Shaofeng Zhang,Qiang Zhou,Zhibin Wang,Hao Li,Junchi Yan
{"title":"EasyOutPainter: One Step Image Outpainting with both Continuous Multiple and Resolution.","authors":"Shaofeng Zhang,Qiang Zhou,Zhibin Wang,Hao Li,Junchi Yan","doi":"10.1109/tpami.2025.3586824","DOIUrl":"https://doi.org/10.1109/tpami.2025.3586824","url":null,"abstract":"Image outpainting aims to generate the content of an input sub-image outside its boundaries, which remains open for existing generative models. This paper explores image outpainting in three directions that have not been achieved in literature to our knowledge: outpainting 1) with continuous multiples (in contrast to the discrete ones by existing methods); 2) with arbitrary resolutions; and 3) in a single step (for any multiples and resolutions). The arbitrary multiple outpainting is achieved by utilizing randomly cropped views from the same image during training to capture arbitrary relative positional information. Specifically, by feeding one view and relative positional embeddings as queries, we can reconstruct another view. At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings. The continuous-resolution outpainting is achieved by introducing the multi-scale training strategy into generative models. Specifically, by disentangling the image resolution and the number of patches, it can generate images with arbitrary resolutions without postprocessing. Meanwhile, we propose a query-based contrastive objective to make our method not rely on a pre-trained backbone network which is otherwise often required in peer methods. The comprehensive experimental results on public benchmarks show its superior performance over state-of-the-art approaches.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"3 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144578805","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":"SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations.","authors":"Xiangchao Yan,Runjian Chen,Bo Zhang,Hancheng Ye,Renqiu Xia,Jiakang Yuan,Hongbin Zhou,Xinyu Cai,Botian Shi,Wenqi Shao,Ping Luo,Yu Qiao,Tao Chen,Junchi Yan","doi":"10.1109/tpami.2025.3586961","DOIUrl":"https://doi.org/10.1109/tpami.2025.3586961","url":null,"abstract":"Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e.g. autonomous driving, yet it still remains notoriously labor-intensive. Pretraining-finetuning approach can alleviate the labeling burden by fine-tuning a pre-trained backbone across various downstream datasets as well as tasks. In this paper, we propose SPOT, namely Scalable Pre-training via Occupancy prediction for learning Transferable 3D representations under such a label-efficient fine-tuning paradigm. SPOT achieves effectiveness on various public datasets with different downstream tasks, showcasing its general representation power, cross-domain robustness and data scalability which are three key factors for real-world application. Specifically, we both theoretically and empirically show, for the first time, that general representations learning can be achieved through the task of occupancy prediction. Then, to address the domain gap caused by different LiDAR sensors and annotation methods, we develop a beam re-sampling technique for point cloud augmentation combined with class-balancing strategy. Furthermore, scalable pre-training is observed, that is, the downstream performance across all the experiments gets better with more pre-training data. Additionally, such pre-training strategy also remains compatible with unlabeled data. The hope is that our findings will facilitate the understanding of LiDAR points and pave the way for future advancements in LiDAR pre-training.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"21 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144578807","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":"Gradient Projection For Continual Parameter- Efficient Tuning.","authors":"Jingyang Qiao,Zhizhong Zhang,Xin Tan,Yanyun Qu,Wensheng Zhang,Zhi Han,Yuan Xie","doi":"10.1109/tpami.2025.3587032","DOIUrl":"https://doi.org/10.1109/tpami.2025.3587032","url":null,"abstract":"Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and protecting old knowledge, leading to zero-shot generalization collapse, and cross-modal hallucination. In this paper, we reformulate Adapter, LoRA, Prefix-tuning, and Prompt-tuning from the perspective of gradient projection, and firstly propose a unified framework called Parameter Efficient Gradient Projection (PEGP). We introduce orthogonal gradient projection into different PET paradigms and theoretically demonstrate that the orthogonal condition for the gradient can effectively resist forgetting even for large-scale models. It therefore modifies the gradient towards the direction that has less impact on the old feature space, with less extra memory space and training time. We extensively evaluate our method with different backbones, including ViT and CLIP, on diverse datasets, and experiments comprehensively demonstrate its efficiency in reducing forgetting in class, online class, domain, task, and multi-modality continual settings.","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"109 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144578806","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":"Unifying Graph Contrastive Learning Via Graph Message Augmentation","authors":"Ziyan Zhang, Bo Jiang, Jin Tang, Bin Luo","doi":"10.1109/tpami.2025.3586651","DOIUrl":"https://doi.org/10.1109/tpami.2025.3586651","url":null,"abstract":"","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"10 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144578246","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}
Haotong Qin, Xianglong Liu, Xudong Ma, Lei Ke, Yulun Zhang, Jie Luo, Michele Magno
{"title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","authors":"Haotong Qin, Xianglong Liu, Xudong Ma, Lei Ke, Yulun Zhang, Jie Luo, Michele Magno","doi":"10.1109/tpami.2025.3584928","DOIUrl":"https://doi.org/10.1109/tpami.2025.3584928","url":null,"abstract":"","PeriodicalId":13426,"journal":{"name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"41 1","pages":""},"PeriodicalIF":23.6,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546910","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}