3.5k citations · 14.1k across the 436 of their papers we have counts for
22 papers · 1 filter
Learn to Interpret Atari Agents
Zhao Yang, Song Bai, Li Zhang +1
Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks. However, the direct mapping from states to actions makes it hard to interpret the rationa…
Visual Dialogue without Vision or Dialogue
Daniela Massiceti, Puneet K. Dokania, N. Siddharth +1
We characterise some of the quirks and shortcomings in the exploration of Visual Dialogue - a sequential question-answering task where the questions and corresponding answers are r…
Fast Online Object Tracking and Segmentation: A Unifying Approach
Qiang Wang, Li Zhang, Luca Bertinetto +2
In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbe…
Proximal Mean-field for Neural Network Quantization
Thalaiyasingam Ajanthan, Puneet K. Dokania, Richard Hartley +1
Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work,…
Meta Learning Deep Visual Words for Fast Video Object Segmentation
Harkirat Singh Behl, Mohammad Najafi, Anurag Arnab +1
Personal robots and driverless cars need to be able to operate in novel environments and thus quickly and efficiently learn to recognise new object classes. We address this problem…
Deeper Interpretability of Deep Networks
Tian Xu, Jiayu Zhan, Oliver G. B. Garrod +4
Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing dema…
Multi-Agent Common Knowledge Reinforcement Learning
Christian A. Schroeder de Witt, Jakob N. Foerster, Gregory Farquhar +3
Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents' ability to coordinate their behaviour. In this paper, we show…
SNIP: Single-shot Network Pruning based on Connection Sensitivity
Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr
Pruning large neural networks while maintaining their performance is often desirable due to the reduced space and time complexity. In existing methods, pruning is done within an it…
Weakly- and Semi-Supervised Panoptic Segmentation
Qizhu Li, Anurag Arnab, Philip H. S. Torr
We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel…
With Friends Like These, Who Needs Adversaries?
Saumya Jetley, Nicholas A. Lord, Philip H. S. Torr
The vulnerability of deep image classification networks to adversarial attack is now well known, but less well understood. Via a novel experimental analysis, we illustrate some fac…
Value Propagation Networks
Nantas Nardelli, Gabriel Synnaeve, Zeming Lin +3
We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement le…
Meta-learning with differentiable closed-form solvers
Luca Bertinetto, João F. Henriques, Philip H. S. Torr +1
Adapting deep networks to new concepts from a few examples is challenging, due to the high computational requirements of standard fine-tuning procedures. Most work on few-shot lear…
Learn To Pay Attention
Saumya Jetley, Nicholas A. Lord, Namhoon Lee +1
We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature ve…
FlipDial: A Generative Model for Two-Way Visual Dialogue
Daniela Massiceti, N. Siddharth, Puneet K. Dokania +1
We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an…
Robustness via Deep Low-Rank Representations
Amartya Sanyal, Varun Kanade, Philip H. S. Torr +1
We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and rando…
DGPose: Deep Generative Models for Human Body Analysis
Rodrigo de Bem, Arnab Ghosh, Thalaiyasingam Ajanthan +4
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not i…
WebSeg: Learning Semantic Segmentation from Web Searches
Qibin Hou, Ming-Ming Cheng, Jiangjiang Liu +1
In this paper, we improve semantic segmentation by automatically learning from Flickr images associated with a particular keyword, without relying on any explicit user annotations,…
Three Birds One Stone: A General Architecture for Salient Object Segmentation, Edge Detection and Skeleton Extraction
Qibin Hou, Jiang-Jiang Liu, Ming-Ming Cheng +2
In this paper, we aim at solving pixel-wise binary problems, including salient object segmentation, skeleton extraction, and edge detection, by introducing a unified architecture.…
Long-term Tracking in the Wild: A Benchmark
Jack Valmadre, Luca Bertinetto, João F. Henriques +5
We introduce the OxUvA dataset and benchmark for evaluating single-object tracking algorithms. Benchmarks have enabled great strides in the field of object tracking by defining sta…
Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded Devices
Oscar Rahnama, Duncan Frost, Ondrej Miksik +1
For many applications in low-power real-time robotics, stereo cameras are the sensors of choice for depth perception as they are typically cheaper and more versatile than their act…
Devon: Deformable Volume Network for Learning Optical Flow
Yao Lu, Jack Valmadre, Heng Wang +3
State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite the…
Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
Arslan Chaudhry, Puneet K. Dokania, Thalaiyasingam Ajanthan +1
Incremental learning (IL) has received a lot of attention recently, however, the literature lacks a precise problem definition, proper evaluation settings, and metrics tailored spe…