General Multi-label Image Classification with Transformers

Lanchantin, Jack; Wang, Tianlu; Ordóñez, Vicente; Qi, Yanjun

doi:10.1109/cvpr46437.2021.01621

Cited by 239 publications

(94 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it develops, it has almost replaced RNN with its excellent effects, such as exploring long-range relationship, better scalability to highcomplexity models and so on. We can observe that transformer has been applied to image classification (Lanchantin et al 2021;Dosovitskiy et al 2020), object detection (Yang et al 2020;Zhu et al 2021;Carion et al 2020) and even natural image restoration (Wang et al 2021;Liang et al 2021).…”

Section: Transformermentioning

confidence: 99%

EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer

Yi,

Chen,

et al. 2021

Preprint

View full text Add to dashboard Cite

Electroencephalogram (EEG) has shown a useful approach to produce a brain-computer interface (BCI). One-dimensional (1-D) EEG signal is yet easily disturbed by certain artifacts (a.k.a. noise) due to the high temporal resolution. Thus, it is crucial to remove the noise in received EEG signal. Recently, deep learning-based EEG signal denoising approaches have achieved impressive performance compared with traditional ones. It is well known that the characteristics of selfsimilarity (including non-local and local ones) of data (e.g., natural images and time-domain signals) are widely leveraged for denoising. However, existing deep learning-based EEG signal denoising methods ignore either the non-local self-similarity (e.g., 1-D convolutional neural network) or local one (e.g., fully connected network and recurrent neural network). To address this issue, we propose a novel 1-D EEG signal denoising network with 2-D transformer, namely EEGDnet. Specifically, we comprehensively take into account the non-local and local self-similarity of EEG signal through the transformer module. By fusing non-local selfsimilarity in self-attention blocks and local self-similarity in feed forward blocks, the negative impact caused by noises and outliers can be reduced significantly. Extensive experiments show that, compared with other state-of-the-art models, EEGDnet achieves much better performance in terms of both quantitative and qualitative metrics.

show abstract

Section: Transformermentioning

confidence: 99%

EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer

Yi,

Chen,

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We inject symmetric label noise (details in Section 4.1) at various corruption levels, from 0% to 60%, and report the mean average precision to asses the impact of wrong labels. mAP is considered by many recent works [Lanchantin et al, 2020, Chen et al, 2019b as important metric for performance evaluation in multi-label classification, since it takes into consideration both false-negative and false-positive rates [Baruch et al, 2020]. Fig.…”

Section: Motivation Examplementioning

confidence: 99%

Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators

Pene,

Ghiassi,

Younesian

et al. 2021

Preprint

View full text Add to dashboard Cite

Multi-label learning is an emerging extension of the multi-class classification where an image contains multiple labels. Not only acquiring a clean and fully labeled dataset in multi-label learning is extremely expensive, but also many of the actual labels are corrupted or missing due to the automated or non-expert annotation techniques. Noisy label data decrease the prediction performance drastically. In this paper, we propose a novel Gold Asymmetric Loss Correction with Single-Label Regulators (GALC-SLR) that operates robust against noisy labels. GALC-SLR estimates the noise confusion matrix using single-label samples, then constructs an asymmetric loss correction via estimated confusion matrix to avoid overfitting to the noisy labels. Empirical results show that our method outperforms the state-of-the-art original asymmetric loss multi-label classifier under all corruption levels, showing mean average precision improvement up to 28.67% on a real world dataset of MS-COCO, yielding a better generalization of the unseen data and increased prediction performance.

show abstract

“…In addition, we also exploit mask token strategy [7,25] to further strengthen the learned representation in the auxiliary task. During the training phase, we randomly set the state of domain information as either positive or negative instead of masking them out as unknown.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation

Yuan¹,

Hou²,

Du³

et al. 2022

Preprint

View full text Add to dashboard Cite

Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data, and multi-source domain adaptation (MSDA) is very attractive for real world applications. By learning from large-scale unlabeled samples, self-supervised learning has now become a new trend in deep learning. It is worth noting that both self-supervised learning and multi-source domain adaptation share a similar goal: they both aim to leverage unlabeled data to learn more expressive representations. Unfortunately, traditional multi-task self-supervised learning faces two challenges: (1) the pretext task may not strongly relate to the downstream task, thus it could be difficult to learn useful knowledge being shared from the pretext task to the target task; (2) when the same feature extractor is shared between the pretext task and the downstream one and only different prediction heads are used, it is ineffective to enable inter-task information exchange and knowledge sharing. To address these issues, we propose a novel Self-Supervised Graph Neural Network (SSG), where a graph neural network is used as the bridge to enable more effective inter-task information exchange and knowledge sharing. More expressive representation is learned by adopting a mask token strategy to mask some domain information. Our extensive experiments have demonstrated that our proposed SSG method has achieved state-ofthe-art results over four multi-source domain adaptation datasets, which have shown the effectiveness of our proposed SSG method from different aspects.

show abstract

General Multi-label Image Classification with Transformers

Cited by 239 publications

References 28 publications

EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer

EEGDnet: Fusing Non-Local and Local Self-Similarity for 1-D EEG Signal Denoising with 2-D Transformer

Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators

Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation

Contact Info

Product

Resources

About