Timezone: »
We present Shape-Tailored Deep Neural Networks (ST-DNN). ST-DNN are deep networks formulated through the use of partial differential equations (PDE) to be defined on arbitrarily shaped regions. This is natural for problems in computer vision such as segmentation, where descriptors should describe regions (e.g., of objects) that have diverse shape. We formulate ST-DNNs through the Poisson PDE, which can be used to generalize convolution to arbitrary regions. We stack multiple PDE layers to generalize a deep CNN to arbitrarily shaped regions. We show that ST-DNN are provably covariant to translations and rotations and robust to domain deformations, which are important properties for computer vision tasks. We show proof-of-concept empirical validation.
Author Information
Naeemullah Khan (University of Oxford)
Angira Sharma (University of Oxford)
Philip Torr (University of Oxford)
Ganesh Sundaramoorthi (Raytheon)
More from the Same Authors
-
2021 : Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge »
Jiyang Qi · Yan Gao · Yao Hu · Xinggang Wang · Xiaoyu Liu · Xiang Bai · Serge Belongie · Alan Yuille · Philip Torr · Song Bai -
2021 : Are Vision Transformers Always More Robust Than Convolutional Neural Networks? »
Francesco Pinto · Philip Torr · Puneet Dokania -
2021 : Mix-MaxEnt: Improving Accuracy and Uncertainty Estimates of Deterministic Neural Networks »
Francesco Pinto · Harry Yang · Ser Nam Lim · Philip Torr · Puneet Dokania -
2023 Poster: ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation »
Shuyang Sun · Weijun Wang · Andrew Howard · Qihang Yu · Philip Torr · Liang-Chieh Chen -
2023 Poster: Language Model Tokenizers Introduce Unfairness Between Languages »
Aleksandar Petrov · Emanuele La Malfa · Philip Torr · Adel Bibi -
2023 Poster: Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union »
Zifu Wang · Maxim Berman · Amal Rannen-Triki · Philip Torr · Devis Tuia · Tinne Tuytelaars · Luc V Gool · Jiaqian Yu · Matthew Blaschko -
2023 Poster: Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models »
Shuo Chen · Jindong Gu · Zhen Han · Yunpu Ma · Philip Torr · Volker Tresp -
2022 Poster: Using Mixup as a Regularizer Can Surprisingly Improve Accuracy & Out-of-Distribution Robustness »
Francesco Pinto · Harry Yang · Ser Nam Lim · Philip Torr · Puneet Dokania -
2022 Poster: Structure-Preserving 3D Garment Modeling with Neural Sewing Machines »
Xipeng Chen · Guangrun Wang · Dizhong Zhu · Xiaodan Liang · Philip Torr · Liang Lin -
2022 Poster: Learn what matters: cross-domain imitation learning with task-relevant embeddings »
Tim Franzmeyer · Philip Torr · João Henriques -
2022 Poster: Make Some Noise: Reliable and Efficient Single-Step Adversarial Training »
Pau de Jorge Aranda · Adel Bibi · Riccardo Volpi · Amartya Sanyal · Philip Torr · Gregory Rogez · Puneet Dokania -
2022 Poster: FedSR: A Simple and Effective Domain Generalization Method for Federated Learning »
A. Tuan Nguyen · Philip Torr · Ser Nam Lim -
2021 : Accelerated PDEs for Construction and Theoretical Analysis of an SGD Extension »
Yuxin Sun · Dong Lao · Ganesh Sundaramoorthi · Anthony Yezzi -
2021 Poster: You Never Cluster Alone »
Yuming Shen · Ziyi Shen · Menghan Wang · Jie Qin · Philip Torr · Ling Shao -
2021 Poster: Looking Beyond Single Images for Contrastive Semantic Segmentation Learning »
FEIHU ZHANG · Philip Torr · Rene Ranftl · Stephan Richter -
2021 Poster: FACMAC: Factored Multi-Agent Centralised Policy Gradients »
Bei Peng · Tabish Rashid · Christian Schroeder de Witt · Pierre-Alexandre Kamienny · Philip Torr · Wendelin Boehmer · Shimon Whiteson -
2021 Poster: Do Different Tracking Tasks Require Different Appearance Models? »
Zhongdao Wang · Hengshuang Zhao · Ya-Li Li · Shengjin Wang · Philip Torr · Luca Bertinetto -
2021 Poster: A Continuous Mapping For Augmentation Design »
Keyu Tian · Chen Lin · Ser Nam Lim · Wanli Ouyang · Puneet Dokania · Philip Torr -
2021 Poster: Overcoming the Convex Barrier for Simplex Inputs »
Harkirat Singh Behl · M. Pawan Kumar · Philip Torr · Krishnamurthy Dvijotham -
2020 Poster: STEER : Simple Temporal Regularization For Neural ODE »
Arnab Ghosh · Harkirat Singh Behl · Emilien Dupont · Philip Torr · Vinay Namboodiri -
2020 Poster: Calibrating Deep Neural Networks using Focal Loss »
Jishnu Mukhoti · Viveka Kulharia · Amartya Sanyal · Stuart Golodetz · Philip Torr · Puneet Dokania -
2020 Poster: Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation »
Bowen Li · Xiaojuan Qi · Philip Torr · Thomas Lukasiewicz -
2020 Poster: Continual Learning in Low-rank Orthogonal Subspaces »
Arslan Chaudhry · Naeemullah Khan · Puneet Dokania · Philip Torr -
2019 : Coffee + Posters »
Changhao Chen · Nils Gählert · Edouard Leurent · Johannes Lehner · Apratim Bhattacharyya · Harkirat Singh Behl · Teck Yian Lim · Shiho Kim · Jelena Novosel · Błażej Osiński · Arindam Das · Ruobing Shen · Jeffrey Hawke · Joachim Sicking · Babak Shahian Jahromi · Theja Tulabandhula · Claudio Michaelis · Evgenia Rusak · WENHANG BAO · Hazem Rashed · JP Chen · Amin Ansari · Jaekwang Cha · Mohamed Zahran · Daniele Reda · Jinhyuk Kim · Kim Dohyun · Ho Suk · Junekyo Jhung · Alexander Kister · Matthias Fahrland · Adam Jakubowski · Piotr Miłoś · Jean Mercat · Bruno Arsenali · Silviu Homoceanu · Xiao-Yang Liu · Philip Torr · Ahmad El Sallab · Ibrahim Sobh · Anurag Arnab · Krzysztof Galias -
2019 Poster: Multi-Agent Common Knowledge Reinforcement Learning »
Christian Schroeder de Witt · Jakob Foerster · Gregory Farquhar · Philip Torr · Wendelin Boehmer · Shimon Whiteson -
2019 Poster: Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model »
Atilim Gunes Baydin · Lei Shao · Wahid Bhimji · Lukas Heinrich · Saeid Naderiparizi · Andreas Munk · Jialin Liu · Bradley Gram-Hansen · Gilles Louppe · Lawrence Meadows · Philip Torr · Victor Lee · Kyle Cranmer · Mr. Prabhat · Frank Wood -
2019 Poster: Controllable Text-to-Image Generation »
Bowen Li · Xiaojuan Qi · Thomas Lukasiewicz · Philip Torr -
2018 Poster: A Unified View of Piecewise Linear Neural Network Verification »
Rudy Bunel · Ilker Turkaslan · Philip Torr · Pushmeet Kohli · Pawan K Mudigonda -
2017 Poster: Learning Disentangled Representations with Semi-Supervised Deep Generative Models »
Siddharth Narayanaswamy · Brooks Paige · Jan-Willem van de Meent · Alban Desmaison · Noah Goodman · Pushmeet Kohli · Frank Wood · Philip Torr -
2016 Poster: Adaptive Neural Compilation »
Rudy Bunel · Alban Desmaison · Pawan K Mudigonda · Pushmeet Kohli · Philip Torr -
2016 Poster: Learning feed-forward one-shot learners »
Luca Bertinetto · João Henriques · Jack Valmadre · Philip Torr · Andrea Vedaldi -
2013 Poster: Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation »
Vibhav Vineet · Carsten Rother · Philip Torr -
2011 Poster: Learning Anchor Planes for Classification »
Ziming Zhang · Lubor Ladicky · Philip Torr · Amir Saffari -
2011 Demonstration: Online structured-output learning for real-time object tracking and detection »
Sam Hare · Amir Saffari · Philip Torr -
2008 Poster: Improved Moves for Truncated Convex Models »
Pawan K Mudigonda · Philip Torr -
2008 Spotlight: Improved Moves for Truncated Convex Models »
Pawan K Mudigonda · Philip Torr -
2007 Oral: An Analysis of Convex Relaxations for MAP Estimation »
Pawan K Mudigonda · Vladimir Kolmogorov · Philip Torr -
2007 Poster: An Analysis of Convex Relaxations for MAP Estimation »
Pawan K Mudigonda · Vladimir Kolmogorov · Philip Torr