Despite recent advances in computer vision based on various convolutional architectures, video understanding remains an important challenge. In this work, we present and discuss a top solution for the large-scale video classification (labeling) problem introduced as a Kaggle competition based on the YouTube-8M dataset. We show and compare different approaches to preprocessing, data augmentation, model architectures, and model combination. Our final model is based on a large ensemble of video- and frame-level models but fits into rather limiting hardware constraints. We apply an approach based on knowledge distillation to deal with noisy labels in the original dataset and the recently developed mixup technique to improve the basic models.
The full loss of thrust of an aircraft requires fast and reliable decisions of the pilot. If no published landing field is within reach, an emergency landing field must be selected. The choice of a suitable emergency landing field denotes a crucial task to avoid unnecessary damage of the aircraft, risk for the civil population as well as the crew and all passengers on board. Especially in case of instrument meteorological conditions it is indispensable to use a database of suitable emergency landing fields. Thus, based on public available digital orthographic photos and digital surface models,…
Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification
The Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information, the School of Computer Science and Engineering, South China University of Technology（广东省计算智能与网络信息重点实验室、计算机科学与工程学院、华南理工大学）；The Pazhou Laboratory（琶洲实验室）
Rethinking Cross-Dose PET Denoising: Mitigating Averaging Effects via Residual Noise Learning
IWR, Heidelberg University（海德堡大学IWR）；Silicon Austria Labs（Silicon Austria实验室）；College of Medicine and Biological Information Engineering, Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University（医学与生物信息工程学院，医学图像智能计算教育部重点实验室，东北大学）；Department of Epidemiology & Global Health, Umeå University（流行病学与全球健康系，乌梅大学）
Natural images are often affected by random noise and image denoising has long been a central topic in Computer Vision. Many algorithms have been introduced to remove the noise from the natural images, such as Gaussian, Wiener filtering and wavelet thresholding. However, many of these algorithms remove the fine edges and make them blur. Recently, many promising denoising algorithms have been introduced such as Non-local Means, Fields of Experts, and BM3D. In this paper, we explore Bayesian method of ensemble learning for image denoising. Ensemble methods seek to combine multiple different algo…
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a pr…
Heterogeneous window transformer for image denoising
Northwestern Polytechnical University（西北工业大学）；National Tsing Hua University（国立清华大学）；Xidian University（西安电子科技大学）；Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Image denoising is still a challenging issue in many computer vision sub-domains. Recent studies show that significant improvements are made possible in a supervised setting. However, few challenges, such as spatial fidelity and cartoon-like smoothing remain unresolved or decisively overlooked. Our study proposes a simple yet efficient architecture for the denoising problem that addresses the aforementioned issues. The proposed architecture revisits the concept of modular concatenation instead of long and deeper cascaded connections, to recover a cleaner approximation of the given image. We fi…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
The development of neural networks has greatly improved the performance in various computer vision tasks. In the filed of image denoising, convolutional neural network based methods such as DnCNN break through the limits of classical methods, achieving better quantitative results. However, the epistemic uncertainty existing in neural networks limits further improvements in their performance over denoising tasks. Therefore, we develop and study different solutions to minimize uncertainty and further improve the removal of noise. From the perspective of ensemble learning, we implement manipulati…
Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
Hefei University of Technology（合肥工业大学）；Hangzhou Dianzi University（杭州电子科技大学）；Jinan University（暨南大学）；South China Agricultural University（华南农业大学）；The University of Tokyo（东京大学）
Harbin Institute of Technology（哈尔滨工业大学）；Megvii Inc（旷视科技有限公司）
Recently, deep learning-based image denoising methods have achieved promising performance on test data with the same distribution as training set, where various denoising models based on synthetic or collected real-world training data have been learned. However, when handling real-world noisy images, the denoising performance is still limited. In this paper, we propose a simple yet effective Bayesian deep ensemble (BDE) method for real-world image denoising, where several representative deep denoisers pre-trained with various training data settings can be fused to improve robustness. The found…
Tampere Universities（坦佩雷大学）；Qatar University（卡塔尔大学）
Convolutional Neural Networks (CNNs) have recently become a favored technique for image denoising due to its adaptive learning ability, especially with a deep configuration. However, their efficacy is inherently limited owing to their homogenous network formation with the unique use of linear convolution. In this study, we propose a heterogeneous network model which allows greater flexibility for embedding additional non-linearity at the core of the data transformation. To this end, we propose the idea of an operational neuron or Operational Neural Networks (ONN), which enables a flexible non-…
From medical research to gaming applications, gaze estimation is becoming a valuable tool. While there exists a number of hardware-based solutions, recent deep learning-based approaches, coupled with the availability of large-scale databases, have allowed to provide a precise gaze estimate using only consumer sensors. However, there remains a number of questions, regarding the problem formulation, architectural choices and learning paradigms for designing gaze estimation systems in order to bridge the gap between geometry-based systems involving specific hardware and approaches using consumer …
School of Computer and Communication Sciences, EPFL（洛桑联邦理工学院计算机与通信科学学院）
Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. 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. The denoising solutions suffer from epistemic uncertainty that can limit further advancements. This uncertainty is traditionally mitigated through different ensemble approaches. However, such ensembles are prohibitively costly with deep networks, which ar…
With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections. While these models perform well on benchmark dataset where low-resolution (LR) images are constructed from high-resolution (HR) references with known blur kernel, real image SR is more challenging when both images in the LR-HR pair are collected from real cameras. Based on existing dense residual networks, a Gaussian process based neural architecture search (GP-NAS) scheme is utilized to fi…
The Chinese University of Hong Kong（香港中文大学）；East China Normal University（华东师范大学）；Nanjing University of Posts and Telecommunications（南京邮电大学）
Single image denoising (SID) has achieved significant breakthroughs with the development of deep learning. However, the proposed methods are often accompanied by plenty of parameters, which greatly limits their application scenarios. Different from previous works that blindly increase the depth of the network, we explore the degradation mechanism of the noisy image and propose a lightweight Multiple Degradation and Reconstruction Network (MDRN) to progressively remove noise. Meanwhile, we propose two novel Heterogeneous Knowledge Distillation Strategies (HMDS) to enable MDRN to learn richer an…
Fast and flexible processing are two essential requirements for a number of practical applications of image denoising. Current state-of-the-art methods, however, still require either high computational cost or limited scopes of the target. We introduce an efficient ensemble network trained via a competition of expert networks, as an application for image blind denoising. We realize automatic division of unlabeled noisy datasets into clusters respectively optimized to enhance denoising performance. The architecture is scalable, can be extended to deal with diverse noise sources/levels without i…
One of the ways to improve the performance of a target task is to learn the transfer of abundant knowledge of a pre-trained network. However, learning of the pre-trained network requires high computation capability and large-scale labeled dataset. To mitigate the burden of large-scale labeling, learning in un/self-supervised manner can be a solution. In addition, using unsupervised multi-task learning, a generalized feature representation can be learned. However, unsupervised multi-task learning can be biased to a specific task. To overcome this problem, we propose the metric-based regularizat…
Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
Hanoi University of Science and Technology（河内科技大学）；University of Information Technology, VNU-HCM（胡志明市国家大学信息技术大学）；Vietnam National University, Ho Chi Minh City（胡志明市国家大学）；VinUniversity；Vietnamese-German University（越南德国大学）
A deep dictionary network-based foundation model for ultra-low-dose CT denoising
Yanshan University（燕山大学）；Capital Medical University（首都医科大学）；Beijing Friendship Hospital（北京友谊医院）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Research（谷歌研究院）
Most image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to address this issue by using per-pixel convolution kernels, but this greatly increases computational cost. In this work, we present Malleable Convolution (MalleConv), which performs spatial-varying processing with minimal computational overhead. MalleConv uses a smaller set of spatially-varying convolution kernels, a compromise between static and per-pixel convo…
Graz University of Technology（格拉茨技术大学）；Infineon Technologies Austria AG（英飞凌科技奥地利股份公司）
Driver assistance systems as well as autonomous cars have to rely on sensors to perceive their environment. A heterogeneous set of sensors is used to perform this task robustly. Among them, radar sensors are indispensable because of their range resolution and the possibility to directly measure velocity. Since more and more radar sensors are deployed on the streets, mutual interference must be dealt with. In the so far unregulated automotive radar frequency band, a sensor must be capable of detecting, or even mitigating the harmful effects of interference, which include a decreased detection s…
