Application of improved transformer based on weakly supervised in crowd localization and crowd counting

Abstract

To the problem of the complex pre-processing and post-processing to obtain head-position existing in the current crowd localization method using pseudo boundary box and pre-designed positioning map, this work proposes an end-to-end crowd localization framework named WSITrans, which reformulates the weakly-supervised crowd localization problem based on Transformer and implements crowd counting. Specifically, we first perform global maximum pooling (GMP) after each stage of pure Transformer, which can extract and retain more detail of heads. In addition, we design a binarization module that binarizes the output features of the decoder and fuses the confidence score to obtain more accurate confidence score. Finally, extensive experiments demonstrate that the proposed method achieves significant improvement on three challenging benchmarks. It is worth mentioning that the WSITrans improves F1-measure by 4.0%.

ED-DKCNN: Advancing Supervised Crowd Counting in Complex Environments

“…These results have undergone rigorous scrutiny across the test, train, and validation domains. Importantly, our proposed model, in contrast to its multi-tasked counterparts such as CMTL [78], DSSI-Net [79], SANet [60], CG-DRCN [80], MBTTBF [36], SFCN [46], DTCC [81], MCNN [24], CSRNet [33], CAN [25] operates as a single-task model. This distinction alleviates the necessity of generating density maps, resulting in a reduction of computational complexity.…”

Neural Network-Based Crowd Counting Systems: State of the Art, Challenges, and Perspectives

“…Gao and Zhao et al [53] proposed a framework for joint crowd counting and localization to increases counting accuracy. The scale adaptive module in JCCL addresses the large scale variation.…”

“…4-6. [50] 194.1 297.8 Switch CNN [67] 318.1 439.2 LR-CNN [13] 325.6 369.4 CAT-CNN [40] 235.5 324.8 CCTrans [34] 245.0 343.6 JCTNet [54] 222.9 306.5 LibraNet [62] 181.2 262.2 MLPCNN [37] 238.63 317.28 HRANet [56] 160.9 235.8 MANet [59] 240.8 311.5 AUCNN [58] 231.8 312.4 AMSNet [42] 236.5 319.2 ASANet [51] 185.5 268.3 [65] 136.26 240.83 DEAL [50] 100.1 166.5 JCTNet [37] 90 161 TransCrowd [33] 97 168 CCTrans [34] 92 158 LibraNet [62] 88.1 143.7 MLPCNN [37] 103.61 168.9 HRANet [56] 84.6 146.2 EDENet [38] 86.6 158.5 JCCL+R [53] 100 169 AUCNN [58] 112.3 195.6 AMSNet [42] 86.5 167.2 WSITrans [55] 86.5 140. From Tables II-IV and its corresponding graph Figs.…”