We present Multiscale Multiview Vision Transformers (MMViT), which introduces multiscale feature maps and multiview encodings to transformer models. Our model encodes different views of the input signal and builds several channel-resolution feature stages to process the multiple views of the input at different resolutions in parallel. At each scale stage, we use a cross-attention block to fuse information across different views. This enables the MMViT model to acquire complex high-dimensional representations of the input at different resolutions. The proposed model can serve as a backbone model in multiple domains. We demonstrate the effectiveness of MMViT on audio and image classification tasks, achieving state-of-the-art results.
Ethylene leakage detection has become one of the most important research directions in the field of target detection due to the fact that ethylene leakage in the petrochemical industry is closely related to production safety and environmental pollution. Under infrared conditions, there are many factors that affect the texture characteristics of ethylene, such as ethylene concentration, background, and so on. We find that the detection criteria used in infrared imaging ethylene leakage detection research cannot fully reflect real-world production conditions, which is not conducive to evaluate the performance of current image-based target detection methods. Therefore, we create a new infrared image dataset of ethylene leakage with different concentrations and backgrounds, including 54275 images. We use the proposed dataset benchmark to evaluate seven advanced image-based target detection algorithms. Experimental results demonstrate the performance and limitations of existing algorithms, and the dataset benchmark has good versatility and effectiveness.
This paper presents our submission to the Expression Classification Challenge of the fifth Affective Behavior Analysis in-the-wild (ABAW) Competition. In our method, multimodal feature combinations extracted by several different pre-trained models are applied to capture more effective emotional information. For these combinations of visual and audio modal features, we utilize two temporal encoders to explore the temporal contextual information in the data. In addition, we employ several ensemble strategies for different experimental settings to obtain the most accurate expression recognition results. Our system achieves the average F1 Score of 0.45774 on the validation set.
Federated learning provides a privacy-aware learning framework by enabling participants to jointly train models without exposing their private data. However, federated learning has exhibited vulnerabilities to Byzantine attacks, where the adversary aims to destroy the convergence and performance of the global model. Meanwhile, we observe that most existing robust AGgregation Rules (AGRs) fail to stop the aggregated gradient deviating from the optimal gradient (the average of honest gradients) in the non-IID setting. We attribute the reason of the failure of these AGRs to two newly proposed concepts: identification failure and integrity failure. The identification failure mainly comes from the exacerbated curse of dimensionality in the non-IID setting. The integrity failure is a combined result of conservative filtering strategy and gradient heterogeneity. In order to address both failures, we propose GAIN, a gradient decomposition scheme that can help adapt existing robust algorithms to heterogeneous datasets. We also provide convergence analysis for integrating existing robust AGRs into GAIN. Experiments on various real-world datasets verify the efficacy of our proposed GAIN.
Dereverberation is often performed directly on the reverberant audio signal, without knowledge of the acoustic environment. Reverberation time, T60, however, is an essential acoustic factor that reflects how reverberation may impact a signal. In this work, we propose to perform dereverberation while leveraging key acoustic information from the environment. More specifically, we develop a joint learning approach that uses a composite T60 module and a separate dereverberation module to simultaneously perform reverberation time estimation and dereverberation. The reverberation time module provides key features to the dereverberation module during fine tuning. We evaluate our approach in simulated and real environments, and compare against several approaches. The results show that this composite framework improves performance in environments.
Data uncertainty is commonly observed in the images for face recognition (FR). However, deep learning algorithms often make predictions with high confidence even for uncertain or irrelevant inputs. Intuitively, FR algorithms can benefit from both the estimation of uncertainty and the detection of out-of-distribution (OOD) samples. Taking a probabilistic view of the current classification model, the temperature scalar is exactly the scale of uncertainty noise implicitly added in the softmax function. Meanwhile, the uncertainty of images in a dataset should follow a prior distribution. Based on the observation, a unified framework for uncertainty modeling and FR, Random Temperature Scaling (RTS), is proposed to learn a reliable FR algorithm. The benefits of RTS are two-fold. (1) In the training phase, it can adjust the learning strength of clean and noisy samples for stability and accuracy. (2) In the test phase, it can provide a score of confidence to detect uncertain, low-quality and even OOD samples, without training on extra labels. Extensive experiments on FR benchmarks demonstrate that the magnitude of variance in RTS, which serves as an OOD detection metric, is closely related to the uncertainty of the input image. RTS can achieve top performance on both the FR and OOD detection tasks. Moreover, the model trained with RTS can perform robustly on datasets with noise. The proposed module is light-weight and only adds negligible computation cost to the model.
Speech quality assessment has been a critical component in many voice communication related applications such as telephony and online conferencing. Traditional intrusive speech quality assessment requires the clean reference of the degraded utterance to provide an accurate quality measurement. This requirement limits the usability of these methods in real-world scenarios. On the other hand, non-intrusive subjective measurement is the ``golden standard" in evaluating speech quality as human listeners can intrinsically evaluate the quality of any degraded speech with ease. In this paper, we propose a novel end-to-end model structure called Convolutional Context-Aware Transformer (CCAT) network to predict the mean opinion score (MOS) of human raters. We evaluate our model on three MOS-annotated datasets spanning multiple languages and distortion types and submit our results to the ConferencingSpeech 2022 Challenge. Our experiments show that CCAT provides promising MOS predictions compared to current state-of-art non-intrusive speech assessment models with average Pearson correlation coefficient (PCC) increasing from 0.530 to 0.697 and average RMSE decreasing from 0.768 to 0.570 compared to the baseline model on the challenge evaluation test set.
End-to-end Speech Translation (ST) aims at translating the source language speech into target language text without generating the intermediate transcriptions. However, the training of end-to-end methods relies on parallel ST data, which are difficult and expensive to obtain. Fortunately, the supervised data for automatic speech recognition (ASR) and machine translation (MT) are usually more accessible, making zero-shot speech translation a potential direction. Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods. In order to enable zero-shot ST, we propose a novel Discrete Cross-Modal Alignment (DCMA) method that employs a shared discrete vocabulary space to accommodate and match both modalities of speech and text. Specifically, we introduce a vector quantization module to discretize the continuous representations of speech and text into a finite set of virtual tokens, and use ASR data to map corresponding speech and text to the same virtual token in a shared codebook. This way, source language speech can be embedded in the same semantic space as the source language text, which can be then transformed into target language text with an MT module. Experiments on multiple language pairs demonstrate that our zero-shot ST method significantly improves the SOTA, and even performers on par with the strong supervised ST baselines.
3D-controllable portrait synthesis has significantly advanced, thanks to breakthroughs in generative adversarial networks (GANs). However, it is still challenging to manipulate existing face images with precise 3D control. While concatenating GAN inversion and a 3D-aware, noise-to-image GAN is a straight-forward solution, it is inefficient and may lead to noticeable drop in editing quality. To fill this gap, we propose 3D-FM GAN, a novel conditional GAN framework designed specifically for 3D-controllable face manipulation, and does not require any tuning after the end-to-end learning phase. By carefully encoding both the input face image and a physically-based rendering of 3D edits into a StyleGAN's latent spaces, our image generator provides high-quality, identity-preserved, 3D-controllable face manipulation. To effectively learn such novel framework, we develop two essential training strategies and a novel multiplicative co-modulation architecture that improves significantly upon naive schemes. With extensive evaluations, we show that our method outperforms the prior arts on various tasks, with better editability, stronger identity preservation, and higher photo-realism. In addition, we demonstrate a better generalizability of our design on large pose editing and out-of-domain images.
In regions that practice common law, relevant historical cases are essential references for sentencing. To help legal practitioners find previous judgement easier, this paper aims to label each court judgement by some tags. These tags are legally important to summarize the judgement and can guide the user to similar judgements. We introduce a heuristic system to solve the problem, which starts from Aspect-driven Topic Modeling and uses Dependency Parsing and Constituency Parsing for phrase generation. We also construct a legal term tree for Hong Kong and implemented a sentence simplification module to support the system. Finally, we propose a similar document recommendation algorithm based on the generated tags. It enables users to find similar documents based on a few selected aspects rather than the whole passage. Experiment results show that this system is the best approach for this specific task. It is better than simple term extraction method in terms of summarizing the document, and the recommendation algorithm is more effective than full-text comparison approaches. We believe that the system has huge potential in law as well as in other areas.