In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion. Then, we introduce a joint decoding structure for emotion classification and valence regression in the decoding stage. A multi-task loss based on uncertainty is also designed to optimize the whole process. Finally, by combining three different structures on the posterior probability level, we obtain the final predictions of discrete and dimensional emotions. When tested on the dataset of multimodal emotion recognition challenge (MER 2023), the proposed framework yields consistent improvements in both emotion classification and valence regression. Our final system achieves state-of-the-art performance and ranks third on the leaderboard on MER-MULTI sub-challenge.
论文检索
输入标题、作者或关键词，从 7,876 篇学术成果中精准定位
The ACM Multimedia 2023 ComParE challenge focuses on classification/regression tasks for spoken customer-agent and emotionally rated conversations. The challenge baseline systems build upon the recent advancement in large-scale supervised/unsupervised foundational acoustic models that demonstrate consistently good performance across tasks. In this work, with the aim of improving the performance further, we present a novel multi-layer feature fusion method. In particular, the proposed approach leverages the hierarchical information from acoustic models using multi-layer statistics pooling, where we compute the weighted sum of layer-wise (mean and standard deviation) features. We further experimented with linguistic features and their late fusion with acoustic features, especially for subtasks involving complex conversations. Exploring various combinations of methods and features, we present four different systems tailored for each subchallenge, demonstrating significant performance gains over the baseline on the development and test set.
This paper presents our solution for the Requests Sub-challenge of the ACM Multimedia 2023 Computational Paralinguistics Challenge. Drawing upon the framework of self-supervised learning, we put forth an automated data augmentation technique for audio classification, accompanied by a multi-channel fusion strategy aimed at enhancing overall performance. Specifically, to tackle the issue of imbalanced classes in complaint classification, we propose an audio data augmentation method that generates appropriate augmentation strategies for the challenge dataset. Furthermore, recognizing the distinctive characteristics of the dual-channel HC-C dataset, we individually evaluate the classification performance of the left channel, right channel, channel difference, and channel sum, subsequently selecting the optimal integration approach. Our approach yields a significant improvement in performance when compared to the competitive baselines, particularly in the context of the complaint task. Moreover, our method demonstrates noteworthy cross-task transferability.
Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the neural network models through training with poisoned data and/or direct model editing, which leads to a common but false belief that backdoor attack can be easily avoided by properly protecting the model. In this paper, we show that backdoor attacks can be achieved without any model modification. Instead of injecting backdoor logic into the training data or the model, we propose to place a carefully-designed patch (namely backdoor patch) in front of the camera, which is fed into the model together with the input images. The patch can be trained to behave normally at most of the time, while producing wrong prediction when the input image contains an attacker-controlled trigger object. Our main techniques include an effective training method to generate the backdoor patch and a digital-physical transformation modeling method to enhance the feasibility of the patch in real deployments. Extensive experiments show that PatchBackdoor can be applied to common deep learning models (VGG, MobileNet, ResNet) with an attack success rate of 93% to 99% on classification tasks. Moreover, we implement PatchBackdoor in real-world scenarios and show that the attack is still threatening.
One big challenge to federated learning is the non-IID data distribution caused by imbalanced classes. Existing federated learning approaches tend to bias towards classes containing a larger number of samples during local updates, which causes unwanted drift in the local classifiers. To address this issue, we propose a classifier debiased federated learning framework named FedCD for non-IID data. We introduce a novel hierarchical prototype contrastive learning strategy to learn fine-grained prototypes for each class. The prototypes characterize the sample distribution within each class, which helps align the features learned in the representation layer of every client's local model. At the representation layer, we use fine-grained prototypes to rebalance the class distribution on each client and rectify the classification layer of each local model. To alleviate the bias of the classification layer of the local models, we incorporate a global information distillation method to enable the local classifier to learn decoupled global classification information. We also adaptively aggregate the class-level classifiers based on their quality to reduce the impact of unreliable classes in each aggregated classifier. This mitigates the impact of client-side classifier bias on the global classifier. Comprehensive experiments conducted on various datasets show that our method, FedCD, effectively corrects classifier bias and outperforms state-of-the-art federated learning methods.
Due to the popularity of Artificial Intelligence (AI) techniques, we are witnessing an increasing number of backdoor injection attacks that are designed to maliciously threaten Deep Neural Networks (DNNs) causing misclassification. Although there exist various defense methods that can effectively erase backdoors from DNNs, they greatly suffer from both high Attack Success Rate (ASR) and a non-negligible loss in Benign Accuracy (BA). Inspired by the observation that a backdoored DNN tends to form a new cluster in its feature spaces for poisoned data, in this paper, we propose a novel two-stage backdoor defense method, named MCLDef, based on Model-Contrastive Learning (MCL). MCLDef can purify the backdoored model by pulling the feature representations of poisoned data towards those of their clean data counterparts. Due to the shrunken cluster of poisoned data, the backdoor formed by end-to-end supervised learning can be effectively eliminated. Comprehensive experimental results show that, with only 5% of clean data, MCLDef significantly outperforms state-of-the-art defense methods by up to 95.79% reduction in ASR, while in most cases, the BA degradation can be controlled within less than 2%. Our code is available at https://github.com/Zhihao151/MCL.
Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder that affects socialization and is characterized by abnormal, restricted, or repetitive language behaviors. Symptoms typically start to appear around the age of 2, making early diagnosis essential for treatment. One standardized screening method is an autism-specific interview with children's parents. However, this diagnostic process requires highly experienced physicians, making questionnaire-based screening less effective. Recently, imaging-based diagnosis has emerged as a more objective option. In this paper, we propose a graph neural network-based model for ASD diagnosis using Diffusion Tensor Imaging (DTI) and functional Magnetic Resonance Imaging (fMRI) data. We first calculate the correlations of 90 brain regions based on the automated anatomical labeling (AAL) template using brain imaging data of DTI and fMRI. This enables the construction of a comprehensive network map that delineates the interconnections among various brain regions. Subsequently, we propose to utilize a graph neural network for the purpose of diagnosing ASD, wherein the graph derived from DTI serves as the adjacency matrix, while the map of the fMRI is utilized as the node features. To improve the performance of diagnosis, we introduce a regularization of maximum inter-class graph distance and minimum intra-class graph distance, in addition to graph classification. We then calculate the correlation matrix between functional areas based on the obtained 90 implicit features corresponding to the nodes of functional areas and their 90 eigenvalues. We also perform hypothesis tests on the 90 eigenvalues corresponding to ASD negative and positive groups in turn to discover the pathogenic functional areas by comparing the eigenvalue distributions between the two groups. Our experiments on 138 real-world samples demonstrate the superior performance of our proposed model for diagnosis.
UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization
PDF ↗The emergence of artificial intelligence-generated content (AIGC) has raised concerns about the authenticity of multimedia content in various fields. However, existing research for forgery content detection has focused mainly on binary classification tasks of complete videos, which has limited applicability in industrial settings. To address this gap, we propose UMMAFormer, a novel universal transformer framework for temporal forgery localization (TFL) that predicts forgery segments with multimodal adaptation. Our approach introduces a Temporal Feature Abnormal Attention (TFAA) module based on temporal feature reconstruction to enhance the detection of temporal differences. We also design a Parallel Cross-Attention Feature Pyramid Network (PCA-FPN) to optimize the Feature Pyramid Network (FPN) for subtle feature enhancement. To evaluate the proposed method, we contribute a novel Temporal Video Inpainting Localization (TVIL) dataset specifically tailored for video inpainting scenes. Our experiments show that our approach achieves state-of-the-art performance on benchmark datasets, including Lav-DF, TVIL, and Psynd, significantly outperforming previous methods. The code and data are available at https://github.com/ymhzyj/UMMAFormer/.
Although Domain Generalization (DG) problem has been fast-growing in the 2D image tasks, its exploration on 3D point cloud data is still insufficient and challenged by more complex and uncertain cross-domain variances with uneven inter-class modality distribution. In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model. Specifically, we first design a Multi-grained Sub-domain Alignment (MSA) method, which can constrain the learned representations to be domain-agnostic and discriminative, by performing a multi-grained feature alignment process between the splitted sub-domains from the single source dataset. Then, a Sample-level Domain-aware Attention (SDA) strategy is presented, which can selectively enhance easy-to-adapt samples from different sub-domains according to the sample-level inter-domain distance to avoid the negative transfer. Experiments demonstrate that our SUG can boost the generalization ability for unseen target domains, even outperforming the existing unsupervised domain adaptation methods that have to access extensive target domain data.
AbCoRD: Exploiting multimodal generative approach for Aspect-based Complaint and Rationale Detection
PDF ↗Valuable feedback can be found in customer reviews about a product or service, but it can be difficult to identify specific complaints and their underlying causes from the text. While various methods have been used to detect and analyze complaints, there has been little research on examining complaints at the aspect level and the reasons behind these complaints. To address this, we added rationale annotation for aspect-based complaint classes to a publicly available benchmark multimodal complaint dataset (CESAMARD) covering five domains (books, electronics, edibles, fashion, and miscellaneous). Current methods treat these tasks as classification problems and do not use external knowledge. Our study proposes a knowledge-infused, hierarchical, multimodal generative approach for aspect-based complaint and rationale detection that reframes the multitasking problem as a multimodal text-to-text generation task. Our approach achieved benchmark performance in the aspect-based complaint and rationale detection task through an extensive evaluation. We demonstrated that our model consistently outperformed all other baselines and state-of-the-art models in both full and few-shot settings. Our study contributes to the development of more accurate and efficient methods for extracting valuable insights from customer reviews to improve products and service 1
Data-Free Knowledge Distillation (DFKD) has started to make breakthroughs in classification tasks for large-scale datasets such as ImageNet-1k. Despite the encouraging results achieved, these modern DFKD methods still suffer from the massive waste of system storage and I/O resources. They either synthesize and store a vast amount of pseudo data or build thousands of generators. In this work, we introduce a storage-efficient scheme called Class-Expanding DFKD (CE-DFKD). It allows us to reduce storage costs by orders of magnitude in large-scale tasks using just one or a few generators without explicitly storing any data. The key to the success of our approach lies in alleviating the mode collapse of the generator by expanding its collapse range. Specifically, we first investigate and address the optimization conflict of previous single-generator-based DFKD methods by introducing conditional constraints. Then, we propose two class-expanding strategies to enrich the conditional information of the generator from both inter-class and intra-class perspectives. With the diversity of generated samples significantly enhanced, the proposed CE-DFKD outperforms existing methods by a large margin while achieving up to thousands of times storage savings. Besides the ImageNet-1k, the proposed CE-DFKD is compatible with widely used small-scale datasets and can be scaled to the more complex ImageNet-21k-P dataset, which was previously unreported in prior DFKD methods.
Pseudo-labelling-based semi-supervised learning (SSL) has demonstrated remarkable success in enhancing model performance by effectively leveraging a large amount of unlabeled data. However, existing studies focus mainly on rectifying individual predictions (i.e., pseudo-labels) on each unlabeled instance but ignore the overall prediction statistics from a global perspective. Such neglect may lead to model collapse and performance degradation in SSL, especially in label-scarce scenarios. In this paper, we emphasize the cruciality of global prediction constraints and propose a new SSL method that employs Entropy-based optimization on both Individual and Global predictions of unlabeled instances, dubbed EntInG. Specifically, we propose two criteria for leveraging unlabeled data in SSL: individual prediction entropy minimization (IPEM) and global distribution entropy maximization (GDEM). On the one hand, we show that current dominant SSL methods can be viewed as an implicit form of IPEM improved by recent augmentation techniques. On the other hand, we construct a new distribution loss to encourage GDEM, which greatly benefits producing better pseudo-labels for unlabeled data. Theoretical analysis also demonstrates that our proposed criteria can be derived by enforcing mutual information maximization on unlabeled instances. Despite its simplicity, our proposed method can achieve significant accuracy gains on popular SSL classification benchmarks.
We address the image-to-video adaptation task that aims to leverage labeled images and unlabeled videos for video recognition. There are two major challenges in this task, including the domain discrepancy between the two domains, and the modality gap between the image and video modalities. Existing methods mainly employ a two-stage paradigm by first adopting frame-level adaptation to reduce the domain discrepancy and then learning a spatio-temporal model to bridge the modality gap. In this paper, we provide a new perspective and propose a single-stage method that synthesizes video from the source static image and converts the image-to-video adaptation problem into a video-to-video adaptation problem. With the synthesized video, we present a simple baseline that a spatio-temporal model is trained with cross entropy loss with source labels and the Batch Nuclear norm Maximization loss to encourage the classification responses of target videos maintain the discriminability and diversity. We further propose a new pseudo label generation method that inherits the robustness of class prototype and the effectiveness of the small loss criterion. Based on the constructed baseline and the proposed pseudo label generation method, we train a model that achieves state-of-the-art performances or gets comparable performances on three standard benchmarks. Our codes are publicly available at https://github.com/junbaoZHUO/ST-I2V.
Satisfactory recognition performance has been achieved for simple and controllable printed molecular images. However, recognizing handwritten chemical structure images remains unresolved due to the inherent ambiguities in handwritten atoms and bonds, as well as the signifcant challenge of converting projected 2D molecular layouts into markup strings. Target to address these problems, this paper proposes an end-to-end framework for handwritten chemical structure images recognition, with novel structure-specific markup language (SSML) and random conditional guided decoder (RCGD). SSML alleviates ambiguity and complexity in Chemfig syntax by designing an innovative markup language to accurately depict molecular structures. Besides, we propose RCGD to address the issue of multiple path decoding of molecular structures, which is composed of conditional attention guidance, memory classification and path selection mechanisms. In order to fully confirm the effectiveness of the end-to-end method, a new database containing 50,000 handwritten chemical structure images (EDU-CHEMC) has been established. Experimental results demonstrate that compared to traditional SMILES sequences, our SSML can significantly reduces the semantic gap between chemical images and markup strings. It is worth noting that our method can also recognize invalid or non-existent organic molecular structures, making it highly applicable for tasks related to teaching evaluations in the fields of chemistry and biology education. The EDU-CHEMC will be released soon in https://github.com/iFLYTEK-CV/EDU-CHEMC.
Neural image compression has gained significant attention thanks to the remarkable success of deep neural networks. However, most existing neural image codecs focus solely on improving human vision perception. In this work, our objective is to enhance image compression methods for both human vision quality and machine vision tasks simultaneously. To achieve this, we introduce a novel approach to Partition, Transmit, Reconstruct, and Aggregate (PTRA) the latent representation of images to balance the optimizations for both aspects. By employing our method as a module in existing neural image codecs, we create a latent representation predictor that dynamically manages the bit-rate cost for machine vision tasks. To further improve the performance of auto-regressive-based coding techniques, we enhance our hyperprior network and predictor module with context modules, resulting in a reduction in bit-rate. The extensive experiments conducted on various machine vision benchmarks such as ILSVRC 2012, VOC 2007, VOC 2012, and COCO demonstrate the superiority of our newly proposed image compression framework. It outperforms existing neural image compression methods in multiple machine vision tasks including classification, segmentation, and detection, while maintaining high-quality image reconstruction for human vision.
AI has made significant progress in solving math problems, but geometry problems remain challenging due to their reliance on both text and diagrams. In the text description, symbolic characters such as "ABC" often serve as a bridge to connect the corresponding diagram. However, by simply tokenizing symbolic characters into individual letters (e.g., 'A', 'B' and 'C'), existing works fail to study them explicitly and thus lose the semantic relationship with the diagram. In this paper, we develop a symbolic character-aware model to fully explore the role of these characters in both text and diagram understanding and optimize the model under a multi-modal reasoning framework. In the text encoder, we propose merging individual symbolic characters to form one semantic unit along with geometric information from the corresponding diagram. For the diagram encoder, we pre-train it under a multi-label classification framework with the symbolic characters as labels. In addition, we enhance the geometry diagram understanding ability via a self-supervised learning method under the masked image modeling auxiliary task. By integrating the proposed model into a general encoder-decoder pipeline for solving geometry problems, we demonstrate its superiority on two benchmark datasets, including GeoQA and Geometry3K, with extensive experiments. Specifically, on GeoQA, the question-solving accuracy is increased from 60.0% to 64.1%, achieving a new state-of-the-art accuracy; on Geometry3K, we reduce the question average solving steps from 6.9 down to 6.0 with marginally higher solving accuracy.
Fine-grained image classification focuses on distinguishing objects from different similar subcategories, which requires the classification model to extract subtle yet discriminative descriptors. Recent Vision Transformer (ViT) has shown an enormous potential for this challenging task, but previous ViT-based methods have primarily focused on improving the relationship between image patches, neglecting the limited expressive capability caused by the single class token.To address this limitation, we propose to learn a Multi-part Token Transformer (MpT-Trans), which extends the class token to multiple tokens presenting various parts, enhancing the model's capability of extracting discriminative information. Specifically, our MpT-Trans model interpolates the vision transformer framework with two modules: (i) the Part-wise Shift Learning (PwSL) module is proposed to extend the single class token to a set of part tokens with differentiable shifts, enabling the model to extract informative representations from different perspectives; (ii) the Dual Contrastive Learning (DuCL) module is introduced to exploit the inter-class and inter-part relationships to regularize the learning of part tokens, enhancing their diversity and discrimination for accurate classification. Extensive experiments and ablation study demonstrate that the proposed MpT-Trans achieves state-of-the-art performance on various fine-grained image benchmark datasets, demonstrating the effectiveness of our proposed method.
Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy).
Lite-MKD: A Multi-modal Knowledge Distillation Framework for Lightweight Few-shot Action Recognition
Existing few-shot action recognition methods have placed primary focus on improving the recognition accuracy while neglecting another important indicator in practical scenarios, i.e., model efficiency. In this paper, we make the first attempt and propose a Lightweight Multi-modal Knowledge Distillation framework (Lite-MKD) for few-shot action recognition. In this framework, the teacher model conducts multi-modal learning to achieve a comprehensive fusion of the optical flow, depth, and appearance features of human movements, thus achieving a more robust representation of actions. The student model is utilized to learn to recognize actions from the single RGB modality at a lower computational cost under the guidance of the teacher. To fully explore and integrate multi-modal information, a hierarchical Multi-modal Fusion Module (MFM) is introduced in the teacher model. Besides, a multi-level Distinguish-to-Mimic (D2M) knowledge distillation component is proposed for the student model. D2M improves the ability of the student model to mimic the action classification probabilities of the teacher model by enhancing the distinguishability of the student model for different video categories in the support set. Extensive experiments on three action recognition datasets Kinetics, HMDB51, and UCF101 demonstrate our framework's effectiveness and stable generalization ability. With a much more lightweight network for inference, we achieve comparable performance to previous state-of-the-art methods. Our source code is available at https://github.com/HuiGuanLab/Lite-MKD
Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences
PDF ↗Cloth-Changing Person Re-Identification (CC-ReID) is a common and realistic problem since fashion constantly changes over time and people's aesthetic preferences are not set in stone. While most existing cloth-changing ReID methods focus on learning cloth-agnostic identity representations from coarse semantic cues (e.g. silhouettes and part segmentation maps), they neglect the continuous shape distributions at the pixel level. In this paper, we propose Continuous Surface Correspondence Learning (CSCL), a new shape embedding paradigm for cloth-changing ReID. CSCL establishes continuous correspondences between a 2D image plane and a canonical 3D body surface via pixel-to-vertex classification, which naturally aligns a person image to the surface of a 3D human model and simultaneously obtains pixel-wise surface embeddings. We further extract fine-grained shape features from the learned surface embeddings and then integrate them with global RGB features via a carefully designed cross-modality fusion module. The shape embedding paradigm based on 2D-3D correspondences remarkably enhances the model's global understanding of human body shape. To promote the study of ReID under clothing change, we construct 3D Dense Persons (DP3D), which is the first large-scale cloth-changing ReID dataset that provides densely annotated 2D-3D correspondences and a precise 3D mesh for each person image, while containing diverse cloth-changing cases over all four seasons. Experiments on both cloth-changing and cloth-consistent ReID benchmarks validate the effectiveness of our method.