StairNet: Top-Down Semantic Aggregation for Accurate One Shot Detection
By Sanghyun Woo, Soonmin Hwang, In-So Kweon. 2017
101 citations recorded by the source corpus.
One-stage object detectors such as SSD or YOLO already have shown promising accuracy with small memory footprint and fast speed. However, it is widely recognized that one-stage detectors have difficulty in detecting small objects while they are competitive with two-stage methods on large objects. In this paper, we investigate how to alleviate this problem starting from the SSD framework. Due to their pyramidal design, the lower layer that is responsible for small objects lacks strong semantics(e.g contextual information). We address this problem by introducing a feature combining module that spreads out the strong semantics in a top-down manner. Our final model StairNet detector unifies the multi-scale representations and semantic distribution effectively. Experiments on PASCAL VOC 2007 and PASCAL VOC 2012 datasets demonstrate that Stair-Net significantly improves the weakness of SSD and outperforms the other state-of-the-art one-stage detectors.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Xiaogang Wang
- Quoc V. Le
- Wanli Ouyang
- Tsung-Yi Lin
- Jiashi Feng
- Golnaz Ghiasi
- In-So Kweon
- Dacheng Tao
In Computer Vision and Pattern Recognition
- Xiaogang Wang
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Yi Yang
- Jiashi Feng
- Chunhua Shen
- Alan L. Yuille
Citations in the corpus
- BAM: Bottleneck Attention Module (2018, methodology): “…mAP@.75 mAP@[.5,.95] ResNet101[15] 48 (a) MS-COCO detection task BackBone Detector mAP@.5 params(M) VGG16[40] SSD [33] 77.8 26.5 VGG16[40] StairNet [39] 78.9 32.0 VGG16[40] StairNet [39] + BAM 79.3 32.1 MobileNet[18] SSD [33] 68.1 5.81 MobileNet[18] StairNet [39] 70.1 5.98 MobileNet[18] notable…”
- NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019, background): “Many recent works [7, 16, 17, 34, 38, 39, 40, 43, 41] propose various crossscale connections or operations to combine features to gen-”
- CBAM: Convolutional Block Attention Module (2018, methodology): “We adopt the StairNet [30] detection framework and apply SE and CBAM to the detectors.”
- Deep Feature Pyramid Reconfiguration for Object Detection (2018, background): “Several works are trying to develop more suitable connection manners [25,46,48], or to add more operations before combination [28].”
- Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, unknown): “[87]proposedStairNetwheredeconvolution wasexploitedtoenlargethefeaturemap,suchlearning-based up-samplingfunctioncanachieveamorerefinedfeaturethan naivekernel-basedup-samplingandallowsthattheinformation ofdifferentpyramidlevelspropagatesmoreefficiently[88].”
- Deep Learning for Generic Object Detection: A Survey (2018, methodology): “12), Scale Transfer Detection Network (STDN) [246], RefineDet [239] and StairNet [217], as shown in Table 3 and contrasted in Fig.”
- Object Detection in 20 Years: A Survey (2019, methodology): “element-wise product, and 3) concatenation, as shown in Fig. 18 (c)-(e). The element-wise sum is the easiest way to perform feature fusion. It has been frequently used in many recent object detectors [22, 55, 241, 243, 246]. The element-wise product [245, 249–251] is very similar to the element-wise”