howardyclo / papernotes

My personal notes and surveys on DL, CV and NLP papers.
128 stars 6 forks source link

DeepCO3: Deep Instance Co-segmentation by Co-peak Search and Co-saliency Detection #51

Open howardyclo opened 5 years ago

howardyclo commented 5 years ago

Metadata

howardyclo commented 5 years ago

What is instance co-segmentation?

Method

Variables in the data flow

Divide the task into Co-peak Search and Instance Mask Segmentation

Co-peak search

(Figure credit: Zhou et al.)

Loss overview:

Co-peak loss:

Affinity loss:

(Note that this equation is corrected by the author, different from the original paper.)

The proposed affinity loss generalizes eq (4) to consider both inter-image and intra-image affinities:

Saliency loss (follows Hsu et al.):

Instance mask segmentation

Evaluation

General preprocessing

Datasets

Performance

Ablation studies

Qualitative results

How is the result computed given 3 images? After optimizing Eq. (1), we simply use the detected peaks on the estimated co-saliency maps as the final co-peaks, because detecting the co-peaks on all possible image pairs is complicated.

How are the (local) peaks sampled from the predicted co-saliency map for an image? They use the 3 x 3 local window to sample peaks on the co-saliency map and then with the sampled peaks, the peak back-propagation proposed in PRM is adopted.

Related Work