CoChat

Controlling explanatory heatmap resolution and semantics via decomposition depth

Open access
Bach, Sebastian, Binder, Alexander, Muller, Klaus-Robert, Samek, Wojciech · 2016 · 2016 IEEE International Conference on Image Processing (ICIP)
Cited by 19

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Abstract

We present an application of the Layer-wise Relevance Propagation (LRP) algorithm to state of the art deep convolutional neural networks and Fisher Vector classifiers to compare the image perception and prediction strategies of both classifiers with the use of visualized heatmaps. Layer-wise Relevance Propagation (LRP) is a method to compute scores for individual components of an input image, denoting their contribution to the prediction of the classifier for one particular test point. We demonstrate the impact of different choices of decomposition cut-off points during the LRP-process, controlling the resolution and semantics of the heatmap on test images from the PASCAL VOC 2007 test data set.

Overview

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

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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

Integrity signals

Registry

Crossref · 10.1109/icip.2016.7532763

Cites

6 of 6 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.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

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 6 references

Research works printed but not linked: 9

  1. 10.1080/14786440109462720 · DOI · Paper page
  2. 10.1145/1873951.1874249 · DOI · Paper page
  3. 10.1145/2647868.2654889 · DOI · Paper page
  4. liu, 2012, What has my classifier learned? visualizing the classification rules of bag-of-feature model by support region detection, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3586
  5. 10.1371/journal.pone.0130140 · DOI · Paper page
  6. 10.1007/s11263-011-0443-1 · DOI
  7. bach, 2016, Analyzing classifiers: Fisher vectors and deep neural networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  8. simonyan, 2014, Deep inside convolutional networks: Visualising image classification models and saliency maps, ICLR Workshop
  9. zeiler, 2014, Visualizing and understanding convolutional networks, ECCV, 818

Cited by

See all 19

Metadata

Authors
Bach, S., Binder, A., Muller, K.-R., & Samek, W.
Venue
2016 IEEE International Conference on Image Processing (ICIP)
Publisher
IEEE
Published
2016-09
Pages
2271-2275
ISSN
1522-4880 (ISSN-L)
OpenAlex
W2306190168
Cited by
19
References
6
FWCI
0.91
Type
conference paper
Language
en
Open access
green

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: Controlling explanatory heatmap resolution and semantics via decomposition depth. https://app.cochat.ai/papers/10.1109/icip.2016.7532763
The paper
Bach, S., Binder, A., Muller, K.-R., & Samek, W. (2016). Controlling explanatory heatmap resolution and semantics via decomposition depth. 2016 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip.2016.7532763

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.