arXiv subjects

Stefan Roth

Publications and source records attributed to Stefan Roth.

At least 73 records · Page 4Linked to original sources

arXiv2021

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. Recent approaches include priors on the feature attribution of a deep neural network (DNN) into the training process to reduce the dependence on unwanted features. However, until now one needed to trade off high-quality attributions, satisfying desirable axioms, against the time required to compute them. This in turn either led to long training times or ineffective attribution priors. In this work, we break this trade-off by considering a special class of efficiently axiomatically attributable DNNs for which an axiomatic feature attribution can be computed with only a single forward/backward pass. We formally prove that nonnegatively homogeneous DNNs, here termed $\mathcal{X}$-DNNs, are efficiently axiomatically attributable and show that they can be effortlessly constructed from a wide range of regular DNNs by simply removing the bias term of each layer. Various experiments demonstrate the advantages of $\mathcal{X}$-DNNs, beating state-of-the-art generic attribution methods on regular DNNs for training with attribution priors.

cs.LG↗

arXiv2021

Dense Unsupervised Learning for Video Segmentation

We present a novel approach to unsupervised learning for video object segmentation (VOS). Unlike previous work, our formulation allows to learn dense feature representations directly in a fully convolutional regime. We rely on uniform grid sampling to extract a set of anchors and train our model to disambiguate between them on both inter- and intra-video levels. However, a naive scheme to train such a model results in a degenerate solution. We propose to prevent this with a simple regularisation scheme, accommodating the equivariance property of the segmentation task to similarity transformations. Our training objective admits efficient implementation and exhibits fast training convergence. On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.

cs.CV↗

arXiv2021

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. Yet, the sequential ordering on the dimensions makes these models computationally expensive and limits their applicability to low-resolution imagery. In this work, we propose Pixel-Pyramids, a block-autoregressive approach employing a lossless pyramid decomposition with scale-specific representations to encode the joint distribution of image pixels. Crucially, it affords a sparser dependency structure compared to fully autoregressive approaches. Our PixelPyramids yield state-of-the-art results for density estimation on various image datasets, especially for high-resolution data. For CelebA-HQ 1024 x 1024, we observe that the density estimates (in terms of bits/dim) are improved to ~44% of the baseline despite sampling speeds superior even to easily parallelizable flow-based models.

cs.CV↗

arXiv2021

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. Despite the widespread success of end-to-end learning, today's multimodal pipelines by and large leverage pre-extracted, fixed features from object detectors, typically Faster R-CNN, as representations of the visual world. The obvious downside is that the visual representation is not specifically tuned to the multimodal task at hand. At the same time, while transformer-based object detectors have gained popularity, they have not been employed in today's multimodal pipelines. We address both shortcomings with TxT, a transformer-based crossmodal pipeline that enables fine-tuning both language and visual components on the downstream task in a fully end-to-end manner. We overcome existing limitations of transformer-based detectors for multimodal reasoning regarding the integration of global context and their scalability. Our transformer-based multimodal model achieves considerable gains from end-to-end learning for multimodal question answering.

cs.CV↗

arXiv2021

A Gas Monitoring Chamber for High Pressure Applications

Time Projection Chambers (TPCs) operated at high pressure have become a topic of interest for future long baseline neutrino experiments. Pressurized gas retains the low momentum threshold for particle detection of atmospheric TPCs, but offers a larger target mass for neutrino interactions at the same volume. Operation at high pressure poses several new challenges in safety aspects regarding overpressure and high voltage safety. The presented High Pressure Gas Monitoring Chamber (HPGMC) can be used to study the suitability of various drift gas mixtures up to 10 bar and a maximum field of $\sim$3000 V/cm . A flexible construction makes it possible to exchange parts of the inner detector and to test new technologies. In this work, the construction of a HPGMC and its commissioning using the P10 gas mixture ($90 \% \mathrm{Ar} + 10 \% \mathrm{CH}_4$) are presented.

physics.ins-det↗

arXiv2021

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. A High Pressure Time Projection Chamber (HPTPC) prototype has been constructed and operated at Royal Holloway University of London and CERN as a first step in the development of a HPTPC capable of performing these measurements as part of a future long-baseline neutrino oscillation experiment such as the Deep Underground Neutrino Experiment. In this paper we describe the design and operation of the prototype HPTPC with an argon based gas mixture. We report on the successful hybrid charge and optical readout, using four CCD cameras, of signals from Am-241 sources.

physics.ins-det↗

arXiv2021

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. Owing to the severe ill-posedness of the problem, the accuracy of current methods has been limited, especially that of efficient, real-time approaches. In this paper, we introduce a multi-frame monocular scene flow network based on self-supervised learning, improving the accuracy over previous networks while retaining real-time efficiency. Based on an advanced two-frame baseline with a split-decoder design, we propose (i) a multi-frame model using a triple frame input and convolutional LSTM connections, (ii) an occlusion-aware census loss for better accuracy, and (iii) a gradient detaching strategy to improve training stability. On the KITTI dataset, we observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.

cs.CV↗

arXiv2021

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. In contrast to previous work, we abandon the use of computationally involved adversarial objectives, network ensembles and style transfer. Instead, we employ standard data augmentation techniques $-$ photometric noise, flipping and scaling $-$ and ensure consistency of the semantic predictions across these image transformations. We develop this principle in a lightweight self-supervised framework trained on co-evolving pseudo labels without the need for cumbersome extra training rounds. Simple in training from a practitioner's standpoint, our approach is remarkably effective. We achieve significant improvements of the state-of-the-art segmentation accuracy after adaptation, consistent both across different choices of the backbone architecture and adaptation scenarios.

cs.CV↗

arXiv2021

Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise

To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by averaging predictions with respect to the posterior weight distribution. 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. Recent sampling-free approaches offer an alternative, but incur a significant parameter overhead. We here propose a more efficient parameterization of the posterior approximation for sampling-free variational inference that relies on the distribution induced by multiplicative Gaussian activation noise. This allows us to combine parameter efficiency with the benefits of sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks including ImageNet.

cs.LG↗

arXiv2020

Localization Attack by Precoder Feedback Overhearing in 5G Networks and Countermeasures

In fifth-generation (5G) cellular networks, users feed back to the base station the index of the precoder (from a codebook) to be used for downlink transmission. The precoder is strongly related to the user channel and in turn to the user position within the cell. We propose a method by which an external attacker determines the user position by passively overhearing this unencrypted layer-2 feedback signal. The attacker first builds a map of fed back precoder indices in the cell. Then, by overhearing the precoder index fed back by the victim user, the attacker finds its position on the map. We focus on the type-I single-panel codebook, which today is the only mandatory solution in the 3GPP standard. We analyze the attack and assess the obtained localization accuracy against various parameters. We analyze the localization error of a simplified precoder feedback model and describe its asymptotic localization precision. We also propose a mitigation against our attack, wherein the user randomly selects the precoder among those providing the highest rate. Simulations confirm that the attack can achieve a high localization accuracy, which is significantly reduced when the mitigation solution is adopted, at the cost of a negligible rate degradation.

cs.IT↗

arXiv2020

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for research. 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. The benchmark is focused on multiple people tracking, since pedestrians are by far the most studied object in the tracking community, with applications ranging from robot navigation to self-driving cars. This paper collects the first three releases of the benchmark: (i) MOT15, along with numerous state-of-the-art results that were submitted in the last years, (ii) MOT16, which contains new challenging videos, and (iii) MOT17, that extends MOT16 sequences with more precise labels and evaluates tracking performance on three different object detectors. The second and third release not only offers a significant increase in the number of labeled boxes but also provide labels for multiple object classes beside pedestrians, as well as the level of visibility for every single object of interest. We finally provide a categorization of state-of-the-art trackers and a broad error analysis. This will help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light on potential future research directions.

cs.CV↗

arXiv2020

Diverse Image Captioning with Context-Object Split Latent Spaces

Diverse image captioning models aim to learn one-to-many mappings that are innate to cross-domain datasets, such as of images and texts. Current methods for this task are based on generative latent variable models, e.g. VAEs with structured latent spaces. Yet, the amount of multimodality captured by prior work is limited to that of the paired training data -- the true diversity of the underlying generative process is not fully captured. To address this limitation, we leverage the contextual descriptions in the dataset that explain similar contexts in different visual scenes. To this end, we introduce a novel factorization of the latent space, termed context-object split, to model diversity in contextual descriptions across images and texts within the dataset. 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. We evaluate our COS-CVAE approach on the standard COCO dataset and on the held-out COCO dataset consisting of images with novel objects, showing significant gains in accuracy and diversity.

cs.CV↗

arXiv2020

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving

General-purpose planning algorithms for automated driving combine mission, behavior, and local motion planning. Such planning algorithms map features of the environment and driving kinematics into complex reward functions. To achieve this, planning experts often rely on linear reward functions. The specification and tuning of these reward functions is a tedious process and requires significant experience. Moreover, a manually designed linear reward function does not generalize across different driving situations. In this work, we propose a deep learning approach based on inverse reinforcement learning that generates situation-dependent reward functions. Our neural network provides a mapping between features and actions of sampled driving policies of a model-predictive control-based planner and predicts reward functions for upcoming planning cycles. In our evaluation, we compare the driving style of reward functions predicted by our deep network against clustered and linear reward functions. Our proposed deep learning approach outperforms clustered linear reward functions and is at par with linear reward functions with a-priori knowledge about the situation.

cs.RO↗

arXiv2020

Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving

Behavior and motion planning play an important role in automated driving. Traditionally, behavior planners instruct local motion planners with predefined behaviors. Due to the high scene complexity in urban environments, unpredictable situations may occur in which behavior planners fail to match predefined behavior templates. Recently, general-purpose planners have been introduced, combining behavior and local motion planning. These general-purpose planners allow behavior-aware motion planning given a single reward function. However, two challenges arise: First, this function has to map a complex feature space into rewards. Second, the reward function has to be manually tuned by an expert. Manually tuning this reward function becomes a tedious task. In this paper, we propose an approach that relies on human driving demonstrations to automatically tune reward functions. This study offers important insights into the driving style optimization of general-purpose planners with maximum entropy inverse reinforcement learning. We evaluate our approach based on the expected value difference between learned and demonstrated policies. Furthermore, we compare the similarity of human driven trajectories with optimal policies of our planner under learned and expert-tuned reward functions. Our experiments show that we are able to learn reward functions exceeding the level of manual expert tuning without prior domain knowledge.

cs.RO↗

arXiv2020

Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning

General-purpose trajectory planning algorithms for automated driving utilize complex reward functions to perform a combined optimization of strategic, behavioral, and kinematic features. The specification and tuning of a single reward function is a tedious task and does not generalize over a large set of traffic situations. Deep learning approaches based on path integral inverse reinforcement learning have been successfully applied to predict local situation-dependent reward functions using features of a set of sampled driving policies. Sample-based trajectory planning algorithms are able to approximate a spatio-temporal subspace of feasible driving policies that can be used to encode the context of a situation. However, the interaction with dynamic objects requires an extended planning horizon, which depends on sequential context modeling. In this work, we are concerned with the sequential reward prediction over an extended time horizon. We present a neural network architecture that uses a policy attention mechanism to generate a low-dimensional context vector by concentrating on trajectories with a human-like driving style. Apart from this, we propose a temporal attention mechanism to identify context switches and allow for stable adaptation of rewards. We evaluate our results on complex simulated driving situations, including other moving vehicles. Our evaluation shows that our policy attention mechanism learns to focus on collision-free policies in the configuration space. Furthermore, the temporal attention mechanism learns persistent interaction with other vehicles over an extended planning horizon.

cs.RO↗

arXiv2020

LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery

State-of-the-art object detection approaches such as Fast/Faster R-CNN, SSD, or YOLO have difficulties detecting dense, small targets with arbitrary orientation in large aerial images. The main reason is that using interpolation to align RoI features can result in a lack of accuracy or even loss of location information. We present the Local-aware Region Convolutional Neural Network (LR-CNN), a novel two-stage approach for vehicle detection in aerial imagery. We enhance translation invariance to detect dense vehicles and address the boundary quantization issue amongst dense vehicles by aggregating the high-precision RoIs' features. Moreover, we resample high-level semantic pooled features, making them regain location information from the features of a shallower convolutional block. This strengthens the local feature invariance for the resampled features and enables detecting vehicles in an arbitrary orientation. The local feature invariance enhances the learning ability of the focal loss function, and the focal loss further helps to focus on the hard examples. Taken together, our method better addresses the challenges of aerial imagery. We evaluate our approach on several challenging datasets (VEDAI, DOTA), demonstrating a significant improvement over state-of-the-art methods. We demonstrate the good generalization ability of our approach on the DLR 3K dataset.

cs.CV↗

arXiv2020

Single-Stage Semantic Segmentation from Image Labels

Recent years have seen a rapid growth in new approaches improving the accuracy of semantic segmentation in a weakly supervised setting, i.e. with only image-level labels available for training. However, this has come at the cost of increased model complexity and sophisticated multi-stage training procedures. 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. In this work, we first define three desirable properties of a weakly supervised method: local consistency, semantic fidelity, and completeness. Using these properties as guidelines, we then develop a segmentation-based network model and a self-supervised training scheme to train for semantic masks from image-level annotations in a single stage. We show that despite its simplicity, our method achieves results that are competitive with significantly more complex pipelines, substantially outperforming earlier single-stage methods.

cs.CV↗

arXiv2020

Remote Short Blocklength Process Monitoring: Trade-off Between Resolution and Data Freshness

In cyber-physical systems, as in 5G and beyond, multiple physical processes require timely online monitoring at a remote device. There, the received information is used to estimate current and future process values. When transmitting the process data over a communication channel, source-channel coding is used in order to reduce data errors. During transmission, a high data resolution is helpful to capture the value of the process variables precisely. However, this typically comes with long transmission delays reducing the utilizability of the data, since the estimation quality gets reduced over time. In this paper, the trade-off between having recent data and precise measurements is captured for a Gauss-Markov process. An Age-of-Information (AoI) metric is used to assess data timeliness, while mean square error (MSE) is used to assess the precision of the predicted process values. AoI appears inherently within the MSE expressions, yet it can be relatively easier to optimize. Our goal is to minimize a time-averaged version of both metrics. We follow a short blocklength source-channel coding approach, and optimize the parameters of the codes being used in order to describe an achievability region between MSE and AoI.

cs.IT↗