Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition

• URL: http://arxiv.org/abs/2605.16387v1
• Date: Mon, 11 May 2026 16:56:15 GMT
• Title: Stabilizing Temporal Inference Dynamics for Online Surgical Phase Recognition
• Abstract summary: Online Surgical Phase Recognition (SPR) models can reach high frame-wise accuracy, yet their predictions often lack temporal stability.<n>We show that this instability is not random noise but arises from two mechanisms: early misclassifications corrupt temporal feature states and propagate forward to form error cascades.<n>We propose a unified Train-Inference-Evaluation framework that explicitly stabilizes temporal inference dynamics using model-agnostic, plug-and-play components.
• Score: 42.76777398447746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online Surgical Phase Recognition (SPR) models can reach high frame-wise accuracy, yet their predictions often lack temporal stability, fragmenting workflow understanding and reducing the reliability of downstream assistance. We show that this instability is not random noise but arises from two mechanisms: early misclassifications corrupt temporal feature states and propagate forward to form error cascades, and phase transitions follow evidence-accumulation dynamics whereas most online SPR systems rely on memoryless frame-wise decisions, making them sensitive to transient confidence fluctuations. We propose a unified Train-Inference-Evaluation framework that explicitly stabilizes temporal inference dynamics using model-agnostic, plug-and-play components. For training, the Temporal Error-Cascade (TEC) loss suppresses error onset and mitigates forward error propagation by stabilizing temporal feature evolution. For inference, the Evidence-Gated Transition Predictor (EGTP) enforces evidence-driven state transitions, allowing phase changes only when accumulated evidence exceeds a confidence boundary. For evaluation, we introduce the Temporal Fragmentation Index (TFI), a reliability-aware metric that quantifies instability-induced temporal disagreement beyond conventional frame-wise and token-based measures. Experiments on Cholec80 and AutoLaparo across three representative backbones show that the proposed framework substantially improves temporal stability and reduces prediction fragmentation, while maintaining or modestly improving frame-wise performance.

Related papers

• Real-time fall detection based on vision for low-power edge platforms [7.916664096508434]
  Falling detection is vital for elderly care and intelligent surveillance.<n> prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching.<n>This paper proposes a physics-informed falling detection framework that recasts falling as a stability-loss event.
  arXiv  Detail & Related papers  (2026-07-14T15:43:41Z)
• Improving Spatio-Temporal Residual Error Propagation by Mitigating Over-Squashing [4.62541204592513]
  We introduce Teger, a structured uncertainty module that overcomes the spa- tial and temporal limitations of error-related autoregressive forecasting.<n>Teger is backbone-agnostic, requiring only the latent state produced by any autoregressive encoder.
  arXiv  Detail & Related papers  (2026-05-18T08:51:33Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift [64.37959940809633]
  We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures.<n>We show Transformer-based sequence policies substantially outperform, RNN, and SSMs in robustness, maintaining high returns even when large fractions of sensors are unavailable.
  arXiv  Detail & Related papers  (2026-03-04T22:21:54Z)
• Kalman-Inspired Runtime Stability and Recovery in Hybrid Reasoning Systems [1.9544213396776273]
  We study stability in hybrid reasoning systems from a Kalman-inspired perspective.<n>We propose a runtime stability framework that monitors innovation statistics, detects emerging instability, and triggers recovery-aware control mechanisms.
  arXiv  Detail & Related papers  (2026-01-24T11:29:57Z)
• On Exact Editing of Flow-Based Diffusion Models [97.0633397035926]
  We propose Conditioned Velocity Correction (CVC) to reformulate flow-based editing as a distribution transformation problem driven by a known source prior.<n>CVC rethinks the role of velocity in inter-distribution transformation by introducing a dual-perspective velocity conversion mechanism.<n>We show that CVC consistently achieves superior fidelity, better semantic alignment, and more reliable editing behavior across diverse tasks.
  arXiv  Detail & Related papers  (2025-12-30T06:29:20Z)
• Stability-Drift Early Warning for Cyber-Physical Systems Under Degradation Attacks [0.0]
  Cyber-physical systems are vulnerable to slow degradation without causing immediate or obvious failures.<n>Small sensor biases or timing irregularities can accumulate over time, gradually reducing stability.<n>This paper introduces an early warning method based on stability drift.
  arXiv  Detail & Related papers  (2025-12-15T15:40:44Z)
• Fair and Explainable Credit-Scoring under Concept Drift: Adaptive Explanation Frameworks for Evolving Populations [0.0]
  We develop adaptive explanation frameworks that recalibrate interpretability and fairness in dynamically evolving credit models.<n>Results show that adaptive methods, particularly rebaselined and surrogate-based explanations, substantially improve temporal stability and reduce disparate impact across demographic groups without degrading predictive accuracy.<n>These findings establish adaptive explainability as a practical mechanism for sustaining transparency, accountability, and ethical reliability in data-driven credit systems.
  arXiv  Detail & Related papers  (2025-11-05T19:14:43Z)
• Temporalizing Confidence: Evaluation of Chain-of-Thought Reasoning with Signal Temporal Logic [0.12499537119440243]
  We propose a structured framework that models stepwise confidence as a temporal signal and evaluates it using Signal Temporal Logic (STL)<n>In particular, we define formal STL-based constraints to capture desirable temporal properties and compute scores that serve as structured, interpretable confidence estimates.<n>Our approach consistently improves calibration metrics and provides more reliable uncertainty estimates than conventional confidence aggregation and post-hoc calibration.
  arXiv  Detail & Related papers  (2025-06-09T21:21:12Z)
• Aurora: Are Android Malware Classifiers Reliable and Stable under Distribution Shift? [51.12297424766236]
  AURORA is a framework to evaluate malware classifiers based on their confidence quality and operational resilience.<n>AURORA is complemented by a set of metrics designed to go beyond point-in-time performance.<n>The fragility in SOTA frameworks across datasets of varying drift suggests the need for a return to the whiteboard.
  arXiv  Detail & Related papers  (2025-05-28T20:22:43Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)

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.