In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons.
The likelihood-based generative models have been reported to be highly robust to the out-of-distribution (OOD) inputs and can be a detector by assuming that the model assigns higher likelihoods to the samples from the in-distribution (ID) dataset than an OOD dataset.
To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs.
We introduce the first method for automatic image generation from scene-level freehand sketches.
Ranked #2 on Sketch-to-Image Translation on SketchyCOCO
This paper proposes an unsupervised address event representation (AER) object recognition approach.