# Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness

arXiv: https://arxiv.org/abs/2209.08647 · HTML: https://mlsanity.com/paper/2209.08647/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 18 Sep 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [On the (In)fidelity and Sensitivity for Explanations](https://mlsanity.com/paper/1901.09392/) (2019)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Feature Purification: How Adversarial Training Performs Robust Deep Learning](https://mlsanity.com/paper/2005.10190/) (2020)
- [Model Agnostic Supervised Local Explanations](https://mlsanity.com/paper/1807.02910/) (2018)
- [Leveraging Sparse Linear Layers for Debuggable Deep Networks](https://mlsanity.com/paper/2105.04857/) (2021)
- [Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets](https://mlsanity.com/paper/2007.05405/) (2020)
- [Structured Adversarial Attack: Towards General Implementation and Better Interpretability](https://mlsanity.com/paper/1808.01664/) (2018)
- [Understanding Failures of Deep Networks via Robust Feature Extraction](https://mlsanity.com/paper/2012.01750/) (2020)
- [Evaluations and Methods for Explanation through Robustness Analysis](https://mlsanity.com/paper/2006.00442/) (2020)
- [DeepPhase: Surgical Phase Recognition in CATARACTS Videos](https://mlsanity.com/paper/1807.10565/) (2018)
- [CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions](https://mlsanity.com/paper/1910.09031/) (2019)
- [Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets](https://mlsanity.com/paper/2204.05235/) (2022)

## Built on by (most cited first, 4 of 4)

- [CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection](https://mlsanity.com/paper/2302.06294/) (2023)
- [Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model](https://mlsanity.com/paper/2505.07449/) (2025)
- [Traffic Video Object Detection using Motion Prior](https://mlsanity.com/paper/2311.10092/) (2023)
- [Surgical Triplet Recognition via Diffusion Model](https://mlsanity.com/paper/2406.13210/) (2024)

## Abstract (arXiv)

Surgical action triplet recognition provides a better understanding of the surgical scene. This task is of high relevance as it provides the surgeon with context-aware support and safety. The current go-to strategy for improving performance is the development of new network mechanisms. However, the performance of current state-of-the-art techniques is substantially lower than other surgical tasks. Why is this happening? This is the question that we address in this work. We present the first study to understand the failure of existing deep learning models through the lens of robustness and explainability. Firstly, we study current existing models under weak and strong δ-perturbations via an adversarial optimisation scheme. We then analyse the failure modes via feature based explanations. Our study reveals that the key to improving performance and increasing reliability is in the core and spurious attributes. Our work opens the door to more trustworthy and reliable deep learning models in surgical data science.