English
Related papers

Related papers: Align then Adapt: Rethinking Parameter-Efficient T…

200 papers

Recent advances in diffusion-based text-to-video models, particularly those built on the diffusion transformer architecture, have achieved remarkable progress in generating high-quality and temporally coherent videos. However, transferring…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zhexin Zhang , Yangyang Xu , Yifeng Zhu , Long Chen , Yong Du , Shengfeng He , Jun Yu

In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant computational challenges due to the extreme variance in sequence lengths within mixed-mode…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-19 Yucheng Guo , Yongjian Guo , Zhong Guan , Haoran Sun , Wen Huang , Wanting Xu , Jing Long , Shuai Di , Junwu Xiong

Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing methods predominantly follow a backward-alignment paradigm, which rigidly aligns incoming…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zhilin Zhu , Yabin Wang , Zhiheng Ma , Yaguang Song , Yaowei Wang , Xiaopeng Hong

Few-shot learning methods aim to embed the data to a low-dimensional embedding space and then classify the unseen query data to the seen support set. While these works assume that the support set and the query set lie in the same embedding…

Computer Vision and Pattern Recognition · Computer Science 2022-05-10 Siyang Jiang , Wei Ding , Hsi-Wen Chen , Ming-Syan Chen

Recognizing human actions from point cloud sequence has attracted tremendous attention from both academia and industry due to its wide applications. However, most previous studies on point cloud action recognition typically require complex…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Shenglin He , Xiaoyang Qu , Jiguang Wan , Guokuan Li , Changsheng Xie , Jianzong Wang

Motivated by the Parameter-Efficient Fine-Tuning (PEFT) in large language models, we propose LoRAT, a method that unveils the power of large ViT model for tracking within laboratory-level resources. The essence of our work lies in adapting…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 Liting Lin , Heng Fan , Zhipeng Zhang , Yaowei Wang , Yong Xu , Haibin Ling

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Computer Vision and Pattern Recognition · Computer Science 2022-02-04 Nico Messikommer , Daniel Gehrig , Mathias Gehrig , Davide Scaramuzza

Automated analysis of optical coherence tomography (OCT) and OCT angiography (OCTA) images is critical for robust ophthalmic diagnosis. Existing mainstream methods trained from scratch rely heavily on massive data and model scale, thereby…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Xiaofei Su , Zengshuo Wang , Minghe Sun , Xin Zhao , Mingzhu Sun

We rethink the role of positional encoding in 3D representation learning and fine-tuning. We argue that using positional encoding in point Transformer-based methods serves to aggregate multi-scale features of point clouds. Additionally, we…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Shaochen Zhang , Zekun Qi , Runpei Dong , Xiuxiu Bai , Xing Wei

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few trainable…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Dongshuo Yin , Xueting Han , Bin Li , Hao Feng , Jing Bai

Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Zhao Jin , Yinjie Lei , Naveed Akhtar , Haifeng Li , Munawar Hayat

Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment,…

Machine Learning · Computer Science 2026-05-26 Qi Yu , Ruizhong Qiu , Zhichen Zeng , My T. Thai , Huan Liu , Hanghang Tong

Video matting is crucial for applications such as film production and virtual reality, yet deploying its computationally intensive models on resource-constrained devices presents challenges. Quantization is a key technique for model…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Tianrui Zhu , Houyuan Chen , Ruihao Gong , Michele Magno , Haotong Qin , Kai Zhang

LiDAR-based 3D object detectors have been largely utilized in various applications, including autonomous vehicles or mobile robots. However, LiDAR-based detectors often fail to adapt well to target domains with different sensor…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Jiyun Jang , Mincheol Chang , Jongwon Park , Jinkyu Kim

3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task, but its performance is limited by different sensor sampling patterns (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Zhimin Yuan , Wankang Zeng , Yanfei Su , Weiquan Liu , Ming Cheng , Yulan Guo , Cheng Wang

LiDAR's dense, sharp point cloud (PC) representations of the surrounding environment enable accurate perception and significantly improve road safety by offering greater scene awareness and understanding. However, LiDAR's high cost…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 William Muckelroy , Mohammed Alsakabi , John Dolan , Ozan Tonguz

Recent advancements in point cloud compression have primarily emphasized geometry compression while comparatively fewer efforts have been dedicated to attribute compression. This study introduces an end-to-end learned dynamic lossy…

Image and Video Processing · Electrical Eng. & Systems 2024-08-21 Dat Thanh Nguyen , Daniel Zieger , Marc Stamminger , Andre Kaup

Embodied outdoor scene understanding forms the foundation for autonomous agents to perceive, analyze, and react to dynamic driving environments. However, existing 3D understanding is predominantly based on 2D Vision-Language Models (VLMs),…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Runwei Guan , Jianan Liu , Ningwei Ouyang , Shaofeng Liang , Daizong Liu , Xiaolou Sun , Lianqing Zheng , Ming Xu , Yutao Yue , Guoqiang Mao , Hui Xiong

3D semantic scene labeling is a fundamental task for Autonomous Driving. Recent work shows the capability of Deep Neural Networks in labeling 3D point sets provided by sensors like LiDAR, and Radar. Imbalanced distribution of classes in the…

Computer Vision and Pattern Recognition · Computer Science 2019-06-27 Mohammed Abdou , Mahmoud Elkhateeb , Ibrahim Sobh , Ahmad Elsallab

Point cloud foundation models demonstrate strong generalization, yet adapting them to downstream tasks remains challenging in low-data regimes. Full fine-tuning often leads to overfitting and significant drift from pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Sneha Paul , Zachary Patterson , Nizar Bouguila