AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

ViTAS: Vision Transformer Architecture Search

Xiu Su, Shan You, Jiyang Xie, Mingkai Zheng, Fei Wang, Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu

ECCV 2022 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS

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
add cyclic weight sharing instead of ordinal sharing (ablation)ViTAS superformer · ImageNet-1k (Twins space, 1.4G)top-1 accuracy: 77.2 -> 77.9Improved
add cyclic weight sharing instead of bilateral sharing (ablation)ViTAS superformer · ImageNet-1k (Twins space, 1.4G)top-1 accuracy: 77.6 -> 77.9Improved
add weak augmentation to superformer training with cyclic sharing (ablation)ViTAS · ImageNet-1k (Twins space, 1.4G)top-1 accuracy: 77.9 -> 79.4Improved
add weak augmentation to ordinal sharing (ablation)AutoSlim-style ordinal superformer · ImageNet-1k (Twins space, 1.4G)top-1 accuracy: 77.2 -> 78.1Improved
add weak augmentation to bilateral sharing (ablation)BCNet-style bilateral superformer · ImageNet-1k (Twins space, 1.4G)top-1 accuracy: 77.6 -> 78.5Improved
progressively remove augmentation and regularization (RandAug, Mixup, CutMix, jitter, erasing, stoch depth, repeated aug, weight decay) from superformer (ablation)ViTAS superformer · ImageNet-1k search (Twins 1.4G)search accuracy: 59.4% -> 67.7%Improved
progressively remove augmentation and regularization from superformer (ablation)ViTAS superformer · ImageNet-1k retraining (Twins 1.4G)retrain top-1: 77.9% -> 79.4%Improved
add identity shifting to the superformer (ablation)ViTAS superformer · ImageNet-100final training loss: 2.4 -> 1.5Improved
add identity shifting; retrain searched architecture from scratch (ablation)ViTAS · ImageNet-100accuracy: 88.3% -> 90.4%Improved
search with private class tokens (ablation)ViTAS-DeiT-A · ImageNet-1k (DeiT space)top-1 accuracy: 75.1 -> 75.6Improved
search with private class tokens (ablation)ViTAS-DeiT-B · ImageNet-1k (DeiT space)top-1 accuracy: 79.9 -> 80.2Improved
use cyclic weight sharing in ResNet50 dimension search instead of bilateral (BCNet) (ablation)ResNet50 search · ImageNet-1k (1.4G)top-1 accuracy: 75.4 -> 75.8Improved

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