Metaphors play a pivotal role in expressing emotions, making them crucial for emotional intelligence. The advent of multimodal data and widespread communication has led to a proliferation of multimodal metaphors, amplifying the complexity of emotion classification compared to single-mode scenarios. However, the scarcity of research on constructing multimodal metaphorical fine-grained emotion datasets hampers progress in this domain. Moreover, existing studies predominantly focus on English, overlooking potential variations in emotional nuances across languages. To address these gaps, we introduce a multimodal dataset in Chinese comprising 5,000 text-image pairs of metaphorical advertisements. Each entry is meticulously annotated for metaphor occurrence, domain relations and fine-grained emotion classification encompassing joy, love, trust, fear, sadness, disgust, anger, surprise, anticipation, and neutral. Our dataset is publicly accessible (https://github.com/DUTIR-YSQ/EmoMeta), facilitating further advancements in this burgeoning field.
In this paper, we present a new automatic diagnosis method of facial acne vulgaris based on convolutional neural network. This method is proposed to overcome the shortcoming of classification types in previous methods. The core of our method is to extract features of images based on convolutional neural network and achieve classification by classifier. We design a binary classifier of skin-and-non-skin to detect skin area and a seven-classifier to achieve the classification of facial acne vulgaris and healthy skin. In the experiment, we compared the effectiveness of our convolutional neural network and the pre-trained VGG16 neural network on the ImageNet dataset. And we use the ROC curve and normal confusion matrix to evaluate the performance of the binary classifier and the seven-classifier. The results of our experiment show that the pre-trained VGG16 neural network is more effective in extracting image features. The classifiers based on the pre-trained VGG16 neural network achieve the skin detection and acne classification and have good robustness.
Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This work proposes a novel method that forces a set of base models to learn different features for a classification task. These models are combined in an ensemble to make a collective classification. The key finding is that by forcing the models to concentrate on different features, the classification accuracy is increased. To learn different feature concepts, a so-called feature distance loss is implemented on the feature maps. The experiments on benchmark convolutional neural networks (VGG16, ResNet, AlexNet), popular datasets (Cifar10, Cifar100, miniImageNet, NEU, BSD, TEX), and different training samples (3, 5, 10, 20, 50, 100 per class) show the effectiveness of the proposed feature loss. The proposed method outperforms classical ensemble versions of the base models. The Class Activation Maps explicitly prove the ability to learn different feature concepts. The code is available at: https://github.com/2Obe/Feature-Distance-Loss.git
Efficient categorization of historical documents is crucial for fields such as genealogy, legal research, and historical scholarship, where manual classification is impractical for large collections due to its labor-intensive and error-prone nature. To address this, we propose a representational learning strategy that integrates semantic segmentation and deep learning models such as ResNet, CLIP, Document Image Transformer (DiT), and masked auto-encoders (MAE), to generate embeddings that capture document features without predefined labels. To the best of our knowledge, we are the first to evaluate embeddings on fine-grained, unsupervised form classification. To improve these embeddings, we propose to first employ semantic segmentation as a preprocessing step. We contribute two novel datasets$\unicode{x2014}$the French 19th-century and U.S. 1950 Census records$\unicode{x2014}$to demonstrate our approach. Our results show the effectiveness of these various embedding techniques in distinguishing similar document types and indicate that applying semantic segmentation can greatly improve clustering and classification results. The census datasets are available at https://github.com/tahlor/census_forms
In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them. The model is pre-trained on four tasks simultaneously: Masked Language Modeling (MLM), Masked Object Classification (MOC), Masked Region Feature Regression (MRFR), and Image Text Matching (ITM). To further enhance the pre-training quality, we have collected a Large-scale weAk-supervised Image-Text (LAIT) dataset from Web. We first pre-train the model on this dataset, then conduct a second stage pre-training on Conceptual Captions and SBU Captions. Our experiments show that multi-stage pre-training strategy outperforms single-stage pre-training. We also fine-tune and evaluate our pre-trained ImageBERT model on image retrieval and text retrieval tasks, and achieve new state-of-the-art results on both MSCOCO and Flickr30k datasets.
Radio signal classification plays a pivotal role in identifying the modulation scheme used in received radio signals, which is essential for demodulation and proper interpretation of the transmitted information. Researchers have underscored the high susceptibility of ML algorithms for radio signal classification to adversarial attacks. Such vulnerability could result in severe consequences, including misinterpretation of critical messages, interception of classified information, or disruption of communication channels. Recent advancements in quantum computing have revolutionized theories and implementations of computation, bringing the unprecedented development of Quantum Machine Learning (QML). It is shown that quantum variational classifiers (QVCs) provide notably enhanced robustness against classical adversarial attacks in image classification. However, no research has yet explored whether QML can similarly mitigate adversarial threats in the context of radio signal classification. This work applies QVCs to radio signal classification and studies their robustness to various adversarial attacks. We also propose the novel application of the approximate amplitude encoding (AAE) technique to encode radio signal data efficiently. Our extensive simulation results present that attacks generated on QVCs transfer well to CNN models, indicating that these adversarial examples can fool neural networks that they are not explicitly designed to attack. However, the converse is not true. QVCs primarily resist the attacks generated on CNNs. Overall, with comprehensive simulations, our results shed new light on the growing field of QML by bridging knowledge gaps in QAML in radio signal classification and uncovering the advantages of applying QML methods in practical applications.
We propose an approach for learning category-level semantic segmentation purely from image-level classification tags indicating presence of categories. It exploits localization cues that emerge from training classification-tasked convolutional networks, to drive a "self-supervision" process that automatically labels a sparse, diverse training set of points likely to belong to classes of interest. Our approach has almost no hyperparameters, is modular, and allows for very fast training of segmentation in less than 3 minutes. It obtains competitive results on the VOC 2012 segmentation benchmark. More, significantly the modularity and fast training of our framework allows new classes to efficiently added for inference.
Deep learning is the current bet for image classification. Its greed for huge amounts of annotated data limits its usage in medical imaging context. In this scenario transfer learning appears as a prominent solution. In this report we aim to clarify how transfer learning schemes may influence classification results. We are particularly focused in the automated melanoma screening problem, a case of medical imaging in which transfer learning is still not widely used. We explored transfer with and without fine-tuning, sequential transfers and usage of pre-trained models in general and specific datasets. Although some issues remain open, our findings may drive future researches.
Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger architectures. Though CNNs achieved promising external classification behavior, understanding of their internal work mechanism is still limited. In this work, we attempt to understand the internal work mechanism of CNNs by probing the internal representations in two comprehensive aspects, i.e., visualizing patches in the representation spaces constructed by different layers, and visualizing visual information kept in each layer. We further compare CNNs with different depths and show the advantages brought by deeper architecture.
Hyperspectral images (HSIs) can distinguish materials with high number of spectral bands, which is widely adopted in remote sensing applications and benefits in high accuracy land cover classifications. However, HSIs processing are tangled with the problem of high dimensionality and limited amount of labelled data. To address these challenges, this paper proposes a deep learning architecture using three dimensional convolutional neural networks with spectral partitioning to perform effective feature extraction. We conduct experiments using Indian Pines and Salinas scenes acquired by NASA Airborne Visible/Infra-Red Imaging Spectrometer. In comparison to prior results, our architecture shows competitive performance for classification results over current methods.
In this work, we propose a new loss to improve feature discriminability and classification performance. Motivated by the adaptive cosine/coherence estimator (ACE), our proposed method incorporates angular information that is inherently learned by artificial neural networks. Our learnable ACE (LACE) transforms the data into a new "whitened" space that improves the inter-class separability and intra-class compactness. We compare our LACE to alternative state-of-the art softmax-based and feature regularization approaches. Our results show that the proposed method can serve as a viable alternative to cross entropy and angular softmax approaches. Our code is publicly available: https://github.com/GatorSense/LACE.
We propose a novel deep learning framework based on Vision Transformers (ViT) for one-class classification. The core idea is to use zero-centered Gaussian noise as a pseudo-negative class for latent space representation and then train the network using the optimal loss function. In prior works, there have been tremendous efforts to learn a good representation using varieties of loss functions, which ensures both discriminative and compact properties. The proposed one-class Vision Transformer (OCFormer) is exhaustively experimented on CIFAR-10, CIFAR-100, Fashion-MNIST and CelebA eyeglasses datasets. Our method has shown significant improvements over competing CNN based one-class classifier approaches.
This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features in the paradigm of kernel methods on infinite-dimensional Riemannian manifolds. Our formulation provides in particular a rich representation of image features by exploiting their non-linear correlations. Theoretically, we provide a finite-dimensional approximation of the Log-Hilbert-Schmidt (Log-HS) distance between covariance operators that is scalable to large datasets, while maintaining an effective discriminating capability. This allows us to efficiently approximate any continuous shift-invariant kernel defined using the Log-HS distance. At the same time, we prove that the Log-HS inner product between covariance operators is only approximable by its finite-dimensional counterpart in a very limited scenario. Consequently, kernels defined using the Log-HS inner product, such as polynomial kernels, are not scalable in the same way as shift-invariant kernels. Computationally, we apply the approximate Log-HS distance formulation to covariance operators of both handcrafted and convolutional features, exploiting both the expressiveness of these features and the power of the covariance representation. Empirically, we tested our framework on the task of image classification on twelve challenging datasets. In almost all cases, the results obtained outperform other state of the art methods, demonstrating the competitiveness and potential of our framework.
A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related attributes, e.g., using brown sparrow instead of sparrow. However, current zero-shot methods select a subset of attributes regardless of commonalities between the target classes, potentially providing no useful information that would have helped to distinguish between them. For instance, they may use color instead of bill shape to distinguish between sparrows and wrens, which are both brown. We propose Follow-up Differential Descriptions (FuDD), a zero-shot approach that tailors the class descriptions to each dataset and leads to additional attributes that better differentiate the target classes. FuDD first identifies the ambiguous classes for each image, and then uses a Large Language Model (LLM) to generate new class descriptions that differentiate between them. The new class descriptions resolve the initial ambiguity and help predict the correct label. In our experiments, FuDD consistently outperforms generic description ensembles and naive LLM-generated descriptions on 12 datasets. We show that differential descriptions are an effective tool to resolve class ambiguities, which otherwise significantly degrade the performance. We also show that high quality natural language class descriptions produced by FuDD result in comparable performance to few-shot adaptation methods.
Visual inspection, or industrial anomaly detection, is one of the most common quality control types in manufacturing. The task is to identify the presence of an anomaly given an image, e.g., a missing component on an image of a circuit board, for subsequent manual inspection. While industrial anomaly detection has seen a surge in recent years, most anomaly detection methods still utilize knowledge only from normal samples, failing to leverage the information from the frequently available anomalous samples. Additionally, they heavily rely on very general feature extractors pre-trained on common image classification datasets. In this paper, we address these shortcomings and propose the new anomaly detection system AnomalousPatchCore~(APC) based on a feature extractor fine-tuned with normal and anomalous in-domain samples and a subsequent memory bank for identifying unusual features. To fine-tune the feature extractor in APC, we propose three auxiliary tasks that address the different aspects of anomaly detection~(classification vs. localization) and mitigate the effect of the imbalance between normal and anomalous samples. Our extensive evaluation on the MVTec dataset shows that APC outperforms state-of-the-art systems in detecting anomalies, which is especially important in industrial anomaly detection given the subsequent manual inspection. In detailed ablation studies, we further investigate the properties of our APC.
Long-tailed distributions in image recognition pose a considerable challenge due to the severe imbalance between a few dominant classes with numerous examples and many minority classes with few samples. Recently, the use of large generative models to create synthetic data for image classification has been realized, but utilizing synthetic data to address the challenge of long-tailed recognition remains relatively unexplored. In this work, we proposed the use of synthetic data as a complement to long-tailed datasets to eliminate the impact of data imbalance. To tackle this real-synthetic mixed dataset, we designed a two-branch model that contains Synthetic-Aware and Unaware branches (SAU). The core ideas are (1) a synthetic-unaware branch for classification that mixes real and synthetic data and treats all data equally without distinguishing between them. (2) A synthetic-aware branch for improving the robustness of the feature extractor by distinguishing between real and synthetic data and learning their discrepancies. Extensive experimental results demonstrate that our method can improve the accuracy of long-tailed image recognition. Notably, our approach achieves state-of-the-art Top-1 accuracy and significantly surpasses other methods on CIFAR-10-LT and CIFAR-100-LT datasets across various imbalance factors. Our code is available at https://github.com/lgX1123/gm4lt.
Traditional Convolutional Neural Networks (CNNs) typically use the same activation function (usually ReLU) for all neurons with non-linear mapping operations. For example, the deep convolutional architecture Inception-v4 uses ReLU. To improve the classification performance of traditional CNNs, a new "Multi-function Convolutional Neural Network" (MCNN) is created by using different activation functions for different neurons. For $n$ neurons and $m$ different activation functions, there are a total of $m^n-m$ MCNNs and only $m$ traditional CNNs. Therefore, the best model is very likely to be chosen from MCNNs because there are $m^n-2m$ more MCNNs than traditional CNNs. For performance analysis, two different datasets for two applications (classifying handwritten digits from the MNIST database and classifying brain MRI images into one of the four stages of Alzheimer's disease (AD)) are used. For both applications, an activation function is randomly selected for each layer of a MCNN. For the AD diagnosis application, MCNNs using a newly created multi-function Inception-v4 architecture are constructed. Overall, simulations show that MCNNs can outperform traditional CNNs in terms of multi-class classification accuracy for both applications. An important future research work will be to efficiently select the best MCNN from $m^n-m$ candidate MCNNs. Current CNN software only provides users with partial functionality of MCNNs since different layers can use different activation functions but not individual neurons in the same layer. Thus, modifying current CNN software systems such as ResNets, DenseNets, and Dual Path Networks by using multiple activation functions and developing more effective and faster MCNN software systems and tools would be very useful to solve difficult practical image classification problems.
To mine the spectral-spatial information of target pixel in hyperspectral image classification (HSIC), convolutional neural network (CNN)-based models widely adopt patch-based input pattern, where a patch represents its central pixel and the neighbor pixels play auxiliary roles in the classification process. However, compared to the central pixel, its neighbor pixels often have different contributions for classification. Although many existing patch-based CNNs could adaptively emphasize the spatial neighbor information, most of them ignore the latent relationship between the center pixel and its neighbor pixels. Moreover, efficient spectral-spatial feature extraction has been a difficult yet vital topic for HSIC. To address the mentioned problems, a central vector oriented self-similarity network (CVSSN) is proposed for HSIC. Specifically, based on two similarity measures, we firstly design an adaptive weight addition based spectral vector self-similarity module (AWA-SVSS) in input space and a Euclidean distance based feature vector self-similarity module (ED-FVSS) in feature space to fully mine the central vector oriented spatial relationships. Besides, a spectral-spatial information fusion module (SSIF) is formulated as a new pattern to fuse the central 1D spectral vector and the corresponding 3D patch for efficient spectral-spatial feature learning of the subsequent modules. Moreover, we implement a channel spatial separation convolution module (CSS-Conv) and a scale information complementary convolution module (SIC-Conv) for efficient spectral-spatial feature learning. Extensive experimental results on four popular HSI data sets demonstrate the effectiveness and efficiency of the proposed method compared with other state-of-the-art methods. The source code is available at https://github.com/lms-07/CVSSN.
Self-supervised pre-training techniques have achieved remarkable progress in Document AI. Most multimodal pre-trained models use a masked language modeling objective to learn bidirectional representations on the text modality, but they differ in pre-training objectives for the image modality. This discrepancy adds difficulty to multimodal representation learning. In this paper, we propose \textbf{LayoutLMv3} to pre-train multimodal Transformers for Document AI with unified text and image masking. Additionally, LayoutLMv3 is pre-trained with a word-patch alignment objective to learn cross-modal alignment by predicting whether the corresponding image patch of a text word is masked. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model for both text-centric and image-centric Document AI tasks. Experimental results show that LayoutLMv3 achieves state-of-the-art performance not only in text-centric tasks, including form understanding, receipt understanding, and document visual question answering, but also in image-centric tasks such as document image classification and document layout analysis. The code and models are publicly available at \url{https://aka.ms/layoutlmv3}.
A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable concept) subsets of the data where an image classifier performs significantly worse. Motivated by observed gaps in prior work, we introduce a new framework for evaluating BDMs, SpotCheck, that uses synthetic image datasets to train models with known blindspots and a new BDM, PlaneSpot, that uses a 2D image representation. We use SpotCheck to run controlled experiments that identify factors that influence BDM performance (e.g., the number of blindspots in a model, or features used to define the blindspot) and show that PlaneSpot is competitive with and in many cases outperforms existing BDMs. Importantly, we validate these findings by designing additional experiments that use real image data from MS-COCO, a large image benchmark dataset. Our findings suggest several promising directions for future work on BDM design and evaluation. Overall, we hope that the methodology and analyses presented in this work will help facilitate a more rigorous science of blindspot discovery.