Search Results for author:
Found 75 papers, 35 papers with code
A Perspective on Deep Vision Performance with Standard Image and Video Codecs
The use of standardized codecs, such as JPEG or H. 264, is prevalent and required to ensure interoperability.
Enhancing the Secrecy Rate with Direction-range Focusing with FDA and RIS
Simulations verify the correctness of the closed-form expressions and demonstrate that we can effectively improve the secrecy rate, especially when the eavesdropper is close to the RIS or the legitimate user.
Pixel State Value Network for Combined Prediction and Planning in Interactive Environments
Automated vehicles operating in urban environments have to reliably interact with other traffic participants.
Vision Relation Transformer for Unbiased Scene Graph Generation
Recent years have seen a growing interest in Scene Graph Generation (SGG), a comprehensive visual scene understanding task that aims to predict entity relationships using a relation encoder-decoder pipeline stacked on top of an object encoder-decoder backbone.
FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods
Using our tools, we report results for 24 different combinations of neural models and XAI methods, demonstrating the strengths and weaknesses of the assessed methods in a fully automatic and systematic manner.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Content-Adaptive Downsampling in Convolutional Neural Networks
Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost.
Efficient Feature Extraction for High-resolution Video Frame Interpolation
The feature extraction layers help to compress the input and extract relevant information for the latter stages, such as motion estimation.
$S^2$-Flow: Joint Semantic and Style Editing of Facial Images
In addition, methods that use semantic masks to edit images have difficulty preserving the identity and are unable to perform controlled style edits.
Semantic Self-adaptation: Enhancing Generalization with a Single Sample
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation.
Diverse Image Captioning with Grounded Style
Stylized image captioning as presented in prior work aims to generate captions that reflect characteristics beyond a factual description of the scene composition, such as sentiments.
Fast Axiomatic Attribution for Neural Networks
Mitigating the dependence on spurious correlations present in the training dataset is a quickly emerging and important topic of deep learning.
Dense Unsupervised Learning for Video Segmentation
On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.
PixelPyramids: Exact Inference Models from Lossless Image Pyramids
Autoregressive models are a class of exact inference approaches with highly flexible functional forms, yielding state-of-the-art density estimates for natural images.
Adaptive Generalization for Semantic Segmentation
In this work, we empirically study an adaptive inference strategy for semantic segmentation that adjusts the model to the test sample before producing the final prediction.
Noise-Contrastive Variational Information Bottleneck Networks
While deep neural networks for classification have shown impressive predictive performance, e. g. in image classification, they generally tend to be overconfident.
xGQA: Cross-Lingual Visual Question Answering
In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task.
TxT: Crossmodal End-to-End Learning with Transformers
Reasoning over multiple modalities, e. g. in Visual Question Answering (VQA), requires an alignment of semantic concepts across domains.
Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring
The classical maximum a-posteriori (MAP) framework for non-blind image deblurring requires defining suitable data and regularization terms, whose interplay yields the desired clear image through optimization.
Self-Supervised Multi-Frame Monocular Scene Flow
Estimating 3D scene flow from a sequence of monocular images has been gaining increased attention due to the simple, economical capture setup.
Self-supervised Augmentation Consistency for Adapting Semantic Segmentation
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate.
Ranked #16 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring
We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning.
Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise
Variational inference methods for BNNs approximate the intractable weight posterior with a tractable distribution, yet mostly rely on sampling from the variational distribution during training and inference.
A High Pressure Time Projection Chamber with Optical Readout
Measurements of proton-nucleus scattering and high resolution neutrino-nucleus interaction imaging are key to reduce neutrino oscillation systematic uncertainties in future experiments.
Instrumentation and Detectors High Energy Physics - Experiment
Localization Attack by Precoder Feedback Overhearing in 5G Networks and Countermeasures
We analyze the attack and assess the obtained localization accuracy against various parameters.
Information Theory Cryptography and Security Signal Processing Information Theory
Diverse Image Captioning with Context-Object Split Latent Spaces
Our framework not only enables diverse captioning through context-based pseudo supervision, but extends this to images with novel objects and without paired captions in the training data.
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data, and create a framework for the standardized evaluation of multiple object tracking methods.
Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning
Furthermore, the temporal attention mechanism learns persistent interaction with other vehicles over an extended planning horizon.
LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery
This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation.
Single-Stage Semantic Segmentation from Image Labels
This is in contrast to earlier work that used only a single stage $-$ training one segmentation network on image labels $-$ which was abandoned due to inferior segmentation accuracy.
Self-Supervised Monocular Scene Flow Estimation
Our model achieves state-of-the-art accuracy among unsupervised/self-supervised learning approaches to monocular scene flow, and yields competitive results for the optical flow and monocular depth estimation sub-tasks.
Normalizing Flows with Multi-Scale Autoregressive Priors
Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis.
Optical Flow Estimation in the Deep Learning Age
Akin to many subareas of computer vision, the recent advances in deep learning have also significantly influenced the literature on optical flow.
Probabilistic Pixel-Adaptive Refinement Networks
Encoder-decoder networks have found widespread use in various dense prediction tasks.
MOT20: A benchmark for multi object tracking in crowded scenes
The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.
Multi-Object Tracking
Multiple Object Tracking with Transformer
+2
Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings
Therefore, we propose a novel semi-supervised framework, which models shared information between domains and domain-specific information separately.
Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving
In this work, we propose a deep learning approach based on inverse reinforcement learning that generates situation-dependent reward functions.
Deep Video Deblurring: The Devil is in the Details
In contrast to these involved models, we found that a simple baseline CNN can perform astonishingly well when particular care is taken w. r. t.
Markov Decision Process for Video Generation
We identify two pathological cases of temporal inconsistencies in video generation: video freezing and video looping.
Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings
One of the key challenges in learning joint embeddings of multiple modalities, e. g. of images and text, is to ensure coherent cross-modal semantics that generalize across datasets.
Learning Task-Specific Generalized Convolutions in the Permutohedral Lattice
When adding our network layer to state-of-the-art networks for optical flow and semantic segmentation, boundary artifacts are removed and the accuracy is improved.
CVPR19 Tracking and Detection Challenge: How crowded can it get?
Standardized benchmarks are crucial for the majority of computer vision applications.
Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving
Behavior and motion planning play an important role in automated driving.
Actor-Critic Instance Segmentation
Most approaches to visual scene analysis have emphasised parallel processing of the image elements.
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation
While leading to more accurate results, the downside of this is an increased number of parameters.
Ranked #10 on
Optical Flow Estimation
on KITTI 2012
Neural Nearest Neighbors Networks
To exploit our relaxation, we propose the neural nearest neighbors block (N3 block), a novel non-local processing layer that leverages the principle of self-similarity and can be used as building block in modern neural network architectures.
Ranked #1 on
Grayscale Image Denoising
on Set12 sigma70
Multi-view X-ray R-CNN
First, we introduce a novel multi-view pooling layer to perform a 3D aggregation of 2D CNN-features extracted from each view.
Normalized Blind Deconvolution
We introduce a family of novel approaches to single-image blind deconvolution, ie , the problem of recovering a sharp image and a blur kernel from a single blurry input.
A Multimodal Translation-Based Approach for Knowledge Graph Representation Learning
Current methods for knowledge graph (KG) representation learning focus solely on the structure of the KG and do not exploit any kind of external information, such as visual and linguistic information corresponding to the KG entities.
Multimodal Frame Identification with Multilingual Evaluation
Our analysis shows that for the German data, textual representations are still competitive with multimodal ones.
Lightweight Probabilistic Deep Networks
Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice.
Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.
Ranked #6 on
3D Object Reconstruction
on Data3D−R2N2
Detail-Preserving Pooling in Deep Networks
This is commonly referred to as pooling, and is applied to reduce the number of parameters, improve invariance to certain distortions, and increase the receptive field size.
Stochastic Variational Inference with Gradient Linearization
In this paper we propose stochastic variational inference with gradient linearization (SVIGL).
UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss
By optionally fine-tuning on the KITTI training data, our method achieves competitive optical flow accuracy on the KITTI 2012 and 2015 benchmarks, thus in addition enabling generic pre-training of supervised networks for datasets with limited amounts of ground truth.
ProbFlow: Joint Optical Flow and Uncertainty Estimation
We overcome the artificial separation of optical flow and confidence estimation by introducing a method that jointly predicts optical flow and its underlying uncertainty.
MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation
The key feature of our model is to fully exploit the symmetry properties that characterize optical flow and occlusions in the two consecutive images.
Benchmarking Denoising Algorithms with Real Photographs
Lacking realistic ground truth data, image denoising techniques are traditionally evaluated on images corrupted by synthesized i. i. d.
Robust Multi-Image HDR Reconstruction for the Modulo Camera
While the concept is appealing, we show that the original reconstruction approach assumes noise-free measurements and quickly breaks down otherwise.
Noise-Blind Image Deblurring
We present a novel approach to noise-blind deblurring, the problem of deblurring an image with known blur, but unknown noise level.
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
Standardized benchmarks are crucial for the majority of computer vision applications.
The Stixel world: A medium-level representation of traffic scenes
We believe this challenge should be faced by introducing a representation of the sensory data that provides compressed and structured access to all relevant visual content of the scene.
Playing for Data: Ground Truth from Computer Games
Recent progress in computer vision has been driven by high-capacity models trained on large datasets.
Stereo Video Deblurring
With this paper we are the first to show how the availability of stereo video can aid the challenging video deblurring task.
Joint Optical Flow and Temporally Consistent Semantic Segmentation
The importance and demands of visual scene understanding have been steadily increasing along with the active development of autonomous systems.
Parametric Object Motion from Blur
A two-stage pipeline, first in derivative space and then in image space, allows to estimate both parametric object motion as well as a motion segmentation from a single image alone.
The Cityscapes Dataset for Semantic Urban Scene Understanding
Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications.
MOT16: A Benchmark for Multi-Object Tracking
Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods.
Registering Images to Untextured Geometry Using Average Shading Gradients
Many existing approaches for image-to-geometry registration assume that either a textured 3D model or a good initial guess of the 3D pose is available to bootstrap the registration process.
Discriminative Shape From Shading in Uncalibrated Illumination
Von Mises-Fisher distributions in the leaves of each tree enable the estimation of surface normals.
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system.
Shrinkage Fields for Effective Image Restoration
To that end we propose shrinkage fields, a random field-based architecture that combines the image model and the optimization algorithm in a single unit.
Cascades of Regression Tree Fields for Image Restoration
We posit two reasons for this: First, the blur kernel is often only known at test time, requiring any discriminative approach to cope with considerable variability.
Discriminative Non-blind Deblurring
From this analysis, we derive a discriminative model cascade for image deblurring.
Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be assigned at most one observation per frame; (2) in trajectory estimation, two trajectories should remain spatially separated at all times to avoid collisions.
A Database and Evaluation Methodology for Optical Flow
The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance.
