Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Niu, Axi"'
There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples (termed Hybrid-AT). With the assumption that adversarial and clean sam
Externí odkaz:
http://arxiv.org/abs/2403.19150
The Joint Detection and Embedding (JDE) framework has achieved remarkable progress for multiple object tracking. Existing methods often employ extracted embeddings to re-establish associations between new detections and previously disrupted tracks. H
Externí odkaz:
http://arxiv.org/abs/2311.02572
Unsupervised domain adaptation (UDA) has been a potent technique to handle the lack of annotations in the target domain, particularly in semantic segmentation task. This study introduces a different UDA scenarios where the target domain contains unla
Externí odkaz:
http://arxiv.org/abs/2309.11711
Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demonstrated that iteratively refining pure Gaussian noise using a U-Net ar
Externí odkaz:
http://arxiv.org/abs/2307.00781
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation
Externí odkaz:
http://arxiv.org/abs/2305.18547
Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly applying to e
Externí odkaz:
http://arxiv.org/abs/2302.14557
Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM to image super-resolution (SR) have shown that iteratively refining a pure Gaussian noise
Externí odkaz:
http://arxiv.org/abs/2302.12831
Autor:
Pham, Trung X., Niu, Axi, Kang, Zhang, Madjid, Sultan Rizky, Hong, Ji Woo, Kim, Daehyeok, Tee, Joshua Tian Jin, Yoo, Chang D.
Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based frameworks have attracted significant attention. Despite being a great success, these momentu
Externí odkaz:
http://arxiv.org/abs/2211.09861
Exponential Moving Average (EMA or momentum) is widely used in modern self-supervised learning (SSL) approaches, such as MoCo, for enhancing performance. We demonstrate that such momentum can also be plugged into momentum-free SSL frameworks, such as
Externí odkaz:
http://arxiv.org/abs/2208.05744
Autor:
Zhang, Chaoning, Zhang, Kang, Zhang, Chenshuang, Niu, Axi, Feng, Jiu, Yoo, Chang D., Kweon, In So
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating AT into SSL, multiple prior works have accomplished a highly signific
Externí odkaz:
http://arxiv.org/abs/2207.10899