[24/August/2022]‼️ We present a new task, video polyp segmentation (VPS), which has been accepted by Machine Intelligence Research (MIR). We release the first large-scale VPS dataset, termed SUN-SEG, containing 158,690 frames with densely-annotated labels. These labels can further support the development of medical colonoscopy diagnosis, localization, and their derivative tasks. For more details, please refer to our project page / technical report.
[06/August/2022] ❗ Our paper about camouflaged object detection (COD) has been accepted by Machine Intelligence Research (MIR) journal. This is a simple but efficient baseline, DGNet, with a novel object gradient supervision for the COD task. Additionally, we construct a comprehensive COD benchmark with 20 competed approaches. Read our technical report for more details. We also implement our model via Jittor & PyTorch toolboxes.
Hi, the Matlab code is easy to use and it has been modified very soon to generate the evaluation result. However, the efficiency is still low because of using CPU only. So, how can I speed up it like using the GPU to process the images?
seq_Smeasure:0.135;seq_wFmeasure:0.095;seq_adpFmeasure:0.041;seq_maxF:0.185;seq_meanF:0.121;seq_adpEmeasure:0.249;seq_maxE:0.627;seq_meanE:0.202;seq_MAE:0.819
Above is one of the lines in the output file, and some pairs have been found in the paper: Smeasure —— 4.2.2 5. structure measure wFmeasure —— adpFmeasure —— maxF —— maximum F-measure meanF —— adpEmeasure —— maxE —— 4.2.2 4. Maximum Enhanced-Alignment Measure meanE —— seq_MAE —— 4.2.2 mae
However, the meanings of the variables not found are still not clear, could you please help me about this? Thank you sincerely!
Thansk for your code. I am not quite understand why you plug a PPM into each decoder. In the last decoder, the ppm extracts features with resolutions of 1x1, 2x2, 3x3, and 6x6. However, the size of the input feature is 88x88. It seems that these intermediate features extracted by ppm are too coarse to facilitate the refinement of the input feature. Have you evaluate the effectiveness of the PPM?
Thank you for sharing this work.
I want to know how to do inference on our personalized dataset, without any ground truth masks and without OF_FlowNet2 images. We only have frames on which we want to detect moving persons. Thank you in advance
Hello, this is a great work. But when I use weights provided in the link Baidu Driver (psw: 36lm) to test on the DAVIS16 dataset, the mean-J and mean-F are only 47.5 and 27.8, respectively. I want to know if the weights are the final weights?