CV/ML Reading

• Personal reading and summarizing the important ideas of CV/ML papers

---

Deep Learning Related

1. Xception: Deep Learning with Depthwise Separable Convolutions
2. Improved Techniques for Training GANs
3. Image-to-Image Translation With Conditional Adversarial Networks
4. RefineNet Multi-path refinement networks with identity mappings for high resolution semantic segmentation

---

Computer Vision Related

1. [Photo-Realistic Single ImageSuper-Resolution Using a Generative Adversarial Network] (https://github.com/seungwooYoo/TreasuredWritingCVMLPapers/blob/master/notes/photo-realistic_single_image_super_resoultion_using_a_generative_adversarial_network.md)
2. Speed/accuracy trade-offs for modern convolutional object detectors

---

Miscellaneous