Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model
This addresses data imbalance in surgical video understanding, enabling more robust models for procedural modeling and intra-operative support, though it is incremental as it builds on existing diffusion methods.
The paper tackled the problem of imbalanced surgical video datasets by proposing SurgiFlowVid, a video diffusion framework that generates synthetic videos for under-represented classes, resulting in consistent gains of 10-20% over baselines in tasks like action recognition and tool detection.
Surgical video datasets are essential for scene understanding, enabling procedural modeling and intra-operative support. However, these datasets are often heavily imbalanced, with rare actions and tools under-represented, which limits the robustness of downstream models. We address this challenge with $SurgiFlowVid$, a sparse and controllable video diffusion framework for generating surgical videos of under-represented classes. Our approach introduces a dual-prediction diffusion module that jointly denoises RGB frames and optical flow, providing temporal inductive biases to improve motion modeling from limited samples. In addition, a sparse visual encoder conditions the generation process on lightweight signals (e.g., sparse segmentation masks or RGB frames), enabling controllability without dense annotations. We validate our approach on three surgical datasets across tasks including action recognition, tool presence detection, and laparoscope motion prediction. Synthetic data generated by our method yields consistent gains of 10-20% over competitive baselines, establishing $SurgiFlowVid$ as a promising strategy to mitigate data imbalance and advance surgical video understanding methods.