Macro placement is a crucial subproblem of chip design, focusing on determining the locations of numerous macros while minimizing multiple metrics. In recent years, reinforcement learning (RL) has gained traction as a favorable technique to improve placement performance. However, existing RL-based placers ignore the orientation of macros, resulting in the state space constrained to two-dimensional discrete coordinates and greatly restricting the exploration opportunities. To address this issue, we propose a novel macro placement method, RSPlace, which guides the bidirectional expansion of the global search tree to offer the RL agent more exploration opportunities, incorporating rotation into the RL-based macro placement solution for the first time. RSPlace intelligently determines the optimal rotation angle to maximize placement benefits by leveraging rotation sensing and placement perturbations. Extensive experiments demonstrate that taking the macro orientation into account substantially broadens the feasible locations and effectively reduces the half-perimeter wirelength (HPWL), thus ensuring that our approach significantly improves the optimization effect compared to the state-of-the-art method.

Active learning (AL) is an effective method to balance annotation costs and model performance under resource-constrained circumstances. Most existing AL studies are typically designed for class-balanced datasets. However, the ubiquity of long-tailed distributions in real-world scenarios largely restricts the applicability of those AL methods. To tackle this problem, we propose a new active learning framework, namely long-tailed active learning (LTAL). The LTAL framework divides the long-tailed dataset into constantly evolving in-distribution (ID) and out-of-distribution (OOD) samples, and views the tail samples as OOD samples distinct from the head ones, thus intuitively converting the LTA problem into an iterative OOD detection task. We leverage an energy-based OOD detection approach with a well-designed class-imbalanced energy regularization loss to further extend the energy gap between head and tail classes, encouraging the model to select more unlabeled tail samples with higher free energy values. Experimental results show that despite its conceptual simplicity, the proposed method significantly outperforms competitive baselines.

Active learning (AL) aims to find a better trade-off between labeling costs and model performance by consciously selecting more informative samples to label. Recently, adversarial approaches have emerged as effective solutions. Most of them leverage generative adversarial networks to align feature distributions of labeled and unlabeled data, upon which discriminators are trained to better distinguish between them. However, these methods fail to consider the relationship between unlabeled samples and decision boundaries, and their training processes are often complex and unstable. To this end, this paper proposes a novel adversarial AL method, namely multi-classifier adversarial optimization for active learning (MAOAL). MAOAL employs task-specific decision boundaries for data alignment while selecting the most informative samples to label. To fulfill this, we introduce a novel classifier class confusion (C3) metric, which represents the classifier discrepancy as the inter-class correlation of classifier outputs. Without any additional hyper-parameters, the C3 metric further reduces the negative impacts of ambiguous samples in the process of distribution alignment and sample selection. More concretely, the network is trained adversarially by adding two auxiliary classifiers, reducing the distribution bias of labeled and unlabeled samples by minimizing the C3 loss between classifiers, while learning tighter decision boundaries and highlighting hard samples by maximizing the C3 loss. Finally, the unlabeled samples with the highest C3 loss are selected to label. Extensive experiments demonstrate the superiority of our approach over state-of-the-art AL methods in terms of image classification and object detection.

Scene text recognition (STR) has been actively studied in recent years, with a wide range of applications in autonomous driving, image retrieval and much more. However, when a pre-trained deep STR model learns a new task, its performance on previous tasks may drop dramatically, due to catastrophic forgetting in deep neural networks. A potential solution to combat the forgetting of prior knowledge is incremental learning (IL), which has shown its effectiveness and significant progress in image classification. Yet, exploiting IL in the context of STR has been barely visited, probably because the forgetting problem is even worse in STR. To address this issue, we propose the lifelong scene text recognizer (LSTR) that learns STR tasks incrementally while alleviating forgetting. Specifically, LSTR assigns each task a set of task-specific expert modules at different stages of an STR model, while other parameters are shared among tasks. These shared parameters are only learned in the first task and remain unchanged during subsequent learning to ensure that no learned knowledge is overlooked. Moreover, in real applications, there is no prior knowledge about which task an input image belongs to, making it impossible to precisely select the corresponding expert modules. To this end, we propose the incremental task prediction network (ITPN) to identify the most related task category by pulling the features of the same task closer and pushing those of different tasks farther apart. To validate the proposed method in our newly-introduced IL setting, we collected a large-scale dataset consisting of both real and synthetic multilingual STR data. Extensive experiments on this dataset clearly show the superiority of our LSTR over state-of-the-art IL methods.

Network Function Virtualization (NFV) technology decoupled Network functions from hardware resources to create more flexible Network services and support more flexible Network resource allocation. By matching and linking different virtual network functions (VNF) to form the Service Function Chain (SFC), NFV technology can provide users with end-to-end network services in a more flexible and rapid manner, and support the expansion and development of new services. In order to maintain the stability of network performance during the dynamic change of network demand, scaling is a basic task in SFC deployment. The key of the NFC scaling is the high accuracy of the time and scale quantity, which can avoid unnecessary resource provisioning and releasing process while maintaining network performance. In this paper, we propose a scaling mechanism based on Reinforcement Learning, which can make better decisions for managing network performance changes in dynamic workloads. Resource utilization is also introduced into the mechanism to avoid the idle waste of network resources. The simulation implements the scaling mechanism in a virtualized EPC network and the result proves that the proposed scaling mechanism has high accuracy in managing network performance and advantages in efficient utilization of network resources.