Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelines

• URL: http://arxiv.org/abs/2607.00747v1
• Date: Wed, 01 Jul 2026 10:30:05 GMT
• Title: Active Learning for Cascaded Object Detection: Balancing Coverage and Uncertainty in Table Extraction Pipelines
• Abstract summary: Table extraction from business documents relies on a cascaded pipeline where Table Detection (TD) first localizes tables and Table Structure Recognition (TSR) then recovers their internal layout.<n>We present the first adaptation of Uncertainty Herding (UHerding), a hybrid coverage-uncertainty sampling method originally proposed for image classification, to cascaded object detection pipelines.<n>We propose two pipeline-aware extensions that exploit the TD-to-TSR dependency: RankFusion adds dual-manifold coverage over both detection and structure representation spaces, while CAPA further incorporates stage-dependent gating and per-task uncertainty calibration.
• Score: 0.4433315630787158
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Table extraction from business documents relies on a cascaded pipeline where Table Detection (TD) first localizes tables and Table Structure Recognition (TSR) then recovers their internal layout. Building task-specific training sets for this pipeline is costly, particularly for TSR which requires fine-grained structural annotations. Active learning (AL) can reduce this annotation burden, yet most AL strategies are designed for single-model tasks and do not account for inter-stage dependencies in cascaded architectures. In this work, we present the first adaptation of Uncertainty Herding (UHerding), a hybrid coverage-uncertainty sampling method originally proposed for image classification, to cascaded object detection pipelines. We propose two pipeline-aware extensions that exploit the TD-to-TSR dependency: RankFusion adds dual-manifold coverage over both detection and structure representation spaces, while CAPA further incorporates stage-dependent gating and per-task uncertainty calibration. Extensive experiments across two public (PubTables-1M and FinTabNet) and two private table extraction datasets, with various annotation budgets (from 71 to 500 documents) show that UHerding generalizes well to table extraction, outperforming each baseline. Among pipeline-aware variants, RankFusion achieves higher expected gains but at the cost of greater variance, while CAPA emerges as the most consistent strategy, outperforming standard UHerding on three out of four datasets.

Related papers

• IntHQ: Task-Interactive Hierarchical Query on Dual-Stream Representations for Generative Recommendation [20.546679348797905]
  We show that existing multi-taskers are inherently prone to a threefold collapse.<n>We propose InHQ, a multi-task generative recommender with three components each alleviating one collapse.<n>In offline evaluations, InHQ consistently outperforms competitive backbones under four representative task-head configurations.
  arXiv  Detail & Related papers  (2026-08-10T14:13:47Z)
• ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition [1.645616881459713]
  Table Structure Recognition (TSR) aims to recover the row and column layout of tables from document images.<n> detection-based approaches treat table elements as generic objects, ignoring a fundamental property of table layout: rows and columns play structurally distinct roles and their boundaries carry unequal importance.<n>We propose an Edge-constrained Fine-grained Localization loss (EFL) that formalizes this structural asymmetry by encoding table-specific geometric priors into the training objective.
  arXiv  Detail & Related papers  (2026-07-01T10:18:12Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• Relatron: Automating Relational Machine Learning over Relational Databases [50.94254514286021]
  We present a study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks.<n>Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and accuracy is an unreliable guide for choice architecture.
  arXiv  Detail & Related papers  (2026-02-26T02:45:22Z)
• MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns [80.05126590825121]
  MonkeyOCR v1.5 is a unified vision-language framework that enhances both layout understanding and content recognition.<n>To address complex table structures, we propose a visual consistency-based reinforcement learning scheme.<n>Two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables.
  arXiv  Detail & Related papers  (2025-11-13T15:12:17Z)
• Relational Deep Dive: Error-Aware Queries Over Unstructured Data [9.0236658372663]
  ReDD (Relational Deep Dive) is a framework that dynamically discovers query-specific schemas, populates relational tables, and ensures error-aware extraction with provable guarantees.<n>Main contribution is SCAPE, a statistically calibrated method for error detection with coverage guarantees, and SCAPE-HYB, a hybrid approach that optimize the trade-off between accuracy and human correction costs.
  arXiv  Detail & Related papers  (2025-11-04T16:30:55Z)
• A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation [59.88864205383671]
  Source-Free Unsupervised Domain Adaptation (SFUDA) addresses the realistic challenge of adapting a source-trained model to a target domain without access to the source data.<n>Existing SFUDA methods either exploit only the source model's predictions or fine-tune large multimodal models.<n>We propose the Experts Cooperative Learning (EXCL) to exploit complementary insights and the latent structure of target data.
  arXiv  Detail & Related papers  (2025-09-26T11:39:50Z)
• A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities [51.08999772842298]
  Tabular Prior-data Fitted Network v2 (TabPFN v2) achieves unprecedented in-context learning performance across diverse downstream datasets.<n>We show that TabPFN v2 can infer attribute relationships even when provided with randomized attribute token inputs.<n>We demonstrate that TabPFN v2's limitations can be addressed through a test-time divide-and-context strategy.
  arXiv  Detail & Related papers  (2025-02-24T17:38:42Z)
• PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts [29.73609439825548]
  Key Information Extraction is a challenging task that aims to extract structured value semantic entities from documents. Existing methods follow a two-stage pipeline strategy, which may lead to the error propagation problem. We introduce Parallel Pointer-based Network (PPN), an end-to-end model that can be applied in zero-shot and few-shot scenarios.
  arXiv  Detail & Related papers  (2023-07-20T03:29:09Z)
• SEMv2: Table Separation Line Detection Based on Instance Segmentation [96.36188168694781]
  We propose an accurate table structure recognizer, termed SEMv2 (SEM: Split, Embed and Merge) We address the table separation line instance-level discrimination problem and introduce a table separation line detection strategy based on conditional convolution. To comprehensively evaluate the SEMv2, we also present a more challenging dataset for table structure recognition, dubbed iFLYTAB.
  arXiv  Detail & Related papers  (2023-03-08T05:15:01Z)
• Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation [103.90033029330527]
  Few-Shot Instance (FSIS) requires detecting and segmenting novel classes with limited support examples. We introduce a unified framework, Reference Twice (RefT), to exploit the relationship between support and query features for FSIS.
  arXiv  Detail & Related papers  (2023-01-03T15:33:48Z)

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.