With the accumulation of resources in the era of Big Data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different strategies for fine-tuning pre-trained models versus training from scratch. However, existing optimizers primarily focus on reducing the loss function by updating model parameters, without fully addressing the unique demands of these two major paradigms. In this paper, we propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for these distinct training scenarios. For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization by aligning with the characteristics of weight updates and network architecture. For more importantly fine-tuning, we integrate weight rollback with the optimizer, incorporating a rollback term into each weight update step. This ensures consistency in the weight distribution between upstream and downstream models, effectively mitigating knowledge forgetting and improving fine-tuning performance. Additionally, we extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks. Extensive experiments across diverse tasks, including image classification, object detection, semantic segmentation, and instance segmentation, demonstrate the broad applicability and state-of-the-art performance of DualOpt.

Recent advances in video action recognition have achieved remarkable performance in coarse-grained macro-action classification by leveraging large-scale visual backbones and transformer architectures. However, extending these successes to fine-grained micro-action recognition remains a fundamental challenge due to the subtlety, brevity, and low motion intensity of micro-actions. In this paper, we propose a high-capacity framework for micro-action recognition, enhancing both representation learning and decision robustness. We scale to large-scale backbones using the VideoMAEv2 Giant model, enabling the extraction of finer spatial-temporal features. A Temporal-Spatial Connector (TSC) is introduced to dynamically highlight discriminative temporal frames and spatial regions, strengthening the model's focus on subtle motion cues critical for micro-action identification. To stabilize optimization and fully exploit the capacity of large models, we design a four-phase progressive training strategy, encompassing linear probing, full fine-tuning, connector-specific optimization, and classifier head refinement. Furthermore, we propose a novel ensemble decision mechanism that integrates Top-K predictions from diverse models via a Large Language Model (LLM), enhancing prediction consistency and robustness through multimodel consensus. Our method achieves an F1mean of 76.54% on the MA-52 dataset, ranking 3rd in the 2025 Micro-Action Analysis Grand Challenge and advancing the state of the art in fine-grained video understanding.

Light field microscopy (LFM) has become an emerging tool in neuroscience for large-scale neural imaging in vivo, with XLFM (eXtended Light Field Microscopy) notable for its single-exposure volumetric imaging, broad field of view, and high temporal resolution. However, learning-based 3D reconstruction in XLFM remains underdeveloped due to two core challenges: the absence of standardized datasets and the lack of methods that can efficiently model its angular–spatial structure while remaining physically grounded. We address these challenges by introducing three key contributions. First, we construct the XLFM-Zebrafish benchmark, a large-scale dataset and evaluation suite for XLFM reconstruction. Second, we propose Masked View Modeling for Light Fields (MVM-LF), a self-supervised task that learns angular priors by predicting occluded views, improving data efficiency. Third, we formulate the Optical Rendering Consistency Loss (ORC Loss), a differentiable rendering constraint that enforces alignment between predicted volumes and their PSF-based forward projections. On the XLFM-Zebrafish benchmark, our method improves PSNR by 7.7\% over state-of-the-art baselines. Code and datasets are publicly available at: https://github.com/hefengcs/XLFM-Former.

In the big data era, the computer vision field benefits from large-scale datasets such as LAION-2B, LAION-400M, and ImageNet-21K, Kinetics, on which popular models like the ViT and ConvNeXt series have been pre-trained, acquiring substantial knowledge. However, numerous downstream tasks in specialized and data-limited scientific domains continue to pose significant challenges. In this paper, we propose a novel Cluster Attention Adapter (CLAdapter), which refines and adapts the rich representations learned from large-scale data to various data-limited downstream tasks. Specifically, CLAdapter introduces attention mechanisms and cluster centers to personalize the enhancement of transformed features through distribution correlation and transformation matrices. This enables models fine-tuned with CLAdapter to learn distinct representations tailored to different feature sets, facilitating the models' adaptation from rich pre-trained features to various downstream scenarios effectively. In addition, CLAdapter's unified interface design allows for seamless integration with multiple model architectures, including CNNs and Transformers, in both 2D and 3D contexts. Through extensive experiments on 10 datasets spanning domains such as generic, multimedia, biological, medical, industrial, agricultural, environmental, geographical, materials science, out-of-distribution (OOD), and 3D analysis, CLAdapter achieves state-of-the-art performance across diverse data-limited scientific domains, demonstrating its effectiveness in unleashing the potential of foundation vision models via adaptive transfer. Code is available at https://github.com/qklee-lz/CLAdapter.

In the field of fine-grained visual recognition (FGVR), the ability to resolve minute and often subtle differences between highly similar object categories is paramount. The advent of vision transformers (ViTs) has marked a significant advancement in this domain, primarily due to their capacity to model the intricate interdependencies among object parts represented as image patches. However, their inherent single-scale processing limitation hampers their effectiveness in FGVR tasks. Furthermore, the challenge of uncertainty inherent in FGVR tasks remains unresolved, necessitating the development of methods that bolster the robustness of these models, particularly across varying scales of visual features. We introduce a new plug-in module that can be seamlessly integrated into ViT, called dual guidance enabled fuzzy inference (DGEFI), which combines fuzzy inference with dual guidance mechanisms. Dual guidance includes scale-aware guidance and probability guidance. The former strengthens the model's focus on salient scales, and the latter refines the distinction between similar categories by optimizing intraclass compactness and interclass separability. Fuzzy inference enables the model to adaptively tweak the influence of distinct scales in the final decision-making phase, thereby enhancing the overall accuracy of recognition tasks. We demonstrate the versatility and efficacy of our DGEFI module by integrating it into several leading ViT backbones, including ViT, Swin, Mvitv2, and EVA-02. Empirical results exhibit exceptional performance gains, with the integration of DGEFI into EVA-02 remarkable accuracy improvements, reaching 93.6% on the CUB-200-2011 dataset and 94.5% on the NA-Birds dataset, respectively, improving over the state-of-the-art method 0.5% and 1.5%.

Video action recognition has been a hot research direction in computer vision, with most existing technologies focusing on coarse-grained macro-action recognition. However, fine-grained action recognition remains challenging. Micro-actions, characterized by high fine-grained, low-intensity, and brief, are crucial for emotion recognition and psychological assessment applications. In this paper, we build on popular video action recognition frameworks as foundation models, introducing multi-auxiliary heads and hybrid loss optimization to advance micro-action recognition. Specifically, the Frame-Level pred and Coarse-Grained Body-Action auxiliary heads work collaboratively to enhance the model and Fine-Grained Micro-Action primary head for perceiving fine-grained and capturing keyframes. Incorporating F1 loss, ArcFace loss, and weighted multi-task loss improves training stability, convergence speed, and performance. Additionally, integrating the optical flow modality enriches the model's diversity, and ensemble learning across all foundational models. Finally, our method achieves a 75.37% F1-mean on the MA-52 dataset, ranking 1st in the Micro-Action Analysis Grand Challenge in conjunction with ACM MM'24. The code is available at https://github.com/qklee-lz/ACMMM2024-MAC.

Abstract Makeup transfer (MT) aims to transfer the makeup style from a given reference makeup face image to a source image while preserving face identity and background information. In recent years, MT has attracted the attention of many scholars, and it has a wide range of application prospects and research value. Since then, many methods have been proposed to accomplish MT, most of which are based on Generative Adversarial Network methods. A taxonomy of existing algorithms in the field of MT is first proposed. Then, evaluation methods are proposed, existing methods are analysed, and existing datasets are introduced. This paper finally discusses the current problems in the field of MT and the trend of future research.

Abstract The authors focus on the makeup transformation problem, which refers to the transfer of makeup from a reference face to a source face image while maintaining the source makeup‐free face image. In recent years, makeup transformation has become a hot issue and a lot of research has been conducted on this basis, but there are some limitations in the existing methods, mainly due to the lack of consideration of age factor, which makes the final generated face makeup images appear not natural and lack appearance attractiveness. In order to further solve this problem, an age‐compensated makeup transformation framework based on homology continuity is proposed. In order to achieve a stable and controllable age‐compensation effect, the authors design a new coding module that can map the face makeup semantic vector into the higher feature space and achieve age compensation by adjusting the direction of the semantic vector. Finally, in order to comprehensively evaluate the effectiveness of the authors’ proposed method, a large number of qualitative and quantitative experiments have been conducted, and the experimental results show that the authors’ proposed framework outperforms existing methods.

Recently, deep neural networks (DNNs) promote mainly by network architectures and loss functions; however, the development of neuron models has been quite limited. In this study, inspired by the mechanism of human cognition, a hyper-sausage coverage function (HSCF) neuron model possessing a high flexible plasticity. Then, a novel cross-entropy and volume-coverage (CE_VC) loss is defined, which compresses the volume of the hyper-sausage to the hilt, and helps alleviate confusion among different classes, thus ensuring the intra-class compactness of the samples. Finally, a divisive iteration method is introduced, which considers each neuron model as a weak classifier, and iteratively increases the number of weak classifiers. Thus, the optimal number of the HSCF neuron is adaptively determined and an end-to-end learning framework is constructed. In particular, to improve the classification performance, the HSCF neuron can be applied to classical DNNs. Comprehensive experiments on eight datasets in several domains demonstrate the effectiveness of the proposed method. The proposed method exhibits the feasibility of boosting DNNs with neuron plasticity and provides a novel perspective for further developments in DNNs. The source code is available at https://github.com/Tough2011/HSCFNet.git .