English
Related papers

Related papers: Learning to Merge Tokens in Vision Transformers

200 papers

Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into context-aware…

Computation and Language · Computer Science 2021-02-17 Mikhail S. Burtsev , Yuri Kuratov , Anton Peganov , Grigory V. Sapunov

While transformer models have been highly successful, they are computationally inefficient. We observe that for each layer, the full width of the layer may be needed only for a small subset of tokens inside a batch and that the "effective"…

Machine Learning · Computer Science 2024-12-19 Bartosz Wójcik , Alessio Devoto , Karol Pustelnik , Pasquale Minervini , Simone Scardapane

Vision transformer has demonstrated promising performance on challenging computer vision tasks. However, directly training the vision transformers may yield unstable and sub-optimal results. Recent works propose to improve the performance…

Computer Vision and Pattern Recognition · Computer Science 2021-06-14 Chengyue Gong , Dilin Wang , Meng Li , Vikas Chandra , Qiang Liu

Collaborative software development is an integral part of the modern software development life cycle, essential to the success of large-scale software projects. When multiple developers make concurrent changes around the same lines of code,…

Learning neural networks using only few available information is an important ongoing research topic with tremendous potential for applications. In this paper, we introduce a powerful regularizer for the variational modeling of inverse…

Machine Learning · Computer Science 2023-05-17 Fabian Altekrüger , Alexander Denker , Paul Hagemann , Johannes Hertrich , Peter Maass , Gabriele Steidl

Recently the Transformer structure has shown good performances in graph learning tasks. However, these Transformer models directly work on graph nodes and may have difficulties learning high-level information. Inspired by the vision…

Machine Learning · Computer Science 2023-04-11 Han Gao , Xu Han , Jiaoyang Huang , Jian-Xun Wang , Li-Ping Liu

Data augmentation is a necessity to enhance data efficiency in deep learning. For vision-language pre-training, data is only augmented either for images or for text in previous works. In this paper, we present MixGen: a joint data…

Computer Vision and Pattern Recognition · Computer Science 2023-01-11 Xiaoshuai Hao , Yi Zhu , Srikar Appalaraju , Aston Zhang , Wanqian Zhang , Bo Li , Mu Li

As generative models scale to larger inputs across language, vision, and video domains, the cost of token-level computation has become a key bottleneck. While prior work suggests that only a subset of tokens significantly influence…

Artificial Intelligence · Computer Science 2025-08-20 Dong Liu , Yanxuan Yu

Transformer-based neural networks have achieved state-of-the-art task performance in a number of machine learning domains including natural language processing and computer vision. To further improve their accuracy, recent work has explored…

Machine Learning · Computer Science 2022-09-01 Salar Latifi , Saurav Muralidharan , Michael Garland

While Convolutional Neural Networks (CNNs) have been widely successful in 2D human pose estimation, Vision Transformers (ViTs) have emerged as a promising alternative to CNNs, boosting state-of-the-art performance. However, the quadratic…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 Kaleab A. Kinfu , Rene Vidal

Ensembling is a well-known technique in neural machine translation (NMT) to improve system performance. Instead of a single neural net, multiple neural nets with the same topology are trained separately, and the decoder generates…

Computation and Language · Computer Science 2017-07-24 Felix Stahlberg , Bill Byrne

Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific…

Computer Vision and Pattern Recognition · Computer Science 2024-02-29 Young Kyung Kim , J. Matías Di Martino , Guillermo Sapiro

It has been well established that increasing scale in deep transformer networks leads to improved quality and performance. However, this increase in scale often comes with prohibitive increases in compute cost and inference latency. We…

Machine Learning · Computer Science 2023-10-05 Cenk Baykal , Dylan Cutler , Nishanth Dikkala , Nikhil Ghosh , Rina Panigrahy , Xin Wang

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yifei Liu , Mathias Gehrig , Nico Messikommer , Marco Cannici , Davide Scaramuzza

Balancing efficiency and accuracy is a long-standing problem for deploying deep learning models. The trade-off is even more important for real-time safety-critical systems like autonomous vehicles. In this paper, we propose an effective…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Mao Ye , Gregory P. Meyer , Yuning Chai , Qiang Liu

The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform…

Sound · Computer Science 2023-01-26 Khaled Koutini , Jan Schlüter , Hamid Eghbal-zadeh , Gerhard Widmer

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Dharma KC , Venkata Ravi Kiran Dayana , Meng-Lin Wu , Venkateswara Rao Cherukuri , Hau Hwang

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Jaemin Son , Sujin Choi , Inyong Yun

The three existing dominant network families, i.e., CNNs, Transformers, and MLPs, differ from each other mainly in the ways of fusing spatial contextual information, leaving designing more effective token-mixing mechanisms at the core of…

Computer Vision and Pattern Recognition · Computer Science 2022-12-26 Guoqiang Wei , Zhizheng Zhang , Cuiling Lan , Yan Lu , Zhibo Chen

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Wentong Li , Yuqian Yuan , Jian Liu , Dongqi Tang , Song Wang , Jie Qin , Jianke Zhu , Lei Zhang
‹ Prev 1 8 9 10 Next ›