AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

SpatialFormer: Towards Generalizable Vision Transformers with Explicit Spatial Understanding

Han Xiao, Wenzhao Zheng, Sicheng Zuo, Peng Gao, Jie Zhou, Jiwen Lu

ECCV 2024 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 2 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
add adaptive spatial tokens initialized with positional encoding (ablation)SpatialFormer-S · ImageNet-1k val 224top-1 accuracy: 81.3 -> 83.8Improved
increase spatial tokens from 4x4 to 8x8 (ablation)SpatialFormer-S · ImageNet-1k val 224top-1 accuracy: 83.0 -> 83.8Improved
increase spatial tokens from 8x8 to 16x16 (ablation)SpatialFormer-S · ImageNet-1k val 224top-1 accuracy: 83.8 -> 84.1 (FLOPs 4.8G -> 7.0G)Improved
use BCA blocks in more stages instead of self-attention in last two stages (ablation)SpatialFormer-S · ImageNet-1k val 224top-1 accuracy: 83.8 -> 84.1 (params 25M -> 37M)Improved
replace conventional positional embeddings with spatial tokens (ablation)SpatialFormer-S · ImageNet-1k val 224top-1 accuracy: 82.1 -> 83.8 (best conventional PE vs spatial tokens)Improved
use 3D positional encodings to initialize spatial tokens instead of 2D (ablation)SpatialFormer with BEVFormer · nuScenes valNDS: 0.389 -> 0.392Improved
replace Swin-T backbone with SpatialFormer in BEVFormerBEVFormer · nuScenes valNDS: 0.369 -> 0.389Improved
transfer 224-trained model to other resolutions without fine-tuningSpatialFormer vs DeiT · ImageNet resolution generalizationtop-1 accuracyImproved
use spatial tokens as initial queries in Deformable DETR (two-stage)SpatialFormer-S · COCO valbox AP: 43.5 -> 46.5Improved

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