
-
Personalized Federated Learning with First Order Model Optimization
While federated learning traditionally aims to train a single global mod...
read it
-
Scalable Active Learning for Object Detection
Deep Neural Networks trained in a fully supervised fashion are the domin...
read it
-
Context Based Emotion Recognition using EMOTIC Dataset
In our everyday lives and social interactions we often try to perceive t...
read it
-
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
We introduce DeepInversion, a new method for synthesizing images from th...
read it
-
Cost Volume Pyramid Based Depth Inference for Multi-View Stereo
We propose a cost volume based neural network for depth inference from m...
read it
-
VACL: Variance-Aware Cross-Layer Regularization for Pruning Deep Residual Networks
Improving weight sparsity is a common strategy for producing light-weigh...
read it
-
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions
Semantic segmentation with Convolutional Neural Networks is a memory-int...
read it
-
Less is More: An Exploration of Data Redundancy with Active Dataset Subsampling
Deep Neural Networks (DNNs) often rely on very large datasets for traini...
read it
-
The Relevance of Bayesian Layer Positioning to Model Uncertainty in Deep Bayesian Active Learning
One of the main challenges of deep learning tools is their inability to ...
read it
-
ExpandNets: Exploiting Linear Redundancy to Train Small Networks
While very deep networks can achieve great performance, they are ill-sui...
read it
-
Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
Annotating the right data for training deep neural networks is an import...
read it
-
Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization
In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scala...
read it
-
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
Training a deep network to perform semantic segmentation requires large ...
read it
-
Compression-aware Training of Deep Networks
In recent years, great progress has been made in a variety of applicatio...
read it
-
Domain-adaptive deep network compression
Deep Neural Networks trained on large datasets can be easily transferred...
read it
-
Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation
Pixel-level annotations are expensive and time-consuming to obtain. Henc...
read it
-
Class-Weighted Convolutional Features for Visual Instance Search
Image retrieval in realistic scenarios targets large dynamic datasets of...
read it
-
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
Pixel-level annotations are expensive and time consuming to obtain. Henc...
read it
-
Invertible Conditional GANs for image editing
Generative Adversarial Networks (GANs) have recently demonstrated to suc...
read it
-
Learning the Number of Neurons in Deep Networks
Nowadays, the number of layers and of neurons in each layer of a deep ne...
read it
-
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
Pixel-level annotations are expensive and time consuming to obtain. Henc...
read it
-
Learning Image Matching by Simply Watching Video
This work presents an unsupervised learning based approach to the ubiqui...
read it
-
Road Detection by One-Class Color Classification: Dataset and Experiments
Detecting traversable road areas ahead a moving vehicle is a key process...
read it
-
Road Detection via On--line Label Transfer
Vision-based road detection is an essential functionality for supporting...
read it