willard-yuan / awesome-cbir-papers Goto Github PK

9.RobustiQ A Robust ANN Search Method for Billion-scale Similarity Search on GPUs
11.Zoom: Multi-View Vector Search for Optimizing Accuracy, Latency and Memory
12. Vector and Line Quantization for Billion-scale Similarity Search on GPUs
I just found that the GGNN(near exactly search) already added.
Did you done some experiments in the large scale image classification vs deep-metric ? Or some work like search engine guided similarity learning .eg Search Engine Guided Neural Machine Translation?

这个对图像做cnn 特征抽取，特征维度都在几千，有点太了吧，是否能够减少维度 提高效率。还是在搜索的时候用什么算法来做进一步处理

Hi, consider adding the SIGMOD 2020 paper: Improving Approximate Nearest Neighbor Search through Learned Adaptive Early Termination, https://www.pdl.cmu.edu/PDL-FTP/BigLearning/mod0246-liA.pdf

你好，

感谢整理这份资料！
阿里的Alibaba Large-scale Image Search Challenge这个竞赛数据现在原始链接已不能下载，请问你那里有保存这个数据集吗？可否上传一份至百度云/Google drive？谢谢！

Thanks for organizing all these materials!
The original download link for Alibaba Large-scale Image Search Challenge data is broken. Do you have a local copy of it? If you do, could you share it with BaiduYunPan / Google drive? Thanks!

thanks for this collection,I have watching this topic for a long time. In practice，inverted-multi and PQ combined index saved a lot of search time and space in ANN searching.and some hardware accelarted method proposaled,multi-ivf
fpga and opencl based acc.Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA.
I think the hardware combined to ANNS is a trend ,do you think so.

Hi~ I'm also interested in the paper of "Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking", but I did not find it online. I wonder if you could provide another URL for this paper. Thanks!

Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval, https://arxiv.org/abs/2002.10310

SPTAG github urlhttps://github.com/microsoft/SPTAG

Hi @willard-yuan , have you found some paper recommendations regarding the significance test of our model for visual search tasks? I'm currently working on this task and would like to know if there is any technique to test the significance of the model experiment. I know one significance test, which is Mcnemar's test, but this test is commonly used for classification tasks. I wondered is there a way to use Mcnemar's test in visual search task?