3 papers
cs.CV2018
Unsupervised Discovery of Object Landmarks as Structural Representations
Yuting Zhang, Yijie Guo, Yixin Jin +3
Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way. This pap…
cs.CV2018
Hierarchical Novelty Detection for Visual Object Recognition
Kibok Lee, Kimin Lee, Kyle Min +3
Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes…
stat.ML2017
Towards Understanding the Invertibility of Convolutional Neural Networks
Anna C. Gilbert, Yi Zhang, Kibok Lee +2
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how…