pith. sign in

arxiv: 2211.11943 · v1 · pith:EC7AYF2Rnew · submitted 2022-11-22 · 💻 cs.CV

Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition

classification 💻 cs.CV
keywords convolutionalconv2formerconvnetssimpledesignmodulationrecognitiontransformers
0
0 comments X
read the original abstract

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent convolutional neural networks ConvNets) and Vision Transformers, we propose to simplify the self-attention by leveraging a convolutional modulation operation. We show that such a simple approach can better take advantage of the large kernels (>=7x7) nested in convolutional layers. We build a family of hierarchical ConvNets using the proposed convolutional modulation, termed Conv2Former. Our network is simple and easy to follow. Experiments show that our Conv2Former outperforms existent popular ConvNets and vision Transformers, like Swin Transformer and ConvNeXt in all ImageNet classification, COCO object detection and ADE20k semantic segmentation.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

    cs.AI 2026-04 unverdicted novelty 6.0

    ClawEnvKit automates generation of diverse verified environments for claw-like agents from natural language, producing the Auto-ClawEval benchmark of 1,040 environments that matches human-curated quality at 13,800x lo...

  2. Advancing Vision Transformer with Enhanced Spatial Priors

    cs.CV 2026-04 unverdicted novelty 4.0

    EVT improves Vision Transformers by using Euclidean distance decay for spatial priors and simpler grouping, achieving 86.6% top-1 accuracy on ImageNet-1k.

  3. ClawEnvKit: Automatic Environment Generation for Claw-Like Agents

    cs.AI 2026-04 conditional novelty 4.0

    EVT improves the RMT backbone by using Euclidean-distance attention decay and 1D token grouping, achieving 86.6% top-1 on ImageNet-1K at 384×384 resolution.