Reinforcement Learning (RL) is a popular machine learning paradigm where intelligent agents interact with the environment to fulfill a long-term goal. Driven by the resurgence of deep learning, Deep RL (DRL) has witnessed great success over a wide spectrum of complex control tasks. Despite the encouraging results achieved, the deep neural network-based backbone is widely deemed as a black box that impedes practitioners to trust and employ trained agents in realistic scenarios where high security and reliability are essential. To alleviate this issue, a large volume of literature devoted to shedding light on the inner workings of the intelligent agents has been proposed, by constructing intrinsic interpretability or post-hoc explainability. In this survey, we provide a comprehensive review of existing works on eXplainable RL (XRL) and introduce a new taxonomy where prior works are clearly categorized into model-explaining, reward-explaining, state-explaining, and task-explaining methods. We also review and highlight RL methods that conversely leverage human knowledge to promote learning efficiency and performance of agents while this kind of method is often ignored in XRL field. Some challenges and opportunities in XRL are discussed. This survey intends to provide a high-level summarization of XRL and to motivate future research on more effective XRL solutions. Corresponding open source codes are collected and categorized at https://github.com/Plankson/awesome-explainable-reinforcement-learning.

Human parsing aims to partition humans in image or video into multiple pixel-level semantic parts. In the last decade, it has gained significantly increased interest in the computer vision community and has been utilized in a broad range of practical applications, from security monitoring, to social media, to visual special effects, just to name a few. Although deep learning-based human parsing solutions have made remarkable achievements, many important concepts, existing challenges, and potential research directions are still confusing. In this survey, we comprehensively review three core sub-tasks: single human parsing, multiple human parsing, and video human parsing, by introducing their respective task settings, background concepts, relevant problems and applications, representative literature, and datasets. We also present quantitative performance comparisons of the reviewed methods on benchmark datasets. Additionally, to promote sustainable development of the community, we put forward a transformer-based human parsing framework, providing a high-performance baseline for follow-up research through universal, concise, and extensible solutions. Finally, we point out a set of under-investigated open issues in this field and suggest new directions for future study. We also provide a regularly updated project page, to continuously track recent developments in this fast-advancing field: https://github.com/soeaver/awesome-human-parsing.

Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality ground-truth data hinders their applications due to the generalization problem. Recently, Implicit Neural Representation (INR) has appeared as a powerful DL-based tool for solving the inverse problem by characterizing the attributes of a signal as a continuous function of corresponding coordinates in an unsupervised manner. In this work, we proposed an INR-based method to improve dynamic MRI reconstruction from highly undersampled k-space data, which only takes spatiotemporal coordinates as inputs. Specifically, the proposed INR represents the dynamic MRI images as an implicit function and encodes them into neural networks. The weights of the network are learned from sparsely-acquired (k, t)-space data itself only, without external training datasets or prior images. Benefiting from the strong implicit continuity regularization of INR together with explicit regularization for low-rankness and sparsity, our proposed method outperforms the compared scan-specific methods at various acceleration factors. E.g., experiments on retrospective cardiac cine datasets show an improvement of 5.5 ~ 7.1 dB in PSNR for extremely high accelerations (up to 41.6-fold). The high-quality and inner continuity of the images provided by INR has great potential to further improve the spatiotemporal resolution of dynamic MRI, without the need of any training data.

The counting task, which plays a fundamental rule in numerous applications (e.g., crowd counting, traffic statistics), aims to predict the number of objects with various densities. Existing object counting tasks are designed for a single object class. However, it is inevitable to encounter newly coming data with new classes in our real world. We name this scenario as \textit{evolving object counting}. In this paper, we build the first evolving object counting dataset and propose a unified object counting network as the first attempt to address this task. The proposed model consists of two key components: a class-agnostic mask module and a class-increment module. The class-agnostic mask module learns generic object occupation prior via predicting a class-agnostic binary mask (e.g., 1 denotes there exists an object at the considering position in an image and 0 otherwise). The class-increment module is used to handle new coming classes and provides discriminative class guidance for density map prediction. The combined outputs of class-agnostic mask module and image feature extractor are used to predict the final density map. When new classes come, we first add new neural nodes into the last regression and classification layers of this module. Then, instead of retraining the model from scratch, we utilize knowledge distilling to help the model remember what have already learned about previous object classes. We also employ a support sample bank to store a small number of typical training samples of each class, which are used to prevent the model from forgetting key information of old data. With this design, our model can efficiently and effectively adapt to new coming classes while keeping good performance on already seen data without large-scale retraining. Extensive experiments on the collected dataset demonstrate the favorable performance.

In this paper, we consider an intelligent reflecting surface (IRS)-aided cell-free massive multiple-input multiple-output system, where the beamforming at access points and the phase shifts at IRSs are jointly optimized to maximize energy efficiency (EE). To solve EE maximization problem, we propose an iterative optimization algorithm by using quadratic transform and Lagrangian dual transform to find the optimum beamforming and phase shifts. However, the proposed algorithm suffers from high computational complexity, which hinders its application in some practical scenarios. Responding to this, we further propose a deep learning based approach for joint beamforming and phase shifts design. Specifically, a two-stage deep neural network is trained offline using the unsupervised learning manner, which is then deployed online for the predictions of beamforming and phase shifts. Simulation results show that compared with the iterative optimization algorithm and the genetic algorithm, the unsupervised learning based approach has higher EE performance and lower running time.

With the ever-growing model size and the limited availability of labeled training data, transfer learning has become an increasingly popular approach in many science and engineering domains. For classification problems, this work delves into the mystery of transfer learning through an intriguing phenomenon termed neural collapse (NC), where the last-layer features and classifiers of learned deep networks satisfy: (i) the within-class variability of the features collapses to zero, and (ii) the between-class feature means are maximally and equally separated. Through the lens of NC, our findings for transfer learning are the following: (i) when pre-training models, preventing intra-class variability collapse (to a certain extent) better preserves the intrinsic structures of the input data, so that it leads to better model transferability; (ii) when fine-tuning models on downstream tasks, obtaining features with more NC on downstream data results in better test accuracy on the given task. The above results not only demystify many widely used heuristics in model pre-training (e.g., data augmentation, projection head, self-supervised learning), but also leads to more efficient and principled fine-tuning method on downstream tasks that we demonstrate through extensive experimental results.

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a limited understanding of the performance trade-offs of different decisions made during the instruction-tuning process. These decisions include the scale and diversity of the instruction-tuning benchmark, different task sampling strategies, fine-tuning with and without demonstrations, training using specialized datasets for reasoning and dialogue, and finally, the fine-tuning objectives themselves. In this paper, we characterize the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. To this end, we create OPT-IML Bench: a large benchmark for Instruction Meta-Learning (IML) of 2000 NLP tasks consolidated into task categories from 8 existing benchmarks, and prepare an evaluation framework to measure three types of model generalizations: to tasks from fully held-out categories, to held-out tasks from seen categories, and to held-out instances from seen tasks. Through the lens of this framework, we first present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT. OPT-IML demonstrates all three generalization abilities at both scales on four different evaluation benchmarks with diverse tasks and input formats -- PromptSource, FLAN, Super-NaturalInstructions, and UnifiedSKG. Not only does it significantly outperform OPT on all benchmarks but is also highly competitive with existing models fine-tuned on each specific benchmark. We release OPT-IML at both scales, together with the OPT-IML Bench evaluation framework.

Time series anomaly detection strives to uncover potential abnormal behaviors and patterns from temporal data, and has fundamental significance in diverse application scenarios. Constructing an effective detection model usually requires adequate training data stored in a centralized manner, however, this requirement sometimes could not be satisfied in realistic scenarios. As a prevailing approach to address the above problem, federated learning has demonstrated its power to cooperate with the distributed data available while protecting the privacy of data providers. However, it is still unclear that how existing time series anomaly detection algorithms perform with decentralized data storage and privacy protection through federated learning. To study this, we conduct a federated time series anomaly detection benchmark, named FedTADBench, which involves five representative time series anomaly detection algorithms and four popular federated learning methods. We would like to answer the following questions: (1)How is the performance of time series anomaly detection algorithms when meeting federated learning? (2) Which federated learning method is the most appropriate one for time series anomaly detection? (3) How do federated time series anomaly detection approaches perform on different partitions of data in clients? Numbers of results as well as corresponding analysis are provided from extensive experiments with various settings. The source code of our benchmark is publicly available at https://github.com/fanxingliu2020/FedTADBench.

In recent years, vision-centric perception has flourished in various autonomous driving tasks, including 3D detection, semantic map construction, motion forecasting, and depth estimation. Nevertheless, the latency of vision-centric approaches is too high for practical deployment (e.g., most camera-based 3D detectors have a runtime greater than 300ms). To bridge the gap between ideal research and real-world applications, it is necessary to quantify the trade-off between performance and efficiency. Traditionally, autonomous-driving perception benchmarks perform the offline evaluation, neglecting the inference time delay. To mitigate the problem, we propose the Autonomous-driving StreAming Perception (ASAP) benchmark, which is the first benchmark to evaluate the online performance of vision-centric perception in autonomous driving. On the basis of the 2Hz annotated nuScenes dataset, we first propose an annotation-extending pipeline to generate high-frame-rate labels for the 12Hz raw images. Referring to the practical deployment, the Streaming Perception Under constRained-computation (SPUR) evaluation protocol is further constructed, where the 12Hz inputs are utilized for streaming evaluation under the constraints of different computational resources. In the ASAP benchmark, comprehensive experiment results reveal that the model rank alters under different constraints, suggesting that the model latency and computation budget should be considered as design choices to optimize the practical deployment. To facilitate further research, we establish baselines for camera-based streaming 3D detection, which consistently enhance the streaming performance across various hardware. ASAP project page: https://github.com/JeffWang987/ASAP.

Medical image segmentation methods typically rely on numerous dense annotated images for model training, which are notoriously expensive and time-consuming to collect. To alleviate this burden, weakly supervised techniques have been exploited to train segmentation models with less expensive annotations. In this paper, we propose a novel point-supervised contrastive variance method (PSCV) for medical image semantic segmentation, which only requires one pixel-point from each organ category to be annotated. The proposed method trains the base segmentation network by using a novel contrastive variance (CV) loss to exploit the unlabeled pixels and a partial cross-entropy loss on the labeled pixels. The CV loss function is designed to exploit the statistical spatial distribution properties of organs in medical images and their variance distribution map representations to enforce discriminative predictions over the unlabeled pixels. Experimental results on two standard medical image datasets demonstrate that the proposed method outperforms the state-of-the-art weakly supervised methods on point-supervised medical image semantic segmentation tasks.