End-to-End Object Detection with Fully Convolutional Network

Wang, Jianfeng; Lin, Song; Li, Zeming; Sun, Hongbin; Sun, Jian; Zheng, Nanning

doi:10.1109/cvpr46437.2021.01559

Cited by 140 publications

(76 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, although DETR achieved a high detection performance, it suffered from slow convergence, e.g., DETR required 500 epochs, whereas conventional Faster R-CNN [27] training required less than 50 epochs [31]. Recent studies have confirmed the great potential for end-to-end object detection [30,32,33]. Hence, bipartite matching cost has become an essential component for achieving end-toend object detection.…”

Section: Vision-based Document Analysismentioning

confidence: 99%

Layout Aware Semantic Element Extraction for Sustainable Science & Technology Decision Support

et al. 2022

View full text Add to dashboard Cite

New scientific and technological (S&T) knowledge is being introduced rapidly, and hence, analysis efforts to understand and analyze new published S&T documents are increasing daily. Automated text mining and vision recognition techniques alleviate the burden somewhat, but the various document layout formats and knowledge content granularities across the S&T field make it challenging. Therefore, this paper proposes LA-SEE (LAME and Vi-SEE), a knowledge graph construction framework that simultaneously extracts meta-information and useful image objects from S&T documents in various layout formats. We adopt Layout-aware Metadata Extraction (LAME), which can accurately extract metadata from various layout formats, and implement a transformer-based instance segmentation (i.e., Vision based Semantic Elements Extraction (Vi-SEE)) to maximize the vision-based semantic element recognition. Moreover, to constructing a scientific knowledge graph consisting of multiple S&T documents, we newly defined an extensible Semantic Elements Knowledge Graph (SEKG) structure. For now, we succeeded in extracting about 6 million semantic elements from 49,649 PDFs. In addition, to illustrate the potential power of our SEKG, we provide two promising application scenarios, such as a scientific knowledge guide across multiple S&T documents and questions and answering over scientific tables.

show abstract

Section: Vision-based Document Analysismentioning

confidence: 99%

Layout Aware Semantic Element Extraction for Sustainable Science & Technology Decision Support

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Very recently, DeFCN [26] adopts a one-to-one matching strategy to enable end-to-end object detection based on a fully convolutional network with competitive performance. Significantly, probably for the first time, DeFCN [26] demonstrates that it is possible to remove NMS from a detector without resorting to sequence-to-sequence (or setto-set) learning that relies on LSTM-RNN or self-attention mechanisms. The work in [21] shares similarities with De-FCN [26] in the one-to-one label assignment and using auxiliary heads to help training.…”

Section: Related Workmentioning

confidence: 99%

“…Significantly, probably for the first time, DeFCN [26] demonstrates that it is possible to remove NMS from a detector without resorting to sequence-to-sequence (or setto-set) learning that relies on LSTM-RNN or self-attention mechanisms. The work in [21] shares similarities with De-FCN [26] in the one-to-one label assignment and using auxiliary heads to help training. The performance reported in [21] is inferior to that of DeFCN [26].…”

Section: Related Workmentioning

confidence: 99%

“…Thus NMS can be removed and the detector becomes end-to-end trainable. Wang et al [26] design a fully convolutional network (FCN) without using Transformers and achieve end-to-end NMS-free object detection. Our work here follows this avenue by designing even simpler FCN detectors with stronger detection accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Our method does not rely attention mechanisms such as Transformers, or cross-level feature aggregation such as the 3D max filtering [26]. Our proposed detector, termed FCOS PSS , enjoys the following advantages.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Object Detection Made Simpler by Eliminating Heuristic NMS

Zhou,

Yu,

Shen

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Better constraints of imperceptibility, better adversarial examples in the text

Wang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

State‐of‐the‐art adversarial attacks in the text domain have shown their power to induce machine learning models to produce abnormal outputs. The samples generated in these attacks have three important attributes: attack ability, transferability, and imperceptibility. However, compared with the other two attributes, the imperceptibility of adversarial examples has not been well investigated. Unlike the pixel‐level perturbations in images, adversarial perturbations in the text are usually traceable, reflecting changes in characters, words, or sentences. The generation of imperceptible samples in texts is more difficult than in images. Therefore, how to constrain adversarial perturbations added in the text is a crucial step to construct more natural adversarial texts. Unfortunately, recent studies merely select measurements to constrain the added adversarial perturbations, but none of them explain where these measurements are suitable, which one is better, and how they perform in different kinds of adversarial attacks. In this paper, we fill this gap by comparing the performance of these metrics in various attacks. Furthermore, we propose a stricter constraint for word‐level attacks to obtain more imperceptible samples. It is also helpful to enhance existing word‐level attacks for adversarial training.

show abstract

End-to-End Object Detection with Fully Convolutional Network

Cited by 140 publications

References 32 publications

Layout Aware Semantic Element Extraction for Sustainable Science & Technology Decision Support

Layout Aware Semantic Element Extraction for Sustainable Science & Technology Decision Support

Object Detection Made Simpler by Eliminating Heuristic NMS

Better constraints of imperceptibility, better adversarial examples in the text

Contact Info

Product

Resources

About