Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning

<div>Variation of both <svg height="9.22069pt" id="M125" style="vertical-align:-3.18151pt" version="1.1" viewbox="-0.0498162 -6.03918 10.5526 9.22069" width="10.5526pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M399 120C363 89 334 79 292 79S154 123 154 256C154 363 199 401 238 401C266 401 298 385 339 349C348 341 354 338 361 338C378 338 404 364 404 393C405 407 401 419 386 429C369 443 336 454 300 454H299C261 454 196 440 130 392C67 345 29 274 29 201C29 92 109 -12 246 -12C307 -12 372 31 418 96L399 120Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.486,3.132)"><path d="M389 0V32C297 38 291 46 291 118V635C234 613 175 595 109 583V556L161 554C203 552 207 547 207 497V118C207 46 201 38 110 32V0H389Z"></path></g></svg> and <svg height="9.22069pt" id="M126" style="vertical-align:-3.18151pt" version="1.1" viewbox="-0.0498162 -6.03918 10.5526 9.22069" width="10.5526pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M399 120C363 89 334 79 292 79S154 123 154 256C154 363 199 401 238 401C266 401 298 385 339 349C348 341 354 338 361 338C378 338 404 364 404 393C405 407 401 419 386 429C369 443 336 454 300 454H299C261 454 196 440 130 392C67 345 29 274 29 201C29 92 109 -12 246 -12C307 -12 372 31 418 96L399 120Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.486,3.132)"><path d="M414 144C384 79 371 75 317 75H135L276 221C367 316 408 376 408 465C408 570 327 635 237 635C179 635 131 609 100 575L42 494L67 471C94 510 138 565 205 565C277 565 321 517 321 435C321 348 258 270 195 195C146 137 88 81 33 26V0H411C423 44 433 88 446 135L414 144Z"></path></g></svg> with same incompressible noise <span class="nowrap"><svg height="6.089pt" id="M127" style="vertical-align:-0.04982042pt" version="1.1" viewbox="-0.0498162 -6.03918 5.90632 6.089" width="5.90632pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M410 152L393 124C355 58 321 44 251 44H187C264 179 330 297 407 428L398 442H153C114 441 100 447 92 463H70C60 419 44 357 30 308L60 295L77 328C106 384 130 399 197 399C214 399 232 399 249 399C173 265 106 147 24 16L37 0H392C404 31 420 82 439 138L410 152Z"></path></g></svg>.</span> Adjoined nine images have same <svg height="6.089pt" id="M128" style="vertical-align:-0.04982042pt" version="1.1" viewbox="-0.0498162 -6.03918 5.90632 6.089" width="5.90632pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M410 152L393 124C355 58 321 44 251 44H187C264 179 330 297 407 428L398 442H153C114 441 100 447 92 463H70C60 419 44 357 30 308L60 295L77 328C106 384 130 399 197 399C214 399 232 399 249 399C173 265 106 147 24 16L37 0H392C404 31 420 82 439 138L410 152Z"></path></g></svg> with different latent codes <svg height="9.22069pt" id="M129" style="vertical-align:-3.18151pt" version="1.1" viewbox="-0.0498162 -6.03918 10.5526 9.22069" width="10.5526pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M399 120C363 89 334 79 292 79S154 123 154 256C154 363 199 401 238 401C266 401 298 385 339 349C348 341 354 338 361 338C378 338 404 364 404 393C405 407 401 419 386 429C369 443 336 454 300 454H299C261 454 196 440 130 392C67 345 29 274 29 201C29 92 109 -12 246 -12C307 -12 372 31 418 96L399 120Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.486,3.132)"><path d="M389 0V32C297 38 291 46 291 118V635C234 613 175 595 109 583V556L161 554C203 552 207 547 207 497V118C207 46 201 38 110 32V0H389Z"></path></g></svg> and <span class="nowrap"><svg height="9.22069pt" id="M130" style="vertical-align:-3.18151pt" version="1.1" viewbox="-0.0498162 -6.03918 10.5526 9.22069" width="10.5526pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M399 120C363 89 334 79 292 79S154 123 154 256C154 363 199 401 238 401C266 401 298 385 339 349C348 341 354 338 361 338C378 338 404 364 404 393C405 407 401 419 386 429C369 443 336 454 300 454H299C261 454 196 440 130 392C67 345 29 274 29 201C29 92 109 -12 246 -12C307 -12 372 31 418 96L399 120Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.486,3.132)"><path d="M414 144C384 79 371 75 317 75H135L276 221C367 316 408 376 408 465C408 570 327 635 237 635C179 635 131 609 100 575L42 494L67 471C94 510 138 565 205 565C277 565 321 517 321 435C321 348 258 270 195 195C146 137 88 81 33 26V0H411C423 44 433 88 446 135L414 144Z"></path></g></svg>.</span> Row of the image denotes difference of <svg height="9.22069pt" id="M131" style="vertical-align:-3.18151pt" version="1.1" viewbox="-0.0498162 -6.03918 10.5526 9.22069" width="10.5526pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M399 120C363 89 334 79 292 79S154 123 154 256C154 363 199 401 238 401C266 401 298 385 339 349C348 341 354 338 361 338C378 338 404 364 404 393C405 407 401 419 386 429C369 443 336 454 300 454H299C261 454 196 440 130 392C67 345 29 274 29 201C29 92 109 -12 246 -12C307 -12 372 31 418 96L399 120Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.486,3.132)"><path d="M389 0V32C297 38 291 46 291 118V635C234 613 175 595 109 583V556L161 554C203 552 207 547 207 497V118C207 46 201 38 110 32V0H389Z"></path></g></svg> while column refers to <span class="nowrap"><svg height="9.22069pt" id="M132" style="vertical-align:-3.18151pt" version="1.1" viewbox="-0.0498162 -6.03918 10.5526 9.22069" width="10.5526pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M399 120C363 89 334 79 292 79S154 123 154 256C154 363 199 401 238 401C266 401 298 385 339 349C348 341 354 338 361 338C378 338 404 364 404 393C405 407 401 419 386 429C369 443 336 454 300 454H299C261 454 196 440 130 392C67 345 29 274 29 201C29 92 109 -12 246 -12C307 -12 372 31 418 96L399 120Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,5.486,3.132)"><path d="M414 144C384 79 371 75 317 75H135L276 221C367 316 408 376 408 465C408 570 327 635 237 635C179 635 131 609 100 575L42 494L67 471C94 510 138 565 205 565C277 565 321 517 321 435C321 348 258 270 195 195C146 137 88 81 33 26V0H411C423 44 433 88 446 135L414 144Z"></path></g></svg>.</span></div>

Computational Intelligence and Neuroscience

fig8

Figure 8

Figure 8: Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning 