3.5k citations · 14.1k across the 436 of their papers we have counts for
37 papers · 1 filter
On Batch Normalisation for Approximate Bayesian Inference
Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr +1
We study batch normalisation in the context of variational inference methods in Bayesian neural networks, such as mean-field or MC Dropout. We show that batch-normalisation does no…
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
Xiaojuan Qi, Zhengzhe Liu, Renjie Liao +3
In this paper, we propose a geometric neural network with edge-aware refinement (GeoNet++) to jointly predict both depth and surface normal maps from a single image. Building on to…
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Sixiao Zheng, Jiachen Lu, Hengshuang Zhao +8
Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution a…
Multi-shot Temporal Event Localization: a Benchmark
Xiaolong Liu, Yao Hu, Song Bai +3
Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured a…
Point Transformer
Hengshuang Zhao, Li Jiang, Jiaya Jia +2
Self-attention networks have revolutionized natural language processing and are making impressive strides in image analysis tasks such as image classification and object detection.…
Data-Dependent Randomized Smoothing
Motasem Alfarra, Adel Bibi, Philip H. S. Torr +1
Randomized smoothing is a recent technique that achieves state-of-art performance in training certifiably robust deep neural networks. While the smoothing family of distributions i…
Learning to Sample the Most Useful Training Patches from Images
Shuyang Sun, Liang Chen, Gregory Slabaugh +1
Some image restoration tasks like demosaicing require difficult training samples to learn effective models. Existing methods attempt to address this data training problem by manual…
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
Christian Schroeder de Witt, Tarun Gupta, Denys Makoviichuk +4
Most recently developed approaches to cooperative multi-agent reinforcement learning in the \emph{centralized training with decentralized execution} setting involve estimating a ce…
Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation
Angira Sharma, Naeemullah Khan, Ganesh Sundaramoorthi +1
In this paper we present a novel loss function, called class-agnostic segmentation (CAS) loss. With CAS loss the class descriptors are learned during training of the network. We do…
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
Bowen Li, Xiaojuan Qi, Philip H. S. Torr +1
We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. To achieve this, a new word-level discriminator…
Continual Learning in Low-rank Orthogonal Subspaces
Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania +1
In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experie…
Diagnosing and Preventing Instabilities in Recurrent Video Processing
Thomas Tanay, Aivar Sootla, Matteo Maggioni +4
Recurrent models are a popular choice for video enhancement tasks such as video denoising or super-resolution. In this work, we focus on their stability as dynamical systems and sh…
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Jonathon Luiten, Aljosa Osep, Patrick Dendorfer +4
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we presen…
Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Carlo Biffi, Steven McDonagh, Philip Torr +2
Object detection has witnessed significant progress by relying on large, manually annotated datasets. Annotating such datasets is highly time consuming and expensive, which motivat…
Bipartite Graph Reasoning GANs for Person Image Generation
Hao Tang, Song Bai, Philip H. S. Torr +1
We present a novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the challenging person image generation task. The proposed graph generator mainly consists of two novel blocks tha…
AutoSimulate: (Quickly) Learning Synthetic Data Generation
Harkirat Singh Behl, Atılım Güneş Baydin, Ran Gal +2
Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with t…
XingGAN for Person Image Generation
Hao Tang, Song Bai, Li Zhang +2
We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. The pro…
WordCraft: An Environment for Benchmarking Commonsense Agents
Minqi Jiang, Jelena Luketina, Nantas Nardelli +4
The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpo…
How benign is benign overfitting?
Amartya Sanyal, Puneet K Dokania, Varun Kanade +1
We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achie…
Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models
Yuge Shi, Brooks Paige, Philip H. S. Torr +1
Multimodal learning for generative models often refers to the learning of abstract concepts from the commonality of information in multiple modalities, such as vision and language.…
STEER: Simple Temporal Regularization For Neural ODEs
Arnab Ghosh, Harkirat Singh Behl, Emilien Dupont +2
Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can becom…
Capturing Label Characteristics in VAEs
Tom Joy, Sebastian M. Schmon, Philip H. S. Torr +2
We present a principled approach to incorporating labels in VAEs that captures the rich characteristic information associated with those labels. While prior work has typically conf…
Progressive Skeletonization: Trimming more fat from a network at initialization
Pau de Jorge, Amartya Sanyal, Harkirat S. Behl +3
Recent studies have shown that skeletonization (pruning parameters) of networks \textit{at initialization} provides all the practical benefits of sparsity both at inference and tra…
A Revised Generative Evaluation of Visual Dialogue
Daniela Massiceti, Viveka Kulharia, Puneet K. Dokania +2
Evaluating Visual Dialogue, the task of answering a sequence of questions relating to a visual input, remains an open research challenge. The current evaluation scheme of the VisDi…