Offline reinforcement learning (RL), which operates solely on static datasets without further interactions with the environment, provides an appealing alternative to learning a safe and promising control policy. The prevailing methods typically learn a conservative policy to mitigate the problem of Q-value overestimation, but it is prone to overdo it, leading to an overly conservative policy. Moreover, they optimize all samples equally with fixed constraints, lacking the nuanced ability to control conservative levels in a fine-grained manner. Consequently, this limitation results in a performance decline. To address the above two challenges in a united way, we propose a framework, adaptive conservative level in Q-learning (ACL-QL), which limits the Q-values in a mild range and enables adaptive control on the conservative level over each state-action pair, i.e., lifting the Q-values more for good transitions and less for bad transitions. We theoretically analyze the conditions under which the conservative level of the learned Q-function can be limited in a mild range and how to optimize each transition adaptively. Motivated by the theoretical analysis, we propose a novel algorithm, ACL-QL, which uses two learnable adaptive weight functions to control the conservative level over each transition. Subsequently, we design a monotonicity loss and surrogate losses to train the adaptive weight functions, Q-function, and policy network alternatively. We evaluate ACL-QL on the commonly used datasets for deep data-driven reinforcement learning (D4RL) benchmark and conduct extensive ablation studies to illustrate the effectiveness and state-of-the-art performance compared with existing offline DRL baselines.

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring the poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity, the main challenge remains and comes from two fundamental issues: pose ambiguity and appearance inconsistency. To alleviate the current limitations and improve the quality of the synthesized images, we propose a pose transfer network with augmented D isentangled F eature C onsistency (DFC-Net) to facilitate human pose transfer. Given a pair of images containing the source and target person, DFC-Net extracts pose and static information from the source and target respectively, then synthesizes an image of the target person with the desired pose from the source. Moreover, DFC-Net leverages disentangled feature consistency losses in the adversarial training to strengthen the transfer coherence and integrates a keypoint amplifier to enhance the pose feature extraction. With the help of the disentangled feature consistency losses, we further propose a novel data augmentation scheme that introduces unpaired support data with the augmented consistency constraints to improve the generality and robustness of DFC-Net. Extensive experimental results on Mixamo-Pose and EDN-10k have demonstrated DFC-Net achieves state-of-the-art performance on pose transfer.

With the emergence of more and more powerful chipsets and hardware and the rise of Artificial Intelligence of Things (AIoT), there is a growing trend for bringing Deep Neural Network (DNN) models to empower mobile and edge devices with intelligence such that they can support attractive AI applications in a real-time manner. To leverage heterogeneous computational resources (such as CPU, GPU, DSP, etc.) to effectively and efficiently support the concurrent inference of multiple DNN models on a mobile or edge device, we propose a novel online Co-Scheduling framework based on deep REinforcement Learning, called COSREL. COSREL has the following desirable features: 1) it achieves significant speedup over commonly-used methods by efficiently utilizing all the computational resources on heterogeneous hardware; 2) it leverages emerging Deep Reinforcement Learning (DRL) to make dynamic and wise online scheduling decisions based on system runtime state; 3) it is capable of making a good tradeoff among inference latency, throughput, and energy efficiency; and 4) it makes no changes to given DNN models, thus preserves their accuracies. To evaluate COSREL, we conduct extensive experiments on an off-the-shelf Android smartphone. The experimental results show that COSREL consistently outperforms other baselines in terms of throughput, latency, and energy efficiency.

Soil temperature and moisture play a significant influence on vegetation and climate. Measurements of soil temperature and moisture can now be obtained through soil temperature and moisture sensors, but the measurements can only be done for a specified period of time in the past. Predicting soil temperature and moisture for the future is of significant importance because it can provide guidance on making plant plans. With deep learning algorithms, the characteristics of soil temperature and moisture in a certain upcoming period can be predicted from data measured in the past. In this letter, we develop a sequence-to-sequence learning model for multistep ahead prediction, which features a long short-term memory (LSTM)-based encoder–decoder structure for modeling long-term temporal correlations as well as an autoencoder for modeling spatial correlations (i.e., considering data from neighboring locations). For performance evaluation, we use real data collected by the temperature and moisture sensors on soils at the Heihe River Basin in the west of China. Our experimental results show that: 1) the proposed model significantly outperforms two widely used time series analysis algorithms, autoregressive integrated moving average (ARIMA) and support vector regression (SVR), and 2) the proposed spatial encoder–decoder LSTM modeling method is indeed effective in that the root-mean-squared error (RMSE) and mean absolute error (MAE) are only 0.22 °C and 0.17 °C for 24-h (144 steps ahead) prediction of soil temperature and the values are only 0.28% and 0.23% for soil moisture.

Cloud radio access networks (CRANs) have become a key enabling technique for the next generation wireless communications. Resource allocation in CRANs still needs to be further improved to reach the objective of minimizing power consumption and meeting demands of wireless users over a long period. Inspired by the success of Deep Reinforcement Learning (DRL) on solving complicated control problems, we present a novel framework,ReCARL, for power-efficient resource allocation in CRANs with deep reinforcement learning. Specifically, we define the state space, action space and reward function for the DRL agent, apply a deep neural network (DNN) to approximating the action-value function, and formally formulate the resource allocation problem (in each decision epoch) as a convex optimization problem. Under ReCARL, we propose two different DRL agents: one has a regular DNN structure trained with the basic deep Q-learning method (ReCARL-Basic); while the other has a context-aware DNN structure trained with a hybrid deep Q-learning method (ReCARL-Hybrid). We evaluated the performance of ReCARL along with the two DRL agents by comparing them with two widely-used baselines via extensive simulation. The simulation results show that ReCARL achieves significant power savings while meeting user demands, and it can well handle highly dynamic cases.

Fine-grained instance segmentation is considerably more complicated and challenging than semantic segmentation. Most existing instance segmentation methods only focus on accuracy without paying much attention to inference latency, which, is critical to real-time applications, such as autonomous driving. In this paper, we aim to bridge the gap between semantic segmentation and instance segmentation by presenting a novel real-time model for instance segmentation, Sem2Ins, which effectively generates instance boundaries according to a semantic segmentation by leveraging conditional generative adversarial networks (cGANs) coupled with deep supervision and a weighted fusion layer. Specifically, supervision is imposed on each output layer, and features from different levels are fused to produce a well-generated boundary map. Sem2Ins has the following desirable features: 1) Combined with some fast semantic segmentation methods, Sem2Ins runs at a real-time speed that is fairly well-balanced against accuracy; 2) Sem2Ins works flexibly with any semantic segmentation model for instance segmentation, and if the given semantic segmentation is sufficiently good, Sem2Ins even achieves state-of-the-art in terms of accuracy; 3) deep supervision and weighted fusion can be leveraged to generate high-quality boundaries; and 4) Sem2Ins can be easily extended to panoptic segmentation. Extensive experiments performed on the Cityscapes, WildDash, KITTI and COCO benchmarks have demonstrated that 1) Sem2Ins, when combined with PSPNet and DDRNet-23-Slim, consistently outperforms the state-of-the-art real-time solution (Box2Pix) in terms of both speed and accuracy; and 2) Sem2Ins combined with DPC performs comparably to some powerful detect-and-segment approaches.

Deep learning has made tremendous success in computer vision, natural language processing and even visual-semantic learning, which requires a huge amount of labeled training data. Nevertheless, the goal of human-level intelligence is to enable a model to quickly obtain an in-depth understanding given a small number of samples, especially with heterogeneity in the multi-modal scenarios such as visual question answering and image captioning. In this paper, we study the few-shot visual-semantic learning and present the Hierarchical Graph ATtention network (HGAT). This two-stage network models the intra- and inter-modal relationships with limited image-text samples. The main contributions of HGAT can be summarized as follows: 1) it sheds light on tackling few-shot multi-modal learning problems, which focuses primarily, but not exclusively on visual and semantic modalities, through better exploitation of the intra-relationship of each modality and an attention-based co-learning framework between modalities using a hierarchical graph-based architecture; 2) it achieves superior performance on both visual question answering and image captioning in the few-shot setting; 3) it can be easily extended to the semi-supervised setting where image-text samples are partially unlabeled. We show via extensive experiments that HGAT delivers state-of-the-art performance on three widely-used benchmarks of two visual-semantic learning tasks.

Video question answering (VideoQA) is a very important but challenging multimedia task, which automatically analyzes questions and videos and generates accurate answers. However, research on VideoQA is still in its infancy. In this article, we propose a novel memory augmented deep recurrent neural network (MA-DRNN) model for VideoQA, which features a new method for encoding videos and questions, and memory augmentation using the emerging differentiable neural computer (DNC). Specifically, we encode textual (questions) information before visual (videos) information, which leads to better visual-textual representations. Moreover, we leverage DNC (with an external memory) for storing and retrieving useful information in questions and videos, and modeling the long-term visual-textual dependence. To evaluate the proposed model, we conducted extensive experiments using the VTW data set and MSVD-QA data set, which are both Widely used large-scale video data sets for language-level understanding. The experimental results have well validated the proposed model and showed that it outperforms the state-of-the-art in terms of various accuracy-related metrics.

In this paper, we present design, implementation and evaluation of a novel predictive control framework to enable reliable distributed stream data processing, which features a Deep Recurrent Neural Network (DRNN) model for performance prediction, and dynamic grouping for flexible control. Specifically, we present a novel DRNN model, which makes accurate performance prediction with careful consideration for interference of co-located worker processes, according to multilevel runtime statistics. Moreover, we design a new grouping method, dynamic grouping, which can distribute/re-distribute data tuples to downstream tasks according to any given split ratio on the fly. So it can be used to re-direct data tuples to bypass misbehaving workers. We implemented the proposed framework based on a widely used Distributed Stream Data Processing System (DSDPS), Storm. For validation and performance evaluation, we developed two representative stream data processing applications: Windowed URL Count and Continuous Queries. Extensive experimental results show: 1) The proposed DRNN model outperforms widely used baseline solutions, ARIMA and SVR, in terms of prediction accuracy; 2) dynamic grouping works as expected; and 3) the proposed framework enhances reliability by offering minor performance degradation with misbehaving workers.

In this paper, we aim to study networking problems from a whole new perspective by leveraging emerging deep learning, to develop an experience-driven approach, which enables a network or a protocol to learn the best way to control itself from its own experience (e.g., runtime statistics data), just as a human learns a skill. We present design, implementation and evaluation of a deep reinforcement learning (DRL)-based control framework, DRL-CC (DRL for Congestion Control), which realizes our experience-driven design philosophy on multi-path TCP (MPTCP) congestion control. DRL-CC utilizes a single (instead of multiple independent) agent to dynamically and jointly perform congestion control for all active MPTCP flows on an end host with the objective of maximizing the overall utility. The novelty of our design is to utilize a flexible recurrent neural network, LSTM, under a DRL framework for learning a representation for all active flows and dealing with their dynamics. Moreover, we, for the first time, integrate the above LSTM-based representation network into an actor-critic framework for continuous (congestion) control, which leverages the emerging deterministic policy gradient to train critic, actor, and LSTM networks in an end-to-end manner. We implemented DRL-CC based on the MPTCP implementation in the Linux kernel. The experimental results show that 1) DRL-CC consistently and significantly outperforms a few well-known MPTCP congestion control algorithms in terms of goodput without sacrificing fairness, 2) it is flexible and robust to highly-dynamic network environments with time-varying flows, and 3) it is friendly to regular TCP.