Featurized Query R-CNN
- URL: http://arxiv.org/abs/2206.06258v2
- Date: Tue, 14 Jun 2022 01:44:06 GMT
- Title: Featurized Query R-CNN
- Authors: Wenqiang Zhang and Tianheng Cheng and Xinggang Wang and Shaoyu Chen
and Qian Zhang and Wenyu Liu
- Abstract summary: We present featurized object queries predicted by a query generation network in the Faster R-CNN framework.
Our Featurized Query R-CNN obtains the best speed-accuracy trade-off among all R-CNN detectors, including the recent state-of-the-art Sparse R-CNN detector.
- Score: 41.40318163261041
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: The query mechanism introduced in the DETR method is changing the paradigm of
object detection and recently there are many query-based methods have obtained
strong object detection performance. However, the current query-based detection
pipelines suffer from the following two issues. Firstly, multi-stage decoders
are required to optimize the randomly initialized object queries, incurring a
large computation burden. Secondly, the queries are fixed after training,
leading to unsatisfying generalization capability. To remedy the above issues,
we present featurized object queries predicted by a query generation network in
the well-established Faster R-CNN framework and develop a Featurized Query
R-CNN. Extensive experiments on the COCO dataset show that our Featurized Query
R-CNN obtains the best speed-accuracy trade-off among all R-CNN detectors,
including the recent state-of-the-art Sparse R-CNN detector. The code is
available at \url{https://github.com/hustvl/Featurized-QueryRCNN}.
Related papers
- Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection [54.041049052843604]
We present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection.
First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network.
Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
arXiv Detail & Related papers (2023-07-01T13:53:14Z) - Logical Message Passing Networks with One-hop Inference on Atomic
Formulas [57.47174363091452]
We propose a framework for complex query answering that decomposes the Knowledge Graph embeddings from neural set operators.
On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning.
Our approach yields the new state-of-the-art neural CQA model.
arXiv Detail & Related papers (2023-01-21T02:34:06Z) - CS-Rep: Making Speaker Verification Networks Embracing
Re-parameterization [27.38202134344989]
This study proposes cross-sequential re- parameterization (CS-Rep) to increase the inference speed and verification accuracy of models.
Rep-TDNN increases the actual inference speed by about 50% and reduces the EER by 10%.
arXiv Detail & Related papers (2021-10-26T08:00:03Z) - DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection [17.326702469604676]
Few-shot object detection aims at detecting novel objects rapidly from extremely few examples of previously unseen classes.
Most existing approaches employ the Faster R-CNN as basic detection framework.
We propose a simple yet effective architecture named Decoupled Faster R-CNN (DeFRCN)
arXiv Detail & Related papers (2021-08-20T06:12:55Z) - Oriented R-CNN for Object Detection [61.78746189807462]
This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN.
In the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner.
The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them.
arXiv Detail & Related papers (2021-08-12T12:47:43Z) - Malicious Requests Detection with Improved Bidirectional Long Short-term
Memory Neural Networks [8.379440129896548]
We formulate the problem of detecting malicious requests as a temporal sequence classification problem.
We propose a novel deep learning model namely Convolutional Neural Network-Bidirectional Long Short-term Memory-Convolutional Neural Network (CNN-BiLSTM-CNN)
Experimental results on HTTP dataset CSIC 2010 have demonstrated the effectiveness of the proposed method.
arXiv Detail & Related papers (2020-10-26T02:27:44Z) - SRDCNN: Strongly Regularized Deep Convolution Neural Network
Architecture for Time-series Sensor Signal Classification Tasks [4.950427992960756]
We present SRDCNN: Strongly Regularized Deep Convolution Neural Network (DCNN) based deep architecture to perform time series classification tasks.
The novelty of the proposed approach is that the network weights are regularized by both L1 and L2 norm penalties.
arXiv Detail & Related papers (2020-07-14T08:42:39Z) - Continual Learning in Recurrent Neural Networks [67.05499844830231]
We evaluate the effectiveness of continual learning methods for processing sequential data with recurrent neural networks (RNNs)
We shed light on the particularities that arise when applying weight-importance methods, such as elastic weight consolidation, to RNNs.
We show that the performance of weight-importance methods is not directly affected by the length of the processed sequences, but rather by high working memory requirements.
arXiv Detail & Related papers (2020-06-22T10:05:12Z) - End-to-End Object Detection with Transformers [88.06357745922716]
We present a new method that views object detection as a direct set prediction problem.
Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components.
The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss.
arXiv Detail & Related papers (2020-05-26T17:06:38Z) - CodNN -- Robust Neural Networks From Coded Classification [27.38642191854458]
Deep Neural Networks (DNNs) are a revolutionary force in the ongoing information revolution.
DNNs are highly sensitive to noise, whether adversarial or random.
This poses a fundamental challenge for hardware implementations of DNNs, and for their deployment in critical applications such as autonomous driving.
By our approach, either the data or internal layers of the DNN are coded with error correcting codes, and successful computation under noise is guaranteed.
arXiv Detail & Related papers (2020-04-22T17:07:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.