![]() Huang, H., Huang, Q., Krähenbühl, P.: Domain transfer through deep activation matching. ![]() Hoffman, J., et al.: C圜ADA: cycle-consistent adversarial domain adaptation. Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Hernandez-Juarez, D., et al.: Slanted stixels: representing San Francisco’s steepest streets. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. IJCV 88, 303–338 (2010)įelzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IJCV 111, 98–136 (2015)Įveringham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes (VOC) challenge. In: CoRL (2017)Įveringham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. ![]() In: ICLR (2017)ĭosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: NeurIPS (2019)ĭosovitskiy, A., Koltun, V.: Learning to act by predicting the future. In: CVPR (2009)ĭoersch, C., Zisserman, A.: Sim2real transfer learning for 3D human pose estimation: motion to the rescue. In: CVPR (2016)ĭeng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. arXiv preprint arXiv:1706.05587 (2017)Ĭordts, M., et al.: The Cityscapes dataset for semantic urban scene understanding. In: CoRL (2019)Ĭhen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1903.11027 (2019)Ĭhen, D., Zhou, B., Koltun, V., Krähenbühl, P.: Learning by cheating. In: RSS (2019)Ĭaesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. ![]() arXiv preprint arXiv:1910.07113 (2019)īansal, M., Krizhevsky, A., Ogale, A.: ChauffeurNet: learning to drive by imitating the best and synthesizing the worst. KeywordsĪkkaya, I., et al.: Solving Rubik’s cube with a robot hand. Furthermore, it shows promising results on standard domain adaptation benchmarks. Our method can successfully transfer navigation policies between drastically different simulators: ViZDoom, SuperTuxKart, and CARLA. We use these recognition datasets to link up a source and target domain to transfer models between them in a task distillation framework. They exist in any interesting domain, simulated or real, and are easy to label and extend. Our core observation is that for certain tasks, such as image recognition, datasets are plentiful. However, this transfer is challenging since simulated and real-world visual experiences vary dramatically. The commonly prescribed solution is simple: learn a representation in simulation and transfer it to the real world. Repeatedly crashing a car into a tree is simply too expensive. Unfortunately, tasks like autonomous driving have virtually no real-world training data. Please note that the promotional version of this map (the one with the brown paper background) is not included in this commercial use license and the text and name of the map are NOT released under this license, and cannot be used in conjunction with this map in a commercial project.Deep networks devour millions of precisely annotated images to build their complex and powerful representations. ![]() Each month while funding is over the $300 mark, each map that achieves the $300+ funding level will be released under this free commercial license. You can use, reuse, remix and/or modify the maps that are being published under this commercial license on a royalty-free basis as long as they include attribution (“Cartography by Dyson Logos” or “Maps by Dyson Logos”). Over 500 amazingly generous people have come together to fund the site and these maps, making them free for your use.īecause of the incredible generosity of my patrons, I’m able to make these maps free for commercial use also. This map is made available to you under a free license for personal or commercial use thanks to the awesome supporters of my Patreon Campaign. ![]()
0 Comments
Leave a Reply. |