PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2409.06311

Seam Carving as Feature Pooling in CNN

This work investigates the potential of seam carving as a feature pooling technique within Convolutional Neural Networks (CNNs) for image classification tasks. We propose replacing the traditional max pooling layer with a seam carving operation. Our experiments on the Caltech-UCSD Birds 200-2011 dataset demonstrate that the seam carving-based CNN achieves better performance compared to the model utilizing max pooling, based on metrics such as accuracy, precision, recall, and F1-score. We further analyze the behavior of both approaches through feature map visualizations, suggesting that seam carving might preserve more structural information during the pooling process. Additionally, we discuss the limitations of our approach and propose potential future directions for research.

arXiv:1804.04338

MelanoGANs: High Resolution Skin Lesion Synthesis with GANs

Generative Adversarial Networks (GANs) have been successfully used to synthesize realistically looking images of faces, scenery and even medical images. Unfortunately, they usually require large training datasets, which are often scarce in the medical field, and to the best of our knowledge GANs have been only applied for medical image synthesis at fairly low resolution. However, many state-of-the-art machine learning models operate on high resolution data as such data carries indispensable, valuable information. In this work, we try to generate realistically looking high resolution images of skin lesions with GANs, using only a small training dataset of 2000 samples. The nature of the data allows us to do a direct comparison between the image statistics of the generated samples and the real dataset. We both quantitatively and qualitatively compare state-of-the-art GAN architectures such as DCGAN and LAPGAN against a modification of the latter for the task of image generation at a resolution of 256x256px. Our investigation shows that we can approximate the real data distribution with all of the models, but we notice major differences when visually rating sample realism, diversity and artifacts. In a set of use-case experiments on skin lesion classification, we further show that we can successfully tackle the problem of heavy class imbalance with the help of synthesized high resolution melanoma samples.

arXiv:2004.08790공식 코드 · Papers with Code

UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation

Recently, a growing interest has been seen in deep learning-based semantic segmentation. UNet, which is one of deep learning networks with an encoder-decoder architecture, is widely used in medical image segmentation. Combining multi-scale features is one of important factors for accurate segmentation. UNet++ was developed as a modified Unet by designing an architecture with nested and dense skip connections. However, it does not explore sufficient information from full scales and there is still a large room for improvement. In this paper, we propose a novel UNet 3+, which takes advantage of full-scale skip connections and deep supervisions. The full-scale skip connections incorporate low-level details with high-level semantics from feature maps in different scales; while the deep supervision learns hierarchical representations from the full-scale aggregated feature maps. The proposed method is especially benefiting for organs that appear at varying scales. In addition to accuracy improvements, the proposed UNet 3+ can reduce the network parameters to improve the computation efficiency. We further propose a hybrid loss function and devise a classification-guided module to enhance the organ boundary and reduce the over-segmentation in a non-organ image, yielding more accurate segmentation results. The effectiveness of the proposed method is demonstrated on two datasets. The code is available at: github.com/ZJUGiveLab/UNet-Version

arXiv:2111.06349공식 코드 · Papers with Code

Unsupervised Part Discovery from Contrastive Reconstruction

The goal of self-supervised visual representation learning is to learn strong, transferable image representations, with the majority of research focusing on object or scene level. On the other hand, representation learning at part level has received significantly less attention. In this paper, we propose an unsupervised approach to object part discovery and segmentation and make three contributions. First, we construct a proxy task through a set of objectives that encourages the model to learn a meaningful decomposition of the image into its parts. Secondly, prior work argues for reconstructing or clustering pre-computed features as a proxy to parts; we show empirically that this alone is unlikely to find meaningful parts; mainly because of their low resolution and the tendency of classification networks to spatially smear out information. We suggest that image reconstruction at the level of pixels can alleviate this problem, acting as a complementary cue. Lastly, we show that the standard evaluation based on keypoint regression does not correlate well with segmentation quality and thus introduce different metrics, NMI and ARI, that better characterize the decomposition of objects into parts. Our method yields semantic parts which are consistent across fine-grained but visually distinct categories, outperforming the state of the art on three benchmark datasets. Code is available at the project page: https://www.robots.ox.ac.uk/~vgg/research/unsup-parts/.

arXiv:2109.06365

From Heatmaps to Structural Explanations of Image Classifiers

This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained. The paper starts with describing the explainable neural network (XNN), which attempts to extract and visualize several high-level concepts purely from the deep network, without relying on human linguistic concepts. This helps users understand network classifications that are less intuitive and substantially improves user performance on a difficult fine-grained classification task of discriminating among different species of seagulls. Realizing that an important missing piece is a reliable heatmap visualization tool, we have developed I-GOS and iGOS++ utilizing integrated gradients to avoid local optima in heatmap generation, which improved the performance across all resolutions. During the development of those visualizations, we realized that for a significant number of images, the classifier has multiple different paths to reach a confident prediction. This has lead to our recent development of structured attention graphs (SAGs), an approach that utilizes beam search to locate multiple coarse heatmaps for a single image, and compactly visualizes a set of heatmaps by capturing how different combinations of image regions impact the confidence of a classifier. Through the research process, we have learned much about insights in building deep network explanations, the existence and frequency of multiple explanations, and various tricks of the trade that make explanations work. In this paper, we attempt to share those insights and opinions with the readers with the hope that some of them will be informative for future researchers on explainable deep learning.

arXiv:2112.00319공식 코드 · Papers with Code

Object-Aware Cropping for Self-Supervised Learning

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that randomly cropped and resized regions of a given image share information about the objects of interest, which the learned representation will capture. This assumption is mostly satisfied in datasets such as ImageNet where there is a large, centered object, which is highly likely to be present in random crops of the full image. However, in other datasets such as OpenImages or COCO, which are more representative of real world uncurated data, there are typically multiple small objects in an image. In this work, we show that self-supervised learning based on the usual random cropping performs poorly on such datasets. We propose replacing one or both of the random crops with crops obtained from an object proposal algorithm. This encourages the model to learn both object and scene level semantic representations. Using this approach, which we call object-aware cropping, results in significant improvements over scene cropping on classification and object detection benchmarks. For example, on OpenImages, our approach achieves an improvement of 8.8% mAP over random scene-level cropping using MoCo-v2 based pre-training. We also show significant improvements on COCO and PASCAL-VOC object detection and segmentation tasks over the state-of-the-art self-supervised learning approaches. Our approach is efficient, simple and general, and can be used in most existing contrastive and non-contrastive self-supervised learning frameworks.

arXiv:2212.03434공식 코드 · Papers with Code

Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer

The long-standing theory that a colour-naming system evolves under dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies, including analysing four decades of diachronic data from the Nafaanra language. This inspires us to explore whether machine learning could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette; meanwhile the Palette Branch utilises a key-point detection way to find proper colours in the palette among the whole colour space. By interacting with colour annotation, CQFormer is able to balance both the machine vision accuracy and colour perceptual structure such as distinct and stable colour distribution for discovered colour system. Very interestingly, we even observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining high performance in high-level recognition tasks such as classification and detection. Extensive experiments demonstrate the superior performance of our method with extremely low bit-rate colours, showing potential to integrate into quantisation network to quantities from image to network activation. The source code is available at https://github.com/ryeocthiv/CQFormer

arXiv:2503.19311공식 코드 · Papers with Code

LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text

This study addresses the technical bottlenecks in handling long text and the "hallucination" issue caused by insufficient short text information in remote sensing vision-language foundation models (VLFM). We propose a novel vision-language foundation model, LRSCLIP, and a multimodal dataset, LRS2M. The main contributions are as follows: (1) By integrating multi-source remote sensing data and adopting a large language model labeling strategy, we construct the LRS2M dataset, which contains 2 million image-text pairs, providing both short and long texts for the first time, thus solving the problem of semantic granularity limitations in existing datasets; (2) The design of the LRSCLIP architecture based on Long-CLIP's KPS module, which extends CLIP's text processing capacity and achieves fine-grained cross-modal feature alignment through a dual-text loss weighting mechanism. Experimental results show that LRSCLIP improves retrieval accuracy by 10\%-20\% over the Long-CLIP baseline in the zero-shot long-text cross-modal retrieval task. For the zero-shot short-text cross-modal retrieval task, LRSCLIP achieves improvements over the current best model, GeoRSCLIP, with increases of 0.17\%, 0.67\%, and 0.92\% in Text to Image R@1, Image to Text R@1, and mR on RSITMD, respectively, and 0.04\%, 2.93\%, and 1.28\% on RSICD. In the zero-shot image classification task (average accuracy=75.75\%) and semantic localization task (Rmi=0.7653), LRSCLIP achieves state-of-the-art performance. These results validate the dual advantages of fine-grained semantic understanding and global feature matching in LRSCLIP. This work provides a new benchmark model and data support for remote sensing multimodal learning. The related code has been open source and is available at https://github.com/MitsuiChen14/LRSCLIP.

arXiv:2011.09041

SoftSeg: Advantages of soft versus binary training for image segmentation

Most image segmentation algorithms are trained on binary masks formulated as a classification task per pixel. However, in applications such as medical imaging, this "black-and-white" approach is too constraining because the contrast between two tissues is often ill-defined, i.e., the voxels located on objects' edges contain a mixture of tissues. Consequently, assigning a single "hard" label can result in a detrimental approximation. Instead, a soft prediction containing non-binary values would overcome that limitation. We introduce SoftSeg, a deep learning training approach that takes advantage of soft ground truth labels, and is not bound to binary predictions. SoftSeg aims at solving a regression instead of a classification problem. This is achieved by using (i) no binarization after preprocessing and data augmentation, (ii) a normalized ReLU final activation layer (instead of sigmoid), and (iii) a regression loss function (instead of the traditional Dice loss). We assess the impact of these three features on three open-source MRI segmentation datasets from the spinal cord gray matter, the multiple sclerosis brain lesion, and the multimodal brain tumor segmentation challenges. Across multiple cross-validation iterations, SoftSeg outperformed the conventional approach, leading to an increase in Dice score of 2.0% on the gray matter dataset (p=0.001), 3.3% for the MS lesions, and 6.5% for the brain tumors. SoftSeg produces consistent soft predictions at tissues' interfaces and shows an increased sensitivity for small objects. The richness of soft labels could represent the inter-expert variability, the partial volume effect, and complement the model uncertainty estimation. The developed training pipeline can easily be incorporated into most of the existing deep learning architectures. It is already implemented in the freely-available deep learning toolbox ivadomed (https://ivadomed.org).

arXiv:1603.07697

Joint Projection and Dictionary Learning using Low-rank Regularization and Graph Constraints

In this paper, we aim at learning simultaneously a discriminative dictionary and a robust projection matrix from noisy data. The joint learning, makes the learned projection and dictionary a better fit for each other, so a more accurate classification can be obtained. However, current prevailing joint dimensionality reduction and dictionary learning methods, would fail when the training samples are noisy or heavily corrupted. To address this issue, we propose a joint projection and dictionary learning using low-rank regularization and graph constraints (JPDL-LR). Specifically, the discrimination of the dictionary is achieved by imposing Fisher criterion on the coding coefficients. In addition, our method explicitly encodes the local structure of data by incorporating a graph regularization term, that further improves the discriminative ability of the projection matrix. Inspired by recent advances of low-rank representation for removing outliers and noise, we enforce a low-rank constraint on sub-dictionaries of all classes to make them more compact and robust to noise. Experimental results on several benchmark datasets verify the effectiveness and robustness of our method for both dimensionality reduction and image classification, especially when the data contains considerable noise or variations.

arXiv:2003.14363

Automated Methods for Detection and Classification Pneumonia based on X-Ray Images Using Deep Learning

Recently, researchers, specialists, and companies around the world are rolling out deep learning and image processing-based systems that can fastly process hundreds of X-Ray and computed tomography (CT) images to accelerate the diagnosis of pneumonia such as SARS, COVID-19, and aid in its containment. Medical images analysis is one of the most promising research areas, it provides facilities for diagnosis and making decisions of a number of diseases such as MERS, COVID-19. In this paper, we present a comparison of recent Deep Convolutional Neural Network (DCNN) architectures for automatic binary classification of pneumonia images based fined tuned versions of (VGG16, VGG19, DenseNet201, Inception_ResNet_V2, Inception_V3, Resnet50, MobileNet_V2 and Xception). The proposed work has been tested using chest X-Ray & CT dataset which contains 5856 images (4273 pneumonia and 1583 normal). As result we can conclude that fine-tuned version of Resnet50, MobileNet_V2 and Inception_Resnet_V2 show highly satisfactory performance with rate of increase in training and validation accuracy (more than 96% of accuracy). Unlike CNN, Xception, VGG16, VGG19, Inception_V3 and DenseNet201 display low performance (more than 84% accuracy).

arXiv:2302.11102공식 코드 · Papers with Code

Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning

Face attribute research has so far used only simple binary attributes for facial hair; e.g., beard / no beard. We have created a new, more descriptive facial hair annotation scheme and applied it to create a new facial hair attribute dataset, FH37K. Face attribute research also so far has not dealt with logical consistency and completeness. For example, in prior research, an image might be classified as both having no beard and also having a goatee (a type of beard). We show that the test accuracy of previous classification methods on facial hair attribute classification drops significantly if logical consistency of classifications is enforced. We propose a logically consistent prediction loss, LCPLoss, to aid learning of logical consistency across attributes, and also a label compensation training strategy to eliminate the problem of no positive prediction across a set of related attributes. Using an attribute classifier trained on FH37K, we investigate how facial hair affects face recognition accuracy, including variation across demographics. Results show that similarity and difference in facial hairstyle have important effects on the impostor and genuine score distributions in face recognition. The code is at https:// github.com/ HaiyuWu/ LogicalConsistency.

arXiv:2305.10082

Imbalanced Aircraft Data Anomaly Detection

Anomaly detection in temporal data from sensors under aviation scenarios is a practical but challenging task: 1) long temporal data is difficult to extract contextual information with temporal correlation; 2) the anomalous data are rare in time series, causing normal/abnormal imbalance in anomaly detection, making the detector classification degenerate or even fail. To remedy the aforementioned problems, we propose a Graphical Temporal Data Analysis (GTDA) framework. It consists three modules, named Series-to-Image (S2I), Cluster-based Resampling Approach using Euclidean Distance (CRD) and Variance-Based Loss (VBL). Specifically, for better extracts global information in temporal data from sensors, S2I converts the data to curve images to demonstrate abnormalities in data changes. CRD and VBL balance the classification to mitigate the unequal distribution of classes. CRD extracts minority samples with similar features to majority samples by clustering and over-samples them. And VBL fine-tunes the decision boundary by balancing the fitting degree of the network to each class. Ablation experiments on the Flights dataset indicate the effectiveness of CRD and VBL on precision and recall, respectively. Extensive experiments demonstrate the synergistic advantages of CRD and VBL on F1-score on Flights and three other temporal datasets.

arXiv:2308.06884

Multi-Receiver Task-Oriented Communications via Multi-Task Deep Learning

This paper studies task-oriented, otherwise known as goal-oriented, communications, in a setting where a transmitter communicates with multiple receivers, each with its own task to complete on a dataset, e.g., images, available at the transmitter. A multi-task deep learning approach that involves training a common encoder at the transmitter and individual decoders at the receivers is presented for joint optimization of completing multiple tasks and communicating with multiple receivers. By providing efficient resource allocation at the edge of 6G networks, the proposed approach allows the communications system to adapt to varying channel conditions and achieves task-specific objectives while minimizing transmission overhead. Joint training of the encoder and decoders using multi-task learning captures shared information across tasks and optimizes the communication process accordingly. By leveraging the broadcast nature of wireless communications, multi-receiver task-oriented communications (MTOC) reduces the number of transmissions required to complete tasks at different receivers. Performance evaluation conducted on the MNIST, Fashion MNIST, and CIFAR-10 datasets (with image classification considered for different tasks) demonstrates the effectiveness of MTOC in terms of classification accuracy and resource utilization compared to single-task-oriented communication systems.

arXiv:2401.15055

Deep learning-based approach for tomato classification in complex scenes

Tracking ripening tomatoes is time consuming and labor intensive. Artificial intelligence technologies combined with those of computer vision can help users optimize the process of monitoring the ripening status of plants. To this end, we have proposed a tomato ripening monitoring approach based on deep learning in complex scenes. The objective is to detect mature tomatoes and harvest them in a timely manner. The proposed approach is declined in two parts. Firstly, the images of the scene are transmitted to the pre-processing layer. This process allows the detection of areas of interest (area of the image containing tomatoes). Then, these images are used as input to the maturity detection layer. This layer, based on a deep neural network learning algorithm, classifies the tomato thumbnails provided to it in one of the following five categories: green, brittle, pink, pale red, mature red. The experiments are based on images collected from the internet gathered through searches using tomato state across diverse languages including English, German, French, and Spanish. The experimental results of the maturity detection layer on a dataset composed of images of tomatoes taken under the extreme conditions, gave a good classification rate.

arXiv:2403.05297공식 코드 · Papers with Code

PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck

CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder. Therefore, they perform poorly on new classes or the classes whose names rarely appear on the Internet (e.g., scientific names of birds). For fine-grained classification, we propose PEEB - an explainable and editable classifier to (1) express the class name into a set of text descriptors that describe the visual parts of that class; and (2) match the embeddings of the detected parts to their textual descriptors in each class to compute a logit score for classification. In a zero-shot setting where the class names are unknown, PEEB outperforms CLIP by a huge margin (~10x in top-1 accuracy). Compared to part-based classifiers, PEEB is not only the state-of-the-art (SOTA) on the supervised-learning setting (88.80% and 92.20% accuracy on CUB-200 and Dogs-120, respectively) but also the first to enable users to edit the text descriptors to form a new classifier without any re-training. Compared to concept bottleneck models, PEEB is also the SOTA in both zero-shot and supervised-learning settings.

arXiv:2403.05030공식 코드 · Papers with Code

Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively search for inputs that may elicit harmful behaviors. Red-teaming and adversarial training (AT) are commonly used to improve robustness, however, they empirically struggle to fix failure modes that differ from the attacks used during training. In this work, we utilize latent adversarial training (LAT) to defend against vulnerabilities without leveraging knowledge of what they are or using inputs that elicit them. LAT makes use of the compressed, abstract, and structured latent representations of concepts that the network actually uses for prediction. Here, we use it to defend against failure modes without examples that elicit them. Specifically, we use LAT to remove trojans and defend against held-out classes of adversarial attacks. We show in image classification, text classification, and text generation tasks that LAT usually improves both robustness to novel attacks and performance on clean data relative to AT. This suggests that LAT can be a promising tool for defending against failure modes that are not explicitly identified by developers.

arXiv:2504.09072

MGS: Markov Greedy Sums for Accurate Low-Bitwidth Floating-Point Accumulation

We offer a novel approach, MGS (Markov Greedy Sums), to improve the accuracy of low-bitwidth floating-point dot products in neural network computations. In conventional 32-bit floating-point summation, adding values with different exponents may lead to loss of precision in the mantissa of the smaller term, which is right-shifted to align with the larger term's exponent. Such shifting (a.k.a. 'swamping') is a significant source of numerical errors in accumulation when implementing low-bitwidth dot products (e.g., 8-bit floating point) as the mantissa has a small number of bits. We avoid most swamping errors by arranging the terms in dot product summation based on their exponents and summing the mantissas without overflowing the low-bitwidth accumulator. We design, analyze, and implement the algorithm to minimize 8-bit floating point error at inference time for several neural networks. In contrast to traditional sequential summation, our method has significantly lowered numerical errors, achieving classification accuracy on par with high-precision floating-point baselines for multiple image classification tasks. Our dMAC hardware units can reduce power consumption by up to 34.1\% relative to conventional MAC units.

arXiv:2507.12568

Safeguarding Federated Learning-based Road Condition Classification

Federated Learning (FL) has emerged as a promising solution for privacy-preserving autonomous driving, specifically camera-based Road Condition Classification (RCC) systems, harnessing distributed sensing, computing, and communication resources on board vehicles without sharing sensitive image data. However, the collaborative nature of FL-RCC frameworks introduces new vulnerabilities: Targeted Label Flipping Attacks (TLFAs), in which malicious clients (vehicles) deliberately alter their training data labels to compromise the learned model inference performance. Such attacks can, e.g., cause a vehicle to mis-classify slippery, dangerous road conditions as pristine and exceed recommended speed. However, TLFAs for FL-based RCC systems are largely missing. We address this challenge with a threefold contribution: 1) we disclose the vulnerability of existing FL-RCC systems to TLFAs; 2) we introduce a novel label-distance-based metric to precisely quantify the safety risks posed by TLFAs; and 3) we propose FLARE, a defensive mechanism leveraging neuron-wise analysis of the output layer to mitigate TLFA effects. Extensive experiments across three RCC tasks, four evaluation metrics, six baselines, and three deep learning models demonstrate both the severity of TLFAs on FL-RCC systems and the effectiveness of FLARE in mitigating the attack impact.

arXiv:2110.01605

CCS-GAN: COVID-19 CT-scan classification with very few positive training images

We present a novel algorithm that is able to classify COVID-19 pneumonia from CT Scan slices using a very small sample of training images exhibiting COVID-19 pneumonia in tandem with a larger number of normal images. This algorithm is able to achieve high classification accuracy using as few as 10 positive training slices (from 10 positive cases), which to the best of our knowledge is one order of magnitude fewer than the next closest published work at the time of writing. Deep learning with extremely small positive training volumes is a very difficult problem and has been an important topic during the COVID-19 pandemic, because for quite some time it was difficult to obtain large volumes of COVID-19 positive images for training. Algorithms that can learn to screen for diseases using few examples are an important area of research. We present the Cycle Consistent Segmentation Generative Adversarial Network (CCS-GAN). CCS-GAN combines style transfer with pulmonary segmentation and relevant transfer learning from negative images in order to create a larger volume of synthetic positive images for the purposes of improving diagnostic classification performance. The performance of a VGG-19 classifier plus CCS-GAN was trained using a small sample of positive image slices ranging from at most 50 down to as few as 10 COVID-19 positive CT-scan images. CCS-GAN achieves high accuracy with few positive images and thereby greatly reduces the barrier of acquiring large training volumes in order to train a diagnostic classifier for COVID-19.