
-
Paint by Word
We investigate the problem of zero-shot semantic image painting. Instead...
read it
-
Understanding the Role of Individual Units in a Deep Neural Network
Deep neural networks excel at finding hierarchical representations that ...
read it
-
What makes fake images detectable? Understanding properties that generalize
The quality of image generation and manipulation is reaching impressive ...
read it
-
Rewriting a Deep Generative Model
A deep generative model such as a GAN learns to model a rich set of sema...
read it
-
Diverse Image Generation via Self-Conditioned GANs
We introduce a simple but effective unsupervised method for generating r...
read it
-
Semantic Photo Manipulation with a Generative Image Prior
Despite the recent success of GANs in synthesizing images conditioned on...
read it
-
Seeing What a GAN Cannot Generate
Despite the success of Generative Adversarial Networks (GANs), mode coll...
read it
-
Dissecting Pruned Neural Networks
Pruning is a standard technique for removing unnecessary structure from ...
read it
-
Visualizing and Understanding Generative Adversarial Networks (Extended Abstract)
Generative Adversarial Networks (GANs) have achieved impressive results ...
read it
-
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
Generative Adversarial Networks (GANs) have recently achieved impressive...
read it
-
Revisiting the Importance of Individual Units in CNNs via Ablation
We revisit the importance of the individual units in Convolutional Neura...
read it
-
Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning
There has recently been a surge of work in explanatory artificial intell...
read it
-
Interpreting Deep Visual Representations via Network Dissection
The success of recent deep convolutional neural networks (CNNs) depends ...
read it
-
Learnable Programming: Blocks and Beyond
Blocks-based programming has become the lingua franca for introductory c...
read it
-
Network Dissection: Quantifying Interpretability of Deep Visual Representations
We propose a general framework called Network Dissection for quantifying...
read it