|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM331781883 |
| 003 |
DE-627 |
| 005 |
20240220231917.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231225s2021 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2021.3119406
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1300.xml
|
| 035 |
|
|
|a (DE-627)NLM331781883
|
| 035 |
|
|
|a (NLM)34637379
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Yong-Lu
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Learning Single/Multi-Attribute of Object with Symmetry and Group
|
| 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 Revised 20.02.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status Publisher
|
| 520 |
|
|
|a Attributes and objects can compose diverse compositions. To model the compositional nature of these concepts, it is a good choice to learn them as transformations, e.g., coupling and decoupling. However, complex transformations need to satisfy specific principles to guarantee rationality. Here, we first propose a previously ignored principle of attribute-object transformation: Symmetry. For example, coupling peeled-apple with attribute peeled should result in peeled-apple, and decoupling peeled from apple should still output apple. Incorporating the symmetry, we propose a transformation framework inspired by group theory, i.e., SymNet. It consists of two modules: Coupling Network and Decoupling Network. We adopt deep neural networks to implement SymNet and train it in an end-to-end paradigm with the group axioms and symmetry as objectives. Then, we propose a Relative Moving Distance (RMD) based method to utilize the attribute change instead of the attribute pattern itself to classify attributes. Besides the compositions of single-attribute and object, our RMD is also suitable for complex compositions of multiple attributes and objects when incorporating attribute correlations. SymNet can be utilized for attribute learning, compositional zero-shot learning and outperforms the state-of-the-art on four widely-used benchmarks. Code is at https://github.com/DirtyHarryLYL/SymNet
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Xu, Yue
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Xinyu
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Mao, Xiaohan
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Lu, Cewu
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g PP(2021) vom: 12. Okt.
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:PP
|g year:2021
|g day:12
|g month:10
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2021.3119406
|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 PP
|j 2021
|b 12
|c 10
|