Alert button
Picture for Ziheng Wang

Ziheng Wang

Alert button

An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

Jun 28, 2023
Haihao Shen, Hengyu Meng, Bo Dong, Zhe Wang, Ofir Zafrir, Yi Ding, Yu Luo, Hanwen Chang, Qun Gao, Ziheng Wang, Guy Boudoukh, Moshe Wasserblat

Figure 1 for An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
Figure 2 for An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
Figure 3 for An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs
Figure 4 for An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs

In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To mitigate the gap, model compression techniques such as structured pruning are being used to improve inference efficiency. However, most existing neural network inference runtimes lack adequate support for structured sparsity. In this paper, we propose an efficient sparse deep learning inference software stack for Transformer-based language models where the weights are pruned with constant block size. Our sparse software accelerator leverages Intel Deep Learning Boost to maximize the performance of sparse matrix - dense matrix multiplication (commonly abbreviated as SpMM) on CPUs. Our SpMM kernel outperforms the existing sparse libraries (oneMKL, TVM, and LIBXSMM) by an order of magnitude on a wide range of GEMM shapes under 5 representative sparsity ratios (70%, 75%, 80%, 85%, 90%). Moreover, our SpMM kernel shows up to 5x speedup over dense GEMM kernel of oneDNN, a well-optimized dense library widely used in industry. We apply our sparse accelerator on widely-used Transformer-based language models including Bert-Mini, DistilBERT, Bert-Base, and BERT-Large. Our sparse inference software shows up to 1.5x speedup over Neural Magic's Deepsparse under same configurations on Xeon on Amazon Web Services under proxy production latency constraints. We also compare our solution with two framework-based inference solutions, ONNX Runtime and PyTorch, and demonstrate up to 37x speedup over ONNX Runtime and 345x over PyTorch on Xeon under the latency constraints. All the source code is publicly available on Github: https://github.com/intel/intel-extension-for-transformers.

Viaarxiv icon

Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems

Jun 02, 2023
Pedro Reviriego, Ziheng Wang, Alvaro Alonso, Zhen Gao, Farzad Niknia, Shanshan Liu, Fabrizio Lombardi

Figure 1 for Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems
Figure 2 for Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems
Figure 3 for Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems
Figure 4 for Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems

The complexity of Machine Learning (ML) systems increases each year, with current implementations of large language models or text-to-image generators having billions of parameters and requiring billions of arithmetic operations. As these systems are widely utilized, ensuring their reliable operation is becoming a design requirement. Traditional error detection mechanisms introduce circuit or time redundancy that significantly impacts system performance. An alternative is the use of Concurrent Error Detection (CED) schemes that operate in parallel with the system and exploit their properties to detect errors. CED is attractive for large ML systems because it can potentially reduce the cost of error detection. In this paper, we introduce Concurrent Classifier Error Detection (CCED), a scheme to implement CED in ML systems using a concurrent ML classifier to detect errors. CCED identifies a set of check signals in the main ML system and feeds them to the concurrent ML classifier that is trained to detect errors. The proposed CCED scheme has been implemented and evaluated on two widely used large-scale ML models: Contrastive Language Image Pretraining (CLIP) used for image classification and Bidirectional Encoder Representations from Transformers (BERT) used for natural language applications. The results show that more than 95 percent of the errors are detected when using a simple Random Forest classifier that is order of magnitude simpler than CLIP or BERT. These results illustrate the potential of CCED to implement error detection in large-scale ML models.

Viaarxiv icon

Movie101: A New Movie Understanding Benchmark

May 20, 2023
Zihao Yue, Qi Zhang, Anwen Hu, Liang Zhang, Ziheng Wang, Qin Jin

Figure 1 for Movie101: A New Movie Understanding Benchmark
Figure 2 for Movie101: A New Movie Understanding Benchmark
Figure 3 for Movie101: A New Movie Understanding Benchmark
Figure 4 for Movie101: A New Movie Understanding Benchmark

To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of actors. Existing works benchmark this challenge as a normal video captioning task via some simplifications, such as removing role names and evaluating narrations with ngram-based metrics, which makes it difficult for automatic systems to meet the needs of real application scenarios. To narrow this gap, we construct a large-scale Chinese movie benchmark, named Movie101. Closer to real scenarios, the Movie Clip Narrating (MCN) task in our benchmark asks models to generate role-aware narration paragraphs for complete movie clips where no actors are speaking. External knowledge, such as role information and movie genres, is also provided for better movie understanding. Besides, we propose a new metric called Movie Narration Score (MNScore) for movie narrating evaluation, which achieves the best correlation with human evaluation. Our benchmark also supports the Temporal Narration Grounding (TNG) task to investigate clip localization given text descriptions. For both two tasks, our proposed methods well leverage external knowledge and outperform carefully designed baselines. The dataset and codes are released at https://github.com/yuezih/Movie101.

* Accepted to ACL 2023 
Viaarxiv icon

Edit As You Wish: Video Description Editing with Multi-grained Commands

May 15, 2023
Linli Yao, Yuanmeng Zhang, Ziheng Wang, Xinglin Hou, Tiezheng Ge, Yuning Jiang, Qin Jin

Figure 1 for Edit As You Wish: Video Description Editing with Multi-grained Commands
Figure 2 for Edit As You Wish: Video Description Editing with Multi-grained Commands
Figure 3 for Edit As You Wish: Video Description Editing with Multi-grained Commands
Figure 4 for Edit As You Wish: Video Description Editing with Multi-grained Commands

Automatically narrating a video with natural language can assist people in grasping and managing massive videos on the Internet. From the perspective of video uploaders, they may have varied preferences for writing the desired video description to attract more potential followers, e.g. catching customers' attention for product videos. The Controllable Video Captioning task is therefore proposed to generate a description conditioned on the user demand and video content. However, existing works suffer from two shortcomings: 1) the control signal is fixed and can only express single-grained control; 2) the video description can not be further edited to meet dynamic user demands. In this paper, we propose a novel Video Description Editing (VDEdit) task to automatically revise an existing video description guided by flexible user requests. Inspired by human writing-revision habits, we design the user command as a {operation, position, attribute} triplet to cover multi-grained use requirements, which can express coarse-grained control (e.g. expand the description) as well as fine-grained control (e.g. add specified details in specified position) in a unified format. To facilitate the VDEdit task, we first automatically construct a large-scale benchmark dataset namely VATEX-EDIT in the open domain describing diverse human activities. Considering the real-life application scenario, we further manually collect an e-commerce benchmark dataset called EMMAD-EDIT. We propose a unified framework to convert the {operation, position, attribute} triplet into a textual control sequence to handle multi-grained editing commands. For VDEdit evaluation, we adopt comprehensive metrics to measure three aspects of model performance, including caption quality, caption-command consistency, and caption-video alignment.

Viaarxiv icon

Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge

May 11, 2023
Aneeq Zia, Kiran Bhattacharyya, Xi Liu, Max Berniker, Ziheng Wang, Rogerio Nespolo, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Bo Liu, David Austin, Yiheng Wang, Michal Futrega, Jean-Francois Puget, Zhenqiang Li, Yoichi Sato, Ryo Fujii, Ryo Hachiuma, Mana Masuda, Hideo Saito, An Wang, Mengya Xu, Mobarakol Islam, Long Bai, Winnie Pang, Hongliang Ren, Chinedu Nwoye, Luca Sestini, Nicolas Padoy, Maximilian Nielsen, Samuel Schüttler, Thilo Sentker, Hümeyra Husseini, Ivo Baltruschat, Rüdiger Schmitz, René Werner, Aleksandr Matsun, Mugariya Farooq, Numan Saaed, Jose Renato Restom Viera, Mohammad Yaqub, Neil Getty, Fangfang Xia, Zixuan Zhao, Xiaotian Duan, Xing Yao, Ange Lou, Hao Yang, Jintong Han, Jack Noble, Jie Ying Wu, Tamer Abdulbaki Alshirbaji, Nour Aldeen Jalal, Herag Arabian, Ning Ding, Knut Moeller, Weiliang Chen, Quan He, Lena Maier-Hein, Danail Stoyanov, Stefanie Speidel, Anthony Jarc

Figure 1 for Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge
Figure 2 for Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge
Figure 3 for Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge
Figure 4 for Surgical tool classification and localization: results and methods from the MICCAI 2022 SurgToolLoc challenge

The ability to automatically detect and track surgical instruments in endoscopic videos can enable transformational interventions. Assessing surgical performance and efficiency, identifying skilled tool use and choreography, and planning operational and logistical aspects of OR resources are just a few of the applications that could benefit. Unfortunately, obtaining the annotations needed to train machine learning models to identify and localize surgical tools is a difficult task. Annotating bounding boxes frame-by-frame is tedious and time-consuming, yet large amounts of data with a wide variety of surgical tools and surgeries must be captured for robust training. Moreover, ongoing annotator training is needed to stay up to date with surgical instrument innovation. In robotic-assisted surgery, however, potentially informative data like timestamps of instrument installation and removal can be programmatically harvested. The ability to rely on tool installation data alone would significantly reduce the workload to train robust tool-tracking models. With this motivation in mind we invited the surgical data science community to participate in the challenge, SurgToolLoc 2022. The goal was to leverage tool presence data as weak labels for machine learning models trained to detect tools and localize them in video frames with bounding boxes. We present the results of this challenge along with many of the team's efforts. We conclude by discussing these results in the broader context of machine learning and surgical data science. The training data used for this challenge consisting of 24,695 video clips with tool presence labels is also being released publicly and can be accessed at https://console.cloud.google.com/storage/browser/isi-surgtoolloc-2022.

Viaarxiv icon

Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery

Apr 28, 2023
Ziheng Wang, Andrea Mariani, Arianna Menciassi, Elena De Momi, Ann Majewicz Fey

Figure 1 for Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery
Figure 2 for Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery
Figure 3 for Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery
Figure 4 for Uncertainty-aware Self-supervised Learning for Cross-domain Technical Skill Assessment in Robot-assisted Surgery

Objective technical skill assessment is crucial for effective training of new surgeons in robot-assisted surgery. With advancements in surgical training programs in both physical and virtual environments, it is imperative to develop generalizable methods for automatically assessing skills. In this paper, we propose a novel approach for skill assessment by transferring domain knowledge from labeled kinematic data to unlabeled data. Our approach leverages labeled data from common surgical training tasks such as Suturing, Needle Passing, and Knot Tying to jointly train a model with both labeled and unlabeled data. Pseudo labels are generated for the unlabeled data through an iterative manner that incorporates uncertainty estimation to ensure accurate labeling. We evaluate our method on a virtual reality simulated training task (Ring Transfer) using data from the da Vinci Research Kit (dVRK). The results show that trainees with robotic assistance have significantly higher expert probability compared to these without any assistance, p < 0.05, which aligns with previous studies showing the benefits of robotic assistance in improving training proficiency. Our method offers a significant advantage over other existing works as it does not require manual labeling or prior knowledge of the surgical training task for robot-assisted surgery.

* Manuscript ACCEPTED on 18-April-2023 for publication in IEEE Transactions on Medical Robotics and Bionics (TMRB). 12 pages, 9 figures, and 2 tables 
Viaarxiv icon

Bringing Telepresence to Every Desk

Apr 03, 2023
Shengze Wang, Ziheng Wang, Ryan Schmelzle, Liujie Zheng, YoungJoong Kwon, Soumyadip Sengupta, Henry Fuchs

Figure 1 for Bringing Telepresence to Every Desk
Figure 2 for Bringing Telepresence to Every Desk
Figure 3 for Bringing Telepresence to Every Desk
Figure 4 for Bringing Telepresence to Every Desk

In this paper, we work to bring telepresence to every desktop. Unlike commercial systems, personal 3D video conferencing systems must render high-quality videos while remaining financially and computationally viable for the average consumer. To this end, we introduce a capturing and rendering system that only requires 4 consumer-grade RGBD cameras and synthesizes high-quality free-viewpoint videos of users as well as their environments. Experimental results show that our system renders high-quality free-viewpoint videos without using object templates or heavy pre-processing. While not real-time, our system is fast and does not require per-video optimizations. Moreover, our system is robust to complex hand gestures and clothing, and it can generalize to new users. This work provides a strong basis for further optimization, and it will help bring telepresence to every desk in the near future. The code and dataset will be made available on our website https://mcmvmc.github.io/PersonalTelepresence/.

Viaarxiv icon

Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels

Mar 31, 2023
Ziheng Wang, Conor Perreault, Xi Liu, Anthony Jarc

Figure 1 for Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels
Figure 2 for Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels
Figure 3 for Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels
Figure 4 for Automatic Detection of Out-of-body Frames in Surgical Videos for Privacy Protection Using Self-supervised Learning and Minimal Labels

Endoscopic video recordings are widely used in minimally invasive robot-assisted surgery, but when the endoscope is outside the patient's body, it can capture irrelevant segments that may contain sensitive information. To address this, we propose a framework that accurately detects out-of-body frames in surgical videos by leveraging self-supervision with minimal data labels. We use a massive amount of unlabeled endoscopic images to learn meaningful representations in a self-supervised manner. Our approach, which involves pre-training on an auxiliary task and fine-tuning with limited supervision, outperforms previous methods for detecting out-of-body frames in surgical videos captured from da Vinci X and Xi surgical systems. The average F1 scores range from 96.00 to 98.02. Remarkably, using only 5% of the training labels, our approach still maintains an average F1 score performance above 97, outperforming fully-supervised methods with 95% fewer labels. These results demonstrate the potential of our framework to facilitate the safe handling of surgical video recordings and enhance data privacy protection in minimally invasive surgery.

* A 15-page journal article submitted to Journal of Medical Robotics Research (JMRR) 
Viaarxiv icon

CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection

Feb 13, 2023
Chinedu Innocent Nwoye, Tong Yu, Saurav Sharma, Aditya Murali, Deepak Alapatt, Armine Vardazaryan, Kun Yuan, Jonas Hajek, Wolfgang Reiter, Amine Yamlahi, Finn-Henri Smidt, Xiaoyang Zou, Guoyan Zheng, Bruno Oliveira, Helena R. Torres, Satoshi Kondo, Satoshi Kasai, Felix Holm, Ege Özsoy, Shuangchun Gui, Han Li, Sista Raviteja, Rachana Sathish, Pranav Poudel, Binod Bhattarai, Ziheng Wang, Guo Rui, Melanie Schellenberg, João L. Vilaça, Tobias Czempiel, Zhenkun Wang, Debdoot Sheet, Shrawan Kumar Thapa, Max Berniker, Patrick Godau, Pedro Morais, Sudarshan Regmi, Thuy Nuong Tran, Jaime Fonseca, Jan-Hinrich Nölke, Estevão Lima, Eduard Vazquez, Lena Maier-Hein, Nassir Navab, Pietro Mascagni, Barbara Seeliger, Cristians Gonzalez, Didier Mutter, Nicolas Padoy

Figure 1 for CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
Figure 2 for CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
Figure 3 for CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection
Figure 4 for CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection

Formalizing surgical activities as triplets of the used instruments, actions performed, and target anatomies is becoming a gold standard approach for surgical activity modeling. The benefit is that this formalization helps to obtain a more detailed understanding of tool-tissue interaction which can be used to develop better Artificial Intelligence assistance for image-guided surgery. Earlier efforts and the CholecTriplet challenge introduced in 2021 have put together techniques aimed at recognizing these triplets from surgical footage. Estimating also the spatial locations of the triplets would offer a more precise intraoperative context-aware decision support for computer-assisted intervention. This paper presents the CholecTriplet2022 challenge, which extends surgical action triplet modeling from recognition to detection. It includes weakly-supervised bounding box localization of every visible surgical instrument (or tool), as the key actors, and the modeling of each tool-activity in the form of <instrument, verb, target> triplet. The paper describes a baseline method and 10 new deep learning algorithms presented at the challenge to solve the task. It also provides thorough methodological comparisons of the methods, an in-depth analysis of the obtained results, their significance, and useful insights for future research directions and applications in surgery.

* MICCAI EndoVis CholecTriplet2022 challenge report. Submitted to journal of Medical Image Analysis. 22 pages, 14 figures, 6 tables 
Viaarxiv icon

Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge

Dec 08, 2022
Aneeq Zia, Kiran Bhattacharyya, Xi Liu, Ziheng Wang, Max Berniker, Satoshi Kondo, Emanuele Colleoni, Dimitris Psychogyios, Yueming Jin, Jinfan Zhou, Evangelos Mazomenos, Lena Maier-Hein, Danail Stoyanov, Stefanie Speidel, Anthony Jarc

Figure 1 for Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge
Figure 2 for Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge
Figure 3 for Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge
Figure 4 for Objective Surgical Skills Assessment and Tool Localization: Results from the MICCAI 2021 SimSurgSkill Challenge

Timely and effective feedback within surgical training plays a critical role in developing the skills required to perform safe and efficient surgery. Feedback from expert surgeons, while especially valuable in this regard, is challenging to acquire due to their typically busy schedules, and may be subject to biases. Formal assessment procedures like OSATS and GEARS attempt to provide objective measures of skill, but remain time-consuming. With advances in machine learning there is an opportunity for fast and objective automated feedback on technical skills. The SimSurgSkill 2021 challenge (hosted as a sub-challenge of EndoVis at MICCAI 2021) aimed to promote and foster work in this endeavor. Using virtual reality (VR) surgical tasks, competitors were tasked with localizing instruments and predicting surgical skill. Here we summarize the winning approaches and how they performed. Using this publicly available dataset and results as a springboard, future work may enable more efficient training of surgeons with advances in surgical data science. The dataset can be accessed from https://console.cloud.google.com/storage/browser/isi-simsurgskill-2021.

* arXiv admin note: substantial text overlap with arXiv:1910.04071 
Viaarxiv icon