postgres
postgres database backup and restoring
I am relatively new to postgres and at first I was backing up and restoring databases using pgadmin4. I was just using postgres user because this is the default one that you get to use when working with pgadmin. After developing a web project using postgres, I needed to move Read more…
deep learning
paper review: “Path Aggregation Network for Instance Segmentation”
arxiv: https://arxiv.org/abs/1803.01534
key point
this paper propose a network structure(“PANet”) with bottom up path augmentation and a few other tweak methods which results in better instance segmentation performance.
(more…)deep learning
paper review: “CBAM: Convolutional Block Attention Module”
arxiv: https://arxiv.org/pdf/1807.06521.pdf
key point
trying to attach attention module to CNN. but instead of blindly attaching it which would compute a 3D attention map which is computationally expensive, this work proposes to compute spatial attention and channel attention separately which achieves a similar effect with much less parameters.
(more…)deep learning
paper review: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
arxiv: https://arxiv.org/abs/1406.4729
key points
pools a fixed number of features from final feature map of backbone which can be fed to the dense layer afterwards, thus allowing network to work in a non-fixed input size manner.
(more…)deep learning
paper review: Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
arxiv: https://arxiv.org/abs/2003.12294
key point
this approach will try to take global context into account by adopting transformer, and also use similar structure to reason semantic content.
(more…)deep learning
paper review: “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications”
arxiv: https://arxiv.org/pdf/1704.04861.pdf key points focus on optimizing for latency, small networks. use depthwise separable convolutions, to reduce computation as much as possible further reduce size of models based on width/resolution multiplier, but at the cost of accuracy depthwise separable convolution This is a combination of depthwise convonlution + pointwise convolution. Read more…
deep learning
paper review: “FastDepth: Fast Monocular Depth Estimation on Embedded Systems”
arxiv: https://arxiv.org/abs/1903.03273
key points
- model to predict depth map
- maximize speed by making it light as possible
- focus not only on encoder network but also on decoder network for speed improvement
- mobilenet for encoder, nearest-neighbor interpolation + NNConv5 for decoders, use skip connection, use depthwise separable convolution where ever possible, do network pruning, use TVM compiler stack to optimize depthwise separable convolution which is not optimized in populate DL frameworks.
deep learning
paper review:”DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks”
arxiv link: https://arxiv.org/abs/1709.08429
key points
- propse dl based VO using RCNN
- end to end approach. previous attempts used CNN for single image. this work will combine with RNN to overcome this drawback.
deep learning
paper review:”Hierarchical multi-scale attention for semantic segmentation”
arxiv: https://arxiv.org/abs/2005.10821
key points
- hierarchical attention mechanism. By using this, the model can handle multiple, non-fixed scaled image inputs
- auto-labelling to get find labels from coarse labels and use then in training to increase performance