Zobrazeno 1 - 10
of 149
pro vyhledávání: '"Ding, Mingli"'
Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to gradually e
Externí odkaz:
http://arxiv.org/abs/2305.12833
Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the exact classes of the unknown objects must be identified without catastr
Externí odkaz:
http://arxiv.org/abs/2212.02969
Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object detection that rel
Externí odkaz:
http://arxiv.org/abs/2205.04042
Autor:
Yang, Guanglei, Fini, Enrico, Xu, Dan, Rota, Paolo, Ding, Mingli, Nabi, Moin, Alameda-Pineda, Xavier, Ricci, Elisa
A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in th
Externí odkaz:
http://arxiv.org/abs/2203.14098
Autor:
Yang, Guanglei, Fini, Enrico, Xu, Dan, Rota, Paolo, Ding, Mingli, Tang, Hao, Alameda-Pineda, Xavier, Ricci, Elisa
Over the past years, semantic segmentation, as many other tasks in computer vision, benefited from the progress in deep neural networks, resulting in significantly improved performance. However, deep architectures trained with gradient-based techniqu
Externí odkaz:
http://arxiv.org/abs/2202.00432
Autor:
Yang, Guanglei, Tang, Hao, Shi, Humphrey, Ding, Mingli, Sebe, Nicu, Timofte, Radu, Van Gool, Luc, Ricci, Elisa
The goal of unpaired image-to-image translation is to produce an output image reflecting the target domain's style while keeping unrelated contents of the input source image unchanged. However, due to the lack of attention to the content change in ex
Externí odkaz:
http://arxiv.org/abs/2111.10346
In autonomous driving, learning a segmentation model that can adapt to various environmental conditions is crucial. In particular, copying with severe illumination changes is an impelling need, as models trained on daylight data will perform poorly a
Externí odkaz:
http://arxiv.org/abs/2111.10339
Deep networks have shown remarkable results in the task of object detection. However, their performance suffers critical drops when they are subsequently trained on novel classes without any sample from the base classes originally used to train the m
Externí odkaz:
http://arxiv.org/abs/2110.15017
Publikováno v:
In Pattern Recognition March 2024 147
In this paper, we study the task of source-free domain adaptation (SFDA), where the source data are not available during target adaptation. Previous works on SFDA mainly focus on aligning the cross-domain distributions. However, they ignore the gener
Externí odkaz:
http://arxiv.org/abs/2105.14138