AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

BATS: Binary ArchitecTure Search

Adrian Bulat, Brais Martinez, Georgios Tzimiropoulos

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 68 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use binary-oriented grouped-convolution search space instead of DARTS search space (ablation)BATS · CIFAR-10Top-1 accuracy: 51.0±7.5 -> 93.7±0.6Improved
lower softmax temperature from 1 to 0.2 (ablation)BATS search · CIFAR-10Top-1 accuracy: 86.0 -> 93.7Improved
lower temperature from 0.5 to 0.2 (ablation)BATS search · CIFAR-10Top-1 accuracy: 92.1 -> 93.7Improved
lower temperature from 0.2 to 0.05 (ablation)BATS search · CIFAR-10Top-1 accuracy: 93.7 -> 93.3Hurt
search with binary activations and real weights instead of real search then binarize (ablation)BATS search · CIFAR-10Top-1 accuracy: 88.4±0.8 -> 93.7±0.6Improved
binarize both weights and activations during search instead of only activations (ablation)BATS search · CIFAR-10Top-1 accuracy: 93.7±0.6 -> 84.6±1.7Hurt
keep activations real and binarize weights during search instead of binarizing activations (ablation)BATS search · CIFAR-10Top-1 accuracy: 93.7±0.6 -> 91.1±1.7Hurt
add autoaugment (ablation)BATS · CIFAR-100Test accuracy: 70.7 -> 71.3Improved
add autoaugment (ablation)BATS (large) · CIFAR-10Test accuracy: 95.5 -> 96.1Improved
scale up width and groups of the cells to large (ablation)BATS · CIFAR-100Test accuracy: 70.7 -> 75.7Improved
widen the network 2x (ablation)BATS · ImageNetTop-1 accuracy: 60.4 -> 66.1Improved
use BATS search space and method for real-valued networks (ablation)BATS · CIFAR-10 real-valuedTest error: 2.40 vs 2.50 (P-DARTS)Improved

Later papers that compared with this method

2 later accepted papers report BATS (Small) as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy