This paper presents SimMIM, a simple framework for masked image modeling. We simplify recently proposed related approaches without special designs such as block-wise masking and tokenization via discrete VAE or clustering. To study what let the masked image modeling task learn good representations, we systematically study the major components in our framework, and find that simple designs of each component have revealed very strong representation learning performance: 1) random masking of the input image with a moderately large masked patch size (e.g., 32) makes a strong pre-text task; 2) predicting raw pixels of RGB values by direct regression performs no worse than the patch classification approaches with complex designs; 3) the prediction head can be as light as a linear layer, with no worse performance than heavier ones. Using ViT-B, our approach achieves 83.8% top-1 fine-tuning accuracy on ImageNet-1K by pre-training also on this dataset, surpassing previous best approach by +0.6%. When applied on a larger model of about 650 million parameters, SwinV2-H, it achieves 87.1% top-1 accuracy on ImageNet-1K using only ImageNet-1K data. We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by $40\times$ less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks. The code and models will be publicly available at https://github.com/microsoft/SimMIM.
Machine Vision Components (MVC) are becoming safety-critical. Assuring their quality, including safety, is essential for their successful deployment. Assurance relies on the availability of precisely specified and, ideally, machine-verifiable requirements. MVCs with state-of-the-art performance rely on machine learning (ML) and training data but largely lack such requirements. In this paper, we address the need for defining machine-verifiable reliability requirements for MVCs against transformations that simulate the full range of realistic and safety-critical changes in the environment. Using human performance as a baseline, we define reliability requirements as: 'if the changes in an image do not affect a human's decision, neither should they affect the MVC's.' To this end, we provide: (1) a class of safety-related image transformations; (2) reliability requirement classes to specify correctness-preservation and prediction-preservation for MVCs; (3) a method to instantiate machine-verifiable requirements from these requirements classes using human performance experiment data; (4) human performance experiment data for image recognition involving eight commonly used transformations, from about 2000 human participants; and (5) a method for automatically checking whether an MVC satisfies our requirements. Further, we show that our reliability requirements are feasible and reusable by evaluating our methods on 13 state-of-the-art pre-trained image classification models. Finally, we demonstrate that our approach detects reliability gaps in MVCs that other existing methods are unable to detect.
임상 진단은 본질적으로 구조화된 추론 과정이지만, 기존의 심층 학습(deep learning) 모델은 임상의가 체계적으로 평가하는 형태학적 및 질감적 기준을 명시적으로 검토하지 않고 영상 특징을 질환 라벨에 직접 매핑함으로써 이러한 구조를 우회하는 경우가 많습니다. 이는 진단 투명성을 제한하며 안전한 임상 적용을 저해할 수 있습니다. 본 연구에서는 비전-언어(vision-language) 아키텍처 내에서 임상 추론을 구체화하는 구조화된 진단 프레임워크인 MedCORE(Medical Criteria-Oriented Reasoning and Evidence)를 제시합니다. 입력 영상마다 MedCORE는 진단 과정을 임상적으로 정의된 기준으로 분해하고, 각 기준을 진단적으로 관련된 영상 영역에 공간적으로 국소화하며, 거시 구조 및 미세 질감의 병리학적 특성을 포착하는 다중 스케일 표현을 통해 근거를 인코딩하고, 기준 간 의존성을 명시적으로 모델링하는 그래프 어텐션 네트워크(Graph Attention Network)를 사용하여 기준 표현을 정제합니다. 또한 기준 표현은 임상 텍스트 기술자와 정렬되고, 클래스별 시각적 프로토타입을 통해 강화되며, 신뢰도가 낮은 진단 근거의 비중을 비례적으로 줄이는 불확실성 보정 가중치를 사용하여 집계됩니다. MedCORE는 ISIC 2018 데이터셋의 피부경 병변 분류(classification), BUSI의 유방 초음파 병변 특성화, IDRiD의 당뇨망막병증 등급 분류를 포함하여 임상적으로 이질적인 세 가지 영상 양식에 걸쳐 검증되었습니다. 정량적으로 MedCORE는 ISIC 2018에서 89.2%의 정확도, 85.7%의 매크로 F1, 96.4%의 AUC를 달성하였고, BUSI에서 96.1%의 정확도, 95.2%의 매크로 F1, 98.4%의 AUC를 달성하였으며, IDRiD에서 84.3%의 정확도, 80.2%의 매크로 F1, 92.8%의 AUC를 달성했습니다. 이러한 결과는 강력한 CNN, 트랜스포머(transformer), 생체의학 비전-언어, 개념 기반 및 프로토타입 기반 베이스라인 대비 일관된 성능 향상을 보여줍니다.
Convolutional neural networks (CNNs) have proven effective for image processing tasks, such as object recognition and classification. Recently, CNNs have been enhanced with concepts of attention, similar to those found in biology. Much of this work on attention has focused on effective serial spatial processing. In this paper, I introduce a simple procedure for applying feature-based attention (FBA) to CNNs and compare multiple implementation options. FBA is a top-down signal applied globally to an input image which aides in detecting chosen objects in cluttered or noisy settings. The concept of FBA and the implementation details tested here were derived from what is known (and debated) about biological object- and feature-based attention. The implementations of FBA described here increase performance on challenging object detection tasks using a procedure that is simple, fast, and does not require additional iterative training. Furthermore, the comparisons performed here suggest that a proposed model of biological FBA (the "feature similarity gain model") is effective in increasing performance.
The applicability of computer vision to real paintings and artworks has been rarely investigated, even though a vast heritage would greatly benefit from techniques which can understand and process data from the artistic domain. This is partially due to the small amount of annotated artistic data, which is not even comparable to that of natural images captured by cameras. In this paper, we propose a semantic-aware architecture which can translate artworks to photo-realistic visualizations, thus reducing the gap between visual features of artistic and realistic data. Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the scene. Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection, and segmentation. Code is publicly available at: https://github.com/aimagelab/art2real.
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors. The inconsistency between the weak supervision and learning objectives introduces significant randomness to object locations and ambiguity to detectors. In this paper, a min-entropy latent model (MELM) is proposed for weakly supervised object detection. Min-entropy serves as a model to learn object locations and a metric to measure the randomness of object localization during learning. It aims to principally reduce the variance of learned instances and alleviate the ambiguity of detectors. MELM is decomposed into three components including proposal clique partition, object clique discovery, and object localization. MELM is optimized with a recurrent learning algorithm, which leverages continuation optimization to solve the challenging non-convexity problem. Experiments demonstrate that MELM significantly improves the performance of weakly supervised object detection, weakly supervised object localization, and image classification, against the state-of-the-art approaches.
Noise reduction is one the most important and still active research topic in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we can observe a substantial increase of interest in the application of deep learning algorithms in many computer vision problems due to its impressive capability of automatic feature extraction and classification. These methods have been also successfully applied in image denoising, significantly improving the performance, but most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering design intended for impulsive noise removal using deep learning. In the proposed method, the impulses are identified using a novel deep neural network architecture and noisy pixels are restored using the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in digital color images.
Recent studies have demonstrated that machine learning approaches like deep neural networks (DNNs) are easily fooled by adversarial attacks. Subtle and imperceptible perturbations of the data are able to change the result of deep neural networks. Leveraging vulnerable machine learning methods raises many concerns especially in domains where security is an important factor. Therefore, it is crucial to design defense mechanisms against adversarial attacks. For the task of image classification, unnoticeable perturbations mostly occur in the high-frequency spectrum of the image. In this paper, we utilize tensor decomposition techniques as a preprocessing step to find a low-rank approximation of images which can significantly discard high-frequency perturbations. Recently a defense framework called Shield could "vaccinate" Convolutional Neural Networks (CNN) against adversarial examples by performing random-quality JPEG compressions on local patches of images on the ImageNet dataset. Our tensor-based defense mechanism outperforms the SLQ method from Shield by 14% against FastGradient Descent (FGSM) adversarial attacks, while maintaining comparable speed.
Although deep neural networks (DNNs) have been shown to be susceptible to image-agnostic adversarial attacks on natural image classification problems, the effects of such attacks on DNN-based texture recognition have yet to be explored. As part of our work, we find that limiting the perturbation's $l_p$ norm in the spatial domain may not be a suitable way to restrict the perceptibility of universal adversarial perturbations for texture images. Based on the fact that human perception is affected by local visual frequency characteristics, we propose a frequency-tuned universal attack method to compute universal perturbations in the frequency domain. Our experiments indicate that our proposed method can produce less perceptible perturbations yet with a similar or higher white-box fooling rates on various DNN texture classifiers and texture datasets as compared to existing universal attack techniques. We also demonstrate that our approach can improve the attack robustness against defended models as well as the cross-dataset transferability for texture recognition problems.
Recent empirical work has shown that hierarchical convolutional kernels inspired by convolutional neural networks (CNNs) significantly improve the performance of kernel methods in image classification tasks. A widely accepted explanation for their success is that these architectures encode hypothesis classes that are suitable for natural images. However, understanding the precise interplay between approximation and generalization in convolutional architectures remains a challenge. In this paper, we consider the stylized setting of covariates (image pixels) uniformly distributed on the hypercube, and characterize exactly the RKHS of kernels composed of single layers of convolution, pooling, and downsampling operations. We use this characterization to compute sharp asymptotics of the generalization error for any given function in high-dimension. In particular, we quantify the gain in sample complexity brought by enforcing locality with the convolution operation and approximate translation invariance with average pooling. Notably, these results provide a precise description of how convolution and pooling operations trade off approximation with generalization power in one layer convolutional kernels.
Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data. Whilst these algorithms have achieved significant performance gains across a wide plethora of tasks, they have also failed to consider and increase comprehensive similarity constraints; thus learning a sub-optimal metric in the embedding space. Moreover, up until now; there have been few studies with respect to their performance in the presence of noisy labels. Here, we address the concern of learning a discriminative deep embedding space by designing a novel, yet effective Deep Class-wise Discrepancy Loss (DCDL) function that segregates the underlying similarity distributions (thus introducing class-wise discrepancy) of the embedding points between each and every class. Our empirical results across three standard image classification datasets and two fine-grained image recognition datasets in the presence and absence of noise clearly demonstrate the need for incorporating such class-wise similarity relationships along with traditional algorithms while learning a discriminative embedding space.
Cloud occlusions obstruct some applications of remote sensing imagery, such as environment monitoring, land cover classification, and poverty prediction. In this paper, we propose the Cloud Transformer Generative Adversarial Network (CTGAN), taking three temporal cloudy images as input and generating a corresponding cloud-free image. Unlike previous work using generative networks, we design the feature extractor to maintain the weight of the cloudless region while reducing the weight of the cloudy region, and we pass the extracted features to a conformed module to find the most critical representations. Meanwhile, to address the lack of datasets, we collected a new dataset named Sen2 MTC from the Sentinel-2 satellite and manually labeled each cloudy and cloud-free image. Finally, we conducted extensive experiments on FS-2, the STGAN dataset, and Sen2 MTC. Our proposed CTGAN demonstrates higher qualitative and quantitative performance than the previous work and achieves state-of-the-art performance on these three datasets. The code is available at https://github.com/come880412/CTGAN
Hyperspectral images have significant applications in various domains, since they register numerous semantic and spatial information in the spectral band with spatial variability of spectral signatures. Two critical challenges in identifying pixels of the hyperspectral image are respectively representing the correlated information among the local and global, as well as the abundant parameters of the model. To tackle this challenge, we propose a Multi-Scale U-shape Multi-Layer Perceptron (MUMLP) a model consisting of the designed MSC (Multi-Scale Channel) block and the UMLP (U-shape Multi-Layer Perceptron) structure. MSC transforms the channel dimension and mixes spectral band feature to embed the deep-level representation adequately. UMLP is designed by the encoder-decoder structure with multi-layer perceptron layers, which is capable of compressing the large-scale parameters. Extensive experiments are conducted to demonstrate our model can outperform state-of-the-art methods across-the-board on three wide-adopted public datasets, namely Pavia University, Houston 2013 and Houston 2018
While large language models (LLMs) have advanced the field of natural language processing (NLP), their "black box" nature obscures their decision-making processes. To address this, researchers developed structured approaches using higher order tensors. These are able to model linguistic relations, but stall when training on classical computers due to their excessive size. Tensors are natural inhabitants of quantum systems and training on quantum computers provides a solution by translating text to variational quantum circuits. In this paper, we develop MultiQ-NLP: a framework for structure-aware data processing with multimodal text+image data. Here, "structure" refers to syntactic and grammatical relationships in language, as well as the hierarchical organization of visual elements in images. We enrich the translation with new types and type homomorphisms and develop novel architectures to represent structure. When tested on a main stream image classification task (SVO Probes), our best model showed a par performance with the state of the art classical models; moreover the best model was fully structured.
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Learning agent to add minimum distortion to input images while still causing misclassification by the target model. The agent uses a novel dual-action method to explore the input image at each step to identify sensitive regions for adding distortions while removing noises that have less impact on the target model. This dual action leads to faster and more efficient convergence of the attack. The platform can also be used to measure the robustness of image classification models against specific distortion types. Also, retraining the model with adversarial samples significantly improved robustness when evaluated on benchmark datasets. The proposed platform outperforms state-of-the-art methods in terms of the average number of queries required to cause misclassification. This advances trustworthiness with a positive social impact.
As deep learning is widely used in the radiology field, the explainability of such models is increasingly becoming essential to gain clinicians' trust when using the models for diagnosis. In this research, three experiment sets were conducted with a U-Net architecture to improve the classification performance while enhancing the heatmaps corresponding to the model's focus through incorporating heatmap generators during training. All of the experiments used the dataset that contained chest radiographs, associated labels from one of the three conditions ("normal", "congestive heart failure (CHF)", and "pneumonia"), and numerical information regarding a radiologist's eye-gaze coordinates on the images. The paper (A. Karargyris and Moradi, 2021) that introduced this dataset developed a U-Net model, which was treated as the baseline model for this research, to show how the eye-gaze data can be used in multi-modal training for explainability improvement. To compare the classification performances, the 95% confidence intervals (CI) of the area under the receiver operating characteristic curve (AUC) were measured. The best method achieved an AUC of 0.913 (CI: 0.860-0.966). The greatest improvements were for the "pneumonia" and "CHF" classes, which the baseline model struggled most to classify, resulting in AUCs of 0.859 (CI: 0.732-0.957) and 0.962 (CI: 0.933-0.989), respectively. The proposed method's decoder was also able to produce probability masks that highlight the determining image parts in model classifications, similarly as the radiologist's eye-gaze data. Hence, this work showed that incorporating heatmap generators and eye-gaze information into training can simultaneously improve disease classification and provide explainable visuals that align well with how the radiologist viewed the chest radiographs when making diagnosis.
Accelerometer measurements are the prime type of sensor information most think of when seeking to measure physical activity. On the market, there are many fitness measuring devices which aim to track calories burned and steps counted through the use of accelerometers. These measurements, though good enough for the average consumer, are noisy and unreliable in terms of the precision of measurement needed in a scientific setting. The contribution of this paper is an innovative and highly accurate regression method which uses an intermediary two-stage classification step to better direct the regression of energy expenditure values from accelerometer counts. We show that through an additional unsupervised layer of intermediate feature construction, we can leverage latent patterns within accelerometer counts to provide better grounds for activity classification than expert-constructed timeseries features. For this, our approach utilizes a mathematical model originating in natural language processing, the bag-of-words model, that has in the past years been appearing in diverse disciplines outside of the natural language processing field such as image processing. Further emphasizing the natural language connection to stochastics, we use a gaussian mixture model to learn the dictionary upon which the bag-of-words model is built. Moreover, we show that with the addition of these features, we're able to improve regression root mean-squared error of energy expenditure by approximately 1.4 units over existing state-of-the-art methods.
We consider classification problems in which the label space has structure. A common example is hierarchical label spaces, corresponding to the case where one label subsumes another (e.g., animal subsumes dog). But labels can also be mutually exclusive (e.g., dog vs cat) or unrelated (e.g., furry, carnivore). To jointly model hierarchy and exclusion relations, the notion of a HEX (hierarchy and exclusion) graph was introduced in [7]. This combined a conditional random field (CRF) with a deep neural network (DNN), resulting in state of the art results when applied to visual object classification problems where the training labels were drawn from different levels of the ImageNet hierarchy (e.g., an image might be labeled with the basic level category "dog", rather than the more specific label "husky"). In this paper, we extend the HEX model to allow for soft or probabilistic relations between labels, which is useful when there is uncertainty about the relationship between two labels (e.g., an antelope is "sort of" furry, but not to the same degree as a grizzly bear). We call our new model pHEX, for probabilistic HEX. We show that the pHEX graph can be converted to an Ising model, which allows us to use existing off-the-shelf inference methods (in contrast to the HEX method, which needed specialized inference algorithms). Experimental results show significant improvements in a number of large-scale visual object classification tasks, outperforming the previous HEX model.
This paper addresses the problem of few-shot skin disease classification by introducing a novel approach called the Sub-Cluster-Aware Network (SCAN) that enhances accuracy in diagnosing rare skin diseases. The key insight motivating the design of SCAN is the observation that skin disease images within a class often exhibit multiple sub-clusters, characterized by distinct variations in appearance. To improve the performance of few-shot learning, we focus on learning a high-quality feature encoder that captures the unique sub-clustered representations within each disease class, enabling better characterization of feature distributions. Specifically, SCAN follows a dual-branch framework, where the first branch learns class-wise features to distinguish different skin diseases, and the second branch aims to learn features which can effectively partition each class into several groups so as to preserve the sub-clustered structure within each class. To achieve the objective of the second branch, we present a cluster loss to learn image similarities via unsupervised clustering. To ensure that the samples in each sub-cluster are from the same class, we further design a purity loss to refine the unsupervised clustering results. We evaluate the proposed approach on two public datasets for few-shot skin disease classification. The experimental results validate that our framework outperforms the state-of-the-art methods by around 2% to 5% in terms of sensitivity, specificity, accuracy, and F1-score on the SD-198 and Derm7pt datasets.
In this letter, we introduce deep active learning (AL) for multi-label classification (MLC) problems in remote sensing (RS). In particular, we investigate the effectiveness of several AL query functions for MLC of RS images. Unlike the existing AL query functions (which are defined for single-label classification or semantic segmentation problems), each query function in this paper is based on the evaluation of two criteria: i) multi-label uncertainty; and ii) multi-label diversity. The multi-label uncertainty criterion is associated to the confidence of the deep neural networks (DNNs) in correctly assigning multi-labels to each image. To assess this criterion, we investigate three strategies: i) learning multi-label loss ordering; ii) measuring temporal discrepancy of multi-label predictions; and iii) measuring magnitude of approximated gradient embeddings. The multi-label diversity criterion is associated to the selection of a set of images that are as diverse as possible to each other that prevents redundancy among them. To assess this criterion, we exploit a clustering based strategy. We combine each of the above-mentioned uncertainty strategies with the clustering based diversity strategy, resulting in three different query functions. All the considered query functions are introduced for the first time in the framework of MLC problems in RS. Experimental results obtained on two benchmark archives show that these query functions result in the selection of a highly informative set of samples at each iteration of the AL process.