driven models of the primate dorsal pathway
Although this approach has been similarly fruitful in other domains (e.g., audition [
