b'Hakan Bilen'

research

∙ 11/29/2021

Learning Multiple Dense Prediction Tasks from Partially Annotated Data

Despite the recent advances in multi-task learning of dense prediction p...

Wei-Hong Li, et al. ∙

research

∙ 11/26/2021

Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation

Scene graph generation (SGG) aims to capture a wide variety of interacti...

Arushi Goel, et al. ∙

research

∙ 10/08/2021

Dataset Condensation with Distribution Matching

Computational cost to train state-of-the-art deep models in many learnin...

Bo Zhao, et al. ∙

research

∙ 07/01/2021

Improving Task Adaptation for Cross-domain Few-shot Learning

In this paper, we look at the problem of cross-domain few-shot classific...

Wei-Hong Li, et al. ∙

research

∙ 04/02/2021

Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

There is a growing interest in developing computer vision methods that c...

Octave Mariotti, et al. ∙

research

∙ 04/01/2021

Unsupervised Foreground-Background Segmentation with Equivariant Layered GANs

We propose an unsupervised foreground-background segmentation method via...

Yu Yang, et al. ∙

research

∙ 03/25/2021

Universal Representation Learning from Multiple Domains for Few-shot Classification

In this paper, we look at the problem of few-shot classification that ai...

Wei-Hong Li, et al. ∙

research

∙ 02/16/2021

Dataset Condensation with Differentiable Siamese Augmentation

In many machine learning problems, large-scale datasets have become the ...

Bo Zhao, et al. ∙

research

∙ 10/05/2020

Deep Anomaly Detection by Residual Adaptation

Deep anomaly detection is a difficult task since, in high dimensions, it...

Lucas Deecke, et al. ∙

research

∙ 07/14/2020

Knowledge Distillation for Multi-task Learning

Multi-task learning (MTL) is to learn one single model that performs mul...

Wei-Hong Li, et al. ∙

research

∙ 06/10/2020

Dataset Condensation with Gradient Matching

Efficient training of deep neural networks is an increasingly important ...

Bo Zhao, et al. ∙

research

∙ 06/08/2020

Continual Representation Learning for Biometric Identification

With the explosion of digital data in recent years, continuously learnin...

Bo Zhao, et al. ∙

research

∙ 06/01/2020

Latent Domain Learning with Dynamic Residual Adapters

A practical shortcoming of deep neural networks is their specialization ...

Lucas Deecke, et al. ∙

research

∙ 01/08/2020

iDLG: Improved Deep Leakage from Gradients

It is widely believed that sharing gradients will not leak private train...

Bo Zhao, et al. ∙

research

∙ 12/22/2019

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

Recent semi-supervised learning methods have shown to achieve comparable...

Wei-Hong Li, et al. ∙

research

∙ 11/22/2019

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

Automatically generating natural language descriptions from an image is ...

Arushi Goel, et al. ∙

research

∙ 10/19/2019

NormGrad: Finding the Pixels that Matter for Training

The different families of saliency methods, either based on contrastive ...

Sylvestre-Alvise Rebuffi, et al. ∙

research

∙ 10/18/2019

Image Deconvolution with Deep Image and Kernel Priors

Image deconvolution is the process of recovering convolutional degraded ...

Zhunxuan Wang, et al. ∙

research

∙ 08/18/2019

Unsupervised Learning of Landmarks by Descriptor Vector Exchange

Equivariance to random image transformations is an effective method to l...

James Thewlis, et al. ∙

research

∙ 07/08/2019

Personalised aesthetics with residual adapters

The use of computational methods to evaluate aesthetics in photography h...

Carlos Rodríguez - Pardo, et al. ∙

research

∙ 07/03/2019

Learning Landmarks from Unaligned Data using Image Translation

We introduce a method for learning landmark detectors from unlabelled vi...

Tomas Jakab, et al. ∙

research

∙ 04/16/2019

Weakly Supervised Gaussian Networks for Action Detection

Detecting temporal extents of human actions in videos is a challenging c...

Basura Fernando, et al. ∙

research

∙ 10/12/2018

Mode Normalization

Normalization methods are a central building block in the deep learning ...

Lucas Deecke, et al. ∙

research

∙ 06/20/2018

Conditional Image Generation for Learning the Structure of Visual Objects

In this paper, we consider the problem of learning landmarks for object ...

Tomas Jakab, et al. ∙

research

∙ 03/27/2018

Efficient parametrization of multi-domain deep neural networks

A practical limitation of deep neural networks is their high degree of s...

Sylvestre-Alvise Rebuffi, et al. ∙

research

∙ 06/09/2017

Unsupervised learning of object frames by dense equivariant image labelling

One of the key challenges of visual perception is to extract abstract mo...

James Thewlis, et al. ∙

research

∙ 05/22/2017

Learning multiple visual domains with residual adapters

There is a growing interest in learning data representations that work w...

Sylvestre-Alvise Rebuffi, et al. ∙

research

∙ 05/05/2017

Unsupervised learning of object landmarks by factorized spatial embeddings

Learning automatically the structure of object categories remains an imp...

James Thewlis, et al. ∙

research

∙ 01/25/2017

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

With the advent of large labelled datasets and high-capacity models, the...

Hakan Bilen, et al. ∙

research

∙ 12/02/2016

Action Recognition with Dynamic Image Networks

We introduce the concept of "dynamic image", a novel compact representat...

Hakan Bilen, et al. ∙

research

∙ 11/21/2016

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

We propose a new self-supervised CNN pre-training technique based on a n...

Basura Fernando, et al. ∙

research

∙ 06/06/2016

Integrated perception with recurrent multi-task neural networks

Modern discriminative predictors have been shown to match natural intell...

Hakan Bilen, et al. ∙

research

∙ 11/09/2015

Weakly Supervised Deep Detection Networks

Weakly supervised learning of object detection is an important problem i...

Hakan Bilen, et al. ∙

Hakan Bilen

Featured Co-authors