AI Paper Atlas

Research map / Detection and segmentation / CNN features

Hilbert Curve-Based Attention Enabling Topology-Preserving Image Tensor Representation for Semantic Segmentation Network

Linkang Xu, Gang Li, Yue Song, Xiangxin Ji

CVPR 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation

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
flatten with Hilbert curve instead of row-first traversal in the decoder attention (ablation)TPDecoder (Swin-T) · BD3 building defectsmIoU: 75.58 -> 79.49Improved
flatten with Hilbert curve instead of Z-order traversal (ablation)TPDecoder (Swin-T) · BD3 building defectsmIoU: 77.89 -> 79.49Improved
flatten with Hilbert curve instead of row-first traversal (ablation)TPDecoder (Swin-T) · BD3 building defectsACC: 86.37 -> 89.51Improved
use Hilbert curve instead of row-first or Z-order for flattening (ablation)2D flattening · locality loss, order 7locality loss: 2064766 (Row-First) -> 16383 (Hilbert)Improved
use Hilbert curve instead of row-first flattening (ablation)2D flattening · runtime, 128x128runtime (s): 0.009974 -> 0.130650Hurt
add Joint Auxiliary Loss (Dice + edge-aware) with weights dice 0.5, edge 1.0 (ablation)TPSegformer (Swin-T) · BD3 building defectsmIoU: 79.49 -> 80.77Improved
add Joint Auxiliary Loss with weights dice 0.5, edge 1.0 (ablation)TPSegformer (Swin-T) · BD3 building defectsACC: 89.51 -> 90.22Improved
scale Swin backbone from Tiny to Large (ablation)TPDecoder · BD3 building defectsmIoU: 79.49 -> 81.37Improved
scale Swin backbone from Tiny to Base (ablation)TPDecoder · BD3 building defectsACC: 89.51 -> 88.57Hurt
scale ResNet backbone from 50 to 101 layers (ablation)TPDecoder · BD3 building defectsmIoU: 79.00 -> 78.22Hurt
use TPSegformer instead of the best baselinesegmentation network · Dacl10kmIoU: 36.21 -> 44.27Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

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