Jose M. Alvarez

Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion

Understanding the behavior and vulnerability of pre-trained deep neural ...
07/13/2021 ∙ by Xin Dong, et al. ∙ 8 ∙ share

read it
Towards Reducing Labeling Cost in Deep Object Detection

Deep neural networks have reached very high accuracy on object detection...
06/22/2021 ∙ by Ismail Elezi, et al. ∙ 7 ∙ share

read it
Distilling Image Classifiers in Object Detectors

Knowledge distillation constitutes a simple yet effective way to improve...
06/09/2021 ∙ by Shuxuan Guo, et al. ∙ 0 ∙ share

read it
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

We present SegFormer, a simple, efficient yet powerful semantic segmenta...
05/31/2021 ∙ by Enze Xie, et al. ∙ 6 ∙ share

read it
See through Gradients: Image Batch Recovery via GradInversion

Training deep neural networks requires gradient estimation from data bat...
04/15/2021 ∙ by Hongxu Yin, et al. ∙ 0 ∙ share

read it
Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection

Training on datasets with long-tailed distributions has been challenging...
04/12/2021 ∙ by Nadine Chang, et al. ∙ 27 ∙ share

read it
Self-supervised Learning of Depth Inference for Multi-view Stereo

Recent supervised multi-view depth estimation networks have achieved pro...
04/07/2021 ∙ by Jiayu Yang, et al. ∙ 4 ∙ share

read it
Contrastive Syn-to-Real Generalization

Training on synthetic data can be beneficial for label or data-scarce sc...
04/06/2021 ∙ by Wuyang Chen, et al. ∙ 7 ∙ share

read it
Active Learning for Deep Object Detection via Probabilistic Modeling

Active learning aims to reduce labeling costs by selecting only the most...
03/30/2021 ∙ by Jiwoong Choi, et al. ∙ 0 ∙ share

read it
Personalized Federated Learning with First Order Model Optimization

While federated learning traditionally aims to train a single global mod...
12/15/2020 ∙ by Michael Zhang, et al. ∙ 17 ∙ share

read it
Scalable Active Learning for Object Detection

Deep Neural Networks trained in a fully supervised fashion are the domin...
04/09/2020 ∙ by Elmar Haussmann, et al. ∙ 13 ∙ share

read it
Context Based Emotion Recognition using EMOTIC Dataset

In our everyday lives and social interactions we often try to perceive t...
03/30/2020 ∙ by Ronak Kosti, et al. ∙ 2 ∙ share

read it
Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion

We introduce DeepInversion, a new method for synthesizing images from th...
12/18/2019 ∙ by Hongxu Yin, et al. ∙ 27 ∙ share

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...
12/18/2019 ∙ by Jiayu Yang, et al. ∙ 18 ∙ share

read it
VACL: Variance-Aware Cross-Layer Regularization for Pruning Deep Residual Networks

Improving weight sparsity is a common strategy for producing light-weigh...
09/10/2019 ∙ by Shuang Gao, et al. ∙ 0 ∙ share

read it
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions

Semantic segmentation with Convolutional Neural Networks is a memory-int...
07/27/2019 ∙ by Kashyap Chitta, et al. ∙ 3 ∙ share

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...
05/29/2019 ∙ by Kashyap Chitta, et al. ∙ 0 ∙ share

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 ...
11/29/2018 ∙ by Jiaming Zeng, et al. ∙ 0 ∙ share

read it
ExpandNets: Exploiting Linear Redundancy to Train Small Networks

While very deep networks can achieve great performance, they are ill-sui...
11/26/2018 ∙ by Shuxuan Guo, et al. ∙ 0 ∙ share

read it
Large-Scale Visual Active Learning with Deep Probabilistic Ensembles

Annotating the right data for training deep neural networks is an import...
11/08/2018 ∙ by Kashyap Chitta, et al. ∙ 0 ∙ share

read it
Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization

In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scala...
11/06/2018 ∙ by Kashyap Chitta, et al. ∙ 0 ∙ share

read it
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation

Training a deep network to perform semantic segmentation requires large ...
07/16/2018 ∙ by Fatemeh Sadat Saleh, et al. ∙ 0 ∙ share

read it
Compression-aware Training of Deep Networks

In recent years, great progress has been made in a variety of applicatio...
11/07/2017 ∙ by Jose M. Alvarez, et al. ∙ 0 ∙ share

read it
Domain-adaptive deep network compression

Deep Neural Networks trained on large datasets can be easily transferred...
09/04/2017 ∙ by Marc Masana, et al. ∙ 0 ∙ share

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...
08/15/2017 ∙ by Fatemeh Sadat Saleh, et al. ∙ 0 ∙ share

read it
Class-Weighted Convolutional Features for Visual Instance Search

Image retrieval in realistic scenarios targets large dynamic datasets of...
07/09/2017 ∙ by Albert Jimenez, et al. ∙ 0 ∙ share

read it
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation

Pixel-level annotations are expensive and time consuming to obtain. Henc...
06/06/2017 ∙ by Fatemeh Sadat Saleh, et al. ∙ 0 ∙ share

read it
Invertible Conditional GANs for image editing

Generative Adversarial Networks (GANs) have recently demonstrated to suc...
11/19/2016 ∙ by Guim Perarnau, et al. ∙ 0 ∙ share

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...
11/19/2016 ∙ by Jose M. Alvarez, et al. ∙ 0 ∙ share

read it
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation

Pixel-level annotations are expensive and time consuming to obtain. Henc...
09/02/2016 ∙ by Fatemehsadat Saleh, et al. ∙ 0 ∙ share

read it
Learning Image Matching by Simply Watching Video

This work presents an unsupervised learning based approach to the ubiqui...
03/19/2016 ∙ by Gucan Long, et al. ∙ 0 ∙ share

read it
Road Detection by One-Class Color Classification: Dataset and Experiments

Detecting traversable road areas ahead a moving vehicle is a key process...
12/11/2014 ∙ by Jose M. Alvarez, et al. ∙ 0 ∙ share

read it
Road Detection via On--line Label Transfer

Vision-based road detection is an essential functionality for supporting...
12/10/2014 ∙ by Jose M. Alvarez, et al. ∙ 0 ∙ share

read it

Jose M. Alvarez

Featured Co-authors