|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM36727194X |
| 003 |
DE-627 |
| 005 |
20240508232304.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240119s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3355461
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1401.xml
|
| 035 |
|
|
|a (DE-627)NLM36727194X
|
| 035 |
|
|
|a (NLM)38236683
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wang, Shijie
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Content-Aware Rectified Activation for Zero-Shot Fine-Grained Image Retrieval
|
| 264 |
|
1 |
|c 2024
|
| 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 07.05.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Fine-grained image retrieval mainly focuses on learning salient features from the seen subcategories as discriminative embedding while neglecting the problems behind zero-shot settings. We argue that retrieving fine-grained objects from unseen subcategories may rely on more diverse clues, which are easily restrained by the salient features learnt from seen subcategories. To address this issue, we propose a novel Content-aware Rectified Activation model, which enables this model to suppress the activation on salient regions while preserving their discrimination, and spread activation to adjacent non-salient regions, thus mining more diverse discriminative features for retrieving unseen subcategories. Specifically, we construct a content-aware rectified prototype (CARP) by perceiving semantics of salient regions. CARP acts as a channel-wise non-destructive activation upper bound and can be selectively used to suppress salient regions for obtaining the rectified features. Moreover, two regularizations are proposed: 1) a semantic coherency constraint that imposes a restriction on semantic coherency of CARP and salient regions, aiming at propagating the discriminative ability of salient regions to CARP, 2) a feature-navigated constraint to further guide the model to adaptively balance the discrimination power of rectified features and the suppression power of salient features. Experimental results on fine-grained and product retrieval benchmarks demonstrate that our method consistently outperforms the state-of-the-art methods
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Chang, Jianlong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Zhihui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Haojie
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ouyang, Wanli
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tian, Qi
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 6 vom: 26. Mai, Seite 4366-4380
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:6
|g day:26
|g month:05
|g pages:4366-4380
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3355461
|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 46
|j 2024
|e 6
|b 26
|c 05
|h 4366-4380
|