Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level representation, which overlooks the positional information of recognized patterns. However, unlike natural image, the semantic of an audio spectrogram is sensitive to positional change, as its vertical and horizontal axes indicate the frequency and temporal information of the audio, instead of naive rectangular coordinates. Thus, the insensitivity of CNN to positional change plays a negative role on audio spectrogram encoding. To address this issue, this paper proposes a new self-supervised learning mechanism, which enhances the audio representation by first generating adversarial samples (\textit{i.e.}, negative samples), then driving CNN to distinguish the embeddings of negative pairs in the latent space. Extensive experiments show that the proposed approach achieves best or competitive results on 9 downstream datasets compared with previous methods, which verifies its effectiveness on audio representation learning.
相關內容
In this paper, we present a multimodal \textit{and} dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. The latent space is structured to dissociate the latent dynamical factors that are shared between the modalities from those that are specific to each modality. A static latent variable is also introduced to encode the information that is constant over time within an audiovisual speech sequence. The model is trained in an unsupervised manner on an audiovisual emotional speech dataset, in two stages. In the first stage, a vector quantized VAE (VQ-VAE) is learned independently for each modality, without temporal modeling. The second stage consists in learning the MDVAE model on the intermediate representation of the VQ-VAEs before quantization. The disentanglement between static versus dynamical and modality-specific versus modality-common information occurs during this second training stage. Extensive experiments are conducted to investigate how audiovisual speech latent factors are encoded in the latent space of MDVAE. These experiments include manipulating audiovisual speech, audiovisual facial image denoising, and audiovisual speech emotion recognition. The results show that MDVAE effectively combines the audio and visual information in its latent space. They also show that the learned static representation of audiovisual speech can be used for emotion recognition with few labeled data, and with better accuracy compared with unimodal baselines and a state-of-the-art supervised model based on an audiovisual transformer architecture.
Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models. To improve the transferability of adversarial samples, several feature-based adversarial attack methods have been proposed to disrupt neuron activation in the middle layers. However, current state-of-the-art feature-based attack methods typically require additional computation costs for estimating the importance of neurons. To address this challenge, we propose a Singular Value Decomposition (SVD)-based feature-level attack method. Our approach is inspired by the discovery that eigenvectors associated with the larger singular values decomposed from the middle layer features exhibit superior generalization and attention properties. Specifically, we conduct the attack by retaining the decomposed Top-1 singular value-associated feature for computing the output logits, which are then combined with the original logits to optimize adversarial examples. Our extensive experimental results verify the effectiveness of our proposed method, which can be easily integrated into various baselines to significantly enhance the transferability of adversarial samples for disturbing normally trained CNNs and advanced defense strategies. The source code of this study is available at \textcolor{blue}{\href{//anonymous.4open.science/r/SVD-SSA-13BF/README.md}{Link}}.
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks. However, ACL needs tremendous running time to generate the adversarial variants of all training data, which limits its scalability to large datasets. To speed up ACL, this paper proposes a robustness-aware coreset selection (RCS) method. RCS does not require label information and searches for an informative subset that minimizes a representational divergence, which is the distance of the representation between natural data and their virtual adversarial variants. The vanilla solution of RCS via traversing all possible subsets is computationally prohibitive. Therefore, we theoretically transform RCS into a surrogate problem of submodular maximization, of which the greedy search is an efficient solution with an optimality guarantee for the original problem. Empirically, our comprehensive results corroborate that RCS can speed up ACL by a large margin without significantly hurting the robustness transferability. Notably, to the best of our knowledge, we are the first to conduct ACL efficiently on the large-scale ImageNet-1K dataset to obtain an effective robust representation via RCS.
Robust watermarking tries to conceal information within a cover image/video imperceptibly that is resistant to various distortions. Recently, deep learning-based approaches for image watermarking have made significant advancements in robustness and invisibility. However, few studies focused on video watermarking using deep neural networks due to the high complexity and computational costs. Our paper aims to answer this research question: Can well-designed deep learning-based image watermarking be efficiently adapted to video watermarking? Our answer is positive. First, we revisit the workflow of deep learning-based watermarking methods that leads to a critical insight: temporal information in the video may be essential for general computer vision tasks but not for specific video watermarking. Inspired by this insight, we propose a method named ItoV for efficiently adapting deep learning-based Image watermarking to Video watermarking. Specifically, ItoV merges the temporal dimension of the video with the channel dimension to enable deep neural networks to treat videos as images. We further explore the effects of different convolutional blocks in video watermarking. We find that spatial convolution is the primary influential component in video watermarking and depthwise convolutions significantly reduce computational cost with negligible impact on performance. In addition, we propose a new frame loss to constrain that the watermark intensity in each video clip frame is consistent, significantly improving the invisibility. Extensive experiments show the superior performance of the adapted video watermarking method compared with the state-of-the-art methods on Kinetics-600 and Inter4K datasets, which demonstrate the efficacy of our method ItoV.
Dataset Distillation aims to distill an entire dataset's knowledge into a few synthetic images. The idea is to synthesize a small number of synthetic data points that, when given to a learning algorithm as training data, result in a model approximating one trained on the original data. Despite recent progress in the field, existing dataset distillation methods fail to generalize to new architectures and scale to high-resolution datasets. To overcome the above issues, we propose to use the learned prior from pre-trained deep generative models to synthesize the distilled data. To achieve this, we present a new optimization algorithm that distills a large number of images into a few intermediate feature vectors in the generative model's latent space. Our method augments existing techniques, significantly improving cross-architecture generalization in all settings.
Multi-scale design has been considered in recent image super-resolution (SR) works to explore the hierarchical feature information. Existing multi-scale networks aim to build elaborate blocks or progressive architecture for restoration. In general, larger scale features concentrate more on structural and high-level information, while smaller scale features contain plentiful details and textured information. In this point of view, information from larger scale features can be derived from smaller ones. Based on the observation, in this paper, we build a sequential hierarchical learning super-resolution network (SHSR) for effective image SR. Specially, we consider the inter-scale correlations of features, and devise a sequential multi-scale block (SMB) to progressively explore the hierarchical information. SMB is designed in a recursive way based on the linearity of convolution with restricted parameters. Besides the sequential hierarchical learning, we also investigate the correlations among the feature maps and devise a distribution transformation block (DTB). Different from attention-based methods, DTB regards the transformation in a normalization manner, and jointly considers the spatial and channel-wise correlations with scaling and bias factors. Experiment results show SHSR achieves superior quantitative performance and visual quality to state-of-the-art methods with near 34\% parameters and 50\% MACs off when scaling factor is $\times4$. To boost the performance without further training, the extension model SHSR$^+$ with self-ensemble achieves competitive performance than larger networks with near 92\% parameters and 42\% MACs off with scaling factor $\times4$.
Generative models are now capable of producing highly realistic images that look nearly indistinguishable from the data on which they are trained. This raises the question: if we have good enough generative models, do we still need datasets? We investigate this question in the setting of learning general-purpose visual representations from a black-box generative model rather than directly from data. Given an off-the-shelf image generator without any access to its training data, we train representations from the samples output by this generator. We compare several representation learning methods that can be applied to this setting, using the latent space of the generator to generate multiple "views" of the same semantic content. We show that for contrastive methods, this multiview data can naturally be used to identify positive pairs (nearby in latent space) and negative pairs (far apart in latent space). We find that the resulting representations rival those learned directly from real data, but that good performance requires care in the sampling strategy applied and the training method. Generative models can be viewed as a compressed and organized copy of a dataset, and we envision a future where more and more "model zoos" proliferate while datasets become increasingly unwieldy, missing, or private. This paper suggests several techniques for dealing with visual representation learning in such a future. Code is released on our project page: //ali-design.github.io/GenRep/
Deep supervised learning has achieved great success in the last decade. However, its deficiencies of dependence on manual labels and vulnerability to attacks have driven people to explore a better solution. As an alternative, self-supervised learning attracts many researchers for its soaring performance on representation learning in the last several years. Self-supervised representation learning leverages input data itself as supervision and benefits almost all types of downstream tasks. In this survey, we take a look into new self-supervised learning methods for representation in computer vision, natural language processing, and graph learning. We comprehensively review the existing empirical methods and summarize them into three main categories according to their objectives: generative, contrastive, and generative-contrastive (adversarial). We further investigate related theoretical analysis work to provide deeper thoughts on how self-supervised learning works. Finally, we briefly discuss open problems and future directions for self-supervised learning. An outline slide for the survey is provided.
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other's generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.
For better user experience and business effectiveness, Click-Through Rate (CTR) prediction has been one of the most important tasks in E-commerce. Although extensive CTR prediction models have been proposed, learning good representation of items from multimodal features is still less investigated, considering an item in E-commerce usually contains multiple heterogeneous modalities. Previous works either concatenate the multiple modality features, that is equivalent to giving a fixed importance weight to each modality; or learn dynamic weights of different modalities for different items through technique like attention mechanism. However, a problem is that there usually exists common redundant information across multiple modalities. The dynamic weights of different modalities computed by using the redundant information may not correctly reflect the different importance of each modality. To address this, we explore the complementarity and redundancy of modalities by considering modality-specific and modality-invariant features differently. We propose a novel Multimodal Adversarial Representation Network (MARN) for the CTR prediction task. A multimodal attention network first calculates the weights of multiple modalities for each item according to its modality-specific features. Then a multimodal adversarial network learns modality-invariant representations where a double-discriminators strategy is introduced. Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations. We conduct extensive experiments on both public and industrial datasets, and the proposed method consistently achieves remarkable improvements to the state-of-the-art methods. Moreover, the approach has been deployed in an operational E-commerce system and online A/B testing further demonstrates the effectiveness.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191