3.5k citations · 14.1k across the 436 of their papers we have counts for
38 papers · 1 filter
General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments
Xiaogang Xu, Hengshuang Zhao, Philip Torr +1
Deep Neural Networks (DNNs) are vulnerable to the black-box adversarial attack that is highly transferable. This threat comes from the distribution gap between adversarial and clea…
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
Jishnu Mukhoti, Tsung-Yu Lin, Omid Poursaeed +4
We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of t…
Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs
Guangrun Wang, Philip H. S. Torr
Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a l…
Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
Jianhao Yuan, Francesco Pinto, Adam Davies +1
Neural image classifiers are known to undergo severe performance degradation when exposed to inputs that are sampled from environmental conditions that differ from their training d…
LUMix: Improving Mixup by Better Modelling Label Uncertainty
Shuyang Sun, Jie-Neng Chen, Ruifei He +3
Modern deep networks can be better generalized when trained with noisy samples and regularization techniques. Mixup and CutMix have been proven to be effective for data augmentatio…
Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis
Hao Tang, Ling Shao, Philip H. S. Torr +1
We present a novel bipartite graph reasoning Generative Adversarial Network (BiGraphGAN) for two challenging tasks: person pose and facial image synthesis. The proposed graph gener…
Structure-Preserving 3D Garment Modeling with Neural Sewing Machines
Xipeng Chen, Guangrun Wang, Dizhong Zhu +3
3D Garment modeling is a critical and challenging topic in the area of computer vision and graphics, with increasing attention focused on garment representation learning, garment r…
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
Nan Xue, Tianfu Wu, Song Bai +4
This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions. HAW…
Is synthetic data from generative models ready for image recognition?
Ruifei He, Shuyang Sun, Xin Yu +5
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applic…
Diversified Dynamic Routing for Vision Tasks
Botos Csaba, Adel Bibi, Yanwei Li +2
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 s…
Learn what matters: cross-domain imitation learning with task-relevant embeddings
Tim Franzmeyer, Philip H. S. Torr, João F. Henriques
We study how an autonomous agent learns to perform a task from demonstrations in a different domain, such as a different environment or different agent. Such cross-domain imitation…
Raising the Bar on the Evaluation of Out-of-Distribution Detection
Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen +4
In image classification, a lot of development has happened in detecting out-of-distribution (OoD) data. However, most OoD detection methods are evaluated on a standard set of datas…
Dynamic Graph Message Passing Networks for Visual Recognition
Li Zhang, Mohan Chen, Anurag Arnab +2
Modelling long-range dependencies is critical for scene understanding tasks in computer vision. Although convolution neural networks (CNNs) have excelled in many vision tasks, they…
Memory-Driven Text-to-Image Generation
Bowen Li, Philip H. S. Torr, Thomas Lukasiewicz
We introduce a memory-driven semi-parametric approach to text-to-image generation, which is based on both parametric and non-parametric techniques. The non-parametric component is…
An Impartial Take to the CNN vs Transformer Robustness Contest
Francesco Pinto, Philip H. S. Torr, Puneet K. Dokania
Following the surge of popularity of Transformers in Computer Vision, several studies have attempted to determine whether they could be more robust to distribution shifts and provi…
Sample-dependent Adaptive Temperature Scaling for Improved Calibration
Tom Joy, Francesco Pinto, Ser-Nam Lim +2
It is now well known that neural networks can be wrong with high confidence in their predictions, leading to poor calibration. The most common post-hoc approach to compensate for t…
Collaborative Quantization Embeddings for Intra-Subject Prostate MR Image Registration
Ziyi Shen, Qianye Yang, Yuming Shen +9
Image registration is useful for quantifying morphological changes in longitudinal MR images from prostate cancer patients. This paper describes a development in improving the lear…
SiamMask: A Framework for Fast Online Object Tracking and Segmentation
Weiming Hu, Qiang Wang, Li Zhang +2
In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the off…
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness
Jindong Gu, Hengshuang Zhao, Volker Tresp +1
Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and impercept…
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
Tim Franzmeyer, Stephen McAleer, João F. Henriques +4
Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attack…
Vision Transformers: From Semantic Segmentation to Dense Prediction
Li Zhang, Jiachen Lu, Sixiao Zheng +6
The emergence of vision transformers (ViTs) in image classification has shifted the methodologies for visual representation learning. In particular, ViTs learn visual representatio…
Universal Adaptive Data Augmentation
Xiaogang Xu, Hengshuang Zhao
Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are n…
RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness
Francesco Pinto, Harry Yang, Ser-Nam Lim +2
We show that the effectiveness of the well celebrated Mixup [Zhang et al., 2018] can be further improved if instead of using it as the sole learning objective, it is utilized as an…
How Robust is Unsupervised Representation Learning to Distribution Shift?
Yuge Shi, Imant Daunhawer, Julia E. Vogt +2
The robustness of machine learning algorithms to distributions shift is primarily discussed in the context of supervised learning (SL). As such, there is a lack of insight on the r…