Linwei Chen, Ying Fu, Lin Gu, Dezhi Zheng, Jifeng Dai
{"title":"Spatial Frequency Modulation for Semantic Segmentation","authors":"Linwei Chen, Ying Fu, Lin Gu, Dezhi Zheng, Jifeng Dai","doi":"10.1109/tpami.2025.3592621","DOIUrl":"https://doi.org/10.1109/tpami.2025.3592621","url":null,"abstract":"","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"4 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144701977","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":"Towards Reliable and Faithful Explanations: A Disentanglement-Augmented Approach for Selective Rationalization.","authors":"Linan Yue,Qi Liu,YiChao Du,Li Wang,Yanqing An,Enhong Chen","doi":"10.1109/tpami.2025.3592313","DOIUrl":"https://doi.org/10.1109/tpami.2025.3592313","url":null,"abstract":"The pursuit of model explainability has prompted the selective rationalization (aka, rationale extraction) which can identify important features (i.e., rationales) from the original input to support prediction results. Existing methods typically involve a cascaded approach with a selector responsible for extracting rationales from the input, followed by a predictor that makes predictions based on the selected rationales. However, these approaches often neglect the information contained in the non-rationales, underutilizing the input. Therefore, in our prior work, we introduce the Disentanglement-Augmented Rationale Extraction (DARE) method, which disentangles the input into rationale and non-rationale components, and enhances rationale representations by minimizing the mutual information between them. While DARE demonstrates strong performance in rationalization, it may still rely on shortcuts in the training distribution, leading to unfaithful rationales. To this end, in this paper, we propose Faith-DARE, an extension of DARE that aims to extract more reliable rationales by mitigating shortcut dependencies. Specifically, we treat the non-rationale features identified by DARE as environments that are decorrelated from the predictions. By shuffling and recombining these environments with rationales, we generate counterfactual samples and identify invariant rationales that remain predictive across shifted distributions. Extensive experiments on graph and textual datasets validate the effectiveness of Faith-DARE. Codes are available at https://github.com/yuelinan/DARE.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"19 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144701343","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":"An Efficient Image Fusion Network Exploiting Unifying Language and Mask Guidance.","authors":"Zi-Han Cao,Yu-Jie Liang,Liang-Jian Deng,Gemine Vivone","doi":"10.1109/tpami.2025.3591930","DOIUrl":"https://doi.org/10.1109/tpami.2025.3591930","url":null,"abstract":"Image fusion aims to merge image pairs collected by different sensors over the same scene, preserving their distinct features. Recent works have often focused on designing various image fusion losses, developing different network architectures, and leveraging downstream tasks (e.g., object detection) for image fusion. However, a few studies have explored how language and semantic masks can serve as guidance to aid image fusion. In this paper, we investigate how the combination of language and masks can guide image fusion tasks, discarding the previously complex frameworks, which rely on downstream tasks, GAN-based cycle training, diffusion models, or deep image priors. Additionally, we exploit a recurrent neural network-like architecture to build a lightweight network that avoids the quadratic-cost of traditional attention mechanisms. To adapt the receptance weighted key value (RWKV) model to an image modality, we modify it into a bidirectional version using an efficient scanning strategy (ESS). To guide image fusion by language and mask features, we introduce a multi-modal fusion module (MFM) to facilitate information exchange. Comprehensive experiments show that the proposed framework achieved state-of-the-art results in various image fusion tasks (i.e., visible-infrared image fusion, multi-focus image fusion, multi-exposure image fusion, medical image fusion, hyperspectral and multispectral image fusion, and pansharpening). Code will be available at https://github.com/294coder/RWKVFusion.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"115 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144693467","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":"Multi-Channel Equilibrium Graph Neural Network for Multi-View Semi-Supervised Learning.","authors":"Shiping Wang,Yueyang Pi,Yang Huang,Fuhai Chen,Le Zhang","doi":"10.1109/tpami.2025.3587216","DOIUrl":"https://doi.org/10.1109/tpami.2025.3587216","url":null,"abstract":"In practical applications, the difficulty of multi-view data annotation poses a challenge for multi-view semi-supervised learning. Although some graph-based approaches have been proposed for this task, they often struggle with capturing long-range information and memory bottlenecks, and usually encounter over-smoothing. To address these issues, this paper proposes an implicit model, named Multi-channel Equilibrium Graph Neural Network (MEGNN). Through an equilibrium point iterative process, the proposed MEGNN naturally captures long-range information and effectively reduces the consumption of memory compared with explicit models. Furthermore, the proposed method deals with the issue of over-smoothing in deep graph convolutional networks by residual connection and shrinkage factor. We analyze the effect of the shrinkage factor on the information capturing capability of the model, and demonstrate that the proposed method does not encounter over-smoothing. Comprehensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"110 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144678165","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}
Runsen Xu, Shuai Yang, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, Dahua Lin
{"title":"PointLLM-V2: Empowering Large Language Models to Better Understand Point Clouds","authors":"Runsen Xu, Shuai Yang, Xiaolong Wang, Tai Wang, Yilun Chen, Jiangmiao Pang, Dahua Lin","doi":"10.1109/tpami.2025.3590784","DOIUrl":"https://doi.org/10.1109/tpami.2025.3590784","url":null,"abstract":"","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"25 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144677420","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}
Bingxin Ke, Kevin Qu, Tianfu Wang, Nando Metzger, Shengyu Huang, Bo Li, Anton Obukhov, Konrad Schindler
{"title":"Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis","authors":"Bingxin Ke, Kevin Qu, Tianfu Wang, Nando Metzger, Shengyu Huang, Bo Li, Anton Obukhov, Konrad Schindler","doi":"10.1109/tpami.2025.3591076","DOIUrl":"https://doi.org/10.1109/tpami.2025.3591076","url":null,"abstract":"","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"13 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144678142","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}