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

• URL: http://arxiv.org/abs/2606.28077v2
• Date: Mon, 29 Jun 2026 02:46:58 GMT
• Title: TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts
• Abstract summary: We propose TextDS, an efficient framework for scene text detection under distribution shifts.<n>First, we propose a data-efficient dual-encoder design with visual foundation models.<n>Second, we introduce Step-wise LoRA adaptation (SWLoRA), which performs progressive low-rank refinement.<n>Third, we construct adverse-condition scene text detection datasets to address the gap in evaluating under imaging degradation.
• Score: 17.372067847674455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In real-world deployments, scene text detectors inevitably face distribution shifts beyond the training distribution. Prior work often depends on large-scale scene-text pretraining, yet evaluation under cross-domain changes and real-world imaging degradations remains limited. We propose TextDS, an efficient framework for scene text detection under distribution shifts. First, we propose a data-efficient dual-encoder design with visual foundation models, eliminating the reliance on large-scale scene-text pretraining. Second, we introduce Step-wise LoRA adaptation (SWLoRA), which performs progressive low-rank refinement with a dynamic early-exit mechanism for effective feature adaptation. Third, we propose Common Subspace Fusion (CSF) to align and fuse the two branches in a shared subspace while retaining complementary, shift-robust information. Finally, we construct adverse-condition scene text detection datasets to address the gap in evaluating under imaging degradation. Experiments show that TextDS achieves competitive performance in scene text detection, demonstrating robustness across domains and adverse imaging conditions with only 4.9M trainable parameters.

Related papers

• Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection [53.789057575175065]
  Region-Aware Prompt Augmentation (RAPTA) and Attention-Driven Multimodal Copy Detection (ADMCD) are presented.<n>RAPTA uses an object detector to find salient regions and turn them into semantically grounded prompt variants.<n>ADMCD aggregates local patch, global semantic, and texture cues with a lightweight transformer to produce a fused representation.<n>Experiments show that RAPTA reduces overfitting while maintaining high synthesis quality, and that ADMCD reliably detects copying, outperforming single-modal metrics.
  arXiv  Detail & Related papers  (2026-03-13T15:16:27Z)
• TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment [68.91073792449201]
  We propose TextGuider, a training-free method that encourages accurate and complete text appearance.<n>Specifically, we analyze attention patterns in Multi-Modal Diffusion Transformer(MM-DiT) models, particularly for text-related tokens intended to be rendered in the image.<n>Our method achieves state-of-the-art performance in test-time text rendering, with significant gains in recall and strong results in OCR accuracy and CLIP score.
  arXiv  Detail & Related papers  (2025-12-10T06:18:30Z)
• Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations [56.816929931908824]
  We pioneer the detection of semantically-coordinated manipulations in multimodal data.<n>We propose a Retrieval-Augmented Manipulation Detection and Grounding (RamDG) framework.<n>Our framework significantly outperforms existing methods, achieving 2.06% higher detection accuracy on SAMM compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-09-16T04:18:48Z)
• Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval [24.544672733180196]
  We introduce a unified text-based person retrieval pipeline considering domain adaptation at both image and region levels.<n>Our dual-level adaptation method has achieved state-of-the-art results on the CUHK-PEDES, ICFG-PEDES, and RSTPReid datasets.
  arXiv  Detail & Related papers  (2025-07-14T12:03:04Z)
• Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models [63.99110667987318]
  We present DiffText, a pipeline that seamlessly blends foreground text with the background's intrinsic features. With fewer text instances, our produced text images consistently surpass other synthetic data in aiding text detectors.
  arXiv  Detail & Related papers  (2023-11-28T06:51:28Z)
• Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance [15.513912470752041]
  The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. Here, we investigate the problem of domain-adaptive scene text spotting, i.e., training a model on multi-domain source data. The results clearly demonstrate the potential of intermediate representations to achieve significant performance on text spotting benchmarks across multiple domains.
  arXiv  Detail & Related papers  (2023-10-02T06:08:01Z)
• TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution [17.95994419104427]
  TextDiff is a diffusion-based framework tailored for scene text image super-resolution.<n>It achieves state-of-the-art (SOTA) performance on public benchmark datasets.<n>Our proposed MRD module is plug-and-play that effectively sharpens the text edges produced by SOTA methods.
  arXiv  Detail & Related papers  (2023-08-13T11:02:16Z)
• TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision [61.186488081379]
  We propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing.
  arXiv  Detail & Related papers  (2023-06-06T03:37:41Z)
• Domain Adaptive Scene Text Detection via Subcategorization [45.580559833129165]
  We study domain adaptive scene text detection, a largely neglected yet very meaningful task. We design SCAST, a subcategory-aware self-training technique that mitigates the network overfitting and noisy pseudo labels. SCAST achieves superior detection performance consistently across multiple public benchmarks.
  arXiv  Detail & Related papers  (2022-12-01T09:15:43Z)
• Text Detection & Recognition in the Wild for Robot Localization [1.52292571922932]
  We propose an end-to-end scene text spotting model that simultaneously outputs the text string and bounding boxes. Our central contribution is introducing utilizing an end-to-end scene text spotting framework to adequately capture the irregular and occluded text regions.
  arXiv  Detail & Related papers  (2022-05-17T18:16:34Z)
• ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection [147.10751375922035]
  We propose the ContourNet, which effectively handles false positives and large scale variance of scene texts. Our method effectively suppresses these false positives by only outputting predictions with high response value in both directions.
  arXiv  Detail & Related papers  (2020-04-10T08:15:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.