PyTorchKR Papers

“Image Classification”

총 17,584편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2312.12102공식 코드 · Papers with Code

I-CEE: Tailoring Explanations of Image Classification Models to User Expertise

Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to generate these explanations. Yet, there is relatively little emphasis on the user (the explainee) in this growing body of work and most XAI techniques generate "one-size-fits-all" explanations. To bridge this gap and achieve a step closer towards human-centered XAI, we present I-CEE, a framework that provides Image Classification Explanations tailored to User Expertise. Informed by existing work, I-CEE explains the decisions of image classification models by providing the user with an informative subset of training data (i.e., example images), corresponding local explanations, and model decisions. However, unlike prior work, I-CEE models the informativeness of the example images to depend on user expertise, resulting in different examples for different users. We posit that by tailoring the example set to user expertise, I-CEE can better facilitate users' understanding and simulatability of the model. To evaluate our approach, we conduct detailed experiments in both simulation and with human participants (N = 100) on multiple datasets. Experiments with simulated users show that I-CEE improves users' ability to accurately predict the model's decisions (simulatability) compared to baselines, providing promising preliminary results. Experiments with human participants demonstrate that our method significantly improves user simulatability accuracy, highlighting the importance of human-centered XAI

arXiv:2503.10731

Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images

Zero-shot learning holds tremendous potential for histopathology image analysis by enabling models to generalize to unseen classes without extensive labeled data. Recent advancements in vision-language models (VLMs) have expanded the capabilities of ZSL, allowing models to perform tasks without task-specific fine-tuning. However, applying VLMs to histopathology presents considerable challenges due to the complexity of histopathological imagery and the nuanced nature of diagnostic tasks. In this paper, we propose a novel framework called Multi-Resolution Prompt-guided Hybrid Embedding (MR-PHE) to address these challenges in zero-shot histopathology image classification. MR-PHE leverages multiresolution patch extraction to mimic the diagnostic workflow of pathologists, capturing both fine-grained cellular details and broader tissue structures critical for accurate diagnosis. We introduce a hybrid embedding strategy that integrates global image embeddings with weighted patch embeddings, effectively combining local and global contextual information. Additionally, we develop a comprehensive prompt generation and selection framework, enriching class descriptions with domain-specific synonyms and clinically relevant features to enhance semantic understanding. A similarity-based patch weighting mechanism assigns attention-like weights to patches based on their relevance to class embeddings, emphasizing diagnostically important regions during classification. Our approach utilizes pretrained VLM, CONCH for ZSL without requiring domain-specific fine-tuning, offering scalability and reducing dependence on large annotated datasets. Experimental results demonstrate that MR-PHE not only significantly improves zero-shot classification performance on histopathology datasets but also often surpasses fully supervised models.

arXiv:1805.02730

Building Disease Detection Algorithms with Very Small Numbers of Positive Samples

Although deep learning can provide promising results in medical image analysis, the lack of very large annotated datasets confines its full potential. Furthermore, limited positive samples also create unbalanced datasets which limit the true positive rates of trained models. As unbalanced datasets are mostly unavoidable, it is greatly beneficial if we can extract useful knowledge from negative samples to improve classification accuracy on limited positive samples. To this end, we propose a new strategy for building medical image analysis pipelines that target disease detection. We train a discriminative segmentation model only on normal images to provide a source of knowledge to be transferred to a disease detection classifier. We show that using the feature maps of a trained segmentation network, deviations from normal anatomy can be learned by a two-class classification network on an extremely unbalanced training dataset with as little as one positive for 17 negative samples. We demonstrate that even though the segmentation network is only trained on normal cardiac computed tomography images, the resulting feature maps can be used to detect pericardial effusion and cardiac septal defects with two-class convolutional classification networks.

arXiv:2211.15459

Classification of Human Monkeypox Disease Using Deep Learning Models and Attention Mechanisms

As the world is still trying to rebuild from the destruction caused by the widespread reach of the COVID-19 virus, and the recent alarming surge of human monkeypox disease outbreaks in numerous countries threatens to become a new global pandemic too. Human monkeypox disease syndromes are quite similar to chickenpox, and measles classic symptoms, with very intricate differences such as skin blisters, which come in diverse forms. Various deep-learning methods have shown promising performances in the image-based diagnosis of COVID-19, tumor cell, and skin disease classification tasks. In this paper, we try to integrate deep transfer-learning-based methods, along with a convolutional block attention module (CBAM), to focus on the relevant portion of the feature maps to conduct an image-based classification of human monkeypox disease. We implement five deep-learning models, VGG19, Xception, DenseNet121, EfficientNetB3, and MobileNetV2, along with integrated channel and spatial attention mechanisms, and perform a comparative analysis among them. An architecture consisting of Xception-CBAM-Dense layers performed better than the other models at classifying human monkeypox and other diseases with a validation accuracy of 83.89%.

arXiv:2411.00988

Retrieval-enriched zero-shot image classification in low-resource domains

Low-resource domains, characterized by scarce data and annotations, present significant challenges for language and visual understanding tasks, with the latter much under-explored in the literature. Recent advancements in Vision-Language Models (VLM) have shown promising results in high-resource domains but fall short in low-resource concepts that are under-represented (e.g. only a handful of images per category) in the pre-training set. We tackle the challenging task of zero-shot low-resource image classification from a novel perspective. By leveraging a retrieval-based strategy, we achieve this in a training-free fashion. Specifically, our method, named CoRE (Combination of Retrieval Enrichment), enriches the representation of both query images and class prototypes by retrieving relevant textual information from large web-crawled databases. This retrieval-based enrichment significantly boosts classification performance by incorporating the broader contextual information relevant to the specific class. We validate our method on a newly established benchmark covering diverse low-resource domains, including medical imaging, rare plants, and circuits. Our experiments demonstrate that CORE outperforms existing state-of-the-art methods that rely on synthetic data generation and model fine-tuning.

arXiv:2505.24301공식 코드 · Papers with Code

Category-aware EEG image generation based on wavelet transform and contrast semantic loss

Reconstructing visual stimuli from EEG signals is a crucial step in realizing brain-computer interfaces. In this paper, we propose a transformer-based EEG signal encoder integrating the Discrete Wavelet Transform (DWT) and the gating mechanism. Guided by the feature alignment and category-aware fusion losses, this encoder is used to extract features related to visual stimuli from EEG signals. Subsequently, with the aid of a pre-trained diffusion model, these features are reconstructed into visual stimuli. To verify the effectiveness of the model, we conducted EEG-to-image generation and classification tasks using the THINGS-EEG dataset. To address the limitations of quantitative analysis at the semantic level, we combined WordNet-based classification and semantic similarity metrics to propose a novel semantic-based score, emphasizing the ability of our model to transfer neural activities into visual representations. Experimental results show that our model significantly improves semantic alignment and classification accuracy, which achieves a maximum single-subject accuracy of 43\%, outperforming other state-of-the-art methods. The source code and supplementary material is available at https://github.com/zes0v0inn/DWT_EEG_Reconstruction/tree/main.

arXiv:1907.11503

DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients

The popularity of Convolutional Neural Network (CNN) in the field of Image Processing and Computer Vision has motivated researchers and industrialist experts across the globe to solve different challenges with high accuracy. The simplest way to train a CNN classifier is to directly feed the original RGB pixels images into the network. However, if we intend to classify images directly with its compressed data, the same approach may not work better, like in case of JPEG compressed images. This research paper investigates the issues of modifying the input representation of the JPEG compressed data, and then feeding into the CNN. The architecture is termed as DCT-CompCNN. This novel approach has shown that CNNs can also be trained with JPEG compressed DCT coefficients, and subsequently can produce a better performance in comparison with the conventional CNN approach. The efficiency of the modified input representation is tested with the existing ResNet-50 architecture and the proposed DCT-CompCNN architecture on a public image classification datasets like Dog Vs Cat and CIFAR-10 datasets, reporting a better performance

arXiv:2005.03337공식 코드 · Papers with Code

Wavelet Integrated CNNs for Noise-Robust Image Classification

Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.

논문 ID: document/8942469

Fusion of Convolutional Neural Network and Statistical Features for Texture classification

Texture is a fundamental characteristic of many types of images, especially those with significant rotation, scale illumination, and viewpoint change. Texture image classification is one of the challenging problems that have various applications such as remote sensing, material recognition, and computer-aided medical diagnosis, etc. Various Computer vision techniques have been used. More recently, Deep learning architectures demonstrated impressive results. This paper aims to investigate combining two feature extraction methods: Handcrafted-based and CNN-based in a two-stream neural network architecture. We believe that Statistical features could enhance the performance of the CNN architecture, especially in the case of small datasets. To test our approach we used two challenging datasets, the Describable Textures Dataset (DTD) and Flicker Material Database (FMD). Results showed that our two-stream neural network which has an image as a first stream and a statistical feature vector as a second stream achieve better results than a Convolutional neural network achieved with just the RGB image as input. The Xception network [9] combined with SIFT-FV demonstrated an accuracy superiority for both datasets.

arXiv:2209.14431

Increasing the Accuracy of a Neural Network Using Frequency Selective Mesh-to-Grid Resampling

Neural networks are widely used for almost any task of recognizing image content. Even though much effort has been put into investigating efficient network architectures, optimizers, and training strategies, the influence of image interpolation on the performance of neural networks is not well studied. Furthermore, research has shown that neural networks are often sensitive to minor changes in the input image leading to drastic drops of their performance. Therefore, we propose the use of keypoint agnostic frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks in this paper. This model-based interpolation method already showed that it is capable of outperforming common interpolation methods in terms of PSNR. Using an extensive experimental evaluation we show that depending on the network architecture and classification task the application of FSMR during training aids the learning process. Furthermore, we show that the usage of FSMR in the application phase is beneficial. The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.

arXiv:2301.12459

The Influences of Color and Shape Features in Visual Contrastive Learning

In the field of visual representation learning, performance of contrastive learning has been catching up with the supervised method which is commonly a classification convolutional neural network. However, most of the research work focuses on improving the accuracy of downstream tasks such as image classification and object detection. For visual contrastive learning, the influences of individual image features (e.g., color and shape) to model performance remain ambiguous. This paper investigates such influences by designing various ablation experiments, the results of which are evaluated by specifically designed metrics. While these metrics are not invented by us, we first use them in the field of representation evaluation. Specifically, we assess the contribution of two primary image features (i.e., color and shape) in a quantitative way. Experimental results show that compared with supervised representations, contrastive representations tend to cluster with objects of similar color in the representation space, and contain less shape information than supervised representations. Finally, we discuss that the current data augmentation is responsible for these results. We believe that exploring an unsupervised augmentation method that

arXiv:2312.06627

An adversarial attack approach for eXplainable AI evaluation on deepfake detection models

With the rising concern on model interpretability, the application of eXplainable AI (XAI) tools on deepfake detection models has been a topic of interest recently. In image classification tasks, XAI tools highlight pixels influencing the decision given by a model. This helps in troubleshooting the model and determining areas that may require further tuning of parameters. With a wide range of tools available in the market, choosing the right tool for a model becomes necessary as each one may highlight different sets of pixels for a given image. There is a need to evaluate different tools and decide the best performing ones among them. Generic XAI evaluation methods like insertion or removal of salient pixels/segments are applicable for general image classification tasks but may produce less meaningful results when applied on deepfake detection models due to their functionality. In this paper, we perform experiments to show that generic removal/insertion XAI evaluation methods are not suitable for deepfake detection models. We also propose and implement an XAI evaluation approach specifically suited for deepfake detection models.

arXiv:2412.12212

Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization

Text-to-image models are vulnerable to the stepwise "Divide-and-Conquer Attack" (DACA) that utilize a large language model to obfuscate inappropriate content in prompts by wrapping sensitive text in a benign narrative. To mitigate stepwise DACA attacks, we propose a two-layer method involving text summarization followed by binary classification. We assembled the Adversarial Text-to-Image Prompt (ATTIP) dataset ($N=940$), which contained DACA-obfuscated and non-obfuscated prompts. From the ATTIP dataset, we created two summarized versions: one generated by a small encoder model and the other by a large language model. Then, we used an encoder classifier and a GPT-4o classifier to perform content moderation on the summarized and unsummarized prompts. When compared with a classifier that operated over the unsummarized data, our method improved F1 score performance by 31%. Further, the highest recorded F1 score achieved (98%) was produced by the encoder classifier on a summarized ATTIP variant. This study indicates that pre-classification text summarization can inoculate content detection models against stepwise DACA obfuscations.

arXiv:2505.13137공식 코드 · Papers with Code

Learning to Adapt to Position Bias in Vision Transformer Classifiers

How discriminative position information is for image classification depends on the data. On the one hand, the camera position is arbitrary and objects can appear anywhere in the image, arguing for translation invariance. At the same time, position information is key for exploiting capture/center bias, and scene layout, e.g.: the sky is up. We show that position bias, the level to which a dataset is more easily solved when positional information on input features is used, plays a crucial role in the performance of Vision Transformers image classifiers. To investigate, we propose Position-SHAP, a direct measure of position bias by extending SHAP to work with position embeddings. We show various levels of position bias in different datasets, and find that the optimal choice of position embedding depends on the position bias apparent in the dataset. We therefore propose Auto-PE, a single-parameter position embedding extension, which allows the position embedding to modulate its norm, enabling the unlearning of position information. Auto-PE combines with existing PEs to match or improve accuracy on classification datasets.

arXiv:2311.12760공식 코드 · Papers with Code

High-resolution Image-based Malware Classification using Multiple Instance Learning

This paper proposes a novel method of classifying malware into families using high-resolution greyscale images and multiple instance learning to overcome adversarial binary enlargement. Current methods of visualisation-based malware classification largely rely on lossy transformations of inputs such as resizing to handle the large, variable-sized images. Through empirical analysis and experimentation, it is shown that these approaches cause crucial information loss that can be exploited. The proposed solution divides the images into patches and uses embedding-based multiple instance learning with a convolutional neural network and an attention aggregation function for classification. The implementation is evaluated on the Microsoft Malware Classification dataset and achieves accuracies of up to $96.6\%$ on adversarially enlarged samples compared to the baseline of $22.8\%$. The Python code is available online at https://github.com/timppeters/MIL-Malware-Images .

arXiv:2108.12828공식 코드 · Papers with Code

MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification

Recent research in disaster informatics demonstrates a practical and important use case of artificial intelligence to save human lives and suffering during natural disasters based on social media contents (text and images). While notable progress has been made using texts, research on exploiting the images remains relatively under-explored. To advance image-based approaches, we propose MEDIC (Available at: https://crisisnlp.qcri.org/medic/index.html), which is the largest social media image classification dataset for humanitarian response consisting of 71,198 images to address four different tasks in a multi-task learning setup. This is the first dataset of its kind: social media images, disaster response, and multi-task learning research. An important property of this dataset is its high potential to facilitate research on multi-task learning, which recently receives much interest from the machine learning community and has shown remarkable results in terms of memory, inference speed, performance, and generalization capability. Therefore, the proposed dataset is an important resource for advancing image-based disaster management and multi-task machine learning research. We experiment with different deep learning architectures and report promising results, which are above the majority baselines for all tasks. Along with the dataset, we also release all relevant scripts (https://github.com/firojalam/medic).

arXiv:2304.00500공식 코드 · Papers with Code

Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images

Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. While these models have numerous benefits across various sectors, they have also raised concerns about the potential misuse of fake images and cast new pressures on fake image detection. In this work, we pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models. Firstly, we conduct a comprehensive analysis of the performance of contrastive and classification-based visual features, respectively extracted from CLIP-based models and ResNet or ViT-based architectures trained on image classification datasets. Our results demonstrate that fake images share common low-level cues, which render them easily recognizable. Further, we devise a multimodal setting wherein fake images are synthesized by different textual captions, which are used as seeds for a generator. Under this setting, we quantify the performance of fake detection strategies and introduce a contrastive-based disentangling method that lets us analyze the role of the semantics of textual descriptions and low-level perceptual cues. Finally, we release a new dataset, called COCOFake, containing about 1.2M images generated from the original COCO image-caption pairs using two recent text-to-image diffusion models, namely Stable Diffusion v1.4 and v2.0.

arXiv:1509.06321

Evaluating the visualization of what a Deep Neural Network has learned

Deep Neural Networks (DNNs) have demonstrated impressive performance in complex machine learning tasks such as image classification or speech recognition. However, due to their multi-layer nonlinear structure, they are not transparent, i.e., it is hard to grasp what makes them arrive at a particular classification or recognition decision given a new unseen data sample. Recently, several approaches have been proposed enabling one to understand and interpret the reasoning embodied in a DNN for a single test image. These methods quantify the ''importance'' of individual pixels wrt the classification decision and allow a visualization in terms of a heatmap in pixel/input space. While the usefulness of heatmaps can be judged subjectively by a human, an objective quality measure is missing. In this paper we present a general methodology based on region perturbation for evaluating ordered collections of pixels such as heatmaps. We compare heatmaps computed by three different methods on the SUN397, ILSVRC2012 and MIT Places data sets. Our main result is that the recently proposed Layer-wise Relevance Propagation (LRP) algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method. We provide theoretical arguments to explain this result and discuss its practical implications. Finally, we investigate the use of heatmaps for unsupervised assessment of neural network performance.

arXiv:1909.11380

Beyond image classification: zooplankton identification with deep vector space embeddings

Zooplankton images, like many other real world data types, have intrinsic properties that make the design of effective classification systems difficult. For instance, the number of classes encountered in practical settings is potentially very large, and classes can be ambiguous or overlap. In addition, the choice of taxonomy often differs between researchers and between institutions. Although high accuracy has been achieved in benchmarks using standard classifier architectures, biases caused by an inflexible classification scheme can have profound effects when the output is used in ecosystem assessments and monitoring. Here, we propose using a deep convolutional network to construct a vector embedding of zooplankton images. The system maps (embeds) each image into a high-dimensional Euclidean space so that distances between vectors reflect semantic relationships between images. We show that the embedding can be used to derive classifications with comparable accuracy to a specific classifier, but that it simultaneously reveals important structures in the data. Furthermore, we apply the embedding to new classes previously unseen by the system, and evaluate its classification performance in such cases. Traditional neural network classifiers perform well when the classes are clearly defined a priori and have sufficiently large labeled data sets available. For practical cases in ecology as well as in many other fields this is not the case, and we argue that the vector embedding method presented here is a more appropriate approach.

arXiv:2204.14224

Enhancing Core Image Classification Using Generative Adversarial Networks (GANs)

In the thrilling world of oil exploration, drill core samples are key to unlocking geological information critical to finding lucrative oil deposits. Despite the importance of these samples, traditional core logging techniques are known to be laborious and, worse still, subjective. Thankfully, the industry has embraced an innovative solution core imaging that allows for nondestructive and noninvasive rapid characterization of large quantities of drill cores. Our preeminent research paper aims to tackle the pressing problem of core detection and classification. Using state-of-the-art techniques, we present a groundbreaking solution that will transform the industry. Our first challenge is detecting the cores and segmenting the holes in images, which we will achieve using the Faster RCNN and Mask RCNN models, respectively. Then, we will address the problem of filling the hole in the core image, utilizing the powerful Generative Adversarial Networks (GANs) and employing Contextual Residual Aggregation (CRA) to create high-frequency residuals for missing contents in images. Finally, we will apply sophisticated texture recognition models for the classification of core images, revealing crucial information to oil companies in their quest to uncover valuable oil deposits. Our research paper presents an innovative and groundbreaking approach to tackling the complex issues surrounding core detection and classification. By harnessing cutting-edge techniques and technologies, we are poised to revolutionize the industry and make significant contributions to the field of oil exploration.