AI Paper Atlas

Research map / Detection and segmentation / CNN features

TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts

Boyuan Chen, Zichen Dang, Chuang Yang, Lap-Pui Chau, Yi Wang

ECCV 2026 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 0 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 Dual-Encoding (SAM2 + DINOv3) (ablation)TextDS baseline · CTW-1500F-measure (%): 82.2 -> 85.3Improved
add Dual-Encoding (SAM2 + DINOv3) (ablation)TextDS baseline · Total-TextF-measure (%): 85.1 -> 86.0Improved
add Dual-Encoding (SAM2 + DINOv3) (ablation)TextDS baseline · MLTF-measure (%): 86.4 -> 88.1Improved
add SWLoRA to dual encoder (ablation)TextDS · CTW-1500F-measure (%): 85.3 -> 87.9Improved
add CSF to dual encoder (ablation)TextDS · CTW-1500F-measure (%): 85.3 -> 88.2Improved
add CSF on top of Dual-Encoding + SWLoRA (ablation)TextDS · CTW-1500F-measure (%): 87.9 -> 90.6Improved
add SWLoRA to dual encoder (ablation)TextDS · Total-TextF-measure (%): 86.0 -> 88.3Improved
add CSF to dual encoder (ablation)TextDS · Total-TextF-measure (%): 86.0 -> 87.8Improved
add SWLoRA on top of Dual-Encoding + CSF (ablation)TextDS · MLTF-measure (%): 91.0 -> 92.2Improved
early-exit in SWLoRA (max step 5) (ablation)SWLoRA · CTW-1500executed refinement steps: 3.652 out of 5, a 27.0% reductionImproved
early-exit in SWLoRA (max step 5) (ablation)SWLoRA · Total-Textexecuted refinement steps: 2.205 out of 5, a 55.9% reductionImproved
increase LoRA rank or maximum step beyond default (rank 8, step 5) (ablation)SWLoRA · CTW-1500, Total-Text, MLTF-measureNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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