Philip H. S. Torr

research

∙ 08/25/2023

Fine-tuning can cripple your foundation model; preserving features may be the solution

Pre-trained foundation models, owing primarily to their enormous capacit...

0 Jishnu Mukhoti, et al. ∙

research

∙ 06/07/2023

Faithful Knowledge Distillation

Knowledge distillation (KD) has received much attention due to its succe...

0 Tom A. Lamb, et al. ∙

research

∙ 05/16/2023

Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?

We revisit the common practice of evaluating adaptation of Online Contin...

0 Hasan Abed Al Kader Hammoud, et al. ∙

research

∙ 04/25/2023

Certifying Ensembles: A General Certification Theory with S-Lipschitzness

Improving and guaranteeing the robustness of deep learning models has be...

0 Aleksandar Petrov, et al. ∙

research

∙ 04/16/2023

Fairness in AI and Its Long-Term Implications on Society

Successful deployment of artificial intelligence (AI) in various setting...

0 Ondrej Bohdal, et al. ∙

research

∙ 03/23/2023

Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs

In this paper we investigate the frequency sensitivity of Deep Neural Ne...

0 Hasan Abed Al Kader Hammoud, et al. ∙

research

∙ 03/20/2023

Computationally Budgeted Continual Learning: What Does Matter?

Continual Learning (CL) aims to sequentially train models on streams of ...

0 Ameya Prabhu, et al. ∙

research

∙ 03/11/2023

Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation

Referring image segmentation segments an image from a language expressio...

0 Zhao Yang, et al. ∙

research

∙ 03/03/2023

MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices

High-quality 3D ground-truth shapes are critical for 3D object reconstru...

0 Kejie Li, et al. ∙

research

∙ 02/02/2023

Real-Time Evaluation in Online Continual Learning: A New Paradigm

Current evaluations of Continual Learning (CL) methods typically assume ...

5 Yasir Ghunaim, et al. ∙

research

∙ 11/27/2022

Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

Classifiers and generators have long been separated. We break down this ...

0 Guangrun Wang, et al. ∙

research

∙ 11/12/2022

Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis

We present a novel bipartite graph reasoning Generative Adversarial Netw...

0 Hao Tang, et al. ∙

research

∙ 11/12/2022

Structure-Preserving 3D Garment Modeling with Neural Sewing Machines

3D Garment modeling is a critical and challenging topic in the area of c...

0 Xipeng Chen, et al. ∙

research

∙ 10/24/2022

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

This paper presents Holistically-Attracted Wireframe Parsing (HAWP) for ...

0 Nan Xue, et al. ∙

research

∙ 09/24/2022

Learn what matters: cross-domain imitation learning with task-relevant embeddings

We study how an autonomous agent learns to perform a task from demonstra...

1 Tim Franzmeyer, et al. ∙

research

∙ 09/24/2022

Raising the Bar on the Evaluation of Out-of-Distribution Detection

In image classification, a lot of development has happened in detecting ...

6 Jishnu Mukhoti, et al. ∙

research

∙ 09/20/2022

Dynamic Graph Message Passing Networks for Visual Recognition

Modelling long-range dependencies is critical for scene understanding ta...

17 Li Zhang, et al. ∙

research

∙ 08/15/2022

Memory-Driven Text-to-Image Generation

We introduce a memory-driven semi-parametric approach to text-to-image g...

8 Bowen Li, et al. ∙

research

∙ 07/22/2022

An Impartial Take to the CNN vs Transformer Robustness Contest

Following the surge of popularity of Transformers in Computer Vision, se...

0 Francesco Pinto, et al. ∙

research

∙ 07/20/2022

Illusionary Attacks on Sequential Decision Makers and Countermeasures

Autonomous intelligent agents deployed to the real-world need to be robu...

5 Tim Franzmeyer, et al. ∙

research

∙ 07/13/2022

Sample-dependent Adaptive Temperature Scaling for Improved Calibration

It is now well known that neural networks can be wrong with high confide...

10 Tom Joy, et al. ∙

research

∙ 07/05/2022

SiamMask: A Framework for Fast Online Object Tracking and Segmentation

In this paper we introduce SiamMask, a framework to perform both visual ...

9 Weiming Hu, et al. ∙

research

∙ 06/29/2022

RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness

We show that the effectiveness of the well celebrated Mixup [Zhang et al...

1 Francesco Pinto, et al. ∙

research

∙ 06/17/2022

How robust are pre-trained models to distribution shift?

The vulnerability of machine learning models to spurious correlations ha...

0 Yuge Shi, et al. ∙

research

∙ 06/16/2022

Catastrophic overfitting is a bug but also a feature

Despite clear computational advantages in building robust neural network...

15 Guillermo Ortiz-Jiménez, et al. ∙

research

∙ 04/25/2022

Zero-Shot Logit Adjustment

Semantic-descriptor-based Generalized Zero-Shot Learning (GZSL) poses ch...

0 Dubing Chen, et al. ∙

research

∙ 04/24/2022

Towards the Semantic Weak Generalization Problem in Generative Zero-Shot Learning: Ante-hoc and Post-hoc

In this paper, we present a simple and effective strategy lowering the p...

0 Dubing Chen, et al. ∙

research

∙ 04/03/2022

BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion

Dense 3D reconstruction from a stream of depth images is the key to many...

0 Kejie Li, et al. ∙

research

∙ 02/28/2022

Local and Global GANs with Semantic-Aware Upsampling for Image Generation

In this paper, we address the task of semantic-guided image generation. ...

0 Hao Tang, et al. ∙

research

∙ 02/02/2022

Make Some Noise: Reliable and Efficient Single-Step Adversarial Training

Recently, Wong et al. showed that adversarial training with single-step ...

11 Pau de Jorge, et al. ∙

research

∙ 01/31/2022

Learning to Hash Naturally Sorts

Locality sensitive hashing pictures a list-wise sorting problem. Its tes...

0 Yuming Shen, et al. ∙

research

∙ 01/31/2022

Adversarial Masking for Self-Supervised Learning

We propose ADIOS, a masked image model (MIM) framework for self-supervis...

0 Yuge Shi, et al. ∙

research

∙ 01/31/2022

On the Robustness of Quality Measures for GANs

This work evaluates the robustness of quality measures of generative mod...

5 Motasem Alfarra, et al. ∙

research

∙ 12/04/2021

LAVT: Language-Aware Vision Transformer for Referring Image Segmentation

Referring image segmentation is a fundamental vision-language task that ...

0 Zhao Yang, et al. ∙

research

∙ 11/23/2021

Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS

Cyber attacks are increasing in volume, frequency, and complexity. In re...

0 Christian Schroeder de Witt, et al. ∙

research

∙ 11/15/2021

Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Although deep learning methods have achieved advanced video object recog...

12 Jiyang Qi, et al. ∙

research

∙ 10/29/2021

Deep Deterministic Uncertainty for Semantic Segmentation

We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty...

0 Jishnu Mukhoti, et al. ∙

research

∙ 10/06/2021

Detecting and Quantifying Malicious Activity with Simulation-based Inference

We propose the use of probabilistic programming techniques to tackle the...

0 Andrew Gambardella, et al. ∙

research

∙ 09/11/2021

RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

Deep neural networks (DNNs) are vulnerable to adversarial noises, which ...

4 Shiyu Tang, et al. ∙

research

∙ 07/09/2021

ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Randomized smoothing has recently emerged as an effective tool that enab...

3 Francisco Eiras, et al. ∙

research

∙ 07/05/2021

Do Different Tracking Tasks Require Different Appearance Models?

Tracking objects of interest in a video is one of the most popular and w...

0 Zhongdao Wang, et al. ∙

research

∙ 07/02/2021

DeformRS: Certifying Input Deformations with Randomized Smoothing

Deep neural networks are vulnerable to input deformations in the form of...

6 Motasem Alfarra, et al. ∙

research

∙ 06/23/2021

Learning Multimodal VAEs through Mutual Supervision

Multimodal VAEs seek to model the joint distribution over heterogeneous ...

0 Tom Joy, et al. ∙

research

∙ 06/14/2021

KL Guided Domain Adaptation

Domain adaptation is an important problem and often needed for real-worl...

0 A. Tuan Nguyen, et al. ∙

research

∙ 06/03/2021

You Never Cluster Alone

Recent advances in self-supervised learning with instance-level contrast...

0 Yuming Shen, et al. ∙

research

∙ 04/20/2021

Gradient Matching for Domain Generalization

Machine learning systems typically assume that the distributions of trai...

0 Yuge Shi, et al. ∙

research

∙ 04/14/2021

Improved Branch and Bound for Neural Network Verification via Lagrangian Decomposition

We improve the scalability of Branch and Bound (BaB) algorithms for form...

6 Alessandro De Palma, et al. ∙

research

∙ 04/12/2021

Cloth Interactive Transformer for Virtual Try-On

2D image-based virtual try-on has attracted increased attention from the...

0 Bin Ren, et al. ∙

research

∙ 03/26/2021

Combating Adversaries with Anti-Adversaries

Deep neural networks are vulnerable to small input perturbations known a...

26 Motasem Alfarra, et al. ∙

research

∙ 02/23/2021

Deterministic Neural Networks with Appropriate Inductive Biases Capture Epistemic and Aleatoric Uncertainty

We show that a single softmax neural net with minimal changes can beat t...

6 Jishnu Mukhoti, et al. ∙

Philip H. S. Torr

Featured Co-authors