English
Related papers

Related papers: Fast-iTPN: Integrally Pre-Trained Transformer Pyra…

200 papers

Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks. A common strategy for multi-scale feature extraction is adopting the classic top-down and bottom-up feature pyramid networks.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Guoyu Yang , Jie Lei , Zhikuan Zhu , Siyu Cheng , Zunlei Feng , Ronghua Liang

Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such as object detection and segmentation. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2021-05-12 Haotian Yan , Zhe Li , Weijian Li , Changhu Wang , Ming Wu , Chuang Zhang

Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus…

Computer Vision and Pattern Recognition · Computer Science 2023-12-18 Ning Liao , Bowen Shi , Xiaopeng Zhang , Min Cao , Junchi Yan , Qi Tian

Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem. However, in this paper we show that the capacity of the architecture has not been fully explored due to the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-17 Fan Yang , Cheng Lu , Yandong Guo , Longin Jan Latecki , Haibin Ling

In the past decade, we have witnessed rapid progress in the machine vision backbone. By introducing the inductive bias from the image processing, convolution neural network (CNN) has achieved excellent performance in numerous computer…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Tan Yu , Xu Li , Yunfeng Cai , Mingming Sun , Ping Li

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive.…

Computer Vision and Pattern Recognition · Computer Science 2017-04-21 Tsung-Yi Lin , Piotr Dollár , Ross Girshick , Kaiming He , Bharath Hariharan , Serge Belongie

Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Meng'en Qin , Yu Song , Quanling Zhao , Xiaodong Yang , Yingtao Che , Xiaohui Yang

ViTs are general and accurate, and address many tasks, but ViTs are slow, and are not always practical when efficiency is key. Existing methods for faster ViTs design hybrid non-ViT architectures, losing generality, or shrink their tokens,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Anthony Fuller , Yousef Yassin , Daniel G. Kyrollos , Evan Shelhamer , James R. Green

The adoption of Vision Transformers (ViTs) in resource-constrained applications necessitates improvements in inference throughput. To this end several token pruning and merging approaches have been proposed that improve efficiency by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Benjamin Bergner , Christoph Lippert , Aravindh Mahendran

This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs), are intended to perform information communication between…

Computer Vision and Pattern Recognition · Computer Science 2023-04-13 Jiahao Wang , Songyang Zhang , Yong Liu , Taiqiang Wu , Yujiu Yang , Xihui Liu , Kai Chen , Ping Luo , Dahua Lin

Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns from convolutional architectures. We show that this explicit image-space reconstruction is not…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Calvin Galagain , Martyna Poreba , François Goulette

Transformer networks have achieved great progress for computer vision tasks. Transformer-in-Transformer (TNT) architecture utilizes inner transformer and outer transformer to extract both local and global representations. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2022-01-05 Kai Han , Jianyuan Guo , Yehui Tang , Yunhe Wang

Neural Processes (NPs), and specifically Transformer Neural Processes (TNPs), have demonstrated remarkable performance across tasks ranging from spatiotemporal forecasting to tabular data modelling. However, many of these applications are…

Machine Learning · Computer Science 2026-02-24 Philip Mortimer , Cristiana Diaconu , Tommy Rochussen , Bruno Mlodozeniec , Richard E. Turner

We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for object detection. This design enables the original ViT architecture to be fine-tuned for object detection without needing to redesign a hierarchical…

Computer Vision and Pattern Recognition · Computer Science 2022-06-13 Yanghao Li , Hanzi Mao , Ross Girshick , Kaiming He

Deploying transformer models in practice is challenging due to their inference cost, which scales quadratically with input sequence length. To address this, we present a novel Learned Token Pruning (LTP) method which adaptively removes…

Computation and Language · Computer Science 2022-06-06 Sehoon Kim , Sheng Shen , David Thorsley , Amir Gholami , Woosuk Kwon , Joseph Hassoun , Kurt Keutzer

Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…

Computer Vision and Pattern Recognition · Computer Science 2020-12-21 Josh Beal , Eric Kim , Eric Tzeng , Dong Huk Park , Andrew Zhai , Dmitry Kislyuk

For sequence models with large vocabularies, a majority of network parameters lie in the input and output layers. In this work, we describe a new method, DeFINE, for learning deep token representations efficiently. Our architecture uses a…

Computation and Language · Computer Science 2020-02-07 Sachin Mehta , Rik Koncel-Kedziorski , Mohammad Rastegari , Hannaneh Hajishirzi

Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging…

Computer Vision and Pattern Recognition · Computer Science 2024-04-09 Hongjie Wang , Bhishma Dedhia , Niraj K. Jha

Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TGAT, and APAN ) and require tailored training frameworks…

Machine Learning · Computer Science 2024-09-19 Qiang Huang , Xiao Yan , Xin Wang , Susie Xi Rao , Zhichao Han , Fangcheng Fu , Wentao Zhang , Jiawei Jiang

The high computational demands of Vision Transformers (ViTs) in processing a large number of tokens often constrain their practical application in analyzing medical images. This research proposes a Prompt-driven Adaptive Token ({\it PrATo})…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Pallabi Dutta , Anubhab Maity , Sushmita Mitra