Large datasets of sub-meter aerial imagery represented as orthophoto mosaics are widely available today, and these data sets may hold a great deal of untapped information. This imagery has a potential to locate several types of features; for example, forests, parking lots, airports, residential areas, or freeways in the imagery. However, the appearances of these things vary based on many things including the time that the image is captured, the sensor settings, processing done to rectify the image, and the geographical and cultural context of the region captured by the image. This thesis explores the use of deep convolutional neural networks to classify land use from very high spatial resolution (VHR), orthorectified, visible band multispectral imagery. Recent technological and commercial applications have driven the collection a massive amount of VHR images in the visible red, green, blue (RGB) spectral bands, this work explores the potential for deep learning algorithms to exploit this imagery for automatic land use/ land cover (LULC) classification.
Machine Learning has been applied in a wide range of tasks throughout the last years, ranging from image classification to autonomous driving and natural language processing. Restricted Boltzmann Machine (RBM) has received recent attention and relies on an energy-based structure to model data probability distributions. Notwithstanding, such a technique is susceptible to adversarial manipulation, i.e., slightly or profoundly modified data. An alternative to overcome the adversarial problem lies in the Generative Adversarial Networks (GAN), capable of modeling data distributions and generating adversarial data that resemble the original ones. Therefore, this work proposes to artificially generate RBMs using Adversarial Learning, where pre-trained weight matrices serve as the GAN inputs. Furthermore, it proposes to sample copious amounts of matrices and combine them into ensembles, alleviating the burden of training new models'. Experimental results demonstrate the suitability of the proposed approach under image reconstruction and image classification tasks, and describe how artificial-based ensembles are alternatives to pre-training vast amounts of RBMs.
Deep Neural Networks (DNNs) are becoming widespread, particularly in safety-critical areas. One prominent application is image recognition in autonomous driving, where the correct classification of objects, such as traffic signs, is essential for safe driving. Unfortunately, DNNs are prone to backdoors, meaning that they concentrate on attributes of the image that should be irrelevant for their correct classification. Backdoors are integrated into a DNN during training, either with malicious intent (such as a manipulated training process, because of which a yellow sticker always leads to a traffic sign being recognised as a stop sign) or unintentional (such as a rural background leading to any traffic sign being recognised as animal crossing, because of biased training data). In this paper, we introduce AGNES, a tool to detect backdoors in DNNs for image recognition. We discuss the principle approach on which AGNES is based. Afterwards, we show that our tool performs better than many state-of-the-art methods for multiple relevant case studies.
In the era of the Internet of Things (IoT), where smartphones, built-in systems, wireless sensors, and nearly every smart device connect through local networks or the internet, billions of smart things communicate with each other and generate vast amounts of time-series data. As IoT time-series data is high-dimensional and high-frequency, time-series classification or regression has been a challenging issue in IoT. Recently, deep learning algorithms have demonstrated superior performance results in time-series data classification in many smart and intelligent IoT applications. However, it is hard to explore the hidden dynamic patterns and trends in time-series. Recent studies show that transforming IoT data into images improves the performance of the learning model. In this paper, we present a review of these studies which use image transformation/encoding techniques in IoT domain. We examine the studies according to their encoding techniques, data types, and application areas. Lastly, we emphasize the challenges and future dimensions of image transformation.
Few-shot image classification aims to classify images from unseen novel classes with few samples. Recent works demonstrate that deep local descriptors exhibit enhanced representational capabilities compared to image-level features. However, most existing methods solely rely on either employing all local descriptors or directly utilizing partial descriptors, potentially resulting in the loss of crucial information. Moreover, these methods primarily emphasize the selection of query descriptors while overlooking support descriptors. In this paper, we propose a novel Task-Aware Adaptive Local Descriptors Selection Network (TALDS-Net), which exhibits the capacity for adaptive selection of task-aware support descriptors and query descriptors. Specifically, we compare the similarity of each local support descriptor with other local support descriptors to obtain the optimal support descriptor subset and then compare the query descriptors with the optimal support subset to obtain discriminative query descriptors. Extensive experiments demonstrate that our TALDS-Net outperforms state-of-the-art methods on both general and fine-grained datasets.
In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Existing studies demonstrated that a subnetwork can replace pointwise convolutional layers with significantly fewer parameters and fewer floating-point computations, while maintaining the learning capacity. In this paper, we propose an improved scheme for reducing the complexity of pointwise convolutions in DCNNs for image classification based on interleaved grouped filters without divisibility constraints. The proposed scheme utilizes grouped pointwise convolutions, in which each group processes a fraction of the input channels. It requires a number of channels per group as a hyperparameter Ch. The subnetwork of the proposed scheme contains two consecutive convolutional layers K and L, connected by an interleaving layer in the middle, and summed at the end. The number of groups of filters and filters per group for layers K and L is determined by exact divisions of the original number of input channels and filters by Ch. If the divisions were not exact, the original layer could not be substituted. In this paper, we refine the previous algorithm so that input channels are replicated and groups can have different numbers of filters to cope with non exact divisibility situations. Thus, the proposed scheme further reduces the number of floating-point computations (11%) and trainable parameters (10%) achieved by the previous method. We tested our optimization on an EfficientNet-B0 as a baseline architecture and made classification tests on the CIFAR-10, Colorectal Cancer Histology, and Malaria datasets. For each dataset, our optimization achieves a saving of 76%, 89%, and 91% of the number of trainable parameters of EfficientNet-B0, while keeping its test classification accuracy.
Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance. However, data obtaining andlabeling is expensive in practice. Data augmentation is one of themethods to alleviate this problem. In this paper, we conduct apreliminary study on how three variables (augmentation method,augmentation rate and size of basic dataset per label) can affectthe accuracy of deep learning for image classification. The studyprovides some guidelines: (1) it is better to use transformationsthat alter the geometry of the images rather than those justlighting and color. (2) 2-3 times augmentation rate is good enoughfor training. (3) the smaller amount of data, the more obviouscontributions could have.
This article describes Jigsaw, a convolutional neural network (CNN) used in geosciences and based on Inception but tailored for geoscientific analyses. Introduces JigsawHSI (based on Jigsaw) and uses it on the land-use land-cover (LULC) classification problem with the Indian Pines, Pavia University and Salinas hyperspectral image data sets. The network is compared against HybridSN, a spectral-spatial 3D-CNN followed by 2D-CNN that achieves state-of-the-art results on the datasets. This short article proves that JigsawHSI is able to meet or exceed HybridSN's performance in all three cases. It also introduces a generalized Jigsaw architecture in d-dimensional space for any number of multimodal inputs. Additionally, the use of jigsaw in geosciences is highlighted, while the code and toolkit are made available.
This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger. As part of arriving at this strong performance, we compare Vision Transformer (ViT) models pretrained using classification objectives to contrastively (SigLIP) pretrained ones. We find that, while slightly underperforming on standard image classification benchmarks, SigLIP-based PaLI shows superior performance across various multimodal benchmarks, especially on localization and visually-situated text understanding. We scale the SigLIP image encoder up to 2 billion parameters, and achieves a new state-of-the-art on multilingual cross-modal retrieval. We hope that PaLI-3, at only 5B parameters, rekindles research on fundamental pieces of complex VLMs, and could fuel a new generation of scaled-up models.
Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks. Currently, frozen features are not modified during training. On the other hand, when networks are trained directly on images, data augmentation is a standard recipe that improves performance with no substantial overhead. In this paper, we conduct an extensive pilot study on few-shot image classification that explores applying data augmentations in the frozen feature space, dubbed 'frozen feature augmentation (FroFA)', covering twenty augmentations in total. Our study demonstrates that adopting a deceptively simple pointwise FroFA, such as brightness, can improve few-shot performance consistently across three network architectures, three large pretraining datasets, and eight transfer datasets.
Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to near-perfect performance when considering hundreds of thousands of training samples. With the advent of large language models (LLMs), which are excellent few-shot learners, the question arises to what extent the document classification problem can be addressed with only a few training samples, or even none at all. In this paper, we investigate this question in the context of zero-shot prompting and few-shot model fine-tuning, with the aim of reducing the need for human-annotated training samples as much as possible.
Ancient artworks obtained in archaeological excavations usually suffer from a certain degree of fragmentation and physical degradation. Often, fragments of multiple artifacts from different periods or artistic styles could be found on the same site. With each fragment containing only partial information about its source, and pieces from different objects being mixed, categorizing broken artifacts based on their visual cues could be a challenging task, even for professionals. As classification is a common function of many machine learning models, the power of modern architectures can be harnessed for efficient and accurate fragment classification. In this work, we present a generalized deep-learning framework for predicting the artistic style of image fragments, achieving state-of-the-art results for pieces with varying styles and geometries.
The loss function is a key component in deep learning models. A commonly used loss function for classification is the cross entropy loss, which is a simple yet effective application of information theory for classification problems. Based on this loss, many other loss functions have been proposed,~\emph{e.g.}, by adding intra-class and inter-class constraints to enhance the discriminative ability of the learned features. However, these loss functions fail to consider the connections between the feature distribution and the model structure. Aiming at addressing this problem, we propose a channel correlation loss (CC-Loss) that is able to constrain the specific relations between classes and channels as well as maintain the intra-class and the inter-class separability. CC-Loss uses a channel attention module to generate channel attention of features for each sample in the training stage. Next, an Euclidean distance matrix is calculated to make the channel attention vectors associated with the same class become identical and to increase the difference between different classes. Finally, we obtain a feature embedding with good intra-class compactness and inter-class separability.Experimental results show that two different backbone models trained with the proposed CC-Loss outperform the state-of-the-art loss functions on three image classification datasets.
This paper introduces an automated vision system for animal detection in trail-camera images taken from a field under the administration of the Texas Parks and Wildlife Department. As traditional wildlife counting techniques are intrusive and labor intensive to conduct, trail-camera imaging is a comparatively non-intrusive method for capturing wildlife activity. However, given the large volume of images produced from trail-cameras, manual analysis of the images remains time-consuming and inefficient. We implemented a two-stage deep convolutional neural network pipeline to find animal-containing images in the first stage and then process these images to detect birds in the second stage. The animal classification system classifies animal images with overall 93% sensitivity and 96% specificity. The bird detection system achieves better than 93% sensitivity, 92% specificity, and 68% average Intersection-over-Union rate. The entire pipeline processes an image in less than 0.5 seconds as opposed to an average 30 seconds for a human labeler. We also addressed post-deployment issues related to data drift for the animal classification system as image features vary with seasonal changes. This system utilizes an automatic retraining algorithm to detect data drift and update the system. We introduce a novel technique for detecting drifted images and triggering the retraining procedure. Two statistical experiments are also presented to explain the prediction behavior of the animal classification system. These experiments investigate the cues that steers the system towards a particular decision. Statistical hypothesis testing demonstrates that the presence of an animal in the input image significantly contributes to the system's decisions.
Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods
Dealing with land cover classification of the new image sources has also turned to be a complex problem requiring large amount of memory and processing time. In order to cope with these problems, statistical learning has greatly helped in the last years to develop statistical retrieval and classification models that can ingest large amounts of Earth observation data. Kernel methods constitute a family of powerful machine learning algorithms, which have found wide use in remote sensing and geosciences. However, kernel methods are still not widely adopted because of the high computational cost when dealing with large scale problems, such as the inversion of radiative transfer models or the classification of high spatial-spectral-temporal resolution data. This paper introduces an efficient kernel method for fast statistical retrieval of bio-geo-physical parameters and image classification problems. The method allows to approximate a kernel matrix with a set of projections on random bases sampled from the Fourier domain. The method is simple, computationally very efficient in both memory and processing costs, and easily parallelizable. We show that kernel regression and classification is now possible for datasets with millions of examples and high dimensionality. Examples on atmospheric parameter retrieval from hyperspectral infrared sounders like IASI/Metop; large scale emulation and inversion of the familiar PROSAIL radiative transfer model on Sentinel-2 data; and the identification of clouds over landmarks in time series of MSG/Seviri images show the efficiency and effectiveness of the proposed technique.
Few-shot classification of hyperspectral images (HSI) faces the challenge of scarce labeled samples. Self-Supervised learning (SSL) and Few-Shot Learning (FSL) offer promising avenues to address this issue. However, existing methods often struggle to adapt to the spatial geometric diversity of HSIs and lack sufficient spectral prior knowledge. To tackle these challenges, we propose a method, Spectral-Spatial Self-Supervised Learning for Few-Shot Hyperspectral Image Classification (S4L-FSC), aimed at improving the performance of few-shot HSI classification. Specifically, we first leverage heterogeneous datasets to pretrain a spatial feature extractor using a designed Rotation-Mirror Self-Supervised Learning (RM-SSL) method, combined with FSL. This approach enables the model to learn the spatial geometric diversity of HSIs using rotation and mirroring labels as supervisory signals, while acquiring transferable spatial meta-knowledge through few-shot learning. Subsequently, homogeneous datasets are utilized to pretrain a spectral feature extractor via a combination of FSL and Masked Reconstruction Self-Supervised Learning (MR-SSL). The model learns to reconstruct original spectral information from randomly masked spectral vectors, inferring spectral dependencies. In parallel, FSL guides the model to extract pixel-level discriminative features, thereby embedding rich spectral priors into the model. This spectral-spatial pretraining method, along with the integration of knowledge from heterogeneous and homogeneous sources, significantly enhances model performance. Extensive experiments on four HSI datasets demonstrate the effectiveness and superiority of the proposed S4L-FSC approach for few-shot HSI classification.
Deep neural networks for video classification, just like image classification networks, may be subjected to adversarial manipulation. The main difference between image classifiers and video classifiers is that the latter usually use temporal information contained within the video. In this work we present a manipulation scheme for fooling video classifiers by introducing a flickering temporal perturbation that in some cases may be unnoticeable by human observers and is implementable in the real world. After demonstrating the manipulation of action classification of single videos, we generalize the procedure to make universal adversarial perturbation, achieving high fooling ratio. In addition, we generalize the universal perturbation and produce a temporal-invariant perturbation, which can be applied to the video without synchronizing the perturbation to the input. The attack was implemented on several target models and the transferability of the attack was demonstrated. These properties allow us to bridge the gap between simulated environment and real-world application, as will be demonstrated in this paper for the first time for an over-the-air flickering attack.
Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more uniform representations across all layers. We explore how these differences arise, finding crucial roles played by self-attention, which enables early aggregation of global information, and ViT residual connections, which strongly propagate features from lower to higher layers. We study the ramifications for spatial localization, demonstrating ViTs successfully preserve input spatial information, with noticeable effects from different classification methods. Finally, we study the effect of (pretraining) dataset scale on intermediate features and transfer learning, and conclude with a discussion on connections to new architectures such as the MLP-Mixer.
Whole-slide image (WSI) classification is a challenging task because 1) patches from WSI lack annotation, and 2) WSI possesses unnecessary variability, e.g., stain protocol. Recently, Multiple-Instance Learning (MIL) has made significant progress, allowing for classification based on slide-level, rather than patch-level, annotations. However, existing MIL methods ignore that all patches from normal slides are normal. Using this free annotation, we introduce a semi-supervision signal to de-bias the inter-slide variability and to capture the common factors of variation within normal patches. Because our method is orthogonal to the MIL algorithm, we evaluate our method on top of the recently proposed MIL algorithms and also compare the performance with other semi-supervised approaches. We evaluate our method on two public WSI datasets including Camelyon-16 and TCGA lung cancer and demonstrate that our approach significantly improves the predictive performance of existing MIL algorithms and outperforms other semi-supervised algorithms. We release our code at https://github.com/AITRICS/pathology_mil.