xzhiyao Goto Github PK

barrier

Open-source KVM software

compactbilinearpooling-pytorch

A Pytorch Implementation for Compact Bilinear Pooling.

detectron2_visualization

CNN Visualization use Grad-CAM on Detectron2

electronbot

evalai

:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI

fsod-code

gsrnet

manipulation-detection

Tampering detection related sources

mantranet

ManTra-Net: Manipulation Tracing Network For Detection And Localization of Image Forgeries With Anomalous Features

must-thesis

latex-template: 澳门科技大学,硕士or博士毕业论文模版

mvss-net

code for Image Manipulation Detection by Multi-View Multi-Scale Supervision

nxdo

Deep RL Code for XDO: A Double Oracle Algorithm for Extensive-Form Games

pysot

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

resnest

ResNeSt: Split-Attention Networks

rgb-n

study

some test

thundernet-review

Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. However, previous CNN-based detectors suffer from enormous computational cost, which hinders them from real-time inference in computation-constrained scenarios. In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight twostage detector named ThunderNet. In the backbone part, we analyze the drawbacks in previous lightweight backbones and present a lightweight backbone designed for object detection. In the detection part, we exploit an extremely efficient RPN and detection head design. To generate more discriminative feature representation, we design two efficient architecture blocks, Context Enhancement Module and Spatial Attention Module. At last, we investigate the balance between the input resolution, the backbone, and the detection head. Compared with lightweight one-stage detectors, ThunderNet achieves superior performance with only 40% of the computational cost on PASCAL VOC and COCO benchmarks. Without bells and whistles, our model runs at 24.1 fps on an ARM-based device. To the best of our knowledge, this is the first real-time detector reported on ARM platforms. Code will be released for paper reproduction.

triplet-attention

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]