上一页 1 ··· 17 18 19 20 21 22 23 24 25 ··· 36 下一页
摘要: Rade R. and Moosavi-Dezfooli S. Helper-based adversarial training: reducing excessive margin to achieve a better accuracy vs. robustness trade-off. In 阅读全文
posted @ 2021-11-10 16:12 馒头and花卷 阅读(530) 评论(0) 推荐(0)
摘要: Zhang J., Xu X., Han B., Niu G., Cui L., Sugiyama M., Kankanhalli M. Attacks which do not kill training make adversarial learning stronger. In Interna 阅读全文
posted @ 2021-11-09 19:01 馒头and花卷 阅读(367) 评论(0) 推荐(0)
摘要: Andriushchenko M. and Flammarion N. Understanding and improving fast adversarial training. In Advances in Neural Information Processing Systems (NIPS) 阅读全文
posted @ 2021-10-23 16:41 馒头and花卷 阅读(190) 评论(0) 推荐(0)
摘要: Mildenhall B., Srinivasan P. P., Tancik M., Barron J. T., Ramamoorthi R. and Ng R. NeRF: representing scenes as neural radiance fields for view synthe 阅读全文
posted @ 2021-10-10 15:53 馒头and花卷 阅读(161) 评论(0) 推荐(0)
摘要: Sitzmann V., Martel J. N. P., Bergman A. W., Lindell D. B., Wetzstein G. Implicit neural representations with periodic activation functions. Advances 阅读全文
posted @ 2021-10-07 16:49 馒头and花卷 阅读(218) 评论(0) 推荐(0)
摘要: Martins P., Marinho Z. and Martins A. \(\infty\)-former: Infinite Memory Transformer. arXiv preprint arXiv:2109.00301, 2021. 概 在transformer中引入一种长期记忆机制 阅读全文
posted @ 2021-09-26 20:23 馒头and花卷 阅读(159) 评论(0) 推荐(0)
摘要: Shi J. and Malik J. Normalized cuts and image segmentation. In IEEE Transactions on Pattern Analysis and Machine Intelligence. 概 在Digital Image Prepro 阅读全文
posted @ 2021-09-18 18:20 馒头and花卷 阅读(796) 评论(0) 推荐(0)
摘要: Hyv"{a}rinen A. Estimation of Non-Normalized Statistical Models by Score Matching. Journal of Machine Learning Research, 2005. 概 我们常常会建模如下的概率模型: \[ p( 阅读全文
posted @ 2021-09-18 16:22 馒头and花卷 阅读(1188) 评论(0) 推荐(0)
摘要: Gonzalez R. C. and Woods R. E. Digital Image Processing (Forth Edition). 单个像素的意义其实很小, 于是有了superpixel的概念, 即一簇pixels的集合(且这堆pixels共用一个值), 这会导致图片有非常有趣的艺术风 阅读全文
posted @ 2021-09-17 20:46 馒头and花卷 阅读(434) 评论(0) 推荐(0)
摘要: 本来想偷懒不记录的, 但是这个Hough Transform实在是有趣. 通过Canny算法等将edge的大体部分检测了出来, 但是往往这些检测出来的点并不是连续的, 那么怎么才能将这些点合理地连接在一起呢? 这个Hough Transform就可以做到这一点. 首先需要明确的一点是, 我们应该将怎 阅读全文
posted @ 2021-09-16 20:37 馒头and花卷 阅读(85) 评论(0) 推荐(0)
摘要: Kernel Density (KD) Feinman R., Curtin R. R., Shintre S. and Gardner A. B. Detecting Adversarial Samples from Artifacts. arXiv preprint arXiv:1703.004 阅读全文
posted @ 2021-09-10 17:08 馒头and花卷 阅读(133) 评论(0) 推荐(0)
摘要: Gonzalez R. C. and Woods R. E. Digital Image Processing (Forth Edition) 符号 即 操作 说明 \(\ominus\) erosion \(\{z:(B)_z \subset A\}\) Erodes the boundary o 阅读全文
posted @ 2021-09-05 17:11 馒头and花卷 阅读(489) 评论(0) 推荐(0)
摘要: [TOC] ## Linux [Linux-命令-Lucifer三思而后行](https://blog.csdn.net/m0_50546016/article/details/119984255?utm_medium=distribute.pc_feed_v2.none-task-blog-hot 阅读全文
posted @ 2021-09-01 18:10 馒头and花卷 阅读(48) 评论(0) 推荐(0)
摘要: Pang T., Zhang H., He D., Dong Y., Su H., Chen W., Zhu J., Liu T. Adversarial training with rectified rejection. arXiv Preprint, arXiv: 2105.14785, 20 阅读全文
posted @ 2021-08-31 21:07 馒头and花卷 阅读(64) 评论(0) 推荐(0)
摘要: Sermanet P., Eigen D., Zhang X., Mathieu M., Fergus R., LeCun Y. OverFeat:integrated recognition, localization and detection using convolutional netwo 阅读全文
posted @ 2021-08-30 19:49 馒头and花卷 阅读(67) 评论(0) 推荐(0)
摘要: Fourier Transform 基本的定义 严格来说, 傅里叶变换是Schwartz space 上的一一映射, 对于$L^1$, 即可积函数我们都可以找到其对应的傅里叶变换. 符号 定义 傅里叶变换: \(\hat{f}(u)\) \(\int_{-\infty}^{+\infty} f(t) 阅读全文
posted @ 2021-08-24 23:42 馒头and花卷 阅读(387) 评论(0) 推荐(0)
摘要: Gonzalez R. C. and Woods R. E. Digital Image Processing (Forth Edition) Coding Redundancy 假设一个图片$f(x, y)$其大小为$M \times N$, 我们可以估计其密度函数: \[ p_r (r_k) = 阅读全文
posted @ 2021-08-18 17:23 馒头and花卷 阅读(434) 评论(0) 推荐(0)
摘要: 目标 首先, 既然是变换, 那么就是从一个域到另一个域, 即如下: \[ f(x) = \sum_k c_{j_0} (k) \varphi_{j_0, k} (x) + \sum_{j=j_0}^{\infty} \sum_k d_j (k) \psi_{j, k}(x), \\ c_{j_0} 阅读全文
posted @ 2021-08-09 22:16 馒头and花卷 阅读(73) 评论(0) 推荐(0)
摘要: Gonzalez R. C. and Woods R. E. Digital Image Processing (Forth Edition) 基本 酉变换 一维的变换: \[ \mathbf{t} = \mathbf{A} \mathbf{f}, \\ \mathbf{f} = \mathbf{A 阅读全文
posted @ 2021-08-04 22:59 馒头and花卷 阅读(180) 评论(0) 推荐(0)
摘要: Gonzalez R. C. and Woods R. E. Digital Image Processing (Forth Edition) 基本 酉变换 一维的变换: \[ \mathbf{t} = \mathbf{A} \mathbf{f}, \\ \mathbf{f} = \mathbf{A 阅读全文
posted @ 2021-08-04 10:56 馒头and花卷 阅读(655) 评论(0) 推荐(0)
上一页 1 ··· 17 18 19 20 21 22 23 24 25 ··· 36 下一页