English
Related papers

Related papers: Sparse Fusion for Multimodal Transformers

200 papers

Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that…

Computation and Language · Computer Science 2024-12-10 Tingyu Xia , Bowen Yu , Kai Dang , An Yang , Yuan Wu , Yuan Tian , Yi Chang , Junyang Lin

We introduce Attention Free Transformer (AFT), an efficient variant of Transformers that eliminates the need for dot product self attention. In an AFT layer, the key and value are first combined with a set of learned position biases, the…

Machine Learning · Computer Science 2021-09-23 Shuangfei Zhai , Walter Talbott , Nitish Srivastava , Chen Huang , Hanlin Goh , Ruixiang Zhang , Josh Susskind

Sparse algorithms offer great flexibility for multi-view temporal perception tasks. In this paper, we present an enhanced version of Sparse4D, in which we improve the temporal fusion module by implementing a recursive form of multi-frame…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Xuewu Lin , Tianwei Lin , Zixiang Pei , Lichao Huang , Zhizhong Su

In the rapidly evolving realm of machine learning, algorithm effectiveness often faces limitations due to data quality and availability. Traditional approaches grapple with data sharing due to legal and privacy concerns. The federated…

Machine Learning · Computer Science 2023-11-16 Sin Cheng Ciou , Pin Jui Chen , Elvin Y. Tseng , Yuh-Jye Lee

Seismic data interpolation is a critical pre-processing step for improving seismic imaging quality and remains a focus of academic innovation. To address the computational inefficiencies caused by extensive iterative resampling in current…

Multiple modalities can provide more valuable information than single one by describing the same contents in various ways. Hence, it is highly expected to learn effective joint representation by fusing the features of different modalities.…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Di Hu , Feiping Nie , Xuelong Li

Transformer architecture has been very successful long runner in the field of Deep Learning (DL) and Large Language Models (LLM) because of its powerful attention-based learning and parallel-natured architecture. As the models grow gigantic…

Machine Learning · Computer Science 2026-01-21 Phani Kumar , Nyshadham , Jyothendra Varma , Polisetty V R K , Aditya Rathore

Multimodal representation learning poses significant challenges in capturing informative and distinct features from multiple modalities. Existing methods often struggle to exploit the unique characteristics of each modality due to unified…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Cam-Van Thi Nguyen , Ngoc-Hoa Thi Nguyen , Duc-Trong Le , Quang-Thuy Ha

Aggregation of multi-stage features has been revealed to play a significant role in semantic segmentation. Unlike previous methods employing point-wise summation or concatenation for feature aggregation, this study proposes the Category…

Computer Vision and Pattern Recognition · Computer Science 2023-08-11 Quan Tang , Chuanjian Liu , Fagui Liu , Yifan Liu , Jun Jiang , Bowen Zhang , Kai Han , Yunhe Wang

Current crowd-counting models often rely on single-modal inputs, such as visual images or wireless signal data, which can result in significant information loss and suboptimal recognition performance. To address these shortcomings, we…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Zhe Cui , Yuli Li , Le-Nam Tran

3D Swin Transformer (3D-ST) known for its hierarchical attention and window-based processing, excels in capturing intricate spatial relationships within images. Spatial-spectral Transformer (SST), meanwhile, specializes in modeling…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Muhammad Ahmad , Manuel Mazzara , Salvatore Distifano

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact…

Computation and Language · Computer Science 2022-04-22 Marcos Treviso , António Góis , Patrick Fernandes , Erick Fonseca , André F. T. Martins

Multi-modal image fusion (MMIF) integrates valuable information from different modality images into a fused one. However, the fusion of multiple visible images with different focal regions and infrared images is a unprecedented challenge in…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Xilai Li , Xiaosong Li , Tao Ye , Xiaoqi Cheng , Wuyang Liu , Haishu Tan

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Shuning Chang , Pichao Wang , Jiasheng Tang , Fan Wang , Yi Yang

We address the multi-focus image fusion problem, where multiple images captured with different focal settings are to be fused into an all-in-focus image of higher quality. Algorithms for this problem necessarily admit the source image…

Computer Vision and Pattern Recognition · Computer Science 2019-05-06 Farshad G. Veshki , Sergiy A. Vorobyov

Multimodal transformers integrate diverse data types like images, audio, and text, advancing tasks such as audio-visual understanding and image-text retrieval; yet their high parameterization limits deployment on resource-constrained edge…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-10 Timo Fudala , Vasileios Tsouvalas , Nirvana Meratnia

Sparse matrix factorization is a popular tool to obtain interpretable data decompositions, which are also effective to perform data completion or denoising. Its applicability to large datasets has been addressed with online and randomized…

Machine Learning · Statistics 2017-11-15 Arthur Mensch , Julien Mairal , Bertrand Thirion , Gaël Varoquaux

Recently, it has attracted more and more attentions to fuse multi-scale features for semantic image segmentation. Various works were proposed to employ progressive local or global fusion, but the feature fusions are not rich enough for…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Fangjian Lin , Tianyi Wu , Sitong Wu , Shengwei Tian , Guodong Guo

With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost…

Machine Learning · Computer Science 2024-06-11 Weixi Song , Zuchao Li , Lefei Zhang , Hai Zhao , Bo Du

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…

Computer Vision and Pattern Recognition · Computer Science 2024-02-19 Noreen Anwar , Guillaume-Alexandre Bilodeau , Wassim Bouachir