SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.10589 · 2018

Diverse feature visualizations reveal invariances in early layers of deep neural networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
sacadena/diverse_feature_vis canonical 6 of 7
FunctionStatusWhere it lives
concat_elu Ran sacadena/diverse_feature_vis/pixel-cnn/pixel_cnn_pp/nn.py
code served (permissive licence) · get_code("919f423798c6a32a")
conv_filter_tile Ran sacadena/diverse_feature_vis/pixel-cnn/utils/plotting.py
code served (permissive licence) · get_code("0cb6bf5e8d04ced1")
deprocess_image Ran sacadena/diverse_feature_vis/diverse_vis_functions.py
code served (permissive licence) · get_code("e5e8e8a0eb923ad9")
img_stretch Ran sacadena/diverse_feature_vis/pixel-cnn/utils/plotting.py
code served (permissive licence) · get_code("6b93fbdaf0e2b9e2")
img_tile Ran sacadena/diverse_feature_vis/pixel-cnn/utils/plotting.py
code served (permissive licence) · get_code("6c57db0a5a8111ab")
int_shape Ran sacadena/diverse_feature_vis/pixel-cnn/pixel_cnn_pp/nn.py
code served (permissive licence) · get_code("3ba6aec873833b39")
log_sum_exp Not yet run sacadena/diverse_feature_vis/pixel-cnn/pixel_cnn_pp/nn.py
code served (permissive licence) · get_code("ba937f5383eb9016")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visualizing features in deep neural networks (DNNs) can help understanding their computations. Many previous studies aimed to visualize the selectivity of individual units by finding meaningful images that maximize their activation. However, comparably little attention has been paid to visualizing to what image transformations units in DNNs are invariant. Here we propose a method to discover invariances in the responses of hidden layer units of deep neural networks. Our approach is based on simultaneously searching for a batch of images that strongly activate a unit while at the same time being as distinct from each other as possible. We find that even early convolutional layers in VGG-19 exhibit various forms of response invariance: near-perfect phase invariance in some units and invariance to local diffeomorphic transformations in others. At the same time, we uncover representational differences with ResNet-50 in its corresponding layers. We conclude that invariance transformations are a major computational component learned by DNNs and we provide a systematic method to study them.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1807.10589")
get_code_for_paper("1807.10589")
have("1807.10589")

Connect an agent — have() is free.