Perceptual Regularization: Visualizing and Learning Generalizable Representations
A deployable machine learning model relies on a good representation. Two desirable criteria of a good representation are to be understandable, and to generalize to new tasks. We propose a technique termed perceptual regularization that enables both visualization of the latent representation and control over the generality of the learned representation. In particular our method provides a direct visualization of the effect that adversarial attacks have on the internal representation of a deep network. By visualizing the learned representation, we are also able to understand the attention of a model, obtaining visual evidence that supervised networks learn task-specific representations. We show models trained with perceptual regularization learn transferrable features, achieving significantly higher accuracy in unseen tasks compared to standard supervised learning and multi-task methods.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Perceptually Optimized Color Selection for Visualization
We propose an approach, called the Equilibrium Distribution Model (EDM), for automatically selecting colors with optimum perceptual contrast for scientific visualization. Given any number of features that need to be emph…
Learning compact generalizable neural representations supporting perceptual grouping
Work at the intersection of vision science and deep learning is starting to explore the efficacy of deep convolutional networks (DCNs) and recurrent networks in solving perceptual grouping problems that underlie primate …
PathfinderTransfer LearningGraph Spectral Regularization For Neural Network Interpretability
Deep neural networks can learn meaningful representations of data. However, these representations are hard to interpret. For example, visualizing a latent layer is generally only possible for at most three dimensions. Ne…
Using Human Perception to Regularize Transfer Learning
Recent trends in the machine learning community show that models with fidelity toward human perceptual measurements perform strongly on vision tasks. Likewise, human behavioral measurements have been used to regularize m…
Transfer LearningSupervise Thyself: Examining Self-Supervised Representations in Interactive Environments
Self-supervised methods, wherein an agent learns representations solely by observing the results of its actions, become crucial in environments which do not provide a dense reward signal or have labels. In most cases, su…
Imitation Learning