
-
Deep Anomaly Detection by Residual Adaptation
Deep anomaly detection is a difficult task since, in high dimensions, it...
read it
-
Knowledge Distillation for Multi-task Learning
Multi-task learning (MTL) is to learn one single model that performs mul...
read it
-
Dataset Condensation with Gradient Matching
Efficient training of deep neural networks is an increasingly important ...
read it
-
Continual Representation Learning for Biometric Identification
With the explosion of digital data in recent years, continuously learnin...
read it
-
Latent Domain Learning with Dynamic Residual Adapters
A practical shortcoming of deep neural networks is their specialization ...
read it
-
iDLG: Improved Deep Leakage from Gradients
It is widely believed that sharing gradients will not leak private train...
read it
-
Learning to Impute: A General Framework for Semi-supervised Learning
Recent semi-supervised learning methods have shown to achieve comparable...
read it
-
Learning to Caption Images with Two-Stream Attention and Sentence Auto-Encoder
Automatically generating natural language descriptions from an image is ...
read it
-
NormGrad: Finding the Pixels that Matter for Training
The different families of saliency methods, either based on contrastive ...
read it
-
Image Deconvolution with Deep Image and Kernel Priors
Image deconvolution is the process of recovering convolutional degraded ...
read it
-
Unsupervised Learning of Landmarks by Descriptor Vector Exchange
Equivariance to random image transformations is an effective method to l...
read it
-
Personalised aesthetics with residual adapters
The use of computational methods to evaluate aesthetics in photography h...
read it
-
Learning Landmarks from Unaligned Data using Image Translation
We introduce a method for learning landmark detectors from unlabelled vi...
read it
-
Weakly Supervised Gaussian Networks for Action Detection
Detecting temporal extents of human actions in videos is a challenging c...
read it
-
Mode Normalization
Normalization methods are a central building block in the deep learning ...
read it
-
Conditional Image Generation for Learning the Structure of Visual Objects
In this paper, we consider the problem of learning landmarks for object ...
read it
-
Efficient parametrization of multi-domain deep neural networks
A practical limitation of deep neural networks is their high degree of s...
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...
read it
-
Learning multiple visual domains with residual adapters
There is a growing interest in learning data representations that work w...
read it
-
Unsupervised learning of object landmarks by factorized spatial embeddings
Learning automatically the structure of object categories remains an imp...
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...
read it
-
Action Recognition with Dynamic Image Networks
We introduce the concept of "dynamic image", a novel compact representat...
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...
read it
-
Integrated perception with recurrent multi-task neural networks
Modern discriminative predictors have been shown to match natural intell...
read it
-
Weakly Supervised Deep Detection Networks
Weakly supervised learning of object detection is an important problem i...
read it