文献紹介:SegFormer: Simple and Efficient Design for Semantic Segmentation with Tr...Toru Tamaki
Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo, SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
https://proceedings.neurips.cc/paper/2021/hash/64f1f27bf1b4ec22924fd0acb550c235-Abstract.html
https://arxiv.org/abs/2105.15203
文献紹介:Selective Feature Compression for Efficient Activity Recognition InferenceToru Tamaki
Chunhui Liu, Xinyu Li, Hao Chen, Davide Modolo, Joseph Tighe; Selective Feature Compression for Efficient Activity Recognition Inference, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13628-13637
https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Selective_Feature_Compression_for_Efficient_Activity_Recognition_Inference_ICCV_2021_paper.html
文献紹介:SegFormer: Simple and Efficient Design for Semantic Segmentation with Tr...Toru Tamaki
Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo, SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
https://proceedings.neurips.cc/paper/2021/hash/64f1f27bf1b4ec22924fd0acb550c235-Abstract.html
https://arxiv.org/abs/2105.15203
文献紹介:Selective Feature Compression for Efficient Activity Recognition InferenceToru Tamaki
Chunhui Liu, Xinyu Li, Hao Chen, Davide Modolo, Joseph Tighe; Selective Feature Compression for Efficient Activity Recognition Inference, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13628-13637
https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Selective_Feature_Compression_for_Efficient_Activity_Recognition_Inference_ICCV_2021_paper.html
Design Method of Directional GenLOT with Trend Vanishing MomentsShogo Muramatsu
Proc. of Proc. of Asia Pacific Signal and Information Proc. Assoc. Annual Summit and Conf. (APSIPA ASC), pp.692-701, Biopolis, Singapore, Dec. 14 – 17, 2010
Design Method of Directional GenLOT with Trend Vanishing MomentsShogo Muramatsu
Proc. of Proc. of Asia Pacific Signal and Information Proc. Assoc. Annual Summit and Conf. (APSIPA ASC), pp.692-701, Biopolis, Singapore, Dec. 14 – 17, 2010
12. シミュレーション結果
PSNR, SSIM,処理時間
地域 先端技術セミナーICT 122018/3/29
TIP 14 S P IC 15 D S P 16 P roposed TIP 14 S P IC 15 D S P 16 P roposed TIP 14 S P IC 15 D S P 16 P roposed
Tex1 32.60 32.70 32.70 33.03 0.9265 0.9275 0.9275 0.9328 19.44 9.20 243.46 5.81
Tex2 33.74 33.84 34.07 34.64 0.9419 0.9436 0.9436 0.9469 23.62 10.83 151.95 7.05
Tex3 24.03 23.30 23.50 23.57 0.9149 0.9163 0.9203 0.9267 60.61 29.67 593.74 19.39
Tex4 24.55 24.65 24.75 25.12 0.9173 0.9124 0.9185 0.9246 34.33 16.41 358.48 10.89
Tex5 25.82 26.01 25.94 26.23 0.8891 0.8915 0.8991 0.8997 24.17 11.48 247.34 7.52
Tex6 31.85 31.93 31.75 32.24 0.8952 0.8920 0.8982 0.9040 34.75 17.25 413.20 10.57
Tex7 31.38 31.75 32.09 32.27 0.9383 0.9396 0.9398 0.9464 42.65 21.50 525.67 13.98
Tex8 26.23 26.42 26.52 26.77 0.8627 0.8655 0.8698 0.8769 17.25 8.11 210.01 5.44
Tex9 17.24 17.81 17.81 18.28 0.8728 0.8769 0.8769 0.8853 18.63 8.73 223.54 5.81
Tex10 35.02 35.49 35.49 36.20 0.9574 0.9582 0.9588 0.9642 11.74 5.16 135.62 4.54
P S N R [dB ] S S IM Tim es[s]
Im age
[TIP14] T. Peleg and M. Elad, “A statistical prediction model based on sparse representations for single image super-
resolution,” IEEE Trans. Image Process., vol. 23, no. 6, pp. 2569-2582, Jun. 2014.
[SPIC15] H. Lakshman et al. “Image interpolation using Shearlet based iterative refinement,” Signal Processing:
Image Comm., vol. 36, pp. 83-94, Aug. 2015.
[DSP16] D. Sun et al. “Image interpolation via collaging its non-local patches,” Digital Signal Process., vol. 49, pp. 33-
43, Feb. 2016.