Search Results for author: Philip Torr

Found 116 papers, 45 papers with code

DreamPolisher: Towards High-Quality Text-to-3D Generation via Geometric Diffusion

no code implementations25 Mar 2024 Yuanze Lin, Ronald Clark, Philip Torr

We present DreamPolisher, a novel Gaussian Splatting based method with geometric guidance, tailored to learn cross-view consistency and intricate detail from textual descriptions.

Text to 3D

RoDLA: Benchmarking the Robustness of Document Layout Analysis Models

no code implementations21 Mar 2024 Yufan Chen, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ruiping Liu, Philip Torr, Rainer Stiefelhagen

To address this, we are the first to introduce a robustness benchmark for DLA models, which includes 450K document images of three datasets.

Benchmarking Document Layout Analysis

On Pretraining Data Diversity for Self-Supervised Learning

1 code implementation20 Mar 2024 Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem

We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget.

Self-Supervised Learning

DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM

no code implementations19 Mar 2024 Yixuan Wu, Yizhou Wang, Shixiang Tang, Wenhao Wu, Tong He, Wanli Ouyang, Jian Wu, Philip Torr

We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini.

Object object-detection +3

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models

no code implementations18 Mar 2024 Junlin Han, Filippos Kokkinos, Philip Torr

This results in a significant disparity in scale compared to the vast quantities of other types of data.

A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization

no code implementations17 Mar 2024 Yudong Luo, Yangchen Pan, Han Wang, Philip Torr, Pascal Poupart

Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications.

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models

1 code implementation14 Mar 2024 Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr

Given that VLMs rely on prompts to adapt to different tasks, an intriguing question emerges: Can a single adversarial image mislead all predictions of VLMs when a thousand different prompts are given?

GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing

no code implementations13 Mar 2024 Jing Wu, Jia-Wang Bian, Xinghui Li, Guangrun Wang, Ian Reid, Philip Torr, Victor Adrian Prisacariu

We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS).

Lifelong Benchmarks: Efficient Model Evaluation in an Era of Rapid Progress

1 code implementation29 Feb 2024 Ameya Prabhu, Vishaal Udandarao, Philip Torr, Matthias Bethge, Adel Bibi, Samuel Albanie

However, with repeated testing, the risk of overfitting grows as algorithms over-exploit benchmark idiosyncrasies.

Benchmarking

Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images

no code implementations22 Feb 2024 Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu

Our research evaluates the adversarial robustness of MLLMs when employing CoT reasoning, finding that CoT marginally improves adversarial robustness against existing attack methods.

Adversarial Robustness

Corrective Machine Unlearning

1 code implementation21 Feb 2024 Shashwat Goel, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Amartya Sanyal

We hope our work spurs research towards developing better methods for corrective unlearning and offers practitioners a new strategy to handle data integrity challenges arising from web-scale training.

Machine Unlearning

SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?

1 code implementation2 Feb 2024 Hasan Abed Al Kader Hammoud, Hani Itani, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem

We present SynthCLIP, a novel framework for training CLIP models with entirely synthetic text-image pairs, significantly departing from previous methods relying on real data.

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

1 code implementation20 Jan 2024 Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu

Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources.

Measuring Value Alignment

no code implementations23 Dec 2023 Fazl Barez, Philip Torr

As artificial intelligence (AI) systems become increasingly integrated into various domains, ensuring that they align with human values becomes critical.

Autonomous Vehicles Recommendation Systems

Scene-Conditional 3D Object Stylization and Composition

no code implementations19 Dec 2023 Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht

Recently, 3D generative models have made impressive progress, enabling the generation of almost arbitrary 3D assets from text or image inputs.

Object

Label Delay in Continual Learning

no code implementations1 Dec 2023 Botos Csaba, Wenxuan Zhang, Matthias Müller, Ser-Nam Lim, Mohamed Elhoseiny, Philip Torr, Adel Bibi

We introduce a new continual learning framework with explicit modeling of the label delay between data and label streams over time steps.

Continual Learning

Improving Adversarial Transferability via Model Alignment

no code implementations30 Nov 2023 Avery Ma, Amir-Massoud Farahmand, Yangchen Pan, Philip Torr, Jindong Gu

During the alignment process, the parameters of the source model are fine-tuned to minimize an alignment loss.

Understanding and Improving In-Context Learning on Vision-language Models

no code implementations29 Nov 2023 Shuo Chen, Zhen Han, Bailan He, Mark Buckley, Philip Torr, Volker Tresp, Jindong Gu

Our findings indicate that ICL in VLMs is predominantly driven by the textual information in the demonstrations whereas the visual information in the demonstrations barely affects the ICL performance.

In-Context Learning

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

1 code implementation16 Oct 2023 Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr, Bo Zhao

Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation.

Image Classification Out-of-Distribution Generalization

Beyond Training Objectives: Interpreting Reward Model Divergence in Large Language Models

no code implementations12 Oct 2023 Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, Philip Torr, Fazl Barez

Large language models (LLMs) fine-tuned by reinforcement learning from human feedback (RLHF) are becoming more widely deployed.

PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction

no code implementations11 Oct 2023 Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip Torr

On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69. 18 to 75. 67, outperforming that with the dataset provided ground-truth pose (75. 14).

Surface Reconstruction

Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks

no code implementations12 Sep 2023 Jindong Gu, Fangyun Wei, Philip Torr, Han Hu

In this work, we first taxonomize the stochastic defense strategies against QBBA.

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

2 code implementations3 Aug 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, DaCheng Tao, Bernard Ghanem

Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting.

Few-Shot Class-Incremental Learning Incremental Learning

A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models

1 code implementation24 Jul 2023 Jindong Gu, Zhen Han, Shuo Chen, Ahmad Beirami, Bailan He, Gengyuan Zhang, Ruotong Liao, Yao Qin, Volker Tresp, Philip Torr

This paper aims to provide a comprehensive survey of cutting-edge research in prompt engineering on three types of vision-language models: multimodal-to-text generation models (e. g. Flamingo), image-text matching models (e. g.

Image-text matching Language Modelling +4

OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?

no code implementations ICCV 2023 Runjia Li, Shuyang Sun, Mohamed Elhoseiny, Philip Torr

Hence, humour generation and understanding can serve as a new task for evaluating the ability of deep-learning methods to process abstract and subjective information.

Image Captioning

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

1 code implementation NeurIPS 2023 Shuyang Sun, Weijun Wang, Qihang Yu, Andrew Howard, Philip Torr, Liang-Chieh Chen

This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment.

Panoptic Segmentation Segmentation

Reliable Evaluation of Adversarial Transferability

no code implementations14 Jun 2023 Wenqian Yu, Jindong Gu, Zhijiang Li, Philip Torr

Adversarial examples (AEs) with small adversarial perturbations can mislead deep neural networks (DNNs) into wrong predictions.

Graph Inductive Biases in Transformers without Message Passing

1 code implementation27 May 2023 Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim

Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings.

Graph Classification Graph Regression +2

Provably Correct Physics-Informed Neural Networks

no code implementations17 May 2023 Francisco Eiras, Adel Bibi, Rudy Bunel, Krishnamurthy Dj Dvijotham, Philip Torr, M. Pawan Kumar

Recent work provides promising evidence that Physics-informed neural networks (PINN) can efficiently solve partial differential equations (PDE).

Online Continual Learning Without the Storage Constraint

1 code implementation16 May 2023 Ameya Prabhu, Zhipeng Cai, Puneet Dokania, Philip Torr, Vladlen Koltun, Ozan Sener

In this paper, we target such applications, investigating the online continual learning problem under relaxed storage constraints and limited computational budgets.

Continual Learning

Towards Robust Prompts on Vision-Language Models

no code implementations17 Apr 2023 Jindong Gu, Ahmad Beirami, Xuezhi Wang, Alex Beutel, Philip Torr, Yao Qin

With the advent of vision-language models (VLMs) that can perform in-context and prompt-based learning, how can we design prompting approaches that robustly generalize to distribution shift and can be used on novel classes outside the support set of the prompts?

In-Context Learning

Influencer Backdoor Attack on Semantic Segmentation

no code implementations21 Mar 2023 Haoheng Lan, Jindong Gu, Philip Torr, Hengshuang Zhao

In this work, we explore backdoor attacks on segmentation models to misclassify all pixels of a victim class by injecting a specific trigger on non-victim pixels during inferences, which is dubbed Influencer Backdoor Attack (IBA).

Backdoor Attack Position +2

Reliability in Semantic Segmentation: Are We on the Right Track?

1 code implementation CVPR 2023 Pau de Jorge, Riccardo Volpi, Philip Torr, Gregory Rogez

We analyze a broad variety of models, spanning from older ResNet-based architectures to novel transformers and assess their reliability based on four metrics: robustness, calibration, misclassification detection and out-of-distribution (OOD) detection.

Out of Distribution (OOD) Detection Semantic Segmentation

PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer

no code implementations7 Feb 2023 Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Yawen Cui, Jiehua Zhang, Philip Torr, Guoying Zhao

As key modules in PhysFormer, the temporal difference transformers first enhance the quasi-periodic rPPG features with temporal difference guided global attention, and then refine the local spatio-temporal representation against interference.

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning

1 code implementation6 Feb 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao

In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).

Few-Shot Class-Incremental Learning Incremental Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning

1 code implementation ICLR 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao

In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).

Few-Shot Class-Incremental Learning Incremental Learning

Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators

no code implementations21 Dec 2022 Jianhao Yuan, Francesco Pinto, Adam Davies, Philip Torr

Neural image classifiers are known to undergo severe performance degradation when exposed to inputs that exhibit covariate shifts with respect to the training distribution.

Domain Generalization Image Augmentation +1

LUMix: Improving Mixup by Better Modelling Label Uncertainty

no code implementations29 Nov 2022 Shuyang Sun, Jie-Neng Chen, Ruifei He, Alan Yuille, Philip Torr, Song Bai

LUMix is simple as it can be implemented in just a few lines of code and can be universally applied to any deep networks \eg CNNs and Vision Transformers, with minimal computational cost.

Data Augmentation

Is synthetic data from generative models ready for image recognition?

1 code implementation14 Oct 2022 Ruifei He, Shuyang Sun, Xin Yu, Chuhui Xue, Wenqing Zhang, Philip Torr, Song Bai, Xiaojuan Qi

Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images.

Text-to-Image Generation Transfer Learning

Diversified Dynamic Routing for Vision Tasks

no code implementations26 Sep 2022 Botos Csaba, Adel Bibi, Yanwei Li, Philip Torr, Ser-Nam Lim

Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all samples.

Instance Segmentation object-detection +2

SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness

1 code implementation25 Jul 2022 Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip Torr

Since SegPGD can create more effective adversarial examples, the adversarial training with our SegPGD can boost the robustness of segmentation models.

Adversarial Attack Segmentation +1

MP2: A Momentum Contrast Approach for Recommendation with Pointwise and Pairwise Learning

no code implementations18 Apr 2022 Menghan Wang, Yuchen Guo, Zhenqi Zhao, Guangzheng Hu, Yuming Shen, Mingming Gong, Philip Torr

To alleviate the influence of the annotation bias, we perform a momentum update to ensure a consistent item representation.

Task-Agnostic Robust Representation Learning

no code implementations15 Mar 2022 A. Tuan Nguyen, Ser Nam Lim, Philip Torr

To tackle this problem, a great amount of research has been done to study the training procedure of a network to improve its robustness.

Representation Learning Self-Supervised Learning

Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting

no code implementations8 Mar 2022 Chuhui Xue, Wenqing Zhang, Yu Hao, Shijian Lu, Philip Torr, Song Bai

Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features, respectively, as well as a visual-textual decoder that models the interaction among textual and visual features for learning effective scene text representations.

Optical Character Recognition Optical Character Recognition (OCR) +2

Gradients without Backpropagation

2 code implementations17 Feb 2022 Atılım Güneş Baydin, Barak A. Pearlmutter, Don Syme, Frank Wood, Philip Torr

Using backpropagation to compute gradients of objective functions for optimization has remained a mainstay of machine learning.

Deeply Explain CNN via Hierarchical Decomposition

no code implementations23 Jan 2022 Ming-Ming Cheng, Peng-Tao Jiang, Ling-Hao Han, Liang Wang, Philip Torr

The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process.

Decision Making

Towards Adversarial Evaluations for Inexact Machine Unlearning

3 code implementations17 Jan 2022 Shashwat Goel, Ameya Prabhu, Amartya Sanyal, Ser-Nam Lim, Philip Torr, Ponnurangam Kumaraguru

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias.

Machine Unlearning Memorization

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

1 code implementation CVPR 2022 Yujun Shi, Kuangqi Zhou, Jian Liang, Zihang Jiang, Jiashi Feng, Philip Torr, Song Bai, Vincent Y. F. Tan

Specifically, we experimentally show that directly encouraging CIL Learner at the initial phase to output similar representations as the model jointly trained on all classes can greatly boost the CIL performance.

Class Incremental Learning Incremental Learning

A Continuous Mapping For Augmentation Design

no code implementations NeurIPS 2021 Keyu Tian, Chen Lin, Ser Nam Lim, Wanli Ouyang, Puneet Dokania, Philip Torr

Automated data augmentation (ADA) techniques have played an important role in boosting the performance of deep models.

Data Augmentation

Overcoming the Convex Barrier for Simplex Inputs

no code implementations NeurIPS 2021 Harkirat Singh Behl, M. Pawan Kumar, Philip Torr, Krishnamurthy Dvijotham

Recent progress in neural network verification has challenged the notion of a convex barrier, that is, an inherent weakness in the convex relaxation of the output of a neural network.

PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer

1 code implementation CVPR 2022 Zitong Yu, Yuming Shen, Jingang Shi, Hengshuang Zhao, Philip Torr, Guoying Zhao

Remote photoplethysmography (rPPG), which aims at measuring heart activities and physiological signals from facial video without any contact, has great potential in many applications (e. g., remote healthcare and affective computing).

Adversarial Examples on Segmentation Models Can be Easy to Transfer

no code implementations22 Nov 2021 Jindong Gu, Hengshuang Zhao, Volker Tresp, Philip Torr

The high transferability achieved by our method shows that, in contrast to the observations in previous work, adversarial examples on a segmentation model can be easy to transfer to other segmentation models.

Adversarial Robustness Attribute +5

TransMix: Attend to Mix for Vision Transformers

2 code implementations CVPR 2022 Jie-Neng Chen, Shuyang Sun, Ju He, Philip Torr, Alan Yuille, Song Bai

The confidence of the label will be larger if the corresponding input image is weighted higher by the attention map.

Instance Segmentation object-detection +3

Towards fast and effective single-step adversarial training

no code implementations29 Sep 2021 Pau de Jorge, Adel Bibi, Riccardo Volpi, Amartya Sanyal, Philip Torr, Grégory Rogez, Puneet K. Dokania

In this work, we methodically revisit the role of noise and clipping in single-step adversarial training.

Mix-MaxEnt: Creating High Entropy Barriers To Improve Accuracy and Uncertainty Estimates of Deterministic Neural Networks

no code implementations29 Sep 2021 Francesco Pinto, Harry Yang, Ser-Nam Lim, Philip Torr, Puneet K. Dokania

We propose an extremely simple approach to regularize a single deterministic neural network to obtain improved accuracy and reliable uncertainty estimates.

Shape-Tailored Deep Neural Networks With PDEs

no code implementations NeurIPS Workshop DLDE 2021 Naeemullah Khan, Angira Sharma, Philip Torr, Ganesh Sundaramoorthi

ST-DNN are deep networks formulated through the use of partial differential equations (PDE) to be defined on arbitrarily shaped regions.

Vision Transformer with Progressive Sampling

1 code implementation ICCV 2021 Xiaoyu Yue, Shuyang Sun, Zhanghui Kuang, Meng Wei, Philip Torr, Wayne Zhang, Dahua Lin

As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image classification, by simply splitting images into tokens with a fixed length, and employing transformers to learn relations between these tokens.

Image Classification

Multilevel Knowledge Transfer for Cross-Domain Object Detection

no code implementations2 Aug 2021 Botos Csaba, Xiaojuan Qi, Arslan Chaudhry, Puneet Dokania, Philip Torr

The key ingredients to our approach are -- (a) mapping the source to the target domain on pixel-level; (b) training a teacher network on the mapped source and the unannotated target domain using adversarial feature alignment; and (c) finally training a student network using the pseudo-labels obtained from the teacher.

Object object-detection +2

Open-World Entity Segmentation

2 code implementations29 Jul 2021 Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia

By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality.

Image Manipulation Image Segmentation +2

Communicating via Markov Decision Processes

1 code implementation17 Jul 2021 Samuel Sokota, Christian Schroeder de Witt, Maximilian Igl, Luisa Zintgraf, Philip Torr, Martin Strohmeier, J. Zico Kolter, Shimon Whiteson, Jakob Foerster

We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME.

Multi-agent Reinforcement Learning

Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation

1 code implementation16 Jul 2021 Angira Sharma, Naeemullah Khan, Muhammad Mubashar, Ganesh Sundaramoorthi, Philip Torr

For low-fidelity training data (incorrect class label) class-agnostic segmentation loss outperforms the state-of-the-art methods on salient object detection datasets by staggering margins of around 50%.

Object object-detection +3

Visual Parser: Representing Part-whole Hierarchies with Transformers

2 code implementations13 Jul 2021 Shuyang Sun, Xiaoyu Yue, Song Bai, Philip Torr

To model the representations of the two levels, we first encode the information from the whole into part vectors through an attention mechanism, then decode the global information within the part vectors back into the whole representation.

Image Classification Instance Segmentation +3

Large-scale Unsupervised Semantic Segmentation

3 code implementations6 Jun 2021 ShangHua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip Torr

In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.

Representation Learning Segmentation +1

General Adversarial Defense via Pixel Level and Feature Level Distribution Alignment

no code implementations1 Jan 2021 Xiaogang Xu, Hengshuang Zhao, Philip Torr, Jiaya Jia

Specifically, compared with previous methods, we propose a more efficient pixel-level training constraint to weaken the hardness of aligning adversarial samples to clean samples, which can thus obviously enhance the robustness on adversarial samples.

Adversarial Defense Image Classification +3

How Benign is Benign Overfitting ?

no code implementations ICLR 2021 Amartya Sanyal, Puneet K. Dokania, Varun Kanade, Philip Torr

We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models.

Adversarial Robustness Representation Learning

Point Transformer

24 code implementations ICCV 2021 Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip Torr, Vladlen Koltun

For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.

3D Part Segmentation 3D Point Cloud Classification +8

Learning to Sample the Most Useful Training Patches from Images

no code implementations24 Nov 2020 Shuyang Sun, Liang Chen, Gregory Slabaugh, Philip Torr

Some image restoration tasks like demosaicing require difficult training samples to learn effective models.

Demosaicking

Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation

1 code implementation28 Oct 2020 Angira Sharma, Naeemullah Khan, Ganesh Sundaramoorthi, Philip Torr

For low-fidelity training data (incorrect class label) class-agnostic segmentation loss outperforms the state-of-the-art methods on salient object detection datasets by staggering margins of around 50%.

Object object-detection +3

Simulation-Based Inference for Global Health Decisions

2 code implementations14 May 2020 Christian Schroeder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Rob Zinkov, Puneet Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip Torr, Atılım Güneş Baydin

The COVID-19 pandemic has highlighted the importance of in-silico epidemiological modelling in predicting the dynamics of infectious diseases to inform health policy and decision makers about suitable prevention and containment strategies.

Bayesian Inference Epidemiology

Global Texture Enhancement for Fake Face Detection in the Wild

1 code implementation CVPR 2020 Zhengzhe Liu, Xiaojuan Qi, Philip Torr

In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets.

Face Detection Fake Image Detection

Domain-invariant Stereo Matching Networks

1 code implementation ECCV 2020 Feihu Zhang, Xiaojuan Qi, Ruigang Yang, Victor Prisacariu, Benjamin Wah, Philip Torr

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture.

Stereo Matching

Efficient Bayesian Inference for Nested Simulators

no code implementations pproximateinference AABI Symposium 2019 Bradley Gram-Hansen, Christian Schroeder de Witt, Robert Zinkov, Saeid Naderiparizi, Adam Scibior, Andreas Munk, Frank Wood, Mehrdad Ghadiri, Philip Torr, Yee Whye Teh, Atilim Gunes Baydin, Tom Rainforth

We introduce two approaches for conducting efficient Bayesian inference in stochastic simulators containing nested stochastic sub-procedures, i. e., internal procedures for which the density cannot be calculated directly such as rejection sampling loops.

Bayesian Inference

The Intriguing Effects of Focal Loss on the Calibration of Deep Neural Networks

no code implementations25 Sep 2019 Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal, Stuart Golodetz, Philip Torr, Puneet Dokania

When combined with temperature scaling, focal loss, whilst preserving accuracy and yielding state-of-the-art calibrated models, also preserves the confidence of the model's correct predictions, which is extremely desirable for downstream tasks.

ShardNet: One Filter Set to Rule Them All

no code implementations25 Sep 2019 Saumya Jetley, Tommaso Cavallari, Philip Torr, Stuart Golodetz

Deep CNNs have achieved state-of-the-art performance for numerous machine learning and computer vision tasks in recent years, but as they have become increasingly deep, the number of parameters they use has also increased, making them hard to deploy in memory-constrained environments and difficult to interpret.

Learning Theory

Res2Net: A New Multi-scale Backbone Architecture

32 code implementations2 Apr 2019 Shang-Hua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr

We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e. g., CIFAR-100 and ImageNet.

Image Classification Instance Segmentation +4

Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

3 code implementations NeurIPS 2019 Atılım Güneş Baydin, Lukas Heinrich, Wahid Bhimji, Lei Shao, Saeid Naderiparizi, Andreas Munk, Jialin Liu, Bradley Gram-Hansen, Gilles Louppe, Lawrence Meadows, Philip Torr, Victor Lee, Prabhat, Kyle Cranmer, Frank Wood

We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which allows general-purpose inference engines to record and control random number draws within simulators in a language-agnostic way.

Probabilistic Programming

A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials

no code implementations24 Jan 2017 Måns Larsson, Anurag Arnab, Fredrik Kahl, Shuai Zheng, Philip Torr

It is empirically demonstrated that such learned potentials can improve segmentation accuracy and that certain label class interactions are indeed better modelled by a non-Gaussian potential.

Segmentation Semantic Segmentation +1

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

4 code implementations ICCV 2017 Gurkirt Singh, Suman Saha, Michael Sapienza, Philip Torr, Fabio Cuzzolin

To the best of our knowledge, ours is the first real-time (up to 40fps) system able to perform online S/T action localisation and early action prediction on the untrimmed videos of UCF101-24.

Early Action Prediction

Deeply supervised salient object detection with short connections

4 code implementations CVPR 2017 Qibin Hou, Ming-Ming Cheng, Xiao-Wei Hu, Ali Borji, Zhuowen Tu, Philip Torr

Recent progress on saliency detection is substantial, benefiting mostly from the explosive development of Convolutional Neural Networks (CNNs).

Boundary Detection Object +5

Joint Object-Material Category Segmentation from Audio-Visual Cues

no code implementations10 Jan 2016 Anurag Arnab, Michael Sapienza, Stuart Golodetz, Julien Valentin, Ondrej Miksik, Shahram Izadi, Philip Torr

It is not always possible to recognise objects and infer material properties for a scene from visual cues alone, since objects can look visually similar whilst being made of very different materials.

Object

Staple: Complementary Learners for Real-Time Tracking

3 code implementations CVPR 2016 Luca Bertinetto, Jack Valmadre, Stuart Golodetz, Ondrej Miksik, Philip Torr

Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes.

regression Visual Object Tracking

Prototypical Priors: From Improving Classification to Zero-Shot Learning

no code implementations3 Dec 2015 Saumya Jetley, Bernardino Romera-Paredes, Sadeep Jayasumana, Philip Torr

Recent works on zero-shot learning make use of side information such as visual attributes or natural language semantics to define the relations between output visual classes and then use these relationships to draw inference on new unseen classes at test time.

Classification General Classification +1

Higher Order Conditional Random Fields in Deep Neural Networks

1 code implementation25 Nov 2015 Anurag Arnab, Sadeep Jayasumana, Shuai Zheng, Philip Torr

Recent deep learning approaches have incorporated CRFs into Convolutional Neural Networks (CNNs), with some even training the CRF end-to-end with the rest of the network.

Segmentation Semantic Segmentation +1

BING: Binarized Normed Gradients for Objectness Estimation at 300fps

no code implementations CVPR 2014 Ming-Ming Cheng, Ziming Zhang, Wen-Yan Lin, Philip Torr

Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm.

Object object-detection +1

Efficient Semidefinite Branch-and-Cut for MAP-MRF Inference

no code implementations20 Apr 2014 Peng Wang, Chunhua Shen, Anton Van Den Hengel, Philip Torr

We propose a Branch-and-Cut (B&C) method for solving general MAP-MRF inference problems.

Higher Order Priors for Joint Intrinsic Image, Objects, and Attributes Estimation

no code implementations NeurIPS 2013 Vibhav Vineet, Carsten Rother, Philip Torr

Many methods have been proposed to recover the intrinsic scene properties such as shape, reflectance and illumination from a single image.

ImageSpirit: Verbal Guided Image Parsing

no code implementations16 Oct 2013 Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Jonathan Warrell, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy Mitra, Philip Torr

This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.

Attribute Object

Learning Anchor Planes for Classification

no code implementations NeurIPS 2011 Ziming Zhang, Lubor Ladicky, Philip Torr, Amir Saffari

It provides a set of anchor points which form a local coordinate system, such that each data point on the manifold can be approximated by a linear combination of its anchor points, and the linear weights become the local coordinate coding.

Classification General Classification

Improved Moves for Truncated Convex Models

no code implementations NeurIPS 2008 Philip Torr, M. P. Kumar

Compared to previous approaches based on the LP relaxation, e. g. interior-point algorithms or tree-reweighted message passing (TRW), our method is faster as it uses only the efficient st-mincut algorithm in its design.

Cannot find the paper you are looking for? You can Submit a new open access paper.