CoChat

Refining activation downsampling with SoftPool

Open access
Stergiou, Alexandros, Poppe, Ronald, Kalliatakis, Grigorios · 2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Cited by 271

The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.

Abstract

Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of the pooling operation is the minimization of information loss, with respect to the initial activation maps, without a significant impact on the computation and memory overhead. To meet these requirements, we propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. Through experiments across a range of architectures and pooling methods, we demonstrate that SoftPool can retain more information in the reduced activation maps. This refined downsampling leads to improvements in a CNN’s classification accuracy. Experiments with pooling layer substitutions on ImageNet1K show an increase in accuracy over both original architectures and other pooling methods. We also test SoftPool on video datasets for action recognition. Again, through the direct replacement of pooling layers, we observe consistent performance improvements while computational loads and memory requirements remain limited1.

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/iccv48922.2021.01019

Cites

44 of 44 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

Research works printed but not linked: 11

  1. boureau, 2010, A theoretical analysis of feature pooling in visual recognition, International Conference on Machine Learning (ICML), 111
  2. lee, 2016, Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree, Artificial Intelligence and Statistics, 464
  3. zhao, 2021, LiftPool: Bidirectional convnet pooling, International Conference on Learning Representations (ICLR)
  4. estrach, 2014, Signal recovery from pooling representations, International Conference on Machine Learning (ICML), 307
  5. ghadiyaram, 2019, Largescale weakly-supervised pre-training for video action recognition, Conference on Computer Vision and Pattern Recognition (CVPR)
  6. chen, 2017, Dual path networks, Advances in Neural IInformation Processing Systems, 4467
  7. chen, 2018, Multi-fiber networks for video recognition, European Conference on Computer Vision (ECCV), 352
  8. deliège, 2019, Ordinal pooling, British Machine Vision Conference
  9. csurka, 2004, Visual categorization with bags of keypoints, European Conference on Computer Vision Workshop, 1
  10. zeiler, 2013, Stochastic pooling for regularization of deep convolutional neural networks, International Conference on Learning Representations (ICLR)
  11. yang, 2009, Linear spatial pyramid matching using sparse coding for image classification, Conference on Computer Vision and Pattern Recognition (CVPR), 1794

Cited by

See all 271

Metadata

Authors
Stergiou, A., Poppe, R., & Kalliatakis, G.
Venue
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2021-10
Pages
10337-10346
OpenAlex
W3119356360
Cited by
271
References
44
FWCI
17.15
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

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.