AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

PSLT: A Light-Weight Vision Transformer With Ladder Self-Attention and Progressive Shift

Gaojie Wu, Wei‐Shi Zheng, Yutong Lu, Qi Chuan Tian

TPAMI 2023 · Architectures and efficiency › Attention and transformers · approach: Efficient and robust vision transformers · 36 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 shift operation in each branch (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 79.3 -> 79.9Improved
add progressive feature delivery between branches (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 79.2 -> 79.9Improved
add pixel-adaptive fusion module instead of FC fusion (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 78.8 -> 79.9Improved
add pixel-adaptive fusion module instead of concatenation (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 77.3 -> 79.9Improved
use spatial-and-channel adaptive weights instead of channel-only SE (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 79.0 -> 79.9Improved
use Light FFN instead of original FFN (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 79.7 -> 79.9No clear effect
increase branches from 3 to 6 (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 79.9 -> 77.9Hurt
decrease branches from 3 to 2 (ablation)PSLT · ImageNet-1k val (ablation, from scratch)top-1 accuracy: 79.9 -> 80.2Improved
add pixel-adaptive fusion on top of LSA and Light FFN (ablation)PSLT · ImageNet-V2top-1 accuracy: 64.6 -> 68.6Improved
add ladder self-attention and Light FFN to replace ViT-B (ablation)PSLT · ImageNet-1k val (from scratch)top-1 accuracy: 77.9 -> 77.3No clear effect
use PSLT with 9.0M params instead of PCB (+RPP) for re-idPSLT · Market-1501mAP: 81.6 -> 86.2Improved
compare PSLT against EfficientNet backbone for detectionPSLT · COCO val2017 RetinaNet 1xAP: 40.5 -> 41.2Improved

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