Classic computer vision algorithms, instance segmentation, and semantic segmentation can not provide a holistic understanding of the surroundings for the visually impaired. In this paper, we utilize panoptic segmentation to assist the navigation of visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired efficiently. To this end, we propose an efficient Attention module -- Lintention which can model long-range interactions in linear time using linear space. Based on Lintention, we then devise a novel panoptic segmentation model which we term Panoptic Lintention Net. Experiments on the COCO dataset indicate that the Panoptic Lintention Net raises the Panoptic Quality (PQ) from 39.39 to 41.42 with 4.6\% performance gain while only requiring 10\% fewer GFLOPs and 25\% fewer parameters in the semantic branch. Furthermore, a real-world test via our designed compact wearable panoptic segmentation system, indicates that our system based on the Panoptic Lintention Net accomplishes a relatively stable and exceptionally remarkable panoptic segmentation in real-world scenes.
Street scene change detection continues to capture researchers' interests in the computer vision community. It aims to identify the changed regions of the paired street-view images captured at different times. The state-of-the-art network based on the encoder-decoder architecture leverages the feature maps at the corresponding level between two channels to gain sufficient information of changes. Still, the efficiency of feature extraction, feature correlation calculation, even the whole network requires further improvement. This paper proposes the temporal attention and explores the impact of the dependency-scope size of temporal attention on the performance of change detection. In addition, based on the Temporal Attention Module (TAM), we introduce a more efficient and light-weight version - Dynamic Receptive Temporal Attention Module (DRTAM) and propose the Concurrent Horizontal and Vertical Attention (CHVA) to improve the accuracy of the network on specific challenging entities. On street scene datasets `GSV', `TSUNAMI' and `VL-CMU-CD', our approach gains excellent performance, establishing new state-of-the-art scores without bells and whistles, while maintaining high efficiency applicable in autonomous vehicles.
In this work, we introduce panoramic panoptic segmentation as the most holistic scene understanding both in terms of field of view and image level understanding. A complete surrounding understanding provides a maximum of information to the agent, which is essential for any intelligent vehicle in order to make informed decisions in a safety-critical dynamic environment such as real-world traffic. In order to overcome the lack of annotated panoramic images, we propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain. Using our proposed method, we manage to achieve significant improvements of over 5\% measured in PQ over non-adapted models on our Wild Panoramic Panoptic Segmentation (WildPPS) dataset. We show that our proposed Panoramic Robust Feature (PRF) framework is not only suitable to improve performance on panoramic images but can be beneficial whenever model training and deployment are executed on data taken from different distributions. As an additional contribution, we publish WildPPS: The first panoramic panoptic image dataset to foster progress in surrounding perception.
Detector-based spectral computed tomography is a recent dual-energy CT (DECT) technology that offers the possibility of obtaining spectral information. From this spectral data, different types of images can be derived, amongst others virtual monoenergetic (monoE) images. MonoE images potentially exhibit decreased artifacts, improve contrast, and overall contain lower noise values, making them ideal candidates for better delineation and thus improved diagnostic accuracy of vascular abnormalities. In this paper, we are training convolutional neural networks~(CNN) that can emulate the generation of monoE images from conventional single energy CT acquisitions. For this task, we investigate several commonly used image-translation methods. We demonstrate that these methods while creating visually similar outputs, lead to a poorer performance when used for automatic classification of pulmonary embolism (PE). We expand on these methods through the use of a multi-task optimization approach, under which the networks achieve improved classification as well as generation results, as reflected by PSNR and SSIM scores. Further, evaluating our proposed framework on a subset of the RSNA-PE challenge data set shows that we are able to improve the Area under the Receiver Operating Characteristic curve (AuROC) in comparison to a na\"ive classification approach from 0.8142 to 0.8420.
Beyond assigning the correct class, an activity recognition model should also be able to determine, how certain it is in its predictions. We present the first study of how welthe confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome and propose a learning-based approach for improving it. First, we extend two popular action recognition datasets with a reliability benchmark in form of the expected calibration error and reliability diagrams. Since our evaluation highlights that confidence values of standard action recognition architectures do not represent the uncertainty well, we introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network. The main idea of our Calibrated Action Recognition with Input Guidance (CARING) model is to learn an optimal scaling parameter depending on the video representation. We compare our model with the native action recognition networks and the temperature scaling approach - a wide spread calibration method utilized in image classification. While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.
A rapidly growing amount of content posted online, such as food recipes, opens doors to new exciting applications at the intersection of vision and language. In this work, we aim to estimate the calorie amount of a meal directly from an image by learning from recipes people have published on the Internet, thus skipping time-consuming manual data annotation. Since there are few large-scale publicly available datasets captured in unconstrained environments, we propose the pic2kcal benchmark comprising 308,000 images from over 70,000 recipes including photographs, ingredients and instructions. To obtain nutritional information of the ingredients and automatically determine the ground-truth calorie value, we match the items in the recipes with structured information from a food item database. We evaluate various neural networks for regression of the calorie quantity and extend them with the multi-task paradigm. Our learning procedure combines the calorie estimation with prediction of proteins, carbohydrates, and fat amounts as well as a multi-label ingredient classification. Our experiments demonstrate clear benefits of multi-task learning for calorie estimation, surpassing the single-task calorie regression by 9.9%. To encourage further research on this task, we make the code for generating the dataset and the models publicly available.
The lack of fine-grained annotations hinders the deployment of automated diagnosis systems, which require human-interpretable justification for their decision process. In this paper, we address the problem of weakly supervised identification and localization of abnormalities in chest radiographs. To that end, we introduce a novel loss function for training convolutional neural networks increasing the \emph{localization confidence} and assisting the overall \emph{disease identification}. The loss leverages both image- and patch-level predictions to generate auxiliary supervision. Rather than forming strictly binary from the predictions as done in previous loss formulations, we create targets in a more customized manner, which allows the loss to account for possible misclassification. We show that the supervision provided within the proposed learning scheme leads to better performance and more precise predictions on prevalent datasets for multiple-instance learning as well as on the NIH~ChestX-Ray14 benchmark for disease recognition than previously used losses.
Unsupervised domain adaptation (UDA) deals with the adaptation of models from a given source domain with labeled data to an unlabeled target domain. In this paper, we utilize the inherent prediction uncertainty of a model to accomplish the domain adaptation task. The uncertainty is measured by Monte-Carlo dropout and used for our proposed Uncertainty-based Filtering and Feature Alignment (UFAL) that combines an Uncertain Feature Loss (UFL) function and an Uncertainty-Based Filtering (UBF) approach for alignment of features in Euclidean space. Our method surpasses recently proposed architectures and achieves state-of-the-art results on multiple challenging datasets. Code is available on the project website.
Multispectral images consisting of aligned visual-optical (VIS) and thermal infrared (IR) image pairs are well-suited for practical applications like autonomous driving or visual surveillance. Such data can be used to increase the performance of pedestrian detection especially for weakly illuminated, small-scaled, or partially occluded instances. The current state-of-the-art is based on variants of Faster R-CNN and thus passes through two stages: a proposal generator network with handcrafted anchor boxes for object localization and a classification network for verifying the object category. In this paper we propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. In this way, we can both simplify the network architecture and achieve higher detection performance, especially for pedestrians under occlusion or at low object resolution. In addition, we provide a study on well-suited multispectral data augmentation techniques that improve the commonly used augmentations. The results show our method's effectiveness in detecting small-scaled pedestrians. We achieve 5.68% log-average miss rate in comparison to the best current state-of-the-art of 7.49% (25% improvement) on the challenging KAIST Multispectral Pedestrian Detection Benchmark. Code: https://github.com/HensoldtOptronicsCV/MultispectralPedestrianDetection