This paper proposes a unified observer–identifier–learning framework (OILF) for predefined-time optimal tracking control with prescribed performance for robotic systems subject to unmeasurable states and uncertain dynamics. Most existing optimal control approaches rely on full-state information or accurate dynamic models, which are often unavailable in practice. To overcome this issue, a predefined-time dynamic regression extension and mixing (PTDREM) method is proposed to realize the co-design of state observer and parameter identifier, enabling synchronous predefined-time estimation of unknown states and dynamic parameters. Subsequently, to achieve optimal tracking control for robotic systems, a prescribed-performance-based critic–actor (PPCA) structure is developed via reinforcement learning (RL), in which all hierarchical tracking errors are driven into prescribed neighborhoods of the origin within a predefined time. In contrast to most existing works that solely ensure uniform ultimate boundedness (UUB) of the closed-loop system, the proposed scheme enables the upper bounds of the convergence time of the state observer, system identifier, and optimal controller to be preset through independent parameter design, thereby establishing global predefined-time stability (G-PTS) for the overall closed-loop system. Numerical simulations on a two-degree-of-freedom (DOF) robotic manipulator verify the effectiveness of the proposed OILF.

Adversarial attack severely degrades the performance of deep face recognition models with minimal image perturbations. Facial attacks can be broadly categorized into dodging and impersonation. Although existing approaches have made satisfactory progress by separately addressing each type of attack, the unification of them still remains unexplored and the potential benefit might be ignored. In this work, we aim to construct a unified facial attack framework that can simultaneously perform both attacks. We first design Unified Attack Modeling, which aligns optimization directions and spaces of two attacks to harmonize optimizing forces of dodging and impersonation. Based on the unified optimization goals, we introduce an Attacking by Decomposing scheme. The proposed scheme leverages the unified optimization goal by decomposing adversarial perturbation synthesis into two steps, orientation exploration and amplified forwarding. Extensive experiments on several facial datasets LFW, CelebA-HQ, and FFHQ show that our proposed unified framework achieves significant performance improvement on dodging and impersonation attacks, compared with the state-of-the-art methods.

Semantic correspondence (SC) aims to establish semantically meaningful matches across different instances of an object category. We illustrate how recent supervised SC methods remain limited in their ability to generalize beyond sparsely annotated training keypoints, effectively acting as keypoint detectors. To address this, we propose a novel approach for learning dense correspondences by lifting 2D keypoints into a canonical 3D space using monocular depth estimation. Our method constructs a continuous canonical manifold that captures object geometry without requiring explicit 3D supervision or camera annotations. Additionally, we introduce SPair-U, an extension of SPair-71k with novel keypoint annotations, to better assess generalization. Experiments not only demonstrate that our model significantly outperforms supervised baselines on unseen keypoints, highlighting its effectiveness in learning robust correspondences, but that unsupervised baselines outperform supervised counterparts when generalized across different datasets.

Detecting objects in low-light scenarios presents a persistent challenge, as detectors trained on well-lit data exhibit significant performance degradation on low-light data due to low visibility. Previous methods mitigate this issue by exploring image enhancement or object detection techniques with real low-light image datasets. However, the progress is impeded by the inherent difficulties about collecting and annotating low-light images. To address this challenge, we propose to boost low-light object detection with zero-shot day-night domain adaptation, which aims to generalize a detector from well-lit scenarios to low-light ones without requiring real low-light data. Re-visiting Retinex theory in the low-level vision, we first de-sign a reflectance representation learning module to learn Retinex-based illumination invariance in images with a carefully designed illumination invariance reinforcement strategy. Next, an interchange-redecomposition-coherence procedure is introduced to improve over the vanilla Retinex image decomposition process by performing two sequential image decompositions and introducing a redecomposition cohering loss. Extensive experiments on ExDark, DARK FACE, and CODaN datasets show strong low-light generalizability of our method. Our code is available at https://github.com/ZPDu/DAI-Net.

Domain shift across crowd data severely hinders crowd counting models to generalize to unseen scenarios. Although domain adaptive crowd counting approaches close this gap to a certain extent, they are still dependent on the target domain data to adapt (e.g. finetune) their models to the specific domain. In this paper, we instead target to train a model based on a single source domain which can generalize well on any unseen domain. This falls into the realm of domain generalization that remains unexplored in crowd counting. We first introduce a dynamic sub-domain division scheme which divides the source domain into multiple sub-domains such that we can initiate a meta-learning framework for domain generalization. The sub-domain division is dynamically refined during the meta-learning. Next, in order to disentangle domain-invariant information from domain-specific information in image features, we design the domain-invariant and -specific crowd memory modules to re-encode image features. Two types of losses, i.e. feature reconstruction and orthogonal losses, are devised to enable this disentanglement. Extensive experiments on several standard crowd counting benchmarks i.e. SHA, SHB, QNRF, and NWPU, show the strong generalizability of our method. Our code is available at: https://github.com/ZPDu/Domain-general-Crowd-Counting-in-Unseen-Scenarios

Perspective distortions and crowd variations make crowd counting a challenging task in computer vision. To tackle it, many previous works have used multi-scale architecture in deep neural networks (DNNs). Multi-scale branches can be either directly merged (e.g. by concatenation) or merged through the guidance of proxies (e.g. attentions) in the DNNs. Despite their prevalence, these combination methods are not sophisticated enough to deal with the per-pixel performance discrepancy over multi-scale density maps. In this work, we redesign the multi-scale neural network by introducing a hierarchical mixture of density experts, which hierarchically merges multi-scale density maps for crowd counting. Within the hierarchical structure, an expert competition and collaboration scheme is presented to encourage contributions from all scales; pixel-wise soft gating nets are introduced to provide pixel-wise soft weights for scale combinations in different hierarchies. The network is optimized using both the crowd density map and the local counting map, where the latter is obtained by local integration on the former. Optimizing both can be problematic because of their potential conflicts. We introduce a new relative local counting loss based on relative count differences among hard-predicted local regions in an image, which proves to be complementary to the conventional absolute error loss on the density map. Experiments show that our method achieves the state-of-the-art performance on five public datasets, i.e. ShanghaiTech, UCF_CC_50, JHU-CROWD++, NWPU-Crowd and Trancos. Our codes will be available at https://github.com/ZPDu/Redesigning-Multi-Scale-Neural-Network-for-Crowd-Counting.