Metric learning projects samples into an embedded space, where similarities and dissimilarities are quantified based on their learned representations. However, existing methods often rely on label-guided representation learning, where representations of different modalities, such as audio and visual data, are aligned based on annotated labels. This approach tends to underutilize latent complex features and potential relationships inherent in the distributions of audio and visual data that are not directly tied to the labels, resulting in suboptimal performance in audio-visual embedding learning. To address this issue, we propose a novel architecture that integrates cross-modal triplet loss with progressive self-distillation. Our method enhances representation learning by leveraging inherent distributions and dynamically refining soft audio-visual alignments -- probabilistic alignments between audio and visual data that capture the inherent relationships beyond explicit labels. Specifically, the model distills audio-visual distribution-based knowledge from annotated labels in a subset of each batch. This self-distilled knowledge is used t
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）
Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network
MoE Key Laboratory of Information Technology（信息科技联合实验室）；Sun Yat-sen University（中山大学）；State Key Laboratory of Mathematical Engineering and Advanced Computing（数学工程与先进计算国家重点实验室）；Alibaba Group（阿里巴巴集团）
University of Waterloo（滑铁卢大学）；DarwinAI Corp.（达尔文人工智能公司）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）
Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged to distill the knowledge encapsulated in the training data itself into a reduced form. In this study, we explore the concept of progressive label distillation, where we leverage a series of teacher-student network pairs to progressively generate distilled training data for learning deep neural networks with greatly reduced input dimensions. To investigate t…
Istituto Italiano di Tecnologia（意大利理工学院）；Università degli Studi di Genova（热那亚大学）；Università di Verona（维罗纳大学）；Huawei Technologies Ltd.（华为技术有限公司）
In this paper, we investigate how to learn rich and robust feature representations for audio classification from visual data and acoustic images, a novel audio data modality. Former models learn audio representations from raw signals or spectral data acquired by a single microphone, with remarkable results in classification and retrieval. However, such representations are not so robust towards variable environmental sound conditions. We tackle this drawback by exploiting a new multimodal labeled action recognition dataset acquired by a hybrid audio-visual sensor that provides RGB video, raw au…
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
Shanghai Innovation Institute（上海创新研究院）；Fudan University（复旦大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University（南京大学）；Baidu（百度）
Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate manner, yet overlooking the modality heterogeneousness over the weakly-supervised setting. In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised audio-visual learning. To address these issues, we propose a modal…
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）
Knowledge distillation has demonstrated encouraging performances in deep model compression. Most existing approaches, however, require massive labeled data to accomplish the knowledge transfer, making the model compression a cumbersome and costly process. In this paper, we investigate the practical few-shot knowledge distillation scenario, where we assume only a few samples without human annotations are available for each category. To this end, we introduce a principled dual-stage distillation scheme tailored for few-shot data. In the first step, we graft the student blocks one by one onto the…
AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation
Nanjing University of Posts and Telecommunications（南京邮电大学）；Surrey Institute for People-Centred Artificial Intelligence, University of Surrey（萨里大学以人为本人工智能研究所）
University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research, iFLYTEK Co. Ltd.（科大讯飞股份有限公司讯飞研究院）
In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher. The parameters of the teacher model are a momentum update of the student. Since our target features are generated online, AV2vec needs no iteration step like AV-HuBERT and the total training time cost is reduced to less than one-fifth. We further propose AV2vec-MLM in this study,…
In this work, we propose a technique to transfer speech recognition capabilities from audio speech recognition systems to visual speech recognizers, where our goal is to utilize audio data during lipreading model training. Impressive progress in the domain of speech recognition has been exhibited by audio and audio-visual systems. Nevertheless, there is still much to be explored with regards to visual speech recognition systems due to the visual ambiguity of some phonemes. To this end, the development of visual speech recognition models is crucial given the instability of audio models. The mai…
MuDD: A Multimodal Deception Detection Dataset and GSR-Guided Progressive Distillation for Non-Contact Deception Detection
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；School of Information and Software Engineering, University of Electronic Science and Technology of China（电子科技大学信息与软件工程学院）
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）；Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Wadhwani School of Data Science & AI（瓦德瓦尼数据科学与人工智能学院）
CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning
School of Computer Science and Electronic Engineering, University of Essex（埃塞克斯大学计算机科学与电子工程学院）；Institute for Analytics and Data Science, University of Essex（埃塞克斯大学分析与数据科学研究所）
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher. These existing distillation approaches simply focus on the improvement of \textit{knowledge quality}, but ignore the significant influence of \textit{knowledge quantity} on the distillation procedure. Opposed to the conventional distillation approaches, which extract knowledge from a fixed teacher computation graph, this paper explores a non-negligible research direction from a novel perspective of \textit{knowledge quantity} to further impro…
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）
One-class novelty detection is to identify anomalous instances that do not conform to the expected normal instances. In this paper, the Generative Adversarial Networks (GANs) based on encoder-decoder-encoder pipeline are used for detection and achieve state-of-the-art performance. However, deep neural networks are too over-parameterized to deploy on resource-limited devices. Therefore, Progressive Knowledge Distillation with GANs (PKDGAN) is proposed to learn compact and fast novelty detection networks. The P-KDGAN is a novel attempt to connect two standard GANs by the designed distillation lo…
Deep neural networks often have a huge number of parameters, which posts challenges in deployment in application scenarios with limited memory and computation capacity. Knowledge distillation is one approach to derive compact models from bigger ones. However, it has been observed that a converged heavy teacher model is strongly constrained for learning a compact student network and could make the optimization subject to poor local optima. In this paper, we propose ProKT, a new model-agnostic method by projecting the supervision signals of a teacher model into the student's parameter space. Suc…
The American University in Cairo（开罗美国大学）；Nahdet Misr AI（纳赫代特米斯尔人工智能公司）
Despite the advancement in the domain of audio and audio-visual speech recognition, visual speech recognition systems are still quite under-explored due to the visual ambiguity of some phonemes. In this work, we propose a new lip-reading model that combines three contributions. First, the model front-end adopts a spatio-temporal attention mechanism to help extract the informative data from the input visual frames. Second, the model back-end utilizes a sequence-level and frame-level Knowledge Distillation (KD) techniques that allow leveraging audio data during the visual model training. Third, …
Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition
School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
HDA-SELD: Hierarchical Cross-Modal Distillation with Multi-Level Data Augmentation for Low-Resource Audio-Visual Sound Event Localization and Detection
University of Science and Technology of China（中国科学技术大学）；University of Palermo（巴勒莫大学）；iFLYTEK Research（iFLYTEK研究院）
Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection
Zhejiang University（浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新区（滨江）区块链与数据安全研究院）；Shanghai Institute for Advanced Study, Zhejiang University（浙江大学上海高等研究院）；Qingdao Institute of Software College of Computer Science and Technology, China University of Petroleum (East China)（中国石油大学（华东）计算机科学与技术学院青岛软件学院）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Amazon Prime Video（亚马逊Prime Video）
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To address this challenge, we introduce a novel training framework based on cross-modal contrastive learning that uses progressive self-distillation and soft image-text alignments to more efficiently learn robust representations from noisy data. Our model distills its own knowledge to dynamically generate soft-alignment targets for a subset of images and captio…
Progressive trajectory matching for medical dataset distillation
National Institute of Health Data Science, Peking University（北京大学健康数据科学研究院）；Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机技术研究院）
MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Science（中国科学院大学人工智能学院）；Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）；Tongji University（同济大学）
Noah’s Ark Lab, Huawei Technologies（华为诺亚方舟实验室）；The University of Sydney（悉尼大学）
Adder Neural Networks (ANNs) which only contain additions bring us a new way of developing deep neural networks with low energy consumption. Unfortunately, there is an accuracy drop when replacing all convolution filters by adder filters. The main reason here is the optimization difficulty of ANNs using $\ell_1$-norm, in which the estimation of gradient in back propagation is inaccurate. In this paper, we present a novel method for further improving the performance of ANNs without increasing the trainable parameters via a progressive kernel based knowledge distillation (PKKD) method. A convolu…
Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
Hangzhou Dianzi University（杭州电子科技大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Xi’an Jiaotong University（西安交通大学）；Macao Polytechnic University（澳门 polytechnic university）
Texas State University（德克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）
Wearable sensor-based Human Action Recognition (HAR) has achieved remarkable success recently. However, the accuracy performance of wearable sensor-based HAR is still far behind the ones from the visual modalities-based system (i.e., RGB video, skeleton, and depth). Diverse input modalities can provide complementary cues and thus improve the accuracy performance of HAR, but how to take advantage of multi-modal data on wearable sensor-based HAR has rarely been explored. Currently, wearable devices, i.e., smartwatches, can only capture limited kinds of non-visual modality data. This hinders the …
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning
School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；School of Automation Engineering, University of Electronic Science and Technology of China（电子科技大学自动化工程学院）；The Hong Kong Polytechnic University（香港理工大学）；Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；No.1 Orthopedic Hospital of Chengdu（成都市第一骨科医院）
Progressive Self-Distillation for Ground-to-Aerial Perception Knowledge Transfer
Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；South China Normal University（华南师范大学）；Samsung Research（三星研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；Tencent PCG（腾讯平台与内容事业群）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even though these data modalities may not be semantically correlated. Rather than directly aligning the representations of different modalities, we compose audio, image, and video representations across modalities to uncover richer multi-modal knowledge. Our main idea is to learn a compositional embedding that closes the cross-modal semantic gap and captures the task…
