Search Results for author: Sabine Süsstrunk

Found 38 papers, 22 papers with code

Fast Adversarial Training with Adaptive Step Size

no code implementations6 Jun 2022 Zhichao Huang, Yanbo Fan, Chen Liu, Weizhong Zhang, Yong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Jue Wang

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

no code implementations CVPR 2022 Tong Zhang, Congpei Qiu, Wei Ke, Sabine Süsstrunk, Mathieu Salzmann

In essence, this strategy ignores the fact that two crops may truly contain different image information, e. g., background and small objects, and thus tends to restrain the diversity of the learned representations.

Self-Supervised Learning Transfer Learning

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

1 code implementation8 Mar 2022 Di Chang, Aljaž Božič, Tong Zhang, Qingsong Yan, Yingcong Chen, Sabine Süsstrunk, Matthias Nießner

Finding accurate correspondences among different views is the Achilles' heel of unsupervised Multi-View Stereo (MVS).

Neural Rendering

Robust Binary Models by Pruning Randomly-initialized Networks

no code implementations3 Feb 2022 Chen Liu, Ziqi Zhao, Sabine Süsstrunk, Mathieu Salzmann

We propose ways to obtain robust models against adversarial attacks from randomly-initialized binary networks.

Image Denoising with Control over Deep Network Hallucination

1 code implementation2 Jan 2022 Qiyuan Liang, Florian Cassayre, Haley Owsianko, Majed El Helou, Sabine Süsstrunk

In this framework, we exploit the outputs of a deep denoising network alongside an image convolved with a reliable filter.

Image Denoising

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training

no code implementations14 Dec 2021 Chen Liu, Zhichao Huang, Mathieu Salzmann, Tong Zhang, Sabine Süsstrunk

This lets us show that the decay in generalization performance of adversarial training is a result of the model's attempt to fit hard adversarial instances.

Optimizing Latent Space Directions For GAN-based Local Image Editing

1 code implementation24 Nov 2021 Ehsan Pajouheshgar, Tong Zhang, Sabine Süsstrunk

Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes.

Disentanglement

Estimating Image Depth in the Comics Domain

no code implementations7 Oct 2021 Deblina Bhattacharjee, Martin Everaert, Mathieu Salzmann, Sabine Süsstrunk

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.

Depth Estimation Translation +1

Improving Adversarial Defense with Self-supervised Test-time Fine-tuning

no code implementations29 Sep 2021 Zhichao Huang, Chen Liu, Mathieu Salzmann, Sabine Süsstrunk, Tong Zhang

Although adversarial training and its variants currently constitute the most effective way to achieve robustness against adversarial attacks, their poor generalization limits their performance on the test samples.

Adversarial Defense

Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks

1 code implementation1 Jun 2021 Xiaoyu Lin, Deblina Bhattacharjee, Majed El Helou, Sabine Süsstrunk

Furthermore, as proof of concept, we show that when using our oracle fidelity map we even outperform the fully retrained methods, whether trained on noisy or restored images.

Classification Image Classification

Modeling Object Dissimilarity for Deep Saliency Prediction

no code implementations8 Apr 2021 Bahar Aydemir, Deblina Bhattacharjee, Seungryong Kim, Tong Zhang, Mathieu Salzmann, Sabine Süsstrunk

Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level one, such as attention and gaze direction for entire objects.

Saliency Prediction

Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion

1 code implementation12 Jan 2021 Xiaoqi Ma, Xiaoyu Lin, Majed El Helou, Sabine Süsstrunk

While novel denoising networks were designed for real images coming from different distributions, or for specific applications, comparatively small improvement was achieved on Gaussian denoising.

Denoising

BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration

1 code implementation3 Nov 2020 Majed El Helou, Sabine Süsstrunk

Our method, though partly reliant on the quality of the generative network inversion, is competitive with state-of-the-art supervised and task-specific restoration methods.

Colorization Denoising +2

Volumetric Transformer Networks

no code implementations ECCV 2020 Seungryong Kim, Sabine Süsstrunk, Mathieu Salzmann

We design our VTN as an encoder-decoder network, with modules dedicated to letting the information flow across the feature channels, to account for the dependencies between the semantic parts.

Fine-Grained Image Recognition Image Retrieval

VIDIT: Virtual Image Dataset for Illumination Transfer

2 code implementations11 May 2020 Majed El Helou, Ruofan Zhou, Johan Barthas, Sabine Süsstrunk

Deep image relighting is gaining more interest lately, as it allows photo enhancement through illumination-specific retouching without human effort.

Domain Adaptation Image Relighting

Editing in Style: Uncovering the Local Semantics of GANs

2 code implementations CVPR 2020 Edo Collins, Raja Bala, Bob Price, Sabine Süsstrunk

Focusing on StyleGAN, we introduce a simple and effective method for making local, semantically-aware edits to a target output image.

Disentanglement Image Generation

Divergence-Based Adaptive Extreme Video Completion

no code implementations14 Apr 2020 Majed El Helou, Ruofan Zhou, Frank Schmutz, Fabrice Guibert, Sabine Süsstrunk

Extreme image or video completion, where, for instance, we only retain 1% of pixels in random locations, allows for very cheap sampling in terms of the required pre-processing.

Motion Estimation

Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency

1 code implementation19 Mar 2020 Gökhan Yildirim, Debashis Sen, Mohan Kankanhalli, Sabine Süsstrunk

In this paper, we corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varying levels of importance.

object-detection RGB Salient Object Detection +2

W2S: Microscopy Data with Joint Denoising and Super-Resolution for Widefield to SIM Mapping

1 code implementation12 Mar 2020 Ruofan Zhou, Majed El Helou, Daniel Sage, Thierry Laroche, Arne Seitz, Sabine Süsstrunk

To study JDSR on microscopy data, we propose such a novel JDSR dataset, Widefield2SIM (W2S), acquired using a conventional fluorescence widefield and SIM imaging.

Denoising Super-Resolution

Image Restoration using Plug-and-Play CNN MAP Denoisers

1 code implementation18 Dec 2019 Siavash Bigdeli, David Honzátko, Sabine Süsstrunk, L. Andrea Dunbar

Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type.

Image Denoising Image Restoration

Training Provably Robust Models by Polyhedral Envelope Regularization

1 code implementation10 Dec 2019 Chen Liu, Mathieu Salzmann, Sabine Süsstrunk

Training certifiable neural networks enables one to obtain models with robustness guarantees against adversarial attacks.

Drone Shadow Tracking

1 code implementation20 May 2019 Xiaoyan Zou, Ruofan Zhou, Majed El Helou, Sabine Süsstrunk

In this paper, we incorporate knowledge of the shadow's physical properties, in the form of shadow detection masks, into a correlation-based tracking algorithm.

Shadow Detection Shadow Removal

Fast and Efficient Zero-Learning Image Fusion

1 code implementation9 May 2019 Fayez Lahoud, Sabine Süsstrunk

Our method generates a single image containing features from multiple sources.

Self-Binarizing Networks

no code implementations2 Feb 2019 Fayez Lahoud, Radhakrishna Achanta, Pablo Márquez-Neila, Sabine Süsstrunk

To obtain similar binary networks, existing methods rely on the sign activation function.

Binarization

Detecting Memorization in ReLU Networks

no code implementations ICLR 2019 Edo Collins, Siavash Arjomand Bigdeli, Sabine Süsstrunk

We propose a new notion of `non-linearity' of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix.

Fourier-Domain Optimization for Image Processing

1 code implementation11 Sep 2018 Majed El Helou, Frederike Dümbgen, Radhakrishna Achanta, Sabine Süsstrunk

Image optimization problems encompass many applications such as spectral fusion, deblurring, deconvolution, dehazing, matting, reflection removal and image interpolation, among others.

Deblurring Image Matting +1

Deep Feature Factorization For Concept Discovery

1 code implementation ECCV 2018 Edo Collins, Radhakrishna Achanta, Sabine Süsstrunk

We propose Deep Feature Factorization (DFF), a method capable of localizing similar semantic concepts within an image or a set of images.

Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal

no code implementations29 May 2018 Daniel Heydecker, Georg Maierhofer, Angelica I. Aviles-Rivero, Qingnan Fan, Dong-Dong Chen, Carola-Bibiane Schönlieb, Sabine Süsstrunk

Removing reflection artefacts from a single image is a problem of both theoretical and practical interest, which still presents challenges because of the massively ill-posed nature of the problem.

Reflection Removal

Deep Residual Network for Joint Demosaicing and Super-Resolution

1 code implementation19 Feb 2018 Ruofan Zhou, Radhakrishna Achanta, Sabine Süsstrunk

By training on high-quality samples, our deep residual demosaicing and super-resolution network is able to recover high-quality super-resolved images from low-resolution Bayer mosaics in a single step without producing the artifacts common to such processing when the two operations are done separately.

Demosaicking SSIM +1

Uniform Information Segmentation

no code implementations27 Nov 2016 Radhakrishna Achanta, Pablo Márquez-Neila, Pascal Fua, Sabine Süsstrunk

Since information is a natural way of measuring image complexity, our proposed algorithm leads to image segments that are smaller and denser in areas of high complexity and larger in homogeneous regions, thus simplifying the image while preserving its details.

Superpixels

God(s) Know(s): Developmental and Cross-Cultural Patterns in Children Drawings

no code implementations11 Nov 2015 Ksenia Konyushkova, Nikolaos Arvanitopoulos, Zhargalma Dandarova Robert, Pierre-Yves Brandt, Sabine Süsstrunk

This paper introduces a novel approach to data analysis designed for the needs of specialists in psychology of religion.

Incorporating Near-Infrared Information into Semantic Image Segmentation

no code implementations24 Jun 2014 Neda Salamati, Diane Larlus, Gabriela Csurka, Sabine Süsstrunk

Based on a state-of-the-art segmentation framework and a novel manually segmented image database (both indoor and outdoor scenes) that contain 4-channel images (RGB+NIR), we study how to best incorporate the specific characteristics of the NIR response.

Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.