In recent years, image forensics has attracted more and more attention, and many forensic methods have been proposed for identifying image processing operations. Up to now, most existing methods are based on hand crafted features, and just one specific operation is considered in their methods. In many forensic scenarios, however, multiple classification for various image processing operations is more practical. Besides, it is difficult to obtain effective features by hand for some image processing operations. In this paper, therefore, we propose a new convolutional neural network (CNN) based method to adaptively learn discriminative features for identifying typical image processing operations. We carefully design the high pass filter bank to get the image residuals of the input image, the channel expansion layer to mix up the resulting residuals, the pooling layers, and the activation functions employed in our method. The extensive results show that the proposed method can outperform the currently best method based on hand crafted features and three related methods based on CNN for image steganalysis and/or forensics, achieving the state-of-the-art results. Furthermore, we provide more supplementary results to show the rationality and robustness of the proposed model.
Sentiment analysis is crucial for extracting social signals from social media content. Due to the prevalence of images in social media, image sentiment analysis is receiving increasing attention in recent years. However, most existing systems are black-boxes that do not provide insight on how image content invokes sentiment and emotion in the viewers. Psychological studies have confirmed that salient objects in an image often invoke emotions. In this work, we investigate more fine-grained and more comprehensive interaction between visual saliency and visual sentiment. In particular, we partition images in several primary scene-type dimensions, including: open-closed, natural-manmade, indoor-outdoor, and face-noface. Using state of the art saliency detection algorithm and sentiment classification algorithm, we examine how the sentiment of the salient region(s) in an image relates to the overall sentiment of the image. The experiments on a representative image emotion dataset have shown interesting correlation between saliency and sentiment in different scene types and in turn shed light on the mechanism of visual sentiment evocation.
Current image processing methods usually operate on the finest-granularity unit; that is, the pixel, which leads to challenges in terms of efficiency, robustness, and understandability in deep learning models. We present an improved granular-ball computing method to represent the image as a graph, in which each node expresses a structural block in the image and each edge represents the association between two nodes. Specifically:(1) We design a gradient-based strategy for the adaptive reorganization of all pixels in the image into numerous rectangular regions, each of which can be regarded as one node. (2) Each node has a connection edge with the nodes with which it shares regions. (3) We design a low-dimensional vector as the attribute of each node. All nodes and their corresponding edges form a graphical representation of a digital image. In the experiments, our proposed graph representation is applied to benchmark datasets for image classification tasks, and the efficiency and good understandability demonstrate that our proposed method offers significant potential in artificial intelligence theory and application.
We consider the paradigm of a black box AI system that makes life-critical decisions. We propose an "arguing machines" framework that pairs the primary AI system with a secondary one that is independently trained to perform the same task. We show that disagreement between the two systems, without any knowledge of underlying system design or operation, is sufficient to arbitrarily improve the accuracy of the overall decision pipeline given human supervision over disagreements. We demonstrate this system in two applications: (1) an illustrative example of image classification and (2) on large-scale real-world semi-autonomous driving data. For the first application, we apply this framework to image classification achieving a reduction from 8.0% to 2.8% top-5 error on ImageNet. For the second application, we apply this framework to Tesla Autopilot and demonstrate the ability to predict 90.4% of system disengagements that were labeled by human annotators as challenging and needing human supervision.
Computer-aided diagnosis via deep learning relies on large-scale annotated data sets, which can be costly when involving expert knowledge. Semi-supervised learning (SSL) mitigates this challenge by leveraging unlabeled data. One effective SSL approach is to regularize the local smoothness of neural functions via perturbations around single data points. In this work, we argue that regularizing the global smoothness of neural functions by filling the void in between data points can further improve SSL. We present a novel SSL approach that trains the neural network on linear mixing of labeled and unlabeled data, at both the input and latent space in order to regularize different portions of the network. We evaluated the presented model on two distinct medical image data sets for semi-supervised classification of thoracic disease and skin lesion, demonstrating its improved performance over SSL with local perturbations and SSL with global mixing but at the input space only. Our code is available at https://github.com/Prasanna1991/LatentMixing.
In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its applicability is especially interesting in specific areas, like remote sensing and medicine, where it is hard to obtain huge amounts of labeled data. In this work, we conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification. We analyze the influence of the number and domain of images used for self-supervised pre-training on the performance on downstream tasks. We show that, for the downstream task of remote sensing image classification, using self-supervised pre-training on remote sensing images can give better results than using supervised pre-training on images of natural scenes. Besides, we also show that self-supervised pre-training can be easily extended to multispectral images producing even better results on our downstream tasks.
Persistent topological properties of an image serve as an additional descriptor providing an insight that might not be discovered by traditional neural networks. The existing research in this area focuses primarily on efficiently integrating topological properties of the data in the learning process in order to enhance the performance. However, there is no existing study to demonstrate all possible scenarios where introducing topological properties can boost or harm the performance. This paper performs a detailed analysis of the effectiveness of topological properties for image classification in various training scenarios, defined by: the number of training samples, the complexity of the training data and the complexity of the backbone network. We identify the scenarios that benefit the most from topological features, e.g., training simple networks on small datasets. Additionally, we discuss the problem of topological consistency of the datasets which is one of the major bottlenecks for using topological features for classification. We further demonstrate how the topological inconsistency can harm the performance for certain scenarios.
Image-text contrastive learning models such as CLIP have demonstrated strong task transfer ability. The high generality and usability of these visual models is achieved via a web-scale data collection process to ensure broad concept coverage, followed by expensive pre-training to feed all the knowledge into model weights. Alternatively, we propose REACT, REtrieval-Augmented CusTomization, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs (~3% of CLIP pre-training data) from the web-scale database as external knowledge, and propose to customize the model by only training new modualized blocks while freezing all the original weights. The effectiveness of REACT is demonstrated via extensive experiments on classification, retrieval, detection and segmentation tasks, including zero, few, and full-shot settings. Particularly, on the zero-shot classification task, compared with CLIP, it achieves up to 5.4% improvement on ImageNet and 3.7% on the ELEVATER benchmark (20 datasets).
In this paper, we design and evaluate a convolutional autoencoder that perturbs an input face image to impart privacy to a subject. Specifically, the proposed autoencoder transforms an input face image such that the transformed image can be successfully used for face recognition but not for gender classification. In order to train this autoencoder, we propose a novel training scheme, referred to as semi-adversarial training in this work. The training is facilitated by attaching a semi-adversarial module consisting of a pseudo gender classifier and a pseudo face matcher to the autoencoder. The objective function utilized for training this network has three terms: one to ensure that the perturbed image is a realistic face image; another to ensure that the gender attributes of the face are confounded; and a third to ensure that biometric recognition performance due to the perturbed image is not impacted. Extensive experiments confirm the efficacy of the proposed architecture in extending gender privacy to face images.
In this paper, we first apply random ferns for classification of real music recordings of a jazz band. No initial segmentation of audio data is assumed, i.e., no onset, offset, nor pitch data are needed. The notion of random ferns is described in the paper, to familiarize the reader with this classification algorithm, which was introduced quite recently and applied so far in image recognition tasks. The performance of random ferns is compared with random forests for the same data. The results of experiments are presented in the paper, and conclusions are drawn.
Dictionary leaning (DL) and dimensionality reduction (DR) are powerful tools to analyze high-dimensional noisy signals. This paper presents a proposal of a novel Riemannian joint dimensionality reduction and dictionary learning (R-JDRDL) on symmetric positive definite (SPD) manifolds for classification tasks. The joint learning considers the interaction between dimensionality reduction and dictionary learning procedures by connecting them into a unified framework. We exploit a Riemannian optimization framework for solving DL and DR problems jointly. Finally, we demonstrate that the proposed R-JDRDL outperforms existing state-of-the-arts algorithms when used for image classification tasks.
This study proposes the use of generative models (GANs) for augmenting the EuroSAT dataset for the Land Use and Land Cover (LULC) Classification task. We used DCGAN and WGAN-GP to generate images for each class in the dataset. We then explored the effect of augmenting the original dataset by about 10% in each case on model performance. The choice of GAN architecture seems to have no apparent effect on the model performance. However, a combination of geometric augmentation and GAN-generated images improved baseline results. Our study shows that GANs augmentation can improve the generalizability of deep classification models on satellite images.
Optimizing computation in an edge-cloud system is an important yet challenging problem. In this paper, we consider a three-way trade-off between bit rate, classification accuracy, and encoding complexity in an edge-cloud image classification system. Our method includes a new training strategy and an efficient encoder architecture to improve the rate-accuracy performance. Our design can also be easily scaled according to different computation resources on the edge device, taking a step towards achieving a rate-accuracy-complexity (RAC) trade-off. Under various settings, our feature coding system consistently outperforms previous methods in terms of the RAC performance.
Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through unsupervised techniques, in this work we investigate how recent CLIP model can be applied in several tasks in artwork domain. We perform exhaustive experiments on the NoisyArt dataset which is a dataset of artwork images crawled from public resources on the web. On such dataset CLIP achieves impressive results on (zero-shot) classification and promising results in both artwork-to-artwork and description-to-artwork domain.
Recent research has shown the great potential of deep learning algorithms in the hyperspectral image (HSI) classification task. Nevertheless, training these models usually requires a large amount of labeled data. Since the collection of pixel-level annotations for HSI is laborious and time-consuming, developing algorithms that can yield good performance in the small sample size situation is of great significance. In this study, we propose a robust self-ensembling network (RSEN) to address this problem. The proposed RSEN consists of two subnetworks including a base network and an ensemble network. With the constraint of both the supervised loss from the labeled data and the unsupervised loss from the unlabeled data, the base network and the ensemble network can learn from each other, achieving the self-ensembling mechanism. To the best of our knowledge, the proposed method is the first attempt to introduce the self-ensembling technique into the HSI classification task, which provides a different view on how to utilize the unlabeled data in HSI to assist the network training. We further propose a novel consistency filter to increase the robustness of self-ensembling learning. Extensive experiments on three benchmark HSI datasets demonstrate that the proposed algorithm can yield competitive performance compared with the state-of-the-art methods. Code is available online (\url{https://github.com/YonghaoXu/RSEN}).
Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful information from this large and noisy data stream and effectively integrating heterogeneous data remains a formidable challenge. In this work, we explore vision language models (VLMs) and advanced fusion strategies to enhance the classification of crisis data in three different tasks. We incorporate LLaVA-generated text to improve text-image alignment. Additionally, we leverage Contrastive Language-Image Pretraining (CLIP)-based vision and text embeddings, which, without task-specific fine-tuning, outperform traditional models. To further refine multimodal fusion, we employ Guided Cross Attention (Guided CA) and combine it with the Differential Attention mechanism to enhance feature alignment by emphasizing critical information while filtering out irrelevant content. Our results show that while Differential Attention improves classification performance, Guided CA remains highly effective in aligning multimodal features. Extensive experiments on the CrisisMMD benchmark data set demonstrate that the combination of pretrained VLMs, enriched textual descriptions, and adaptive fusion strategies consistently outperforms state-of-the-art models in classification accuracy, contributing to more reliable and interpretable models for three different tasks that are crucial for disaster response. Our code is available at https://github.com/Munia03/Multimodal_Crisis_Event.
Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree of invariance to pose, articulation and background. A solution is to use pose-normalized representations: first localize semantic parts in each image, and then describe images by characterizing the appearance of each part. While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification. With a minimal increase in model capacity, pose normalization improves accuracy between 10 and 20 percentage points for shallow and deep architectures, generalizes better to new domains, and is effective for multiple few-shot algorithms and network backbones. Code is available at https://github.com/Tsingularity/PoseNorm_Fewshot
Examining most streaming clustering algorithms leads to the understanding that they are actually incremental classification models. They model existing and newly discovered structures via summary information that we call footprints. Incoming data is normally assigned a crisp label (into one of the structures) and that structure's footprint is incrementally updated. There is no reason that these assignments need to be crisp. In this paper, we propose a new streaming classification algorithm that uses Neural Gas prototypes as footprints and produces a possibilistic label vector (of typicalities) for each incoming vector. These typicalities are generated by a modified possibilistic k-nearest neighbor algorithm. The approach is tested on synthetic and real image datasets. We compare our approach to three other streaming classifiers based on the Adaptive Random Forest, Very Fast Decision Rules, and the DenStream algorithm with excellent results.
Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model performance post-hoc, without additional training. Although test-time augmentation (TTA) can be applied to any data modality, it has seen limited adoption in NLP due in part to the difficulty of identifying label-preserving transformations. In this paper, we present augmentation policies that yield significant accuracy improvements with language models. A key finding is that augmentation policy design -- for instance, the number of samples generated from a single, non-deterministic augmentation -- has a considerable impact on the benefit of TTA. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements over current state-of-the-art approaches.
Vision-language models have been extensively explored across a wide range of tasks, achieving satisfactory performance; however, their application in medical imaging remains underexplored. In this work, we propose a unified framework - LiteGPT - for the medical imaging. We leverage multiple pre-trained visual encoders to enrich information and enhance the performance of vision-language models. To the best of our knowledge, this is the first study to utilize vision-language models for the novel task of joint localization and classification in medical images. Besides, we are pioneers in providing baselines for disease localization in chest X-rays. Finally, we set new state-of-the-art performance in the image classification task on the well-benchmarked VinDr-CXR dataset. All code and models are publicly available online: https://github.com/leduckhai/LiteGPT