English
Related papers

Related papers: Less is More: Focus Attention for Efficient DETR

200 papers

For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives. While in the few-shot setup we…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Quentin Bouniot , Angélique Loesch , Romaric Audigier , Amaury Habrard

In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD, the one-to-one assignment…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Tahira Shehzadi , Khurram Azeem Hashmi , Didier Stricker , Muhammad Zeshan Afzal

Table detection within document images is a crucial task in document processing, involving the identification and localization of tables. Recent strides in deep learning have substantially improved the accuracy of this task, but it still…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Tahira Shehzadi , Shalini Sarode , Didier Stricker , Muhammad Zeshan Afzal

Standard inference and training with transformer based architectures scale quadratically with input sequence length. This is prohibitively large for a variety of applications especially in web-page translation, query-answering etc.…

Computation and Language · Computer Science 2023-03-20 Lovish Madaan , Srinadh Bhojanapalli , Himanshu Jain , Prateek Jain

Various models have been proposed to perform object detection. However, most require many handdesigned components such as anchors and non-maximum-suppression(NMS) to demonstrate good performance. To mitigate these issues, Transformer-based…

Computer Vision and Pattern Recognition · Computer Science 2022-06-16 Sang Yon Lee

Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts…

Computation and Language · Computer Science 2024-06-04 Jungmin Yun , Mihyeon Kim , Youngbin Kim

In this paper, we propose EDIT (Encoder-Decoder Image Transformer), a novel architecture designed to mitigate the attention sink phenomenon observed in Vision Transformer models. Attention sink occurs when an excessive amount of attention…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Wenfeng Feng , Hongxiang Wang , Jianlong Wang , Xin Zhang , Jingjing Zhao , Yueyue Liang , Xiang Chen , Duokui Han

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

Computation and Language · Computer Science 2026-05-05 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Jeffrey Ouyang-Zhang , Jang Hyun Cho , Xingyi Zhou , Philipp Krähenbühl

DETR-like methods have significantly increased detection performance in an end-to-end manner. The mainstream two-stage frameworks of them perform dense self-attention and select a fraction of queries for sparse cross-attention, which is…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Xiuquan Hou , Meiqin Liu , Senlin Zhang , Ping Wei , Badong Chen

The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extremely slow convergence, which increases the training cost…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Gongjie Zhang , Zhipeng Luo , Yingchen Yu , Kaiwen Cui , Shijian Lu

Dual encoders perform retrieval by encoding documents and queries into dense lowdimensional vectors, scoring each document by its inner product with the query. We investigate the capacity of this architecture relative to sparse bag-of-words…

Computation and Language · Computer Science 2021-02-18 Yi Luan , Jacob Eisenstein , Kristina Toutanova , Michael Collins

Real-time object detection is crucial for real-world applications as it requires high accuracy with low latency. While Detection Transformers (DETR) have demonstrated significant performance improvements, current real-time DETR models are…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jiannan Huang , Aditya Kane , Fengzhe Zhou , Yunchao Wei , Humphrey Shi

Attention is sparse in vision transformers. We observe the final prediction in vision transformers is only based on a subset of most informative tokens, which is sufficient for accurate image recognition. Based on this observation, we…

Computer Vision and Pattern Recognition · Computer Science 2021-10-27 Yongming Rao , Wenliang Zhao , Benlin Liu , Jiwen Lu , Jie Zhou , Cho-Jui Hsieh

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Peng Gao , Minghang Zheng , Xiaogang Wang , Jifeng Dai , Hongsheng Li

Over the last few years, contextualized pre-trained transformer models such as BERT have provided substantial improvements on information retrieval tasks. Recent approaches based on pre-trained transformer models such as BERT, fine-tune…

Information Retrieval · Computer Science 2021-09-23 Negar Arabzadeh , Xinyi Yan , Charles L. A. Clarke

Detection Transformers (DETR) are renowned object detection pipelines, however computationally efficient multiscale detection using DETR is still challenging. In this paper, we propose a Cross-Resolution Encoding-Decoding (CRED) mechanism…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Ashish Kumar , Jaesik Park

In this paper, we propose an extension to Longformer Encoder-Decoder, a popular sparse transformer architecture. One common challenge with sparse transformers is that they can struggle with encoding of long range context, such as…

Computation and Language · Computer Science 2024-10-14 Evan Lucas , Dylan Kangas , Timothy C Havens

Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Saksham Suri , Sai Saketh Rambhatla , Rama Chellappa , Abhinav Shrivastava

One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Shilong Zhang , Xinjiang Wang , Jiaqi Wang , Jiangmiao Pang , Chengqi Lyu , Wenwei Zhang , Ping Luo , Kai Chen