Table 2 Summary of state-of-the-art methods. See Sect. 3 for more detailed description
From: A survey of deep learning methods for density estimation and crowd counting
Methods | Year&Venue | Network architecture | Reference manner | Supervision form | Learning paradigm | Supervision level |
|---|---|---|---|---|---|---|
Fu et al. [54] | 2015 EAAI | Basic | Patch-based | Fully-Sup. | STL | Instance level |
Wang et al. [53] | 2015 ACMMM | Basic | Patch-based | Fully-Sup. | STL | Instance level |
Cross scene [55] | 2015 CVPR | Basic | Patch-based | Fully-Sup. | MTL | Instance level |
MCNN [1] | 2016 CVPR | Multi-column | Whole image-based | Fully-Sup. | STL | Instance level |
Crowdnet [3] | 2016 ACMMM | Multi-column | Patch-based | Fully-Sup. | STL | Instance level |
CNN-Boosting [15] | 2016 ECCV | Basic | Patch-based | Fully-Sup. | STL | Instance level |
Hydra-CNN [2] | 2016 ECCV | Multi-column | Patch-based | Fully-Sup. | MTL | Instance level |
Shang et al. [82] | 2016 ECCV | Multi-column | Whole image-based | Fully-Sup. | STL | Instance level |
CMTL [56] | 2017 AVSS | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
Switching CNN [5] | 2017 CVPR | Multi-column | Patch-based | Fully-Sup. | MTL | Instance level |
CP-CNN [6] | 2017 ICCV | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
D-ConvNet [83] | 2018 CVPR | Single-column | Whole image-based | Filly-Sup. | STL | Instance level |
CSRNet [12] | 2018 CVPR | Single-column | Whole image-based | Fully-Sup. | STL | Instance level |
DRSAN [84] | 2018 IJCAI | Multi-column | Whole image-based | Fully-Sup. | STL | Instance level |
DecideNet [7] | 2018 CVPR | Multi-column | Patch-based | Fully-Sup. | MTL | Instance level |
SaCNN [9] | 2018 WACV | Single column | Whole image-based | Fully-Sup. | MTL | Instance level |
SACNN [11] | 2018 ECCV | Single column | Patch-based | Fully-Sup. | MTL | Instance level |
IG-CNN [85] | 2018 CVPR | Multi-column | Patch-based | Fully-Sup. | MTL | Instance level |
ic-CNN [86] | 2018 ECCV | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
ACSCP [87] | 2018 CVPR | Multi-column | Patch-based | Fully-Sup. | MTL | Instance level |
NetVLAD [88] | 2018 TII | Single-column | Whole image-based | Fully-Sup. | MTL | Instance level |
CL [89] | 2018 ECCV | Single-column | Patch-based | Fully-Sup. | MTL | Instance level |
L2R [90] | 2018 CVPR | Basic | Whole image-based | Self-Sup. | MTL | – |
GAN-MTR [91] | 2018 WACV | Basic | Whole image-based | Semi-Sup. | MTL | – |
PaDNet [92] | 2019 TIP | Single-column | Patch-based | Fully-Sup. | STL | Instance level |
ASD [93] | 2019 ICASSP | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
SPN [94] | 2019 WACV | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
SR-GAN [95] | 2019 CVIU | Basic | Whole image-based | Semi-Sup. | MTL | – |
ADCrowdnet [96] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
SAAN [8] | 2019 WACV | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
SAA-Net [13] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | MTL | Instance level |
SFCN\(\dag ^2\) [97] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
SE Cycle GAN [97] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
PACNN [98] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
CAN&ECAN [99] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
CFF [100] | 2019 ICCV | Single-column | Whole image-based | Fully-Sup. | MTL | Instance level |
PCC Net [101] | 2019 TCSVT | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
SFANet [102] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | MTL | Instance level |
W-Net [103] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
SL2R [104] | 2019 CVPR | Basic | Whole image-based | Self-Sup. | MTL | – |
TEDnet [105] | 2019 CVPR | Single column | Whole image-based | Fully-Sup. | STL | Instance level |
RReg [106] | 2019 CVPR | Multi-column | Whole image-based | Fully-Sup. | STL | Instance level |
RAZNet [107] | 2019 CVPR | Multi-column | Whole image-based | Fully-Sup. | MTL | Instance level |
AT-CNN [108] | 2019 CVPR | Single-column | Whole image-based | Fully-Sup. | MTL | Instance level |
GWTA-CCNN [109] | 2019 AAAI | Single column | Patch-based | Un-Sup. | STL | – |
HA-CCN [110] | 2019 TIP | Single column | Whole image-based | Fully-Sup./Weak-Sup. | STL | Instance/Image level |
L2SM [111] | 2019 ICCV | Single column | Patch-based | Fully-Sup. | STL | Instance level |
RANet [112] | 2019 ICCV | Multi-column | Whole image-based | Fully-Sup. | STL | Instance level |
McML [113] | 2019 ACM MM | Multi-column | Whole image-based | Fully-Sup. | STL | Instance level |
ILC [114] | 2019 CVPR | Multi-column | Whole image-based | Fully-Sup. | MTL | Image level |
GPIL [115] | 2020 ECCV | Single-column | Whole image-based | Semi-Sup. | STL | – |
IRAST [116] | 2020 ECCV | Single-column | Whole image-based | Semi-Sup. | MTL | – |
LibraNet [117] | 2020 ECCV | Single-column | Patch-based | Fully-Sup. | STL | Instance level |