{"title":"Enhancing Feature Learning with Hard Samples in Mutual Learning for Online Class Incremental Learning.","authors":"Guoqiang Liang,Shibin Su,De Cheng,Shizhou Zhang,Peng Wang,Yanning Zhang","doi":"10.1109/tip.2025.3616626","DOIUrl":"https://doi.org/10.1109/tip.2025.3616626","url":null,"abstract":"Online Class-Incremental Learning (OCIL) aims to solve the problem of incrementally learning new classes from a non-i.i.d. and single-pass data stream. Compared to the offline setting, OCIL is much closer to a live learning experience requiring higher model update frequency at less computational budget. Due to its one-epoch training constraint, the model is likely to learn non-essential features and encounter the under-fitting issue, which severely affects the model's stability. In this paper, we investigate how to use hard samples to improve data variability, eventually enhancing feature learning and addressing the under-fitting problem. Specifically, by introducing a scoring function assessing the sample value, we build an OCIL formulation that simultaneously generates high-value samples and optimizes the OCIL model, improving generalization ability within the constraint of single-epoch training. Empirically, we found that strong data augmentation is a simple but effective way to generate a higher proportion of high-score samples. To make the most of these augmented samples, we design an OCIL model based on mutual learning with two networks of identical structures. Moreover, a collaborative learning mechanism is developed by aligning the features and class probabilities from the two networks to promote their interaction. Extensive experiments on three widely used datasets for OCIL have demonstrated the effectiveness of our method, obtaining superior performance to state-of-the-art methods. The code is available at https://github.com/susususushi/SDA-MCL.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"128 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xi Yang,Haoyuan Shi,Ziyun Li,Maoying Qiao,Fei Gao,Nannan Wang
{"title":"S3OIL: Semi-Supervised SAR-to-Optical Image Translation via Multi-Scale and Cross-Set Matching.","authors":"Xi Yang,Haoyuan Shi,Ziyun Li,Maoying Qiao,Fei Gao,Nannan Wang","doi":"10.1109/tip.2025.3616576","DOIUrl":"https://doi.org/10.1109/tip.2025.3616576","url":null,"abstract":"Image-to-image translation has achieved great success, but still faces the significant challenge of limited paired data, particularly in translating Synthetic Aperture Radar (SAR) images to optical images. Furthermore, most existing semi-supervised methods place limited emphasis on leveraging the data distribution. To address those challenges, we propose a Semi-Supervised SAR-to-Optical Image Translation (S3OIL) method that achieves high-quality image generation using minimal paired data and extensive unpaired data while strategically exploiting the data distribution. To this end, we first introduce a Cross-Set Alignment Matching (CAM) mechanism to create local correspondences between the generated results of paired and unpaired data, ensuring cross-set consistency. In addition, for unpaired data, we apply weak and strong perturbations and establish intra-set Multi-Scale Matching (MSM) constraints. For paired data, intra-modal semantic consistency (ISC) is presented to ensure alignment with the ground truth. Finally, we propose local and global cross-modal semantic consistency (CSC) to boost structural identity during translation. We conduct extensive experiments on SAR-to-optical datasets and another sketch-to-anime task, demonstrating that S3OIL delivers competitive performance compared to state-of-the-art unsupervised, supervised, and semi-supervised methods, both quantitatively and qualitatively. Ablation studies further reveal that S3OIL can ensure the preservation of both semantic content and structural integrity of the generated images. Our code is available at: https://github.com/XduShi/SOIL.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"30 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Robust Single-shot 3D Reconstruction by Sparse-to-dense Stereo Matching and Spline Function based Parallax Modeling.","authors":"ZhenZhou Wang","doi":"10.1109/tip.2025.3616615","DOIUrl":"https://doi.org/10.1109/tip.2025.3616615","url":null,"abstract":"Single-shot 3D surface imaging techniques with high accuracy and high resolution are very important in both academia and industry. In this paper, we propose a sparse-to-dense structured light (SL) line-pattern based active stereo vision (ASV) approach to reconstruct the 3D shapes robustly with high-resolution. We propose a sparse-to-dense stereo matching (SDSM) method to solve the challenging problem of line clustering and line matching. We design the structured light line pattern with four colors and the distances between lines of different color range from sparse to dense. Accordingly, the sparse color lines could be clustered and matched at first while the dense color lines could be matched subsequently with the constraint of the clustered and matched sparse color lines. After all the color lines are matched, a spline-function based parallax model (SFPM) is computed based on the points on the matched color lines. Then, the depths of the points in the regions between the color lines are computed by the parallax model. Experimental results show that the proposed SDSM-SFPM ASV approach is more robust than existing methods especially in reconstructing the complex 3D shapes.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"16 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Shared-memory Parallel Alpha-Tree Algorithm for Extreme Dynamic Ranges.","authors":"Jiwoo Ryu,Scott C Trager,Michael H F Wilkinson","doi":"10.1109/tip.2025.3616578","DOIUrl":"https://doi.org/10.1109/tip.2025.3616578","url":null,"abstract":"The α-tree is an effective hierarchical image representation used for connected filtering or segmentation in remote sensing and other image applications. The α-tree constructs a tree based on the dissimilarities of the pixels in an image. Compared to other hierarchical image representations such as the component tree, the α-tree provides a better representation of the granularity of images and is easier to apply to multichannel images. The major drawback of the α-tree is its processing speed, due to the large amount of data to be processed and the lack of studies on an efficient algorithms, especially on multichannel and high dynamic range images. In this study, we introduce a novel adaptation of the hybrid component tree algorithm on the α-tree for fast parallel α-tree construction in any dynamic range of pixel dissimilarity. We tested the hybrid α-tree algorithm on Sentinel-2 remote sensing images from the European Space Agency (ESA) as well as randomly generated images, on the Hábrók high performance computing cluster. Experimental results show that the hybrid α-tree algorithm achieves the processing speed of 10-30Mpix/s and the speedup of 10-30 on a 128-core computer, proving the efficiency of the first parallel α-tree algorithm in high dynamic range, to the best of our knowledge.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"348 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PFIG-Palm: Controllable Palmprint Generation via Pixel and Feature Identity Guidance.","authors":"Yuchen Zou,Huikai Shao,Chengcheng Liu,Siyu Zhu,Zongqing Hou,Dexing Zhong","doi":"10.1109/tip.2025.3616611","DOIUrl":"https://doi.org/10.1109/tip.2025.3616611","url":null,"abstract":"Palmprint recognition offers a promising solution for convenient and private authentication. However, the scarcity of large-scale palmprint datasets constrains its development and application. Recent approaches have sought to mitigate this issue by synthesizing palmprints based on Bézier curves. Due to the lack of paired data between curves and palmprints, it is difficult to generate curve-driven palmprints with precise identity. To address this challenge, we propose a novel Pixel and Feature Identity Guidance (PFIG) framework to synthesize realistic palmprints, whose IDs are strictly governed by the Bézier curves. In order to establish ID mapping, an ID Injection (IDI) module is constructed to synthesize pseudo-paired data. Two cross-domain ID consistency losses at pixel and feature levels are further proposed to strictly preserve the semantic information of the input ID curves. Experimental results demonstrate that our ID-guided approach can synthesize more realistic palmprints with controllable identities. Based on only 80,000 synthesized palmprints for pre-training, the recognition accuracy can be improved by more than 18% in terms of TAR@1e-6. When trained exclusively on synthetic data, our method achieves superior performance to existing synthetic approaches. The source code is available at https://github.com/YuchenZou/PFIG-Palm.","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"58 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145240876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kun Dai, Tao Xie, Zhiqiang Jiang, Ke Wang, Ruifeng Li, Lijun Zhao, Chuqing Cao
{"title":"AGHL: Anchor-Guided Point Cloud Registration Network with Hybrid Local Feature Perception","authors":"Kun Dai, Tao Xie, Zhiqiang Jiang, Ke Wang, Ruifeng Li, Lijun Zhao, Chuqing Cao","doi":"10.1109/tip.2025.3613987","DOIUrl":"https://doi.org/10.1109/tip.2025.3613987","url":null,"abstract":"","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":"22 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145203269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}