Hao GaoA short note on “Semantically-Guided Representation Learning for Self-Supervised Monocular Depth”Paper: https://arxiv.org/abs/2002.123191 min read·Jun 22, 2020----
Hao GaoA short note on “Pixel-Adaptive Convolutional Neural Networks”Office Paper and Code: https://github.com/NVlabs/pacnet2 min read·Jun 17, 2020----
Hao GaoNotes on tracking algorithms SORT and DeepSortEssentially, sort uses kalman filter for object tracking without using ego-motion information. The correction information is from…1 min read·Sep 10, 2019----
Hao GaoAn Explanation of Discretized Logistic Mixture LikelihoodDiscretized logistic mixture likelyhood is used in PixelCNN++ and WaveNet to predict discrete values. Logistic here is from logistic…3 min read·Jul 23, 2019--1--1
Hao GaoVarational Auto-EncoderAuto-Encoder is a class of generative models, which tries to compute hidden states from training examples, and generates new examples from…2 min read·Jul 10, 2019----
Hao GaoMobilenet Based Single Short Multi-box Detector in Pytorch, ONNX and Caffe2This is a brief note on how to change VGG net based SSD to Mobilenet based SSD. For the implemenatation, please check this repo. For the…2 min read·Jul 24, 2018--2--2
Hao GaoUnderstand Single Shot MultiBox Detector (SSD) and Implement It in PytorchSSD (Single Shot MultiBox Detector) is a popular algorithm in object detection. It’s generally faster than Faster RCNN. In this post, I…6 min read·Jun 6, 2018--20--20
Hao GaoCurriculum Learning & Multiple Stage LearningCurriculum learning is borrowed from the human education system. In our education system, we present students easier concepts first and…1 min read·May 7, 2018----
Hao GaoNotes on Focal Loss and RetinaNetRetinaNet[1] is a one-stage object detector (like SSD and YOLO), which has the performance of two-stage detectors (like Faster-RCNN). The…2 min read·Jan 25, 2018----