Featurized Query R-CNN
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 {https://github.com/hustvl/Featurized-QueryRCNN.
Code (1)
Tasks
Objectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Efficient Featurized Image Pyramid Network for Single Shot Detector
Single-stage object detectors have recently gained popularity due to their combined advantage of high detection accuracy and real-time speed. However, while promising results have been achieved by these detectors on stan…
GPUFeaturized Bidirectional GAN: Adversarial Defense via Adversarially Learned Semantic Inference
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense metho…
Adversarial DefenseInducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures
Adapting pretrained large language models (LLMs) to various downstream tasks in tens or hundreds of human languages is computationally expensive. Parameter-efficient fine-tuning (PEFT) significantly reduces the adaptatio…
parameter-efficient fine-tuningXScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
We propose XScale-NVS for high-fidelity cross-scale novel view synthesis of real-world large-scale scenes. Existing representations based on explicit surface suffer from discretization resolution or UV distortion, while …
Neural RenderingNovel View SynthesisEvaluating generative networks using Gaussian mixtures of image features
We develop a measure for evaluating the performance of generative networks given two sets of images. A popular performance measure currently used to do this is the Fr\'echet Inception Distance (FID). FID assumes that ima…