|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM328288446 |
| 003 |
DE-627 |
| 005 |
20231225202631.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2021 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2021.3097187
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1094.xml
|
| 035 |
|
|
|a (DE-627)NLM328288446
|
| 035 |
|
|
|a (NLM)34283715
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wang, Dan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Interpreting Bottom-Up Decision-Making of CNNs via Hierarchical Inference
|
| 264 |
|
1 |
|c 2021
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 27.07.2021
|
| 500 |
|
|
|a Date Revised 27.07.2021
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a With the great success of convolutional neural networks (CNNs), interpretation of their internal network mechanism has been increasingly critical, while the network decision-making logic is still an open issue. In the bottom-up hierarchical logic of neuroscience, the decision-making process can be deduced from a series of sub-decision-making processes from low to high levels. Inspired by this, we propose the Concept-harmonized HierArchical INference (CHAIN) interpretation scheme. In CHAIN, a network decision-making process from shallow to deep layers is interpreted by the hierarchical backward inference based on visual concepts from high to low semantic levels. Firstly, we learned a general hierarchical visual-concept representation in CNN layered feature space by concept harmonizing model on a large concept dataset. Secondly, for interpreting a specific network decision-making process, we conduct the concept-harmonized hierarchical inference backward from the highest to the lowest semantic level. Specifically, the network learning for a target concept at a deeper layer is disassembled into that for concepts at shallower layers. Finally, a specific network decision-making process is explained as a form of concept-harmonized hierarchical inference, which is intuitively comparable to the bottom-up hierarchical visual recognition way. Quantitative and qualitative experiments demonstrate the effectiveness of the proposed CHAIN at both instance and class levels
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Cui, Xinrui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Chen, Xun
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ward, Rabab
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Z Jane
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 30(2021) vom: 15., Seite 6701-6714
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:30
|g year:2021
|g day:15
|g pages:6701-6714
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2021.3097187
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 30
|j 2021
|b 15
|h 6701-6714
|