Open AccessProceedings Article
Deformable DETR: Deformable Transformers for End-to-End Object Detection
TLDR
Deformable DETR as discussed by the authors proposes to only attend to a small set of key sampling points around a reference, which can achieve better performance than DETR with 10× less training epochs.Abstract:
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10× less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code shall be released.read more
Citations
More filters
Posted Content
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries
TL;DR: In this paper, a top-down approach is proposed for multi-camera 3D object detection, which extracts 2D features from multiple camera images and then uses a sparse set of 3D objects queries to index into these features, linking 3D positions to multi-view images using camera transformation matrices.
Posted Content
Suppress-and-Refine Framework for End-to-End 3D Object Detection.
TL;DR: SRDet as discussed by the authors proposes a suppress-and-refine framework to remove the handcrafted components used to eliminate redundant boxes, and achieves state-of-the-art performance on the challenging ScanNetV2 and SUN RGB-D datasets.
Posted Content
SwinTrack: A Simple and Strong Baseline for Transformer Tracking
TL;DR: Lin et al. as discussed by the authors proposed a fully attentional-based Transformer tracking algorithm, SwinTrack, which uses Transformer for both feature extraction and feature fusion, allowing full interactions between the target object and the search region for tracking.
Posted Content
3D Object Tracking with Transformer.
TL;DR: Li et al. as discussed by the authors proposed a feature fusion network based on transformer architecture, which captures the inter-and intra-relations among different regions of the point cloud to make similarity computing more efficient by including target object information.
Posted Content
Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)
Yunzhong Hou,Liang Zheng +1 more
TL;DR: Zhang et al. as discussed by the authors proposed a novel multiview detector, MVDeTr, which adopts a newly introduced shadow transformer to aggregate multi-view information, which attends differently at different positions and cameras to deal with various shadowlike distortions.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.