In this paper, we will evaluate the performance of graph neural networks in two distinct domains: computer vision and reinforcement learning. In the computer vision section, we seek to learn whether a novel non-redundant representation for images as graphs can improve performance over trivial pixel to node mapping on a graph-level prediction graph, specifically image classification. For the reinforcement learning section, we seek to learn if explicitly modeling solving a Rubik's cube as a graph problem can improve performance over a standard model-free technique with no inductive bias.
Analyzing Pap cytology slides is an important tasks in detecting and grading precancerous and cancerous cervical cancer stages. Processing cytology images usually involve segmenting nuclei and overlapping cells. We introduce a cervical cytology dataset that can be used to evaluate nucleus detection, as well as image classification methods in the cytology image processing area. This dataset contains 93 real image stacks with their grade labels and manually annotated nuclei within images. We also present two methods: a baseline method based on a previously proposed approach, and a deep learning method, and compare their results with other state-of-the-art methods. Both the baseline method and the deep learning method outperform other state-of-the-art methods by significant margins. Along with the dataset, we publicly make the evaluation code and the baseline method available to download for further benchmarking.
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models.
Action classification in still images is an important task in computer vision. It is challenging as the appearances of ac- tions may vary depending on their context (e.g. associated objects). Manually labeling of context information would be time consuming and difficult to scale up. To address this challenge, we propose a method to automatically discover and cluster action concepts, and learn their classifiers from weakly supervised image-sentence corpora. It obtains candidate action concepts by extracting verb-object pairs from sentences and verifies their visualness with the associated images. Candidate action concepts are then clustered by using a multi-modal representation with image embeddings from deep convolutional networks and text embeddings from word2vec. More than one hundred human action concept classifiers are learned from the Flickr 30k dataset with no additional human effort and promising classification results are obtained. We further apply the AdaBoost algorithm to automatically select and combine relevant action concepts given an action query. Promising results have been shown on the PASCAL VOC 2012 action classification benchmark, which has zero overlap with Flickr30k.
Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, deep learning method usually requires numerous computational resources and high-quality labelled dataset, while the cost of high-performance computing and data annotation is expensive. In this paper, to reduce dependence on massive calculation and labelled samples, we propose a lightweight network architecture (LiteDenseNet) based on DenseNet for Hyperspectral Image Classification. Inspired by GoogLeNet and PeleeNet, we design a 3D two-way dense layer to capture the local and global features of the input. As convolution is a computationally intensive operation, we introduce group convolution to decrease calculation cost and parameter size further. Thus, the number of parameters and the consumptions of calculation are observably less than contrapositive deep learning methods, which means LiteDenseNet owns simpler architecture and higher efficiency. A series of quantitative experiences on 6 widely used hyperspectral datasets show that the proposed LiteDenseNet obtains the state-of-the-art performance, even though when the absence of labelled samples is severe.
Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables the use of more complex features when predicting transformation parameters. However, since STNs perform a purely spatial transformation, they do not, in the general case, have the ability to align the feature maps of a transformed image with those of its original. STNs are therefore unable to support invariance when transforming CNN feature maps. We present a simple proof for this and study the practical implications, showing that this inability is coupled with decreased classification accuracy. We therefore investigate alternative STN architectures that make use of complex features. We find that while deeper localization networks are difficult to train, localization networks that share parameters with the classification network remain stable as they grow deeper, which allows for higher classification accuracy on difficult datasets. Finally, we explore the interaction between localization network complexity and iterative image alignment.
The quality and generality of deep image features is crucially determined by the data they have been trained on, but little is known about this often overlooked effect. In this paper, we systematically study the effect of variations in the training data by evaluating deep features trained on different image sets in a few-shot classification setting. The experimental protocol we define allows to explore key practical questions. What is the influence of the similarity between base and test classes? Given a fixed annotation budget, what is the optimal trade-off between the number of images per class and the number of classes? Given a fixed dataset, can features be improved by splitting or combining different classes? Should simple or diverse classes be annotated? In a wide range of experiments, we provide clear answers to these questions on the miniImageNet, ImageNet and CUB-200 benchmarks. We also show how the base dataset design can improve performance in few-shot classification more drastically than replacing a simple baseline by an advanced state of the art algorithm.
We find that the way we choose to represent data labels can have a profound effect on the quality of trained models. For example, training an image classifier to regress audio labels rather than traditional categorical probabilities produces a more reliable classification. This result is surprising, considering that audio labels are more complex than simpler numerical probabilities or text. We hypothesize that high dimensional, high entropy label representations are generally more useful because they provide a stronger error signal. We support this hypothesis with evidence from various label representations including constant matrices, spectrograms, shuffled spectrograms, Gaussian mixtures, and uniform random matrices of various dimensionalities. Our experiments reveal that high dimensional, high entropy labels achieve comparable accuracy to text (categorical) labels on the standard image classification task, but features learned through our label representations exhibit more robustness under various adversarial attacks and better effectiveness with a limited amount of training data. These results suggest that label representation may play a more important role than previously thought. The project website is at \url{https://www.creativemachineslab.com/label-representation.html}.
This paper presents DeepI2P: a novel approach for cross-modality registration between an image and a point cloud. Given an image (e.g. from a rgb-camera) and a general point cloud (e.g. from a 3D Lidar scanner) captured at different locations in the same scene, our method estimates the relative rigid transformation between the coordinate frames of the camera and Lidar. Learning common feature descriptors to establish correspondences for the registration is inherently challenging due to the lack of appearance and geometric correlations across the two modalities. We circumvent the difficulty by converting the registration problem into a classification and inverse camera projection optimization problem. A classification neural network is designed to label whether the projection of each point in the point cloud is within or beyond the camera frustum. These labeled points are subsequently passed into a novel inverse camera projection solver to estimate the relative pose. Extensive experimental results on Oxford Robotcar and KITTI datasets demonstrate the feasibility of our approach. Our source code is available at https://github.com/lijx10/DeepI2P
Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.
Fine-grained bird image classification (FBIC) is not only of great significance for ecological monitoring and species identification, but also holds broad research value in the fields of image recognition and fine-grained visual modeling. Compared with general image classification tasks, FBIC poses more formidable challenges: 1) the differences in species size and imaging distance result in the varying sizes of birds presented in the images; 2) complex natural habitats often introduce strong background interference; 3) and highly flexible poses such as flying, perching, or foraging result in substantial intra-class variability. These factors collectively make it difficult for traditional methods to stably extract discriminative features, thereby limiting the generalizability and interpretability of models in real-world applications. To address these challenges, this paper proposes a fine-grained bird classification framework based on strip-aware spatial perception, which aims to capture long-range spatial dependencies across entire rows or columns in bird images, thereby enhancing the model's robustness and interpretability. The proposed method incorporates two novel modules: extensional perception aggregator (EPA) and channel semantic weaving (CSW). Specifically, EPA integrates local texture details with global structural cues by aggregating information across horizontal and vertical spatial directions. CSW further refines the semantic representations by adaptively fusing long-range and short-range information along the channel dimension. Built upon a ResNet-50 backbone, the model enables jump-wise connection of extended structural features across the spatial domain. Experimental results on the CUB-200-2011 dataset demonstrate that our framework achieves significant performance improvements while maintaining architectural efficiency.
Experiencing images with suitable music can greatly enrich the overall user experience. The proposed image analysis method treats an artwork image differently from a photograph image. Automatic image classification is performed using deep-learning based models. An illustrative analysis showcasing the ability of our deep-models to inherently learn and utilize perceptually relevant features when classifying artworks is also presented. The Mean Opinion Score (MOS) obtained from subjective assessments of the respective image and recommended music pairs supports the effectiveness of our approach.
Deep neural networks have achieved impressive experimental results in image classification, but can surprisingly be unstable with respect to adversarial perturbations, that is, minimal changes to the input image that cause the network to misclassify it. With potential applications including perception modules and end-to-end controllers for self-driving cars, this raises concerns about their safety. We develop a novel automated verification framework for feed-forward multi-layer neural networks based on Satisfiability Modulo Theory (SMT). We focus on safety of image classification decisions with respect to image manipulations, such as scratches or changes to camera angle or lighting conditions that would result in the same class being assigned by a human, and define safety for an individual decision in terms of invariance of the classification within a small neighbourhood of the original image. We enable exhaustive search of the region by employing discretisation, and propagate the analysis layer by layer. Our method works directly with the network code and, in contrast to existing methods, can guarantee that adversarial examples, if they exist, are found for the given region and family of manipulations. If found, adversarial examples can be shown to human testers and/or used to fine-tune the network. We implement the techniques using Z3 and evaluate them on state-of-the-art networks, including regularised and deep learning networks. We also compare against existing techniques to search for adversarial examples and estimate network robustness.
Change detection in multi-temporal remote sensing data enables crucial urban analysis and environmental monitoring applications. However, complex factors like illumination variance and occlusion make robust automated change interpretation challenging. We propose MaskChanger - a novel deep learning paradigm tailored for satellite image change detection. Our method adapts the segmentation-specialized Mask2Former architecture by incorporating Siamese networks to extract features separately from bi-temporal images, while retaining the original mask transformer decoder. To our knowledge, this is the first study in which change detection is converted from the existing per-pixel classification approach into a mask classification approach. Evaluated on the LEVIR-CD benchmark of over 600 very high-resolution image pairs exhibiting real-world rural and urban changes, MaskChanger achieves Fl-Score of 91.96%, outperforming prior transformer-based change detection approaches.
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.
This project focuses on the self-supervised training of convolutional neural networks (CNNs) and transformer networks for the task of image recognition. A simple siamese network with different backbones is used in order to maximize the similarity of two augmented transformed images from the same source image. In this way, the backbone is able to learn visual information without supervision. Finally, the method is evaluated on three image recognition datasets.
Early advancements in convolutional neural networks (CNNs) architectures are primarily driven by human expertise and by elaborate design processes. Recently, neural architecture search was proposed with the aim of automating the network design process and generating task-dependent architectures. While existing approaches have achieved competitive performance in image classification, they are not well suited to problems where the computational budget is limited for two reasons: (1) the obtained architectures are either solely optimized for classification performance, or only for one deployment scenario; (2) the search process requires vast computational resources in most approaches. To overcome these limitations, we propose an evolutionary algorithm for searching neural architectures under multiple objectives, such as classification performance and floating-point operations (FLOPs). The proposed method addresses the first shortcoming by populating a set of architectures to approximate the entire Pareto frontier through genetic operations that recombine and modify architectural components progressively. Our approach improves computational efficiency by carefully down-scaling the architectures during the search as well as reinforcing the patterns commonly shared among past successful architectures through Bayesian model learning. The integration of these two main contributions allows an efficient design of architectures that are competitive and in most cases outperform both manually and automatically designed architectures on benchmark image classification datasets: CIFAR, ImageNet, and human chest X-ray. The flexibility provided from simultaneously obtaining multiple architecture choices for different compute requirements further differentiates our approach from other methods in the literature. Code is available at https://github.com/mikelzc1990/nsganetv1
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem. In order to better learn the correlations among images features, as well as labels, we attempt to explore a latent space, where images and labels are embedded via two unique deep neural networks, respectively. To capture the relationships between image features and labels, we aim to learn a \emph{two-way} deep distance metric over the embedding space from two different views, i.e., the distance between one image and its labels is not only smaller than those distances between the image and its labels' nearest neighbors, but also smaller than the distances between the labels and other images corresponding to the labels' nearest neighbors. Moreover, a reconstruction module for recovering correct labels is incorporated into the whole framework as a regularization term, such that the label embedding space is more representative. Our model can be trained in an end-to-end manner. Experimental results on publicly available image datasets corroborate the efficacy of our method compared with the state-of-the-arts.
The rapid growth of image data has led to the development of advanced image processing and computer vision techniques, which are crucial in various applications such as image classification, image segmentation, and pattern recognition. Texture is an important feature that has been widely used in many image processing tasks. Therefore, analyzing and understanding texture plays a pivotal role in image analysis and understanding.Local binary pattern (LBP) is a powerful operator that describes the local texture features of images. This paper provides a novel mathematical representation of the LBP by separating the operator into three matrices, two of which are always fixed and do not depend on the input data. These fixed matrices are analyzed in depth, and a new algorithm is proposed to optimize them for improved classification performance. The optimization process is based on the singular value decomposition (SVD) algorithm. As a result, the authors present optimal LBPs that effectively describe the texture of human face images. Several experiment results presented in this paper convincingly verify the efficiency and superiority of the optimized LBPs for face detection and facial expression recognition tasks.
In Fine-Grained Visual Classification (FGVC), distinguishing highly similar subcategories remains a formidable challenge, often necessitating datasets with extensive variability. The acquisition and annotation of such FGVC datasets are notably difficult and costly, demanding specialized knowledge to identify subtle distinctions among closely related categories. Our study introduces a novel approach employing the Sequence Latent Diffusion Model (SLDM) for augmenting FGVC datasets, called Sequence Generative Image Augmentation (SGIA). Our method features a unique Bridging Transfer Learning (BTL) process, designed to minimize the domain gap between real and synthetically augmented data. This approach notably surpasses existing methods in generating more realistic image samples, providing a diverse range of pose transformations that extend beyond the traditional rigid transformations and style changes in generative augmentation. We demonstrate the effectiveness of our augmented dataset with substantial improvements in FGVC tasks on various datasets, models, and training strategies, especially in few-shot learning scenarios. Our method outperforms conventional image augmentation techniques in benchmark tests on three FGVC datasets, showcasing superior realism, variability, and representational quality. Our work sets a new benchmark and outperforms the previous state-of-the-art models in classification accuracy by 0.5% for the CUB-200-2011 dataset and advances the application of generative models in FGVC data augmentation.