Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost. To solve this problem, existing approaches either compress well-trained large-scale models or learn lightweight models with carefully designed network structures. In this work, we make a close study of the convolution operator, which is the basic unit used in CNNs, to reduce its computing load. In particular, we propose a compact convolution module, called CompConv, to facilitate efficient feature learning. With the divide-and-conquer strategy, CompConv is able to save a great many computations as well as parameters to produce a certain dimensional feature map. Furthermore, CompConv discreetly integrates the input features into the outputs to efficiently inherit the input information. More importantly, the novel CompConv is a plug-and-play module that can be directly applied to modern CNN structures to replace the vanilla convolution layers without further effort. Extensive experimental results suggest that CompConv can adequately compress the benchmark CNN structures yet barely sacrifice the performance, surpassing other competitors.
In China, stroke is the first leading cause of death in recent years. It is a major cause of long-term physical and cognitive impairment, which bring great pressure on the National Public Health System. Evaluation of the risk of getting stroke is important for the prevention and treatment of stroke in China. A data set with 2000 hospitalized stroke patients in 2018 and 27583 residents during the year 2017 to 2020 is analyzed in this study. Due to data incompleteness, inconsistency, and non-structured formats, missing values in the raw data are filled with -1 as an abnormal class. With the cleaned features, three models on risk levels of getting stroke are built by using machine learning methods. The importance of "8+2" factors from China National Stroke Prevention Project (CSPP) is evaluated via decision tree and random forest models. Except for "8+2" factors the importance of features and SHAP1 values for lifestyle information, demographic information, and medical measurement are evaluated and ranked via a random forest model. Furthermore, a logistic regression model is applied to evaluate the probability of getting stroke for different risk levels. Based on the census data in both communities and hospitals from Shanxi Province, we investigate different risk factors of getting stroke and their ranking with interpretable machine learning models. The results show that Hypertension (Systolic blood pressure, Diastolic blood pressure), Physical Inactivity (Lack of sports), and Overweight (BMI) are ranked as the top three high-risk factors of getting stroke in Shanxi province. The probability of getting stroke for a person can also be predicted via our machine learning model.
This paper presents a framework for Convolutional Neural Network (CNN)-based quality enhancement task, by taking advantage of coding information in the compressed video signal. The motivation is that normative decisions made by the encoder can significantly impact the type and strength of artifacts in the decoded images. In this paper, the main focus has been put on decisions defining the prediction signal in intra and inter frames. This information has been used in the training phase as well as input to help the process of learning artifacts that are specific to each coding type. Furthermore, to retain a low memory requirement for the proposed method, one model is used for all Quantization Parameters (QPs) with a QP-map, which is also shared between luma and chroma components. In addition to the Post Processing (PP) approach, the In-Loop Filtering (ILF) codec integration has also been considered, where the characteristics of the Group of Pictures (GoP) are taken into account to boost the performance. The proposed CNN-based Quality Enhancement(QE) framework has been implemented on top of the VVC Test Model (VTM-10). Experiments show that the prediction-aware aspect of the proposed method improves the coding efficiency gain of the default CNN-based QE method by 1.52%, in terms of BD-BR, at the same network complexity compared to the default CNN-based QE filter.
Differentiable Architecture Search (DARTS) is a recently proposed neural architecture search (NAS) method based on a differentiable relaxation. Due to its success, numerous variants analyzing and improving parts of the DARTS framework have recently been proposed. By considering the problem as a constrained bilevel optimization, we propose and analyze three improvements to architectural weight competition, update scheduling, and regularization towards discretization. First, we introduce a new approach to the activation of architecture weights, which prevents confounding competition within an edge and allows for fair comparison across edges to aid in discretization. Next, we propose a dynamic schedule based on per-minibatch network information to make architecture updates more informed. Finally, we consider two regularizations, based on proximity to discretization and the Alternating Directions Method of Multipliers (ADMM) algorithm, to promote early discretization. Our results show that this new activation scheme reduces final architecture size and the regularizations improve reliability in search results while maintaining comparable performance to state-of-the-art in NAS, especially when used with our new dynamic informed schedule.
Multiple object tracking faces several challenges that may be alleviated with trajectory information. Knowing the posterior locations of an object helps disambiguating and solving situations such as occlusions, re-identification, and identity switching. In this work, we show that trajectory estimation can become a key factor for tracking, and present TrajE, a trajectory estimator based on recurrent mixture density networks, as a generic module that can be added to existing object trackers. To provide several trajectory hypotheses, our method uses beam search. Also, relying on the same estimated trajectory, we propose to reconstruct a track after an occlusion occurs. We integrate TrajE into two state of the art tracking algorithms, CenterTrack [63] and Tracktor [3]. Their respective performances in the MOTChallenge 2017 test set are boosted 6.3 and 0.3 points in MOTA score, and 1.8 and 3.1 in IDF1, setting a new state of the art for the CenterTrack+TrajE configuration
Similarity matching is a core operation in Siamese trackers. Most Siamese trackers carry out similarity learning via cross correlation that originates from the image matching field. However, unlike 2-D image matching, the matching network in object tracking requires 4-D information (height, width, channel and time). Cross correlation neglects the information from channel and time dimensions, and thus produces ambiguous matching. This paper proposes a spatio-temporal matching process to thoroughly explore the capability of 4-D matching in space (height, width and channel) and time. In spatial matching, we introduce a space-variant channel-guided correlation (SVC-Corr) to recalibrate channel-wise feature responses for each spatial location, which can guide the generation of the target-aware matching features. In temporal matching, we investigate the time-domain context relations of the target and the background and develop an aberrance repressed module (ARM). By restricting the abrupt alteration in the interframe response maps, our ARM can clearly suppress aberrances and thus enables more robust and accurate object tracking. Furthermore, a novel anchor-free tracking framework is presented to accommodate these innovations. Experiments on challenging benchmarks including OTB100, VOT2018, VOT2020, GOT-10k, and LaSOT demonstrate the state-of-the-art performance of the proposed method.
The relationship between two entities in a sentence is often implied by word order and common sense, rather than an explicit predicate. For example, it is evident that "Fed chair Powell indicates rate hike" implies (Powell, is a, Fed chair) and (Powell, works for, Fed). These tuples are just as significant as the explicit-predicate tuple (Powell, indicates, rate hike), but have much lower recall under traditional Open Information Extraction (OpenIE) systems. Implicit tuples are our term for this type of extraction where the relation is not present in the input sentence. There is very little OpenIE training data available relative to other NLP tasks and none focused on implicit relations. We develop an open source, parse-based tool for converting large reading comprehension datasets to OpenIE datasets and release a dataset 35x larger than previously available by sentence count. A baseline neural model trained on this data outperforms previous methods on the implicit extraction task.
In this work, we describe our method for tackling the valence-arousal estimation challenge from ABAW FG-2020 Competition. The competition organizers provide an in-the-wild Aff-Wild2 dataset for participants to analyze affective behavior in real-life settings. We use MIMAMO Net \cite{deng2020mimamo} model to achieve information about micro-motion and macro-motion for improving video emotion recognition and achieve Concordance Correlation Coefficient (CCC) of 0.415 and 0.511 for valence and arousal on the reselected validation set.
The performance of a reinforcement learning (RL) system depends on the computational architecture used to approximate a value function. Deep learning methods provide both optimization techniques and architectures for approximating nonlinear functions from noisy, high-dimensional observations. However, prevailing optimization techniques are not designed for strictly-incremental online updates. Nor are standard architectures designed for observations with an a priori unknown structure: for example, light sensors randomly dispersed in space. This paper proposes an online RL prediction algorithm with an adaptive architecture that efficiently finds useful nonlinear features. The algorithm is evaluated in a spatial domain with high-dimensional, stochastic observations. The algorithm outperforms non-adaptive baseline architectures and approaches the performance of an architecture given side-channel information. These results are a step towards scalable RL algorithms for more general problems, where the observation structure is not available.
Recently, we have struck the balance between the information freshness, in terms of age of information (AoI), experienced by users and energy consumed by sensors, by appropriately activating sensors to update their current status in caching enabled Internet of Things (IoT) networks [1]. To solve this problem, we cast the corresponding status update procedure as a continuing Markov Decision Process (MDP) (i.e., without termination states), where the number of state-action pairs increases exponentially with respect to the number of considered sensors and users. Moreover, to circumvent the curse of dimensionality, we have established a methodology for designing deep reinforcement learning (DRL) algorithms to maximize (resp. minimize) the average reward (resp. cost), by integrating R-learning, a tabular reinforcement learning (RL) algorithm tailored for maximizing the long-term average reward, and traditional DRL algorithms, initially developed to optimize the discounted long-term cumulative reward rather than the average one. In this technical report, we would present detailed discussions on the technical contributions of this methodology.