%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 ] /Type /Pages /Count 9 >> 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 (2015) /EventType (Spotlight) /Description-Abstract (Convolutional Neural Networks define an exceptionallypowerful class of model\054 but are still limited by the lack of abilityto be spatially invariant to the input data in a computationally and parameterefficient manner\056 In this work we introduce a new learnable module\054 theSpatial Transformer\054 which explicitly allows the spatial manipulation ofdata within the network\056 This differentiable module can be insertedinto existing convolutional architectures\054 giving neural networks the ability toactively spatially transform feature maps\054 conditional on the feature map itself\054without any extra training supervision or modification to the optimisation process\056 We show that the useof spatial transformers results in models which learn invariance to translation\054scale\054 rotation and more generic warping\054 resulting in state\055of\055the\055artperformance on several benchmarks\054 and for a numberof classes of transformations\056) /Producer (PyPDF2) /Title (Spatial Transformer Networks) /Date (2015) /ModDate (D\07220151218143941\05508\04700\047) /Published (2015) /Type (Conference Proceedings) /firstpage (2008) /Book (Advances in Neural Information Processing Systems 28) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (C\056 Cortes and N\056D\056 Lawrence and D\056D\056 Lee and M\056 Sugiyama and R\056 Garnett and R\056 Garnett) /Author (Max Jaderberg\054 Karen Simonyan\054 Andrew Zisserman\054 koray kavukcuoglu) /lastpage (2016) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 13 0 R /Parent 1 0 R /Resources 14 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 40 0 R 41 0 R 42 0 R ] /Type /Page >> endobj 5 0 obj << /Contents 43 0 R /Parent 1 0 R /Resources 44 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 69 0 R 70 0 R 71 0 R 72 0 R 73 0 R 74 0 R 75 0 R 76 0 R 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 97 0 R 98 0 R 99 0 R 100 0 R 101 0 R ] /Type /Page >> endobj 6 0 obj << /Contents 102 0 R /Parent 1 0 R /Resources 103 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 215 0 R 216 0 R 217 0 R 218 0 R 219 0 R 220 0 R 221 0 R 222 0 R 223 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 224 0 R /Parent 1 0 R /Resources 225 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 228 0 R 229 0 R 230 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 231 0 R /Parent 1 0 R /Resources 232 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 237 0 R 238 0 R 239 0 R 240 0 R 241 0 R 242 0 R 243 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 244 0 R /Parent 1 0 R /Resources 245 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 284 0 R 285 0 R 286 0 R 287 0 R 288 0 R 289 0 R 290 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 291 0 R /Parent 1 0 R /Resources 292 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 329 0 R 330 0 R 331 0 R 332 0 R 333 0 R 334 0 R 335 0 R 336 0 R 337 0 R 338 0 R 339 0 R 340 0 R 341 0 R 342 0 R 343 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 344 0 R /Parent 1 0 R /Resources 345 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 399 0 R 400 0 R 401 0 R 402 0 R 403 0 R 404 0 R 405 0 R 406 0 R 407 0 R 408 0 R 409 0 R 410 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 411 0 R /Parent 1 0 R /Type /Page /Resources 412 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 3051 /Filter /FlateDecode >> stream xڍْ}TՈ?^o?RW?$2AzV?p"F7Zsv|C ٶ