Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 498

The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.

Towards Better Analysis of Deep Convolutional Neural Networks

Open access
Liu, Mengchen, Shi, Jiaxin, Li, Zhen, Li, Chongxuan, Zhu, Jun, Liu, Shixia·2017·IEEE Transactions on Visualization and Computer Graphics

Abstract

Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount of trial-and-error, as there is still no clear understanding of when and why a deep model works. In this paper, we present a visual analytics approach for better understanding, diagnosing, and refining deep CNNs. We formulate a deep CNN as a directed acyclic graph. Based on this formulation, a hybrid visualization is developed to disclose the multiple facets of each neuron and the interactions between them. In particular, we introduce a hierarchical rectangle packing algorithm and a matrix reordering algorithm to show the derived features of a neuron cluster. We also propose a biclustering-based edge bundling method to reduce visual clutter caused by a large number of connections between neurons. We evaluated our method on a set of CNNs and the results are generally favorable.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tvcg.2016.2598831

Cites

55 of 55 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 55 references

Research works printed but not linked: 8

  1. 10.1007/s10479-008-0463-6 · doi:10.1007/s10479-008-0463-6
  2. 10.1137/0110015 · doi:10.1137/0110015
  3. huang, 2012, Optimal rectangle packing: An absolute placement approach, J AIR, 46, 47
  4. 10.1109/TVCG.2015.2392771 · doi:10.1109/tvcg.2015.2392771
  5. 10.1109/TVCG.2015.2467813 · doi:10.1109/tvcg.2015.2467813
  6. 10.1109/TVCG.2014.2346433 · doi:10.1109/tvcg.2014.2346433
  7. erhan, 2009, Visualizing Higher-layer Features of Deep Networks
  8. bergstra, 2010, Theano a CPU and GPU math expression compiler

Cited by

See all 498

Metadata

Authors
Liu, M., Shi, J., Li, Z., Li, C., Zhu, J., & Liu, S.
Venue
IEEE Transactions on Visualization and Computer Graphics
Published
2017-01
Volume
23
Issue
1
Pages
91-100
ISSN
1077-2626 (ISSN-L)
OpenAlex
W2343061342
Cited by
498
References
55
FWCI
31.26
Type
journal article
Language
en
Open access
green
Funders
  • National NSF of China (61672308, 61322308, 61332007)
  • Microsoft Research (FY15-RES-OPP-112)
  • National Basic Research Program (973 Program) of China (2013CB329403)
  • Youth Top-notch Talent Support Program

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Towards Better Analysis of Deep Convolutional Neural Networks. https://app.cochat.ai/papers/10.1109/tvcg.2016.2598831
The paper
Liu, M., Shi, J., Li, Z., Li, C., Zhu, J., & Liu, S. (2017). Towards Better Analysis of Deep Convolutional Neural Networks. IEEE Transactions on Visualization and Computer Graphics. https://doi.org/10.1109/tvcg.2016.2598831

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.