Going deeper with Image Transformers
read the original abstract
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
TFM-Retouche is an architecture-agnostic input-space residual adapter that improves tabular foundation model accuracy on 51 datasets by learning input corrections through the frozen backbone, with an identity guard to...
-
BEiT: BERT Pre-Training of Image Transformers
BEiT pre-trains vision transformers via masked image modeling on visual tokens and reaches 83.2% ImageNet top-1 accuracy for the base model and 86.3% for the large model using only ImageNet-1K data.
-
Graph Set Transformer
GST interleaves local graph feature propagation and set-level contextual modeling via gating, outperforming separate GNN+SetTransformer baselines on synthetic set-conditional reasoning and real benchmarks in chemistry...
-
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
TFM-Retouche is an input-space residual adapter that lifts TabICLv2 performance by 56 Elo points on 51 tabular datasets while remaining architecture-agnostic and computationally light.
-
Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers
TaperNorm gradually removes internal normalization in pre-norm transformers via learned gates that reach zero, revealing final norm as a scale anchor and enabling up to 1.18x faster KV-cached decoding with small loss ...
-
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
MobileViT is a lightweight vision transformer that reports 78.4% top-1 accuracy on ImageNet-1k with ~6M parameters, outperforming MobileNetv3 by 3.2% and DeIT by 6.2% at similar size, plus gains on MS-COCO detection.
-
Review Residuals: Update-Conditioned Residual Gating for Transformers
Review Residuals add an update-conditioned gate to transformer residual connections, yielding depth-stable training and performance gains that emerge and grow with model size from 590M parameters upward.
-
Attention Residuals
Attention Residuals replaces fixed residual summation with input-dependent softmax attention over preceding layers, and a blocked variant is shown to improve uniformity and downstream performance in a 48B-parameter mo...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.