Home

Person

Mathieu Salzmann

About
Privacy
Disclaimer

Graph Chatbot

Related publications (169)

Estimating Image Depth in the Comics Domain

Mathieu Salzmann, Sabine Süsstrunk, Deblina Bhattacharjee, Martin Nicolas Everaert

Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy. We thus, use an off-the-shelf unsupervised image to image tra ...

2021

Distilling Image Classifiers in Object Detectors

Mathieu Salzmann, Shuxuan Guo

Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation literature remains limited to the scenari ...

Curran Associates, Inc.2021

Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images

Pascal Fua, Mathieu Salzmann, Carlos Joaquin Becker, Róger Bermúdez Chacón, Okan Altingövde

We present an Unsupervised Domain Adaptation strategy to compensate for domain shifts on Electron Microscopy volumes. Our method aggregates visual correspondences—motifs that are visually similar across different acquisitions—to infer changes on the parame ...

Institute of Electrical and Electronics Engineers2020

Shape Reconstruction by Learning Differentiable Surface Representations

Pascal Fua, Mathieu Salzmann, Erhan Gündogdu, Shaifali Parashar, Jan Bednarík

Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations. Unfortunately, they offer no control over the deformations of the su ...

IEEE2020

DUNIT: Detection-based Unsupervised Image-to-Image Translation

Mathieu Salzmann, Deblina Bhattacharjee, Seungryong Kim

Image-to-image translation has made great strides in recent years, with current techniques being able to handle unpaired training images and to account for the multimodality of the translation problem. Despite this, most methods treat the image as a whole, ...

IEEE2020

Motion Prediction Using Temporal Inception Module

Pascal Fua, Mathieu Salzmann, Sena Kiciroglu, Wei Wang

Human motion prediction is a necessary component for many applications in robotics and autonomous driving. Recent methods propose using sequence-to-sequence deep learning models to tackle this problem. However, they do not focus on exploiting different tem ...

Springer, Cham2020

Evaluating the search phase of neural architecture search

Mathieu Salzmann, Claudiu-Cristian Musat, Kaicheng Yu, Martin Jaggi

Neural Architecture Search (NAS) aims to facilitate the design of deep networks fornew tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS algorithms are currently compared solely b ...

2020

A Stochastic Conditioning Scheme for Diverse Human Motion Prediction

Mathieu Salzmann, Fatemehsadat Saleh

Human motion prediction, the task of predicting future 3D human poses given a sequence of observed ones, has been mostly treated as a deterministic problem. However, human motion is a stochastic process: Given an observed sequence of poses, multiple future ...

IEEE2020

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

Pascal Fua, Mathieu Salzmann, Agata Justyna Mosinska, Mateusz Kozinski

The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, we show that we can train a Deep Net to perform 3D volumetric delineation giv ...

2020

Estimating People Flows to Better Count Them in Crowded Scenes

Pascal Fua, Mathieu Salzmann, Weizhe Liu

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

2020

History Repeats Itself: Human Motion Prediction Via Motion Attention

Mathieu Salzmann

Human motion prediction aims to forecast future human poses given a past motion. Whether based on recurrent or feed-forward neural networks, existing methods fail to model the observation that human motion tends to repeat itself, even for complex sports ac ...

Springer Nature2020

Better Patch Stitching for Parametric Surface Reconstruction

Pascal Fua, Mathieu Salzmann, Jan Bednarík, Zhantao Deng

Recently, parametric mappings have emerged as highly effective surface representations, yielding low reconstruction error. In particular, the latest works represent the target shape as an atlas of multiple mappings, which can closely encode object parts. A ...

IEEE2020

Volumetric Transformer Networks

Mathieu Salzmann, Sabine Süsstrunk, Seungryong Kim

Existing techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature channels can represent different sema ...

2020

Single-Stage 6D Object Pose Estimation

Pascal Fua, Mathieu Salzmann, Yinlin Hu, Wei Wang

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage process, how ...

IEEE2020

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

Mathieu Salzmann, Shuxuan Guo

We introduce an approach to training a given compact network. To this end, we leverage over-parameterization, which typically improves both neural network optimization and generalization. Specifically, we propose to expand each linear layer of the compact ...

Curran Associates Inc.2020

ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture

Pascal Fua, Mathieu Salzmann, Sudipta Sinha, Sena Kiciroglu, Helge Jochen Rhodin

The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured. While freely moving cameras, such as on drones, provide control over this viewpoint, automatically positioning them at the location which will yie ...

IEEE2020

Indirect Local Attacks for Context-aware Semantic Segmentation Networks

Mathieu Salzmann, Krishna Kanth Nakka

Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information. In this paper, we show that the resulting networks are sensitive not only to global adversarial attacks, ...

Springer Nature2020

Local Non-Rigid Structure-from-Motion from Locally Diffeomorphic Mappings

Pascal Fua, Mathieu Salzmann, Shaifali Parashar

We propose a new formulation to the non-rigid structure-from-motion problem that only requires the deforming surface to meaning that its differential structure is preserved. This is a much weaker assumption than the traditional ones of isometry or conforma ...

2020

Domain-Adaptive Multibranch Networks

Pascal Fua, Mathieu Salzmann, Róger Bermúdez Chacón

We tackle unsupervised domain adaptation by accounting for the fact that different domains may need to be processed differently to arrive to a common feature representation effective for recognition. To this end, we introduce a deep learning framework wher ...

2020

Recurrent U-Net for Resource-Constrained Segmentation

Pascal Fua, Mathieu Salzmann, Joachim Ludovic Hugonot, Kaicheng Yu, Wei Wang

State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. In this paper, we introduce a novel recurrent U-Net architecture ...

IEEE COMPUTER SOC2019

Page 5 of 9