Abstract | ||
---|---|---|
Deep detection approaches are powerful in controlled conditions, but appear brittle and fail when source models are used off-the-shelf on unseen domains. Most of the existing works on domain adaptation simplify the setting and access jointly both a large source dataset and a sizable amount of target samples. However this scenario is unrealistic in many practical cases as when monitoring image feeds from social media: only a pretrained source model is available and every target image uploaded by the users belongs to a different domain not foreseen during training. We address this challenging setting by presenting an object detection algorithm able to exploit a pre-trained source model and perform unsupervised adaptation by using only one target sample seen at test time. Our multi-task architecture includes a self-supervised branch that we exploit to meta-train the whole model with single-sample cross-domain episodes, and prepare to the test condition. At deployment time the self-supervised task is iteratively solved on any incoming sample to one-shot adapt on it. We introduce a new dataset of social media image feeds and present a thorough benchmark with the most recent cross-domain detection methods showing the advantages of our approach. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.cviu.2022.103549 | Computer Vision and Image Understanding |
Keywords | DocType | Volume |
68T01,68T05,68T10,68T45 | Journal | 223 |
ISSN | Citations | PageRank |
1077-3142 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
F. Cappio Borlino | 1 | 0 | 0.34 |
S. Polizzotto | 2 | 0 | 0.34 |
Barbara Caputo | 3 | 3298 | 201.26 |
Tatiana Tommasi | 4 | 502 | 29.31 |