%PDF-1.3 1 0 obj << /Kids [ 4 0 R 5 0 R 6 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R 13 0 R 14 0 R ] /Type /Pages /Count 11 >> endobj 2 0 obj << /Subject (Neural Information Processing Systems http\072\057\057nips\056cc\057) /Publisher (Curran Associates\054 Inc\056) /Language (en\055US) /Created (2019) /EventType (Poster) /Description-Abstract (Deep neural networks \050DNNs\051 excel at learning representations when trained on large\055scale datasets\056 Pre\055trained DNNs also show strong transferability when fine\055tuned to other labeled datasets\056 However\054 such transferability becomes weak when the target dataset is fully unlabeled as in Unsupervised Domain Adaptation \050UDA\051\056 We envision that the loss of transferability may stem from the intrinsic limitation of the architecture design of DNNs\056 In this paper\054 we delve into the components of DNN architectures and propose Transferable Normalization \050TransNorm\051 in place of existing normalization techniques\056 TransNorm is an end\055to\055end trainable layer to make DNNs more transferable across domains\056 As a general method\054 TransNorm can be easily applied to various deep neural networks and domain adaption methods\054 without introducing any extra hyper\055parameters or learnable parameters\056 Empirical results justify that TransNorm not only improves classification accuracies but also accelerates convergence for mainstream DNN\055based domain adaptation methods\056) /Producer (PyPDF2) /Title (Transferable Normalization\072 Towards Improving Transferability of Deep Neural Networks) /Date (2019) /ModDate (D\07220200212220306\05508\04700\047) /Published (2019) /Type (Conference Proceedings) /firstpage (1953) /Book (Advances in Neural Information Processing Systems 32) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (H\056 Wallach and H\056 Larochelle and A\056 Beygelzimer and F\056 d\047Alch\351\055Buc and E\056 Fox and R\056 Garnett) /Author (Ximei Wang\054 Ying Jin\054 Mingsheng Long\054 Jianmin Wang\054 Michael I\056 Jordan) /lastpage (1963) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 15 0 R /Parent 1 0 R /Resources 16 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 47 0 R 48 0 R 49 0 R 50 0 R 51 0 R 52 0 R 53 0 R 54 0 R 55 0 R 56 0 R 57 0 R 58 0 R 59 0 R 60 0 R 61 0 R 62 0 R 63 0 R 64 0 R 65 0 R 66 0 R 67 0 R 68 0 R 69 0 R 70 0 R ] /Type /Page >> endobj 5 0 obj << /Contents 71 0 R /Parent 1 0 R /Resources 72 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 77 0 R 78 0 R 79 0 R 80 0 R 81 0 R 82 0 R 83 0 R 84 0 R 85 0 R 86 0 R 87 0 R 88 0 R 89 0 R 90 0 R 91 0 R 92 0 R 93 0 R 94 0 R 95 0 R 96 0 R ] /Type /Page >> endobj 6 0 obj << /Contents 97 0 R /Parent 1 0 R /Resources 98 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 123 0 R 124 0 R 125 0 R 126 0 R 127 0 R 128 0 R 129 0 R 130 0 R 131 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 132 0 R /Parent 1 0 R /Resources 133 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 151 0 R 152 0 R 153 0 R 154 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 155 0 R /Parent 1 0 R /Resources 156 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 169 0 R 170 0 R 171 0 R 172 0 R 173 0 R 174 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 175 0 R /Parent 1 0 R /Resources 176 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 229 0 R 230 0 R 231 0 R 232 0 R 233 0 R 234 0 R 235 0 R 236 0 R 237 0 R 238 0 R 239 0 R 240 0 R 241 0 R 242 0 R 243 0 R 244 0 R 245 0 R 246 0 R 247 0 R 248 0 R 249 0 R 250 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 251 0 R /Parent 1 0 R /Resources 252 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 253 0 R 254 0 R 255 0 R 256 0 R 257 0 R 258 0 R 259 0 R 260 0 R 261 0 R 262 0 R 263 0 R 264 0 R 265 0 R 266 0 R 267 0 R 268 0 R 269 0 R 270 0 R 271 0 R 272 0 R 273 0 R 274 0 R 275 0 R 276 0 R 277 0 R 278 0 R 279 0 R 280 0 R 281 0 R 282 0 R 283 0 R 284 0 R 285 0 R 286 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 287 0 R /Parent 1 0 R /Resources 288 0 R /Group 360 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 426 0 R 427 0 R 428 0 R 429 0 R 430 0 R 431 0 R 432 0 R 433 0 R 434 0 R 435 0 R 436 0 R 437 0 R 438 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 439 0 R /Parent 1 0 R /Resources 440 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 534 0 R 535 0 R 536 0 R 537 0 R 538 0 R 539 0 R ] /Type /Page >> endobj 13 0 obj << /Contents 540 0 R /Parent 1 0 R /Type /Page /Resources 541 0 R /MediaBox [ 0 0 612 792 ] >> endobj 14 0 obj << /Contents 542 0 R /Parent 1 0 R /Type /Page /Resources 543 0 R /MediaBox [ 0 0 612 792 ] >> endobj 15 0 obj << /Length 3579 /Filter /FlateDecode >> stream xڥZے}߯#U5oy+rvqR