PMID- 37616139
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20230905
IS  - 1941-0042 (Electronic)
IS  - 1057-7149 (Linking)
VI  - 32
DP  - 2023
TI  - Randomized Spectrum Transformations for Adapting Object Detector in Unseen 
      Domains.
PG  - 4868-4879
LID - 10.1109/TIP.2023.3306915 [doi]
AB  - We propose a Meta Learning on Randomized Transformations (MLRT) to learn domain 
      invariant object detectors. Domain generalization is a problem about learning an 
      invariant model from multiple source domains which can generalize well on unseen 
      target domains. This problem is overlooked in object detection field, which is 
      formally named as domain generalizable object detection (DGOD). Moreover, 
      existing domain generalization methods have the problem of domain bias so that 
      they can easily overfit to some specific domain (e.g., source domain). In order 
      to alleviate the domain bias, in MLRT model, a novel randomized spectrum 
      transformation (RST) module is proposed to increase the diversity of source 
      domains. Specifically, RST randomizes the domain specific information of images 
      in frequency-space, which can transform single or multiple source domains into 
      various new domains. Besides, we observe a prior that the gradient imbalance 
      degree among domains can also reflect the domain bias. Therefore, we further 
      propose to alleviate the domain bias from the perspective of gradient balancing, 
      and a novel gradient weighting (GW) module is proposed to balance the gradients 
      over all domains via a hand-crafted weight. Finally we embed our RST and GW into 
      a general meta learning framework and the proposed MLRT model is formalized for 
      DGOD task. Extensive experiments are conducted on six benchmarks, and our method 
      achieves the SOTA performance.
FAU - Zhang, Lei
AU  - Zhang L
FAU - Qin, Lingyun
AU  - Qin L
FAU - Xu, Mingjun
AU  - Xu M
FAU - Chen, Weijie
AU  - Chen W
FAU - Pu, Shiliang
AU  - Pu S
FAU - Zhang, Wensheng
AU  - Zhang W
LA  - eng
PT  - Journal Article
DEP - 20230901
PL  - United States
TA  - IEEE Trans Image Process
JT  - IEEE transactions on image processing : a publication of the IEEE Signal 
      Processing Society
JID - 9886191
SB  - IM
EDAT- 2023/08/24 13:43
MHDA- 2023/08/24 13:44
CRDT- 2023/08/24 12:23
PHST- 2023/08/24 13:44 [medline]
PHST- 2023/08/24 13:43 [pubmed]
PHST- 2023/08/24 12:23 [entrez]
AID - 10.1109/TIP.2023.3306915 [doi]
PST - ppublish
SO  - IEEE Trans Image Process. 2023;32:4868-4879. doi: 10.1109/TIP.2023.3306915. Epub 
      2023 Sep 1.