|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM372759939 |
| 003 |
DE-627 |
| 005 |
20250306055545.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240525s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3402981
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1241.xml
|
| 035 |
|
|
|a (DE-627)NLM372759939
|
| 035 |
|
|
|a (NLM)38787668
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wu, Zhihao
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Misclassification in Weakly Supervised Object Detection
|
| 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 03.06.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Weakly supervised object detection (WSOD) aims to train detectors using only image-category labels. Current methods typically first generate dense class-agnostic proposals and then select objects based on the classification scores of these proposals. These methods mainly focus on selecting the proposal having high Intersection-over-Union with the true object location, while ignoring the problem of misclassification, which occurs when some proposals exhibit semantic similarities with objects from other categories due to viewing perspective and background interference. We observe that the positive class that is misclassified typically has the following two characteristics: 1) It is usually misclassified as one or a few specific negative classes, and the scores of these negative classes are high; 2) Compared to other negative classes, the score of the positive class is relatively high. Based on these two characteristics, we propose misclassification correction (MCC) and misclassification tolerance (MCT) respectively. In MCC, we establish a misclassification memory bank to record and summarize the class-pairs with high frequencies of potential misclassifications in the early stage of training, that is, cases where the score of a negative class is significantly higher than that of the positive class. In the later stage of training, when such cases occur and correspond to the summarized class-pairs, we select the top-scoring negative class proposal as the positive training example. In MCT, we decrease the loss weights of misclassified classes in the later stage of training to avoid them dominating training and causing misclassification of objects from other classes that are semantically similar to them during inference. Extensive experiments on the PASCAL VOC and MS COCO demonstrate our method can alleviate the problem of misclassification and achieve the state-of-the-art results
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Xu, Yong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yang, Jian
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Li, Xuelong
|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 33(2024) vom: 24., Seite 3413-3427
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnas
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:24
|g pages:3413-3427
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3402981
|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 33
|j 2024
|b 24
|h 3413-3427
|