Zero-shot neural decoding of visual categories withoutprior exemplars
O'Connell, T.; Chun, M. M.; Kreiman, G.
Show abstract
Decoding information from neural responses in visual cortex demonstrates interpolation across repetitions or exemplars. Is it possible to decode novel categories from neural activity without any prior training on activity from those categories? We built zero-shot neural decoders by mapping responses from macaque inferior temporal cortex onto a deep neural network. The resulting models correctly interpreted responses to novel categories, even extrapolating from a single category.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Increasing neural network robustness improves match to macaque V1 eigenspectrum, spatial frequency preference and predictivity 95%
- Recurrent neural networks can explain flexible trading of speed and accuracy in biological vision 95%
- The representational hierarchy in human and artificial visual systems in the presence of object-scene regularities 95%
Similar papers in this journal
- Brain-Guided Convolutional Neural Networks Reveal Task-Specific Representations in Scene Processing 95%
- Orthogonal Representations of Object Shape and Category in Deep Convolutional Neural Networks and Human Visual Cortex 93%
- DAMM for the detection and tracking of multiple animals within complex social and environmental settings 93%
Similar papers in this journal
Similar papers in this journal
- Modulatory feedback determines attentional object segmentation in a model of the ventral stream 93%
- Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images 93%
- Small hand-designed convolutional neural networks outperform transfer learning in automated cell shape detection in confluent tissues 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.