English
Related papers

Related papers: How Many Tokens Do 3D Point Cloud Transformer Arch…

200 papers

Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for consumer hardware. We introduce MERGE$^3$, an efficient framework that makes evolutionary merging feasible on a…

Neural and Evolutionary Computing · Computer Science 2025-05-12 Tommaso Mencattini , Adrian Robert Minut , Donato Crisostomi , Andrea Santilli , Emanuele Rodolà

Early stopping techniques can be utilized to decrease the time cost, however currently the ultimate goal of early stopping techniques is closely related to the accuracy upgrade or the ability of the neural network to generalize better on…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Thanasis Zoumpekas , Maria Salamó , Anna Puig

Recent token reduction methods for Vision Transformers (ViTs) incorporate token merging, which measures the similarities between token embeddings and combines the most similar pairs. However, their merging policies are directly dependent on…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Dong Hoon Lee , Seunghoon Hong

Generative models have proven effective at modeling 3D shapes and their statistical variations. In this paper we investigate their application to point clouds, a 3D shape representation widely used in computer vision for which, however,…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Roman Klokov , Edmond Boyer , Jakob Verbeek

3D object detection plays a pivotal role in many applications, most notably autonomous driving and robotics. These applications are commonly deployed on edge devices to promptly interact with the environment, and often require near…

Networking and Internet Architecture · Computer Science 2023-09-06 Jingzong Li , Yik Hong Cai , Libin Liu , Yu Mao , Chun Jason Xue , Hong Xu

Query-based models are extensively used in 3D object detection tasks, with a wide range of pre-trained checkpoints readily available online. However, despite their popularity, these models often require an excessive number of object…

Computer Vision and Pattern Recognition · Computer Science 2025-11-14 Lizhen Xu , Zehao Wu , Wenzhao Qiu , Shanmin Pang , Xiuxiu Bai , Kuizhi Mei , Jianru Xue

Point cloud obtained from 3D scanning is often sparse, noisy, and irregular. To cope with these issues, recent studies have been separately conducted to densify, denoise, and complete inaccurate point cloud. In this paper, we advocate that…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Jaesung Choe , Byeongin Joung , Francois Rameau , Jaesik Park , In So Kweon

Recent progress in vision-language modeling for 3D medical imaging has been fueled by large-scale computed tomography (CT) corpora with paired free-text reports, stronger architectures, and powerful pretrained models. This has enabled…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Ibrahim Ethem Hamamci , Sezgin Er , Suprosanna Shit , Hadrien Reynaud , Dong Yang , Pengfei Guo , Marc Edgar , Daguang Xu , Bernhard Kainz , Bjoern Menze

The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of…

Computer Vision and Pattern Recognition · Computer Science 2021-10-01 Rolandos Alexandros Potamias , Giorgos Bouritsas , Stefanos Zafeiriou

Ultra-fine-grained image recognition (UFGIR) is a challenging task that involves classifying images within a macro-category. While traditional FGIR deals with classifying different species, UFGIR goes beyond by classifying sub-categories…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Edwin Arkel Rios , Jansen Christopher Yuanda , Vincent Leon Ghanz , Cheng-Wei Yu , Bo-Cheng Lai , Min-Chun Hu

Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…

Robotics · Computer Science 2022-05-10 Prajval Kumar Murali , Cong Wang , Ravinder Dahiya , Mohsen Kaboli

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

Computer Vision and Pattern Recognition · Computer Science 2020-08-27 Xin Kong , Guangyao Zhai , Baoquan Zhong , Yong Liu

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Dimple A Shajahan , Mukund Varma T , Ramanathan Muthuganapathy

Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging methods improve…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Min-Jeong Lee , Hee-Dong Kim , Seong-Whan Lee

Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Tianchen Zhao , Xuefei Ning , Ke Hong , Zhongyuan Qiu , Pu Lu , Yali Zhao , Linfeng Zhang , Lipu Zhou , Guohao Dai , Huazhong Yang , Yu Wang

We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Daniel Bolya , Cheng-Yang Fu , Xiaoliang Dai , Peizhao Zhang , Christoph Feichtenhofer , Judy Hoffman

Maintaining robust 3D perception under dynamic and unpredictable test-time conditions remains a critical challenge for autonomous driving systems. Existing test-time adaptation (TTA) methods often fail in high-variance tasks like 3D object…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Huitong Yang , Zhuoxiao Chen , Fengyi Zhang , Zi Huang , Yadan Luo

We present Token-UNet, adopting the TokenLearner and TokenFuser modules to encase Transformers into UNets. While Transformers have enabled global interactions among input elements in medical imaging, current computational challenges hinder…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Louis Fabrice Tshimanga , Andrea Zanola , Federico Del Pup , Manfredo Atzori

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs…

Computer Vision and Pattern Recognition · Computer Science 2023-09-29 Quan Tang , Bowen Zhang , Jiajun Liu , Fagui Liu , Yifan Liu

Utilizing patch-based transformers for unstructured geometric data such as polygon meshes presents significant challenges, primarily due to the absence of a canonical ordering and variations in input sizes. Prior approaches to handling 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Mohammad Farazi , Yalin Wang
‹ Prev 1 4 5 6 7 8 10 Next ›