SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks Using cGANs

Ambekar, Sameer; Tafuro, Matteo; Ankit, Ankit; Mast, Diego van der; Alence, Mark; Athanasiadis, Christos

doi:10.1007/978-3-031-25069-9_43

Cited by 2 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In real-world scenarios, the source data is usually inaccessible due to data privacy, leading to the SFOD problem (Lee et al 2022;Zong et al 2022;Ding et al 2022;Kothandaraman et al 2022;Wang et al 2022b). Due to complex background and negative examples, SFOD is far more challenging than conventional source-free image classification (Agarwal et al 2022;Ambekar et al 2022;Bohdal et al 2022;Xia, Zhao, and Ding 2021). SFOD-Mosaic (Li et al 2021a) first formulated the SFOD problem and proposed to search for a fairly good confidence threshold and enabled self-training via generated pseudo labels.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Alignment for Source Free Object Detection

Chu,

Li,

Chen

et al. 2023

AAAI

View full text Add to dashboard Cite

Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most existing SFOD methods generate pseudo labels via a source-pretrained model to guide training, these pseudo labels usually contain high noises due to heavy domain discrepancy. In order to obtain better pseudo supervisions, we divide the target domain into source-similar and source-dissimilar parts and align them in the feature space by adversarial learning.Specifically, we design a detection variance-based criterion to divide the target domain. This criterion is motivated by a finding that larger detection variances denote higher recall and larger similarity to the source domain. Then we incorporate an adversarial module into a mean teacher framework to drive the feature spaces of these two subsets indistinguishable. Extensive experiments on multiple cross-domain object detection datasets demonstrate that our proposed method consistently outperforms the compared SFOD methods. Our implementation is available at https://github.com/ChuQiaosong.

show abstract

Section: Related Workmentioning

confidence: 99%

Adversarial Alignment for Source Free Object Detection

Chu,

Li,

Chen

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…The challenges mentioned above can be effectively addressed by utilizing neural networks [20][21][22]. Neural networks have the ability to optimize learning outcomes by using the backpropagation algorithm to determine necessary adjustments in internal parameters [23,24].…”

Section: Introductionmentioning

confidence: 99%

Automatic Extraction of the Calving Front of Pine Island Glacier Based on Neural Network

Song,

Du,

Guo

2023

Remote Sensing

View full text Add to dashboard Cite

Calving front location plays a crucial role in studying ice–ocean interaction, mapping glacier area change, and constraining ice dynamic models. However, relying solely on visual interpretation to extract annual changes in the calving front of ice shelves is a time-consuming process. In this study, a comparative analysis was conducted on the segmentation obtained from fully convolutional networks (FCN), U-Net, and U2-Net models, revealing that U2-Net exhibited the most effective classification. Notably, U2-Net outperformed the other two models by more than 30 percent in terms of the F1 parameter. Therefore, this paper introduces an automated approach that utilizes the U2-Net model to extract the calving front of ice shelves based on a Landsat image, achieving an extraction accuracy of 58 m. To assess the model’s performance on additional ice shelves in the polar region, the calving front of the Totten and Filchner ice shelves were also extracted for the past decade. The findings demonstrated that the ice velocity of the Filchner ice shelf exceeded that of the Totten ice shelf. Between February 2014 and March 2015, the majority of the calving fronts along the Filchner Ice Shelf showed an advancing trend, with the fastest-moving front measuring 3532 ± 58 m/yr.

show abstract

SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks Using cGANs

Cited by 2 publications

References 8 publications

Adversarial Alignment for Source Free Object Detection

Adversarial Alignment for Source Free Object Detection

Automatic Extraction of the Calving Front of Pine Island Glacier Based on Neural Network

Contact Info

Product

Resources

About