PyTorchKR Papers

“Image Classification”

총 18,385편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1803.04349

Linking ImageNet WordNet Synsets with Wikidata

The linkage of ImageNet WordNet synsets to Wikidata items will leverage deep learning algorithm with access to a rich multilingual knowledge graph. Here I will describe our on-going efforts in linking the two resources and issues faced in matching the Wikidata and WordNet knowledge graphs. I show an example on how the linkage can be used in a deep learning setting with real-time image classification and labeling in a non-English language and discuss what opportunities lies ahead.

arXiv:1606.02407

Structured Convolution Matrices for Energy-efficient Deep learning

We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a family of structured convolutional matrices and achieve state-of-the-art trade-off between energy efficiency and classification accuracy for well-known image recognition tasks. We also put forward a novel method to train binary convolutional networks by utilising an existing connection between noisy-rectified linear units and binary activations.

arXiv:1412.6012

CITlab ARGUS for historical data tables

We describe CITlab's recognition system for the ANWRESH-2014 competition attached to the 14. International Conference on Frontiers in Handwriting Recognition, ICFHR 2014. The task comprises word recognition from segmented historical documents. The core components of our system are based on multi-dimensional recurrent neural networks (MDRNN) and connectionist temporal classification (CTC). The software modules behind that as well as the basic utility technologies are essentially powered by PLANET's ARGUS framework for intelligent text recognition and image processing.

arXiv:2006.11821

An Improved Relevance Feedback in CBIR

Relevance Feedback in Content-Based Image Retrieval is a method where the feedback of the performance is being used to improve itself. Prior works use feature re-weighting and classification techniques as the Relevance Feedback methods. This paper shows a novel addition to the prior methods to further improve the retrieval accuracy. In addition to all of these, the paper also shows a novel idea to even improve the 0-th iteration retrieval accuracy from the information of Relevance Feedback.

arXiv:2502.01873

Explaining Automatic Image Assessment

Previous work in aesthetic categorization and explainability utilizes manual labeling and classification to explain aesthetic scores. These methods require a complex labeling process and are limited in size. Our proposed approach attempts to explain aesthetic assessment models through visualizing dataset trends and automatic categorization of visual aesthetic features through training neural networks on different versions of the same dataset. By evaluating the models adapted to each specific modality using existing and novel metrics, we can capture and visualize aesthetic features and trends.

arXiv:2103.16022

Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays

Pre-trained models, e.g., from ImageNet, have proven to be effective in boosting the performance of many downstream applications. It is too demanding to acquire large-scale annotations to build such models for medical imaging. Meanwhile, there are numerous clinical data (in the form of images and text reports) stored in the hospital information systems. The paired image-text data from the same patient study could be utilized for the pre-training task in a weakly supervised manner. However, the integrity, accessibility, and amount of such raw data vary across different institutes, e.g., paired vs. unpaired (image-only or text-only). In this work, we introduce an image-text pre-training framework that can learn from these raw data with mixed data inputs, i.e., paired image-text data, a mixture of paired and unpaired data. The unpaired data can be sourced from one or multiple institutes (e.g., images from one institute coupled with texts from another). Specifically, we propose a transformer-based training framework for jointly learning the representation of both the image and text data. In addition to the existing masked language modeling, multi-scale masked vision modeling is introduced as a self-supervised training task for image patch regeneration. We not only demonstrate the feasibility of pre-training across mixed data inputs but also illustrate the benefits of adopting such pre-trained models in 3 chest X-ray applications, i.e., classification, retrieval, and image regeneration. Superior results are reported in comparison to prior art using MIMIC-CXR, NIH14-CXR, and OpenI-CXR datasets.

arXiv:2205.12438

Skin Cancer Diagnostics with an All-Inclusive Smartphone Application

Among the different types of skin cancer, melanoma is considered to be the deadliest and is difficult to treat at advanced stages. Detection of melanoma at earlier stages can lead to reduced mortality rates. Desktop-based computer-aided systems have been developed to assist dermatologists with early diagnosis. However, there is significant interest in developing portable, at-home melanoma diagnostic systems which can assess the risk of cancerous skin lesions. Here, we present a smartphone application that combines image capture capabilities with preprocessing and segmentation to extract the Asymmetry, Border irregularity, Color variegation, and Diameter (ABCD) features of a skin lesion. Using the feature sets, classification of malignancy is achieved through support vector machine classifiers. By using adaptive algorithms in the individual data-processing stages, our approach is made computationally light, user friendly, and reliable in discriminating melanoma cases from benign ones. Images of skin lesions are either captured with the smartphone camera or imported from public datasets. The entire process from image capture to classification runs on an Android smartphone equipped with a detachable 10x lens, and processes an image in less than a second. The overall performance metrics are evaluated on a public database of 200 images with Synthetic Minority Over-sampling Technique (SMOTE) (80% sensitivity, 90% specificity, 88% accuracy, and 0.85 area under curve (AUC)) and without SMOTE (55% sensitivity, 95% specificity, 90% accuracy, and 0.75 AUC). The evaluated performance metrics and computation times are comparable or better than previous methods. This all-inclusive smartphone application is designed to be easy-to-download and easy-to-navigate for the end user, which is imperative for the eventual democratization of such medical diagnostic systems.

arXiv:2308.00323

Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis

Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the Sports, Yoga, and Dance (SYD) postures for maintaining health conditions. The SYD pose categories are regarded as a fine-grained image classification task due to the complex movement of body parts. Deep Convolutional Neural Networks (CNNs) have attained significantly improved performance in solving various human body-pose estimation problems. Though decent progress has been achieved in yoga postures recognition using deep learning techniques, fine-grained sports, and dance recognition necessitates ample research attention. However, no benchmark public image dataset with sufficient inter-class and intra-class variations is available yet to address sports and dance postures classification. To solve this limitation, we have proposed two image datasets, one for 102 sport categories and another for 12 dance styles. Two public datasets, Yoga-82 which contains 82 classes and Yoga-107 represents 107 classes are collected for yoga postures. These four SYD datasets are experimented with the proposed deep model, SYD-Net, which integrates a patch-based attention (PbA) mechanism on top of standard backbone CNNs. The PbA module leverages the self-attention mechanism that learns contextual information from a set of uniform and multi-scale patches and emphasizes discriminative features to understand the semantic correlation among patches. Moreover, random erasing data augmentation is applied to improve performance. The proposed SYD-Net has achieved state-of-the-art accuracy on Yoga-82 using five base CNNs. SYD-Net's accuracy on other datasets is remarkable, implying its efficiency. Our Sports-102 and Dance-12 datasets are publicly available at https://sites.google.com/view/syd-net/home.

arXiv:1704.07657공식 코드 · Papers with Code

Decision Stream: Cultivating Deep Decision Trees

Various modifications of decision trees have been extensively used during the past years due to their high efficiency and interpretability. Tree node splitting based on relevant feature selection is a key step of decision tree learning, at the same time being their major shortcoming: the recursive nodes partitioning leads to geometric reduction of data quantity in the leaf nodes, which causes an excessive model complexity and data overfitting. In this paper, we present a novel architecture - a Decision Stream, - aimed to overcome this problem. Instead of building a tree structure during the learning process, we propose merging nodes from different branches based on their similarity that is estimated with two-sample test statistics, which leads to generation of a deep directed acyclic graph of decision rules that can consist of hundreds of levels. To evaluate the proposed solution, we test it on several common machine learning problems - credit scoring, twitter sentiment analysis, aircraft flight control, MNIST and CIFAR image classification, synthetic data classification and regression. Our experimental results reveal that the proposed approach significantly outperforms the standard decision tree learning methods on both regression and classification tasks, yielding a prediction error decrease up to 35%.

arXiv:2010.00741

Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation

The presence of any type of defect on the glass screen of smart devices has a great impact on their quality. We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass. Our model features the efficient recognition and labeling of three types of defects: scratches, light leakage due to cracks, and pits. Our method also differentiates between the defects and light reflections due to dust particles and sensor regions, which are classified as non-defect areas. We use a partially labeled dataset to achieve high robustness and excellent classification of defect and non-defect areas as compared to principal components analysis (PCA), multi-resolution and information-fusion-based algorithms. In addition, we incorporated two classifiers at different stages of our inspection framework for labeling and refining the unlabeled defects. We successfully enhanced the inspection depth-limit up to 5 microns. The experimental results show that our method outperforms manual inspection in testing the quality of glass screen samples by identifying defects on samples that have been marked as good by human inspection.

arXiv:2101.12073공식 코드 · Papers with Code

A Neural Few-Shot Text Classification Reality Check

Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision and Natural Language Processing. In the latter, such models used to rely on fixed word embeddings before the advent of transformers. Additionally, some models used in Computer Vision are yet to be tested in NLP applications. In this paper, we compare all these models, first adapting those made in the field of image processing to NLP, and second providing them access to transformers. We then test these models equipped with the same transformer-based encoder on the intent detection task, known for having a large number of classes. Our results reveal that while methods perform almost equally on the ARSC dataset, this is not the case for the Intent Detection task, where the most recent and supposedly best competitors perform worse than older and simpler ones (while all are given access to transformers). We also show that a simple baseline is surprisingly strong. All the new developed models, as well as the evaluation framework, are made publicly available.

arXiv:2109.13225

Predicting Driver Self-Reported Stress by Analyzing the Road Scene

Several studies have shown the relevance of biosignals in driver stress recognition. In this work, we examine something important that has been less frequently explored: We develop methods to test if the visual driving scene can be used to estimate a drivers' subjective stress levels. For this purpose, we use the AffectiveROAD video recordings and their corresponding stress labels, a continuous human-driver-provided stress metric. We use the common class discretization for stress, dividing its continuous values into three classes: low, medium, and high. We design and evaluate three computer vision modeling approaches to classify the driver's stress levels: (1) object presence features, where features are computed using automatic scene segmentation; (2) end-to-end image classification; and (3) end-to-end video classification. All three approaches show promising results, suggesting that it is possible to approximate the drivers' subjective stress from the information found in the visual scene. We observe that the video classification, which processes the temporal information integrated with the visual information, obtains the highest accuracy of $0.72$, compared to a random baseline accuracy of $0.33$ when tested on a set of nine drivers.

arXiv:2207.01376공식 코드 · Papers with Code

Task Discrepancy Maximization for Fine-grained Few-Shot Classification

Recognizing discriminative details such as eyes and beaks is important for distinguishing fine-grained classes since they have similar overall appearances. In this regard, we introduce Task Discrepancy Maximization (TDM), a simple module for fine-grained few-shot classification. Our objective is to localize the class-wise discriminative regions by highlighting channels encoding distinct information of the class. Specifically, TDM learns task-specific channel weights based on two novel components: Support Attention Module (SAM) and Query Attention Module (QAM). SAM produces a support weight to represent channel-wise discriminative power for each class. Still, since the SAM is basically only based on the labeled support sets, it can be vulnerable to bias toward such support set. Therefore, we propose QAM which complements SAM by yielding a query weight that grants more weight to object-relevant channels for a given query image. By combining these two weights, a class-wise task-specific channel weight is defined. The weights are then applied to produce task-adaptive feature maps more focusing on the discriminative details. Our experiments validate the effectiveness of TDM and its complementary benefits with prior methods in fine-grained few-shot classification.

arXiv:2505.21597

Optimizing Deep Learning for Skin Cancer Classification: A Computationally Efficient CNN with Minimal Accuracy Trade-Off

The rapid advancement of deep learning in medical image analysis has greatly enhanced the accuracy of skin cancer classification. However, current state-of-the-art models, especially those based on transfer learning like ResNet50, come with significant computational overhead, rendering them impractical for deployment in resource-constrained environments. This study proposes a custom CNN model that achieves a 96.7\% reduction in parameters (from 23.9 million in ResNet50 to 692,000) while maintaining a classification accuracy deviation of less than 0.022\%. Our empirical analysis of the HAM10000 dataset reveals that although transfer learning models provide a marginal accuracy improvement of approximately 0.022\%, they result in a staggering 13,216.76\% increase in FLOPs, considerably raising computational costs and inference latency. In contrast, our lightweight CNN architecture, which encompasses only 30.04 million FLOPs compared to ResNet50's 4.00 billion, significantly reduces energy consumption, memory footprint, and inference time. These findings underscore the trade-off between the complexity of deep models and their real-world feasibility, positioning our optimized CNN as a practical solution for mobile and edge-based skin cancer diagnostics.

arXiv:2311.07623

PadChannel: Improving CNN Performance through Explicit Padding Encoding

In convolutional neural networks (CNNs), padding plays a pivotal role in preserving spatial dimensions throughout the layers. Traditional padding techniques do not explicitly distinguish between the actual image content and the padded regions, potentially causing CNNs to incorrectly interpret the boundary pixels or regions that resemble boundaries. This ambiguity can lead to suboptimal feature extraction. To address this, we propose PadChannel, a novel padding method that encodes padding statuses as an additional input channel, enabling CNNs to easily distinguish genuine pixels from padded ones. By incorporating PadChannel into several prominent CNN architectures, we observed small performance improvements and notable reductions in the variances on the ImageNet-1K image classification task at marginal increases in the computational cost. The source code is available at https://github.com/AussieSeaweed/pad-channel

arXiv:2412.16651

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, \ie, adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the model's predicted labels. Due to the output complexity and deeper network architectures, research on adversarial examples for segmentation models is still limited, particularly for universal adversarial perturbations. In this paper, we propose a novel universal adversarial attack method designed for segmentation models, which includes dual feature separation and low-frequency scattering modules. The two modules guide the training of adversarial examples in the pixel and frequency space, respectively. Experiments demonstrate that our method achieves high attack success rates surpassing the state-of-the-art methods, and exhibits strong transferability across different models.

arXiv:2303.03462

Towards Composable Distributions of Latent Space Augmentations

We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety of image classification and generation tasks. Our framework is based on the Variational Autoencoder architecture and uses a novel approach for augmentation via linear transformation within the latent space itself. We explore losses and augmentation latent geometry to enforce the transformations to be composable and involuntary, thus allowing the transformations to be readily combined or inverted. Finally, we show these properties are better performing with certain pairs of augmentations, but we can transfer the latent space to other sets of augmentations to modify performance, effectively constraining the VAE's bottleneck to preserve the variance of specific augmentations and features of the image which we care about. We demonstrate the effectiveness of our approach with initial results on the MNIST dataset against both a standard VAE and a Conditional VAE. This latent augmentation method allows for much greater control and geometric interpretability of the latent space, making it a valuable tool for researchers and practitioners in the field.

arXiv:2112.01686

Make A Long Image Short: Adaptive Token Length for Vision Transformers

The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably increased computational cost. Motivated by the proverb "A picture is worth a thousand words" we aim to accelerate the ViT model by making a long image short. To this end, we propose a novel approach to assign token length adaptively during inference. Specifically, we first train a ViT model, called Resizable-ViT (ReViT), that can process any given input with diverse token lengths. Then, we retrieve the "token-length label" from ReViT and use it to train a lightweight Token-Length Assigner (TLA). The token-length labels are the smallest number of tokens to split an image that the ReViT can make the correct prediction, and TLA is learned to allocate the optimal token length based on these labels. The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference. Thus, the inference speed is boosted by reducing the token numbers in the ViT model. Our approach is general and compatible with modern vision transformer architectures and can significantly reduce computational expanse. We verified the effectiveness of our methods on multiple representative ViT models (DeiT, LV-ViT, and TimesFormer) across two tasks (image classification and action recognition).

arXiv:1902.06148

BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding

This paper presents the BigEarthNet that is a new large-scale multi-label Sentinel-2 benchmark archive. The BigEarthNet consists of 590,326 Sentinel-2 image patches, each of which is a section of i) 120x120 pixels for 10m bands; ii) 60x60 pixels for 20m bands; and iii) 20x20 pixels for 60m bands. Unlike most of the existing archives, each image patch is annotated by multiple land-cover classes (i.e., multi-labels) that are provided from the CORINE Land Cover database of the year 2018 (CLC 2018). The BigEarthNet is significantly larger than the existing archives in remote sensing (RS) and thus is much more convenient to be used as a training source in the context of deep learning. This paper first addresses the limitations of the existing archives and then describes the properties of the BigEarthNet. Experimental results obtained in the framework of RS image scene classification problems show that a shallow Convolutional Neural Network (CNN) architecture trained on the BigEarthNet provides much higher accuracy compared to a state-of-the-art CNN model pre-trained on the ImageNet (which is a very popular large-scale benchmark archive in computer vision). The BigEarthNet opens up promising directions to advance operational RS applications and research in massive Sentinel-2 image archives.

arXiv:1912.12385공식 코드 · Papers with Code

Statistical Loss and Analysis for Deep Learning in Hyperspectral Image Classification

Nowadays, deep learning methods, especially the convolutional neural networks (CNNs), have shown impressive performance on extracting abstract and high-level features from the hyperspectral image. However, general training process of CNNs mainly considers the pixel-wise information or the samples' correlation to formulate the penalization while ignores the statistical properties especially the spectral variability of each class in the hyperspectral image. These samples-based penalizations would lead to the uncertainty of the training process due to the imbalanced and limited number of training samples. To overcome this problem, this work characterizes each class from the hyperspectral image as a statistical distribution and further develops a novel statistical loss with the distributions, not directly with samples for deep learning. Based on the Fisher discrimination criterion, the loss penalizes the sample variance of each class distribution to decrease the intra-class variance of the training samples. Moreover, an additional diversity-promoting condition is added to enlarge the inter-class variance between different class distributions and this could better discriminate samples from different classes in hyperspectral image. Finally, the statistical estimation form of the statistical loss is developed with the training samples through multi-variant statistical analysis. Experiments over the real-world hyperspectral images show the effectiveness of the developed statistical loss for deep learning.