Single shot object detection with top-down refinement

Han, Guangxing; Zhang, Xuan; Li, Chongrong

doi:10.1109/icip.2017.8296905

Cited by 16 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proposal-based methods [11,15,17,18,33] divide object detection into two sequential stages by firstly generating a set of region proposals and then performing classification and bounding box regression for each proposal. Proposal-free methods [16,28,32,39] directly predict the bounding boxes and the corresponding class labels on top of CNN features. Recently, the transformer based object detection models [1,53] show promising results, but still suffer from slow convergence problem.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Object Detection with Fully Cross-Transformer

Han¹,

Ma²,

Huang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Few-shot object detection (FSOD), with the aim to detect novel objects using very few training examples, has recently attracted great research interest in the community. Metriclearning based methods have been demonstrated to be effective for this task using a two-branch based siamese network, and calculate the similarity between image regions and fewshot examples for detection. However, in previous works, the interaction between the two branches is only restricted in the detection head, while leaving the remaining hundreds of layers for separate feature extraction. Inspired by the recent work on vision transformers and vision-language transformers, we propose a novel Fully Cross-Transformer based model (FCT) for FSOD by incorporating cross-transformer into both the feature backbone and detection head. The asymmetric-batched cross-attention is proposed to aggregate the key information from the two branches with different batch sizes. Our model can improve the few-shot similarity learning between the two branches by introducing the multilevel interactions. Comprehensive experiments on both PAS-CAL VOC and MSCOCO FSOD benchmarks demonstrate the effectiveness of our model.

show abstract

Section: Related Workmentioning

confidence: 99%

Few-Shot Object Detection with Fully Cross-Transformer

Han¹,

Ma²,

Huang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently deep learning [17,11] based methods have dominated the SOTA of object detection. They can be roughly grouped into proposal based methods [24,10,7,9] and proposal-free methods [23,20,8,27]. Our method is mainly inspired by the first kind as the goal of this paper is to push the limit of detection accuracy, which is still the top priority for FSOD, and these proposal based methods usually have higher accuracy.…”

Section: Related Workmentioning

confidence: 99%

Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment

Han¹,

Huang²,

Ma³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Few-shot object detection (FSOD) aims to detect objects using only few examples. It's critically needed for many practical applications but so far remains challenging. We propose a meta-learning based few-shot object detection method by transferring meta-knowledge learned from data-abundant base classes to data-scarce novel classes. Our method incorporates a coarse-to-fine approach into the proposal based object detection framework and integrates prototype based classifiers into both the proposal generation and classification stages. To improve proposal generation for few-shot novel classes, we propose to learn a lightweight matching network to measure the similarity between each spatial position in the query image feature map and spatially-pooled class features, instead of the traditional object/nonobject classifier, thus generating category-specific proposals and improving proposal recall for novel classes. To address the spatial misalignment between generated proposals and fewshot class examples, we propose a novel attentive feature alignment method, thus improving the performance of fewshot object detection. Meanwhile we jointly learn a Faster R-CNN detection head for base classes. Extensive experiments conducted on multiple FSOD benchmarks show our proposed approach achieves state of the art results under (incremental) few-shot learning settings.

show abstract

“…The object detection module considers the refined anchors as input from the anchor refinement module to improve the multi-class label. Furlán et al adapted the method of a single-shot-detector (SSD) network to detect rocks in planetary images [21]. The limitation observed in RefineDet 512 [20] is that as it is a two-step cascaded process, real-time detection is slow.…”

Section: Refinedet512mentioning

confidence: 99%

An Efficient Deep Convolutional Neural Network Approach for Object Detection and Recognition Using a Multi-Scale Anchor Box in Real-Time

2021

View full text Add to dashboard Cite

Deep learning is a relatively new branch of machine learning in which computers are taught to recognize patterns in massive volumes of data. It primarily describes learning at various levels of representation, which aids in understanding data that includes text, voice, and visuals. Convolutional neural networks have been used to solve challenges in computer vision, including object identification, image classification, semantic segmentation and a lot more. Object detection in videos involves confirming the presence of the object in the image or video and then locating it accurately for recognition. In the video, modelling techniques suffer from high computation and memory costs, which may decrease performance measures such as accuracy and efficiency to identify the object accurately in real-time. The current object detection technique based on a deep convolution neural network requires executing multilevel convolution and pooling operations on the entire image to extract deep semantic properties from it. For large objects, detection models can provide superior results; however, those models fail to detect the varying size of the objects that have low resolution and are greatly influenced by noise because the features after the repeated convolution operations of existing models do not fully represent the essential characteristics of the objects in real-time. With the help of a multi-scale anchor box, the proposed approach reported in this paper enhances the detection accuracy by extracting features at multiple convolution levels of the object. The major contribution of this paper is to design a model to understand better the parameters and the hyper-parameters which affect the detection and the recognition of objects of varying sizes and shapes, and to achieve real-time object detection and recognition speeds by improving accuracy. The proposed model has achieved 84.49 mAP on the test set of the Pascal VOC-2007 dataset at 11 FPS, which is comparatively better than other real-time object detection models.

show abstract

Single shot object detection with top-down refinement

Cited by 16 publications

References 5 publications

Few-Shot Object Detection with Fully Cross-Transformer

Few-Shot Object Detection with Fully Cross-Transformer

Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment

An Efficient Deep Convolutional Neural Network Approach for Object Detection and Recognition Using a Multi-Scale Anchor Box in Real-Time

Contact Info

Product

Resources

About