Hakan Bilen

Deep Anomaly Detection by Residual Adaptation

Deep anomaly detection is a difficult task since, in high dimensions, it...
10/05/2020 ∙ by Lucas Deecke, et al. ∙ 30 ∙ share

read it
Knowledge Distillation for Multi-task Learning

Multi-task learning (MTL) is to learn one single model that performs mul...
07/14/2020 ∙ by Wei-Hong Li, et al. ∙ 0 ∙ share

read it
Dataset Condensation with Gradient Matching

Efficient training of deep neural networks is an increasingly important ...
06/10/2020 ∙ by Bo Zhao, et al. ∙ 0 ∙ share

read it
Continual Representation Learning for Biometric Identification

With the explosion of digital data in recent years, continuously learnin...
06/08/2020 ∙ by Bo Zhao, et al. ∙ 0 ∙ share

read it
Latent Domain Learning with Dynamic Residual Adapters

A practical shortcoming of deep neural networks is their specialization ...
06/01/2020 ∙ by Lucas Deecke, et al. ∙ 0 ∙ share

read it
iDLG: Improved Deep Leakage from Gradients

It is widely believed that sharing gradients will not leak private train...
01/08/2020 ∙ by Bo Zhao, et al. ∙ 0 ∙ share

read it
Learning to Impute: A General Framework for Semi-supervised Learning

Recent semi-supervised learning methods have shown to achieve comparable...
12/22/2019 ∙ by Wei-Hong Li, et al. ∙ 9 ∙ share

read it
Learning to Caption Images with Two-Stream Attention and Sentence Auto-Encoder

Automatically generating natural language descriptions from an image is ...
11/22/2019 ∙ by Arushi Goel, et al. ∙ 0 ∙ share

read it
NormGrad: Finding the Pixels that Matter for Training

The different families of saliency methods, either based on contrastive ...
10/19/2019 ∙ by Sylvestre-Alvise Rebuffi, et al. ∙ 0 ∙ share

read it
Image Deconvolution with Deep Image and Kernel Priors

Image deconvolution is the process of recovering convolutional degraded ...
10/18/2019 ∙ by Zhunxuan Wang, et al. ∙ 29 ∙ share

read it
Unsupervised Learning of Landmarks by Descriptor Vector Exchange

Equivariance to random image transformations is an effective method to l...
08/18/2019 ∙ by James Thewlis, et al. ∙ 13 ∙ share

read it
Personalised aesthetics with residual adapters

The use of computational methods to evaluate aesthetics in photography h...
07/08/2019 ∙ by Carlos Rodríguez - Pardo, et al. ∙ 7 ∙ share

read it
Learning Landmarks from Unaligned Data using Image Translation

We introduce a method for learning landmark detectors from unlabelled vi...
07/03/2019 ∙ by Tomas Jakab, et al. ∙ 2 ∙ share

read it
Weakly Supervised Gaussian Networks for Action Detection

Detecting temporal extents of human actions in videos is a challenging c...
04/16/2019 ∙ by Basura Fernando, et al. ∙ 0 ∙ share

read it
Mode Normalization

Normalization methods are a central building block in the deep learning ...
10/12/2018 ∙ by Lucas Deecke, et al. ∙ 0 ∙ share

read it
Conditional Image Generation for Learning the Structure of Visual Objects

In this paper, we consider the problem of learning landmarks for object ...
06/20/2018 ∙ by Tomas Jakab, et al. ∙ 2 ∙ share

read it
Efficient parametrization of multi-domain deep neural networks

A practical limitation of deep neural networks is their high degree of s...
03/27/2018 ∙ by Sylvestre-Alvise Rebuffi, et al. ∙ 0 ∙ share

read it
Unsupervised learning of object frames by dense equivariant image labelling

One of the key challenges of visual perception is to extract abstract mo...
06/09/2017 ∙ by James Thewlis, et al. ∙ 0 ∙ share

read it
Learning multiple visual domains with residual adapters

There is a growing interest in learning data representations that work w...
05/22/2017 ∙ by Sylvestre-Alvise Rebuffi, et al. ∙ 0 ∙ share

read it
Unsupervised learning of object landmarks by factorized spatial embeddings

Learning automatically the structure of object categories remains an imp...
05/05/2017 ∙ by James Thewlis, et al. ∙ 0 ∙ share

read it
Universal representations:The missing link between faces, text, planktons, and cat breeds

With the advent of large labelled datasets and high-capacity models, the...
01/25/2017 ∙ by Hakan Bilen, et al. ∙ 0 ∙ share

read it
Action Recognition with Dynamic Image Networks

We introduce the concept of "dynamic image", a novel compact representat...
12/02/2016 ∙ by Hakan Bilen, et al. ∙ 0 ∙ share

read it
Self-Supervised Video Representation Learning With Odd-One-Out Networks

We propose a new self-supervised CNN pre-training technique based on a n...
11/21/2016 ∙ by Basura Fernando, et al. ∙ 0 ∙ share

read it
Integrated perception with recurrent multi-task neural networks

Modern discriminative predictors have been shown to match natural intell...
06/06/2016 ∙ by Hakan Bilen, et al. ∙ 0 ∙ share

read it
Weakly Supervised Deep Detection Networks

Weakly supervised learning of object detection is an important problem i...
11/09/2015 ∙ by Hakan Bilen, et al. ∙ 0 ∙ share

read it

Hakan Bilen

Featured Co-authors

Andrea Vedaldi

Stephen Gould

Rui Zhao

Timothy Hospedales

Efstratios Gavves

Iain Murray

Basura Fernando

Bo Zhao

Samuel Albanie

Dapeng Chen

Chuan Sheng Foo

Deep Anomaly Detection by Residual Adaptation

Knowledge Distillation for Multi-task Learning

Dataset Condensation with Gradient Matching

Continual Representation Learning for Biometric Identification

Latent Domain Learning with Dynamic Residual Adapters

iDLG: Improved Deep Leakage from Gradients

Learning to Impute: A General Framework for Semi-supervised Learning

Learning to Caption Images with Two-Stream Attention and Sentence Auto-Encoder

NormGrad: Finding the Pixels that Matter for Training

Image Deconvolution with Deep Image and Kernel Priors

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

Personalised aesthetics with residual adapters

Learning Landmarks from Unaligned Data using Image Translation

Weakly Supervised Gaussian Networks for Action Detection

Mode Normalization

Conditional Image Generation for Learning the Structure of Visual Objects

Efficient parametrization of multi-domain deep neural networks

Unsupervised learning of object frames by dense equivariant image labelling

Learning multiple visual domains with residual adapters

Unsupervised learning of object landmarks by factorized spatial embeddings

Universal representations:The missing link between faces, text, planktons, and cat breeds

Action Recognition with Dynamic Image Networks

Self-Supervised Video Representation Learning With Odd-One-Out Networks

Integrated perception with recurrent multi-task neural networks

Weakly Supervised Deep Detection Networks