Traditional image classification techniques often produce unsatisfactory results when applied to high spatial resolution data because classes in high resolution images are not spectrally homogeneous. Texture offers an alternative source of information for classifying these images. This paper evaluates a recently developed, computationally simple texture metric called Weber Local Descriptor (WLD) for use in classifying high resolution QuickBird panchromatic data. We compared WLD with state-of-the art texture descriptors (TD) including Local Binary Pattern (LBP) and its rotation-invariant version LBPRIU. We also investigated whether incorporating VAR, a TD that captures brightness variation, would improve the accuracy of LBPRIU and WLD. We found that WLD generally produces more accurate classification results than the other TD we examined, and is also more robust to varying parameters. We have implemented an optimised algorithm for calculating WLD which makes the technique practical in terms of computation time. Overall, our results indicate that WLD is a promising approach for classifying high resolution remote sensing data.
This article aims to classify diabetic retinopathy (DR) disease into five different classes using an ensemble approach based on two popular pre-trained convolutional neural networks: VGG16 and Inception V3. The proposed model aims to leverage the strengths of the two individual nets to enhance the classification performance for diabetic retinopathy. The ensemble model architecture involves freezing a portion of the layers in each pre-trained model to utilize their learned representations effectively. Global average pooling layers are added to transform the output feature maps into fixed-length vectors. These vectors are then concatenated to form a consolidated representation of the input image. The ensemble model is trained using a dataset of diabetic retinopathy images (APTOS), divided into training and validation sets. During the training process, the model learns to classify the retinal images into the corresponding diabetic retinopathy classes. Experimental results on the test set demonstrate the efficacy of the proposed ensemble model for DR classification achieving an accuracy of 96.4%.
We introduce a new, challenging benchmark and a dataset, FungiTastic, based on fungal records continuously collected over a twenty-year span. The dataset is labeled and curated by experts and consists of about 350k multimodal observations of 5k fine-grained categories (species). The fungi observations include photographs and additional data, e.g., meteorological and climatic data, satellite images, and body part segmentation masks. FungiTastic is one of the few benchmarks that include a test set with DNA-sequenced ground truth of unprecedented label reliability. The benchmark is designed to support (i) standard closed-set classification, (ii) open-set classification, (iii) multi-modal classification, (iv) few-shot learning, (v) domain shift, and many more. We provide baseline methods tailored for many use-cases, a multitude of ready-to-use pre-trained models on HuggingFace and a framework for model training. A comprehensive documentation describing the dataset features and the baselines are available at https://bohemianvra.github.io/FungiTastic/ and https://www.kaggle.com/datasets/picekl/fungitastic.
과매개변수화된 심층 신경망의 학습 동역학(training dynamics)을 이해하고 활용하는 것은 현대 머신러닝의 핵심 과제로 남아 있습니다. 신경 붕괴(Neural Collapse, NC)에 관한 최근 연구 결과는 클래스 표현과 분류기가 고도로 구조화된 기하학적 형태를 보임을 보여주는 반면, 터널 효과(Tunnel Effect)는 일부 층(layer)만이 특징 추출에 필수적임을 시사합니다. 본 연구에서는 이 두 가지 관점을 결합하여 학습 도중 심층 신경망을 단순화하는 NC 기반의 학습 프레임워크를 제안합니다. 제안된 방법은 변동성 붕괴(variability collapse) 현상을 안정적이고 효율적으로 대변하는 대리 지표인 역 피셔 기준(Inverse Fisher Criterion)을 통해 표현 동역학을 모니터링하여, 특징 추출과 분류 사이의 분기점 및 단순화가 가능해지는 학습 단계를 모두 식별합니다. 이후 후속 층들을 경량 분류 헤드로 대체하고 축소된 모델에 대해 학습을 지속합니다. MLP, VGG, ResNet 아키텍처를 아우르는 이미지 분류 벤치마크 실험 결과, 제안 기법은 전체 모델과 대등한 정확도를 유지하면서도 상당한 매개변수 감소를 달성함을 보여줍니다. 실험 재현을 위한 코드는 https://github.com/LorenzoSciandra/NNS 에서 확인할 수 있습니다.
The ability to distinguish whether an image is generated by artificial intelligence (AI) is a crucial ingredient in human intelligence, usually accompanied by a complex and dialectical forensic and reasoning process. However, current fake image detection models and databases focus on binary classification without understandable explanations for the general populace. This weakens the credibility of authenticity judgment and may conceal potential model biases. Meanwhile, large multimodal models (LMMs) have exhibited immense visual-text capabilities on various tasks, bringing the potential for explainable fake image detection. Therefore, we pioneer the probe of LMMs for explainable fake image detection by presenting a multimodal database encompassing textual authenticity descriptions, the FakeBench. For construction, we first introduce a fine-grained taxonomy of generative visual forgery concerning human perception, based on which we collect forgery descriptions in human natural language with a human-in-the-loop strategy. FakeBench examines LMMs with four evaluation criteria: detection, reasoning, interpretation and fine-grained forgery analysis, to obtain deeper insights into image authenticity-relevant capabilities. Experiments on various LMMs confirm their merits and demerits in different aspects of fake image detection tasks. This research presents a paradigm shift towards transparency for the fake image detection area and reveals the need for greater emphasis on forensic elements in visual-language research and AI risk control. FakeBench will be available at https://github.com/Yixuan423/FakeBench.
The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it difficult to identify good video architectures, as most methods obtain similar performance on existing small-scale benchmarks. This paper re-evaluates state-of-the-art architectures in light of the new Kinetics Human Action Video dataset. Kinetics has two orders of magnitude more data, with 400 human action classes and over 400 clips per class, and is collected from realistic, challenging YouTube videos. We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics. We also introduce a new Two-Stream Inflated 3D ConvNet (I3D) that is based on 2D ConvNet inflation: filters and pooling kernels of very deep image classification ConvNets are expanded into 3D, making it possible to learn seamless spatio-temporal feature extractors from video while leveraging successful ImageNet architecture designs and even their parameters. We show that, after pre-training on Kinetics, I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.9% on HMDB-51 and 98.0% on UCF-101.
Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks. This paper studies the effects of different design choices in 3D group convolutional networks for video classification. We empirically demonstrate that the amount of channel interactions plays an important role in the accuracy of 3D group convolutional networks. Our experiments suggest two main findings. First, it is a good practice to factorize 3D convolutions by separating channel interactions and spatiotemporal interactions as this leads to improved accuracy and lower computational cost. Second, 3D channel-separated convolutions provide a form of regularization, yielding lower training accuracy but higher test accuracy compared to 3D convolutions. These two empirical findings lead us to design an architecture -- Channel-Separated Convolutional Network (CSN) -- which is simple, efficient, yet accurate. On Sports1M, Kinetics, and Something-Something, our CSNs are comparable with or better than the state-of-the-art while being 2-3 times more efficient.
Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class skews network output probabilities further from ground-truth distributions. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. By stochastically masking labels during loss computation, the method balances this ratio for each class, leading to improved recall on minority classes and improved precision on frequent classes. The ratio is estimated adaptively based on the network's performance by minimizing the KL divergence between predicted and ground-truth distributions. Whereas most existing approaches addressing data imbalance are mainly focused on single-label classification and do not generalize well to the multi-label case, this work proposes a general approach to solve the long-tail data imbalance issue for multi-label classification. PLM is versatile: it can be applied to most objective functions and it can be used alongside other strategies for class imbalance. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
Recent advancements in low-cost ensemble learning have demonstrated improved efficiency for image classification. However, the existing low-cost ensemble methods show relatively lower accuracy compared to conventional ensemble learning. In this paper, we propose a new low-cost ensemble learning, which can simultaneously achieve high efficiency and classification performance. A CNN is transformed into a multi-branch structure without introduction of additional components, which maintains the computational complexity as that of the original single model and also enhances diversity among the branches' outputs via sufficient separation between different pathways of the branches. In addition, we propose a new strategy that applies grouped convolution in the branches with different numbers of groups in different branches, which boosts the diversity of the branches' outputs. For training, we employ knowledge distillation using the ensemble of the outputs as the teacher signal. The high diversity among the outputs enables to form a powerful teacher, enhancing the individual branch's classification performance and consequently the overall ensemble performance. Experimental results show that our method achieves state-of-the-art classification accuracy and higher uncertainty estimation performance compared to previous low-cost ensemble methods. The code is available at https://github.com/hjdw2/SEMBG.
The ongoing crisis of the COVID-19 (Coronavirus disease 2019) pandemic has changed the world. According to the World Health Organization (WHO), 4 million people have died due to this disease, whereas there have been more than 180 million confirmed cases of COVID-19. The collapse of the health system in many countries has demonstrated the need of developing tools to automatize the diagnosis of the disease from medical imaging. Previous studies have used deep learning for this purpose. However, the performance of this alternative highly depends on the size of the dataset employed for training the algorithm. In this work, we propose a classification framework based on sparse coding in order to identify the pneumonia patterns associated with different pathologies. Specifically, each chest X-ray (CXR) image is partitioned into different tiles. The most relevant features extracted from PCA are then used to build the dictionary within the sparse coding procedure. Once images are transformed and reconstructed from the elements of the dictionary, classification is performed from the reconstruction errors of individual patches associated with each image. Performance is evaluated in a real scenario where simultaneously differentiation between four different pathologies: control vs bacterial pneumonia vs viral pneumonia vs COVID-19. The accuracy when identifying the presence of pneumonia is 93.85%, whereas 88.11% is obtained in the 4-class classification context. The excellent results and the pioneering use of sparse coding in this scenario evidence the applicability of this approach as an aid for clinicians in a real-world environment.
The last decade of computer vision has been dominated by Deep Learning architectures, thanks to their unparalleled success. Their performance, however, often comes at the cost of explainability owing to their highly non-linear nature. Consequently, a parallel field of eXplainable Artificial Intelligence (XAI) has developed with the aim of generating insights regarding the decision making process of deep learning models. An important problem in XAI is that of the generation of saliency maps. These are regions in an input image which contributed most towards the model's final decision. Most work in this regard, however, has been focused on image classification, and image segmentation - despite being a ubiquitous task - has not received the same attention. In the present work, we propose MiSuRe (Minimally Sufficient Region) as an algorithm to generate saliency maps for image segmentation. The goal of the saliency maps generated by MiSuRe is to get rid of irrelevant regions, and only highlight those regions in the input image which are crucial to the image segmentation decision. We perform our analysis on 3 datasets: Triangle (artificially constructed), COCO-2017 (natural images), and the Synapse multi-organ (medical images). Additionally, we identify a potential usecase of these post-hoc saliency maps in order to perform post-hoc reliability of the segmentation model.
This paper proposes a new technique for automatic face recognition using integrated peaks of the Hough transformed significant blocks of the binary gradient image. In this approach firstly the gradient of an image is calculated and a threshold is set to obtain a binary gradient image, which is less sensitive to noise and illumination changes. Secondly, significant blocks are extracted from the absolute gradient image, to extract pertinent information with the idea of dimension reduction. Finally the best fitted Hough peaks are extracted from the Hough transformed significant blocks for efficient face recognition. Then these Hough peaks are concatenated together, which are used as feature in classification process. The efficiency of the proposed method is demonstrated by the experiment on 1100 images from the FRAV2D face database, 2200 images from the FERET database, where the images vary in pose, expression, illumination and scale and 400 images from the ORL face database, where the images slightly vary in pose. Our method has shown 93.3%, 88.5% and 99% recognition accuracy for the FRAV2D, FERET and the ORL database respectively.
Scene parsing aims to recognize the object category of every pixel in scene images, and it plays a central role in image content understanding and computer vision applications. However, accurate scene parsing from unconstrained real-world data is still a challenging task. In this paper, we present the non-parametric Spatially Constrained Local Prior (SCLP) for scene parsing on realistic data. For a given query image, the non-parametric SCLP is learnt by first retrieving a subset of most similar training images to the query image and then collecting prior information about object co-occurrence statistics between spatial image blocks and between adjacent superpixels from the retrieved subset. The SCLP is powerful in capturing both long- and short-range context about inter-object correlations in the query image and can be effectively integrated with traditional visual features to refine the classification results. Our experiments on the SIFT Flow and PASCAL-Context benchmark datasets show that the non-parametric SCLP used in conjunction with superpixel-level visual features achieves one of the top performance compared with state-of-the-art approaches.
Medical image segmentation have drawn massive attention as it is important in biomedical image analysis. Good segmentation results can assist doctors with their judgement and further improve patients' experience. Among many available pipelines in medical image analysis, Unet is one of the most popular neural networks as it keeps raw features by adding concatenation between encoder and decoder, which makes it still widely used in industrial field. In the mean time, as a popular model which dominates natural language process tasks, transformer is now introduced to computer vision tasks and have seen promising results in object detection, image classification and semantic segmentation tasks. Therefore, the combination of transformer and Unet is supposed to be more efficient than both methods working individually. In this article, we propose Transformer-Unet by adding transformer modules in raw images instead of feature maps in Unet and test our network in CT82 datasets for Pancreas segmentation accordingly. We form an end-to-end network and gain segmentation results better than many previous Unet based algorithms in our experiment. We demonstrate our network and show our experimental results in this paper accordingly.
Self-replication is a key aspect of biological life that has been largely overlooked in Artificial Intelligence systems. Here we describe how to build and train self-replicating neural networks. The network replicates itself by learning to output its own weights. The network is designed using a loss function that can be optimized with either gradient-based or non-gradient-based methods. We also describe a method we call regeneration to train the network without explicit optimization, by injecting the network with predictions of its own parameters. The best solution for a self-replicating network was found by alternating between regeneration and optimization steps. Finally, we describe a design for a self-replicating neural network that can solve an auxiliary task such as MNIST image classification. We observe that there is a trade-off between the network's ability to classify images and its ability to replicate, but training is biased towards increasing its specialization at image classification at the expense of replication. This is analogous to the trade-off between reproduction and other tasks observed in nature. We suggest that a self-replication mechanism for artificial intelligence is useful because it introduces the possibility of continual improvement through natural selection.
This paper addresses the difficult problem of finding an optimal neural architecture design for a given image classification task. We propose a method that aggregates two main results of the previous state-of-the-art in neural architecture search. These are, appealing to the strong sampling efficiency of a search scheme based on sequential model-based optimization (SMBO), and increasing training efficiency by sharing weights among sampled architectures. Sequential search has previously demonstrated its capabilities to find state-of-the-art neural architectures for image classification. However, its computational cost remains high, even unreachable under modest computational settings. Affording SMBO with weight-sharing alleviates this problem. On the other hand, progressive search with SMBO is inherently greedy, as it leverages a learned surrogate function to predict the validation error of neural architectures. This prediction is directly used to rank the sampled neural architectures. We propose to attenuate the greediness of the original SMBO method by relaxing the role of the surrogate function so it predicts architecture sampling probability instead. We demonstrate with experiments on the CIFAR-10 dataset that our method, denominated Efficient progressive neural architecture search (EPNAS), leads to increased search efficiency, while retaining competitiveness of found architectures.
An accurate and timely detection of diseases and pests in rice plants can help farmers in applying timely treatment on the plants and thereby can reduce the economic losses substantially. Recent developments in deep learning based convolutional neural networks (CNN) have greatly improved the image classification accuracy. Being motivated by the success of CNNs in image classification, deep learning based approaches have been developed in this paper for detecting diseases and pests from rice plant images. The contribution of this paper is two fold: (i) State-of-the-art large scale architectures such as VGG16 and InceptionV3 have been adopted and fine tuned for detecting and recognizing rice diseases and pests. Experimental results show the effectiveness of these models with real datasets. (ii) Since large scale architectures are not suitable for mobile devices, a two-stage small CNN architecture has been proposed, and compared with the state-of-the-art memory efficient CNN architectures such as MobileNet, NasNet Mobile and SqueezeNet. Experimental results show that the proposed architecture can achieve the desired accuracy of 93.3\% with a significantly reduced model size (e.g., 99\% less size compared to that of VGG16).
In machine learning, the cost function is crucial because it measures how good or bad a system is. In image classification, well-known networks only consider modifying the network structures and applying cross-entropy loss at the end of the network. However, using only cross-entropy loss causes a network to stop updating weights when all training images are correctly classified. This is the problem of the early saturation. This paper proposes a novel cost function, called mixture separability loss (MSL), which updates the weights of the network even when most of the training images are accurately predicted. MSL consists of between-class and within-class loss. Between-class loss maximizes the differences between inter-class images, whereas within-class loss minimizes the similarities between intra-class images. We designed the proposed loss function to attach to different convolutional layers in the network in order to utilize intermediate feature maps. Experiments show that a network with MSL deepens the learning process and obtains promising results with some public datasets, such as Street View House Number (SVHN), Canadian Institute for Advanced Research (CIFAR), and our self-collected Inha Computer Vision Lab (ICVL) gender dataset.
Training end-to-end networks for classifying gigapixel size histopathological images is computationally intractable. Most approaches are patch-based and first learn local representations (patch-wise) before combining these local representations to produce image-level decisions. However, dividing large tissue structures into patches limits the context available to these networks, which may reduce their ability to learn representations from clinically relevant structures. In this paper, we introduce a novel attention-based network, the Holistic ATtention Network (HATNet) to classify breast biopsy images. We streamline the histopathological image classification pipeline and show how to learn representations from gigapixel size images end-to-end. HATNet extends the bag-of-words approach and uses self-attention to encode global information, allowing it to learn representations from clinically relevant tissue structures without any explicit supervision. It outperforms the previous best network Y-Net, which uses supervision in the form of tissue-level segmentation masks, by 8%. Importantly, our analysis reveals that HATNet learns representations from clinically relevant structures, and it matches the classification accuracy of human pathologists for this challenging test set. Our source code is available at \url{https://github.com/sacmehta/HATNet}
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which poses a significant challenge when attempting to debug models based on such explanations. To this end, we seek a methodology that can improve the faithfulness of an explanation method with respect to model predictions which does not require ground truth explanations. We achieve this through a novel explanation-driven data augmentation (EDDA) technique that augments the training data with occlusions inferred from model explanations; this is based on the simple motivating principle that \emph{if} the explainer is faithful to the model \emph{then} occluding salient regions for the model prediction should decrease the model confidence in the prediction, while occluding non-salient regions should not change the prediction. To verify that the proposed augmentation method has the potential to improve faithfulness, we evaluate EDDA using a variety of datasets and classification models. We demonstrate empirically that our approach leads to a significant increase of faithfulness, which can facilitate better debugging and successful deployment of image classification models in real-world applications.