Publications

Automated Detection of Anatomical Landmarks During Colonoscopy Using a Deep Learning Model

Mahsa Taghiakbari

Sina Hamidi Ghalehjegh

Emmanuel Jehanno

Tess Berthier

Lisa Di Jorio

Saber Ghadakzadeh

Alan Barkun

Mark Takla

Mickael Bouin

Eric Deslandres

Simon Bouchard

Sacha Sidani

Yoshua Bengio

Daniel von Renteln

Abstract Background and aims Identification and photo-documentation of the ileocecal valve (ICV) and appendiceal orifice (AO) confirm comple… (see more)teness of colonoscopy examinations. We aimed to develop and test a deep convolutional neural network (DCNN) model that can automatically identify ICV and AO, and differentiate these landmarks from normal mucosa and colorectal polyps. Methods We prospectively collected annotated full-length colonoscopy videos of 318 patients undergoing outpatient colonoscopies. We created three nonoverlapping training, validation, and test data sets with 25,444 unaltered frames extracted from the colonoscopy videos showing four landmarks/image classes (AO, ICV, normal mucosa, and polyps). A DCNN classification model was developed, validated, and tested in separate data sets of images containing the four different landmarks. Results After training and validation, the DCNN model could identify both AO and ICV in 18 out of 21 patients (85.7%). The accuracy of the model for differentiating AO from normal mucosa, and ICV from normal mucosa were 86.4% (95% CI 84.1% to 88.5%), and 86.4% (95% CI 84.1% to 88.6%), respectively. Furthermore, the accuracy of the model for differentiating polyps from normal mucosa was 88.6% (95% CI 86.6% to 90.3%). Conclusion This model offers a novel tool to assist endoscopists with automated identification of AO and ICV during colonoscopy. The model can reliably distinguish these anatomical landmarks from normal mucosa and colorectal polyps. It can be implemented into automated colonoscopy report generation, photo-documentation, and quality auditing solutions to improve colonoscopy reporting quality.

2023-05-01

Journal of the Canadian Association of Gastroenterology (published)

doi.org

Cone-Traced Supersampling for Signed Distance Field Rendering

Andrei Chubarau

Yangyang Zhao

Ruby Rao

Paul Kry

D. Nowrouzezahrai

While Signed Distance Fields (SDFs) in theory offer infinite level of detail, they are typically rendered using the sphere tracing algorithm… (see more) at finite resolutions, which causes the common rasterized image synthesis problem of aliasing. Most existing optimized antialiasing solutions rely on polygon mesh representations; SDF-based geometry can only be directly antialiased with the computationally expensive supersampling or with post-processing filters that often lead to undesirable blurriness and ghosting. In this work, we present cone-traced supersampling (CTSS), an efficient and robust spatial antialiasing solution that naturally complements the sphere tracing algorithm, does not require casting additional rays per pixel or offline pre-filtering, and can be easily implemented in existing real-time SDF renderers. CTSS performs supersampling along the traced ray near surfaces with partial visibility identified by evaluating cone intersections within a pixel's view frustum. We further devise a specialized sampling strategy to minimize the number of shading computations and aggregate the collected samples based on their correlated visibility. Depending on configuration, CTSS incurs roughly 15-30% added computational cost and significantly outperforms conventional supersampling approaches while offering comparative antialiasing and visual image quality for most geometric edges.

2023-05-01

graphicsinterface.org/Graphics_Interface/2023/Conference_SD (published)

openreview.net

Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP

Anya Belz

Craig Thomson

Ehud Reiter

Gavin Abercrombie

Jose M. Alonso-moral

Mohammad Arvan

Jackie CK Cheung

Mark Cieliebak

Elizabeth Clark

Kees Van Deemter

Tanvi Dinkar

Ondrej Dusek

Steffen Eger

Qixiang Fang

Albert Gatt

Dimitra Gkatzia

Javier Gonz'alez-Corbelle

Dirk Hovy

Manuela Hurlimann

Takumi Ito … (see 19 more)

John D. Kelleher

Filip Klubicka

Huiyuan Lai

Chris van der Lee

Emiel van Miltenburg

Yiru Li

Saad Mahamood

Margot Mieskes

Malvina Nissim

Natalie Paige Parde

Ondvrej Pl'atek

Verena Teresa Rieser

Pablo Mosteiro Romero

Joel Joel Tetreault

Antonio Toral

Xiao-Yi Wan

Leo Wanner

Lewis Joshua Watson

Diyi Yang

We report our efforts in identifying a set of previous human evaluations in NLP that would be suitable for a coordinated study examining wha… (see more)t makes human evaluations in NLP more/less reproducible. We present our results and findings, which include that just 13% of papers had (i) sufficiently low barriers to reproduction, and (ii) enough obtainable information, to be considered for reproduction, and that all but one of the experiments we selected for reproduction was discovered to have flaws that made the meaningfulness of conducting a reproduction questionable. As a result, we had to change our coordinated study design from a reproduce approach to a standardise-then-reproduce-twice approach. Our overall (negative) finding that the great majority of human evaluations in NLP is not repeatable and/or not reproducible and/or too flawed to justify reproduction, paints a dire picture, but presents an opportunity for a rethink about how to design and report human evaluations in NLP.

2023-05-01

ArXiv (preprint)

doi.org

arxiv.org

156. Modeling Eye Gaze to Videos Using Dynamic Trajectory Variability Analysis

Qianying Wu

Na Yeon Kim

Jasmin Turner

Umit Keles

Lynn Paul

Danilo Bzdok

Ralph Adolphs

2023-04-30

Biological Psychiatry (published)

doi.org

ArK: Augmented Reality with Knowledge Interactive Emergent Ability

Qiuyuan Huang

J. Park

Abhinav Gupta

Pan Lu

Paul N. Bennett

Ran Gong

Subhojit Som

Baolin Peng

Owais Khan Mohammed

Christopher Pal

Yejin Choi

Jianfeng Gao

Despite the growing adoption of mixed reality and interactive AI agents, it remains challenging for these systems to generate high quality 2… (see more)D/3D scenes in unseen environments. The common practice requires deploying an AI agent to collect large amounts of data for model training for every new task. This process is costly, or even impossible, for many domains. In this study, we develop an infinite agent that learns to transfer knowledge memory from general foundation models (e.g. GPT4, DALLE) to novel domains or scenarios for scene understanding and generation in the physical or virtual world. The heart of our approach is an emerging mechanism, dubbed Augmented Reality with Knowledge Inference Interaction (ArK), which leverages knowledge-memory to generate scenes in unseen physical world and virtual reality environments. The knowledge interactive emergent ability (Figure 1) is demonstrated as the observation learns i) micro-action of cross-modality: in multi-modality models to collect a large amount of relevant knowledge memory data for each interaction task (e.g., unseen scene understanding) from the physical reality; and ii) macro-behavior of reality-agnostic: in mix-reality environments to improve interactions that tailor to different characterized roles, target variables, collaborative information, and so on. We validate the effectiveness of ArK on the scene generation and editing tasks. We show that our ArK approach, combined with large foundation models, significantly improves the quality of generated 2D/3D scenes, compared to baselines, demonstrating the potential benefit of incorporating ArK in generative AI for applications such as metaverse and gaming simulation.

2023-04-30

ArXiv (preprint)

doi.org

arxiv.org

Bird Distribution Modelling using Remote Sensing and Citizen Science data

Mlisande Teng

Amna Elmustafa

Benjamin Akera

Hugo Larochelle

David Rolnick

2023-04-30

arXiv (preprint)

doi.org

arxiv.org

Broken Neural Scaling Laws

Ethan Caballero

Kshitij Gupta

Irina Rish

David Krueger

We present a smoothly broken power law functional form (that we refer to as a Broken Neural Scaling Law (BNSL)) that accurately models &… (see more) extrapolates the scaling behaviors of deep neural networks (i.e. how the evaluation metric of interest varies as amount of compute used for training (or inference), number of model parameters, training dataset size, model input size, number of training steps, or upstream performance varies) for various architectures & for each of various tasks within a large & diverse set of upstream & downstream tasks, in zero-shot, prompted, & finetuned settings. This set includes large-scale vision, language, audio, video, diffusion, generative modeling, multimodal learning, contrastive learning, AI alignment, AI capabilities, robotics, out-of-distribution (OOD) generalization, continual learning, transfer learning, uncertainty estimation / calibration, OOD detection, adversarial robustness, distillation, sparsity, retrieval, quantization, pruning, fairness, molecules, computer programming/coding, math word problems, "emergent phase transitions", arithmetic, supervised learning, unsupervised/self-supervised learning, & reinforcement learning (single agent & multi-agent). When compared to other functional forms for neural scaling, this functional form yields extrapolations of scaling behavior that are considerably more accurate on this set. Moreover, this functional form accurately models & extrapolates scaling behavior that other functional forms are incapable of expressing such as the nonmonotonic transitions present in the scaling behavior of phenomena such as double descent & the delayed, sharp inflection points present in the scaling behavior of tasks such as arithmetic. Lastly, we use this functional form to glean insights about the limit of the predictability of scaling behavior. Code is available at https://github.com/ethancaballero/broken_neural_scaling_laws

2023-04-30

International Conference on Learning Representations (Accept: poster)

doi.org

openreview.net

E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking

Bozitao Zhong

In silico prediction of the ligand binding pose to a given protein target is a crucial but challenging task in drug discovery. This work foc… (see more)uses on blind flexible selfdocking, where we aim to predict the positions, orientations and conformations of docked molecules. Traditional physics-based methods usually suffer from inaccurate scoring functions and high inference cost. Recently, data-driven methods based on deep learning techniques are attracting growing interest thanks to their efficiency during inference and promising performance. These methods usually either adopt a two-stage approach by first predicting the distances between proteins and ligands and then generating the final coordinates based on the predicted distances, or directly predicting the global roto-translation of ligands. In this paper, we take a different route. Inspired by the resounding success of AlphaFold2 for protein structure prediction, we propose E3Bind, an end-to-end equivariant network that iteratively updates the ligand pose. E3Bind models the protein-ligand interaction through careful consideration of the geometric constraints in docking and the local context of the binding site. Experiments on standard benchmark datasets demonstrate the superior performance of our end-to-end trainable model compared to traditional and recently-proposed deep learning methods.

2023-04-30

International Conference on Learning Representations (Accept: poster)

doi.org

openreview.net

Embracing Channel Estimation in Multi-Packet Reception of ZigBee

Zhe Wang

Linghe Kong

Xue Liu

Guihai Chen

As a low-power and low-cost wireless protocol, the promising ZigBee has been widely used in sensor networks and cyber-physical systems. Sinc… (see more)e ZigBee based networks usually adopt tree or cluster topology, the convergecast scenarios are common in which multiple transmitters send packets to one receiver, leading to the severe collision problem. The conventional ZigBee adopts carrier sense multiple access with collisions avoidance to avoid collisions, which introduces additional time/energy overhead. The state-of-the-art methods resolve collisions instead of avoidance, in which mZig decomposes a collision by the collision itself and reZig decodes a collision by comparing with reference waveforms. However, mZig falls into high decoding errors only exploiting the signal amplitudes while reZig incurs high computational complexity for waveform comparison. In this paper, we propose CmZig to embrace channel estimation in multiple-packet reception (MPR) of ZigBee, which effectively improves MPR via lightweight computing used for channel estimation and collision decomposition. First, CmZig enables accurate collision decomposition with low computational complexity, which uses the estimated channel parameters modeling both signal amplitudes and phases. Second, CmZig adopts reference waveform comparison only for collisions without chip-level time offsets, instead of the complex machine learning based method. We implement CmZig on USRP-N210 and establish a six-node testbed. Results show that CmZig achieves a bit error rate in the order of

2023-04-30

IEEE Transactions on Mobile Computing (published)

doi.org

A General Framework for Proving the Equivariant Strong Lottery Ticket Hypothesis

Damien Ferbach

Christos Tsirigotis

Gauthier Gidel

Avishek (Joey) Bose

The Strong Lottery Ticket Hypothesis (SLTH) stipulates the existence of a subnetwork within a sufficiently overparameterized (dense) neural … (see more)network that -- when initialized randomly and without any training -- achieves the accuracy of a fully trained target network. Recent works by Da Cunha et. al 2022; Burkholz 2022 demonstrate that the SLTH can be extended to translation equivariant networks -- i.e. CNNs -- with the same level of overparametrization as needed for the SLTs in dense networks. However, modern neural networks are capable of incorporating more than just translation symmetry, and developing general equivariant architectures such as rotation and permutation has been a powerful design principle. In this paper, we generalize the SLTH to functions that preserve the action of the group

2023-04-30

International Conference on Learning Representations (Accept: poster)

doi.org

openreview.net

GFlowNets and Variational Inference

Nikolay Malkin

This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically us… (see more)ed to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs. We demonstrate that, in certain cases, VI algorithms are equivalent to special cases of GFlowNets in the sense of equality of expected gradients of their learning objectives. We then point out the differences between the two families and show how these differences emerge experimentally. Notably, GFlowNets, which borrow ideas from reinforcement learning, are more amenable than VI to off-policy training without the cost of high gradient variance induced by importance sampling. We argue that this property of GFlowNets can provide advantages for capturing diversity in multimodal target distributions.

2023-04-30

International Conference on Learning Representations (Accept: poster)

doi.org

openreview.net

How Gradient Estimator Variance and Bias Could Impact Learning in Neural Circuits

Arna Ghosh

Yuhan Helena Liu

Guillaume Lajoie

Konrad Kording

Blake A. Richards

2023-04-30

International Conference on Learning Representations (Accept: poster)