AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding

Hanrong Ye, Dan Xu

TPAMI 2024 · Architectures and efficiency › Attention and transformers · approach: Efficient image transformers · 32 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 UP-Transformer block (ablation)InvPT++ Baseline (MT) · NYUD-v2Semseg mIoU: 41.06 -> 43.18Improved
add UP-Transformer block (ablation)InvPT++ Baseline (MT) · NYUD-v2Depth RMSE: 0.6350 -> 0.5643Improved
add UP-Transformer block (ablation)InvPT++ Baseline (MT) · NYUD-v2Normal mErr: 21.47 -> 21.05Improved
add Fusion Attention to UTB (ablation)InvPT++ · PASCAL-Context (Swin-T)Semseg mIoU: 72.34 -> 73.29Improved
add Encoder Feature Aggregation (ablation)InvPT++ w/ UTB+FA · PASCAL-Context (Swin-T)Semseg mIoU: 73.29 -> 73.93Improved
add Encoder Feature Aggregation (ablation)InvPT++ w/ UTB+FA · NYUD-v2 (Swin-T)Semseg mIoU: 43.64 -> 44.27Improved
add Encoder Feature Aggregation (ablation)InvPT++ w/ UTB+FA · NYUD-v2 (Swin-T)Boundary odsF: 76.10 -> 76.10No clear effect
multi-task learning versus single-task modelsInvPT++ · NYUD-v2multi-task gain: 2.59Improved
multi-task learning versus single-task modelsInvPT++ · PASCAL-Contextmulti-task gain: 1.76Improved
use Selective Attention instead of Fusion Attention (ablation)InvPT++ (ViT-L) · PASCAL-ContextSemseg mIoU: 79.03 -> 80.22Improved
use Selective Attention instead of Fusion Attention (ablation)InvPT++ (ViT-L) · PASCAL-Contextdecoder FLOPs: -22.51%Improved
use Selective Attention instead of Fusion Attention (ablation)InvPT++ (ViT-L) · NYUD-v2Depth RMSE: 0.5183 -> 0.5096Improved

Later papers that compared with this method

1 later accepted paper reports InvPT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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