Papers › Systematic evaluation of CNN advances on the ImageNet

Systematic evaluation of CNN advances on the ImageNet

7 Jun 2016arXiv:1606.02228archive 2025-07-28

Dmytro Mishkin, Nikolay Sergievskiy, Jiri Matas

The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem. The evalution tests the influence of the following choices of the architecture: non-linearity (ReLU, ELU, maxout, compatibility with batch normalization), pooling variants (stochastic, max, average, mixed), network width, classifier design (convolutional, fully-connected, SPP), image pre-processing, and of learning parameters: learning rate, batch size, cleanliness of the data, etc. The performance gains of the proposed modifications are first tested individually and then in combination. The sum of individual gains is bigger than the observed improvement when all modifications are introduced, but the "deficit" is small suggesting independence of their benefits. We show that the use of 128x128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets. The results are obtained an order of magnitude faster than with the standard 224 pixel images.

PaperPDFCode

Code

ducha-aiki/caffenet-benchmark officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Categorization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionDense ConnectionsDropoutELUMax PoolingReLUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections