Aligning the recent large language models (LLMs) with computer vision models leads to large vision-language models (LVLMs), which have paved the way for zero-shot image reasoning tasks. However, LVLMs are usually trained on short high-level captions only referring to sparse focus regions in images. Such a ``tunnel vision'' limits LVLMs to exploring other relevant contexts in complex scenes. To address this challenge, we introduce Question-Driven Visual Exploration (QVix), a novel prompting strategy that enhances the exploratory capabilities of LVLMs in zero-shot reasoning tasks. QVix leverages LLMs' strong language prior to generate input-exploratory questions with more details than the original query, guiding LVLMs to explore visual content more comprehensively and uncover subtle or peripheral details. QVix enables a wider exploration of visual scenes, improving the LVLMs' reasoning accuracy and depth in tasks such as visual question answering and visual entailment. Our evaluations on various challenging zero-shot vision-language benchmarks, including ScienceQA and fine-grained visual classification, demonstrate that QVix significantly outperforms existing methods, highlighting its effectiveness in bridging the gap between complex visual data and LVLMs' exploratory abilities.
Autonomous vehicles increasingly utilize the vision-based perception module to acquire information about driving environments and detect obstacles. Correct detection and classification are important to ensure safe driving decisions. Existing works have demonstrated the feasibility of fooling the perception models such as object detectors and image classifiers with printed adversarial patches. However, most of them are indiscriminately offensive to every passing autonomous vehicle. In this paper, we propose TPatch, a physical adversarial patch triggered by acoustic signals. Unlike other adversarial patches, TPatch remains benign under normal circumstances but can be triggered to launch a hiding, creating or altering attack by a designed distortion introduced by signal injection attacks towards cameras. To avoid the suspicion of human drivers and make the attack practical and robust in the real world, we propose a content-based camouflage method and an attack robustness enhancement method to strengthen it. Evaluations with three object detectors, YOLO V3/V5 and Faster R-CNN, and eight image classifiers demonstrate the effectiveness of TPatch in both the simulation and the real world. We also discuss possible defenses at the sensor, algorithm, and system levels.
Deep Neural Networks ( DNN s) are known to make overconfident mistakes, which makes their use problematic in safety-critical applications. State-of-the-art ( SOTA ) calibration techniques improve on the confidence of predicted labels alone and leave the confidence of non-max classes (e.g. top-2, top-5) uncalibrated. Such calibration is not suitable for label refinement using post-processing. Further, most SOTA techniques learn a few hyper-parameters post-hoc, leaving out the scope for image, or pixel specific calibration. This makes them unsuitable for calibration under domain shift, or for dense prediction tasks like semantic segmentation. In this paper, we argue for intervening at the train time itself, so as to directly produce calibrated DNN models. We propose a novel auxiliary loss function: Multi-class Difference in Confidence and Accuracy ( MDCA ), to achieve the same MDCA can be used in conjunction with other application/task-specific loss functions. We show that training with MDCA leads to better-calibrated models in terms of Expected Calibration Error ( ECE ), and Static Calibration Error ( SCE ) on image classification, and segmentation tasks. We report ECE ( SCE ) score of 0.72 (1.60) on the CIFAR 100 dataset, in comparison to 1.90 (1.71) by the SOTA. Under domain shift, a ResNet-18 model trained on PACS dataset using MDCA gives an average ECE ( SCE ) score of 19.7 (9.7) across all domains, compared to 24.2 (11.8) by the SOTA. For the segmentation task, we report a 2X reduction in calibration error on PASCAL - VOC dataset in comparison to Focal Loss. Finally, MDCA training improves calibration even on imbalanced data, and for natural language classification tasks. We have released the code here: code is available at https://github.com/mdca-loss
Deep learning's recent history has been one of achievement: from triumphing over humans in the game of Go to world-leading performance in image classification, voice recognition, translation, and other tasks. But this progress has come with a voracious appetite for computing power. This article catalogs the extent of this dependency, showing that progress across a wide variety of applications is strongly reliant on increases in computing power. Extrapolating forward this reliance reveals that progress along current lines is rapidly becoming economically, technically, and environmentally unsustainable. Thus, continued progress in these applications will require dramatically more computationally-efficient methods, which will either have to come from changes to deep learning or from moving to other machine learning methods.
The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points. To demonstrate the latest progress of deep learning for 3D point cloud understanding, this paper summarizes recent remarkable research contributions in this area from several different directions (classification, segmentation, detection, tracking, flow estimation, registration, augmentation and completion), together with commonly used datasets, metrics and state-of-the-art performances. More information regarding this survey can be found at: https://github.com/SHI-Labs/3D-Point-Cloud-Learning.
Although deep generative models such as Defense-GAN and Defense-VAE have made significant progress in terms of adversarial defenses of image classification neural networks, several methods have been found to circumvent these defenses. Based on Defense-VAE, in our research we introduce several methods to improve the robustness of defense models. The methods introduced in this paper are straight forward yet show promise over the vanilla Defense-VAE. With extensive experiments on MNIST data set, we have demonstrated the effectiveness of our algorithms against different attacks. Our experiments also include attacks on the latent space of the defensive model. We also discuss the applicability of existing adversarial latent space attacks as they may have a significant flaw.
Complex prediction models such as deep learning are the output from fitting machine learning, neural networks, or AI models to a set of training data. These are now standard tools in science. A key challenge with the current generation of models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into pictures representing a topological view. The result is a map of the predictions that enables inspection. The methods scale up to large datasets across different domains and enable us to detect labeling errors in training data, understand generalization in image classification, and inspect predictions of likely pathogenic mutations in the BRCA1 gene.
The availability of large public datasets and the increased amount of computing power have shifted the interest of the medical community to high-performance algorithms. However, little attention is paid to the quality of the data and their annotations. High performance on benchmark datasets may be reported without considering possible shortcuts or artifacts in the data, besides, models are not tested on subpopulation groups. With this work, we aim to raise awareness about shortcuts problems. We validate previous findings, and present a case study on chest X-rays using two publicly available datasets. We share annotations for a subset of pneumothorax images with drains. We conclude with general recommendations for medical image classification.
Speaker recognition technology is applied to various tasks, from personal virtual assistants to secure access systems. However, the robustness of these systems against adversarial attacks, particularly to additive perturbations, remains a significant challenge. In this paper, we pioneer applying robustness certification techniques to speaker recognition, initially developed for the image domain. Our work covers this gap by transferring and improving randomized smoothing certification techniques against norm-bounded additive perturbations for classification and few-shot learning tasks to speaker recognition. We demonstrate the effectiveness of these methods on VoxCeleb 1 and 2 datasets for several models. We expect this work to improve the robustness of voice biometrics and accelerate the research of certification methods in the audio domain.
While deep neural networks are highly effective at solving complex tasks, large pre-trained models are commonly employed even to solve consistently simpler downstream tasks, which do not necessarily require a large model's complexity. Motivated by the awareness of the ever-growing AI environmental impact, we propose an efficiency strategy that leverages prior knowledge transferred by large models. Simple but effective, we propose a method relying on an Entropy-bASed Importance mEtRic (EASIER) to reduce the depth of over-parametrized deep neural networks, which alleviates their computational burden. We assess the effectiveness of our method on traditional image classification setups. Our code is available at https://github.com/VGCQ/EASIER.
Creating responsible artificial intelligence (AI) systems is an important issue in contemporary research and development of works on AI. One of the characteristics of responsible AI systems is their explainability. In the paper, we are interested in explainable deep learning (XDL) systems. On the basis of the creation of digital twins of physical objects, we introduce the idea of creating readable twins (in the form of imprecise information flow models) for unreadable deep learning models. The complete procedure for switching from the deep learning model (DLM) to the imprecise information flow model (IIFM) is presented. The proposed approach is illustrated with an example of a deep learning classification model for image recognition of handwritten digits from the MNIST data set.
Domain generalization (DG) is a difficult transfer learning problem aiming to learn a generalizable model for unseen domains. Recent foundation models (FMs) are robust to many distribution shifts and, therefore, should substantially improve the performance of DG. In this work, we study generic ways to adopt CLIP, a Visual-Language Foundation Model, for DG problems in image classification. While ERM greatly improves the accuracy with bigger backbones and training datasets using standard DG benchmarks, fine-tuning FMs is not practical in many real-world situations. We propose Domain Prompt Learning (DPL) as a novel approach for domain inference in the form of conditional prompt generation. DPL achieved a significant accuracy improvement with only training a lightweight prompt generator (a three-layer MLP), whose parameter is of equivalent scale to the classification projector in the previous DG literature. Combining \dplshort~with CLIP provides surprising performance, raising the accuracy of zero-shot CLIP from 73.7% to 79.3% on several standard datasets, namely PACS, VLCS, OfficeHome, and TerraIncognita. We hope the simplicity and success of our approach lead to broader adoption and analysis of foundation models in the domain generalization field. Our code is available at https://github.com/shogi880/DPLCLIP.
Deep neural networks have demonstrated prominent capacities for image classification tasks in a closed set setting, where the test data come from the same distribution as the training data. However, in a more realistic open set scenario, traditional classifiers with incomplete knowledge cannot tackle test data that are not from the training classes. Open set recognition (OSR) aims to address this problem by both identifying unknown classes and distinguishing known classes simultaneously. In this paper, we propose a novel approach to OSR that is based on the vision transformer (ViT) technique. Specifically, our approach employs two separate training stages. First, a ViT model is trained to perform closed set classification. Then, an additional detection head is attached to the embedded features extracted by the ViT, trained to force the representations of known data to class-specific clusters compactly. Test examples are identified as known or unknown based on their distance to the cluster centers. To the best of our knowledge, this is the first time to leverage ViT for the purpose of OSR, and our extensive evaluation against several OSR benchmark datasets reveals that our approach significantly outperforms other baseline methods and obtains new state-of-the-art performance.
Brain tumors are an abnormal growth of cells in the brain. They can be classified into distinct grades based on their growth. Often grading is performed based on a histological image and is one of the most significant predictors of a patients prognosis, the higher the grade, the more aggressive the tumor. Correct diagnosis of a tumor grade remains challenging. Though histopathological grading has been shown to be prognostic, results are subject to interobserver variability, even among experienced pathologists. Recently, the World Health Organization reported that advances in molecular genetics have led to improvements in tumor classification. This paper seeks to integrate histological images and genetic data for improved computer-aided diagnosis. We propose a novel Multi-modal Outer Arithmetic Block (MOAB) based on arithmetic operations to combine latent representations of the different modalities for predicting the tumor grade (Grade \rom{2}, \rom{3} and \rom{4}). Extensive experiments evaluate the effectiveness of our approach. By applying MOAB to The Cancer Genome Atlas (TCGA) glioma dataset, we show that it can improve separation between similar classes (Grade \rom{2} and \rom{3}) and outperform prior state-of-the-art grade classification techniques.
Out-of-distribution (OOD) detection, crucial for reliable pattern classification, discerns whether a sample originates outside the training distribution. This paper concentrates on the high-dimensional features output by the final convolutional layer, which contain rich image features. Our key idea is to project these high-dimensional features into two specific feature subspaces, leveraging the dimensionality reduction capacity of the network's linear layers, trained with Predefined Evenly-Distribution Class Centroids (PEDCC)-Loss. This involves calculating the cosines of three projection angles and the norm values of features, thereby identifying distinctive information for in-distribution (ID) and OOD data, which assists in OOD detection. Building upon this, we have modified the batch normalization (BN) and ReLU layer preceding the fully connected layer, diminishing their impact on the output feature distributions and thereby widening the distribution gap between ID and OOD data features. Our method requires only the training of the classification network model, eschewing any need for input pre-processing or specific OOD data pre-tuning. Extensive experiments on several benchmark datasets demonstrates that our approach delivers state-of-the-art performance. Our code is available at https://github.com/Hewell0/ProjOOD.
Neural networks can learn spurious correlations that lead to the correct prediction in a validation set, but generalise poorly because the predictions are right for the wrong reason. This undesired learning of naive shortcuts (Clever Hans effect) can happen for example in echocardiogram view classification when background cues (e.g. metadata) are biased towards a class and the model learns to focus on those background features instead of on the image content. We propose a simple, yet effective random background augmentation method called BackMix, which samples random backgrounds from other examples in the training set. By enforcing the background to be uncorrelated with the outcome, the model learns to focus on the data within the ultrasound sector and becomes invariant to the regions outside this. We extend our method in a semi-supervised setting, finding that the positive effects of BackMix are maintained with as few as 5% of segmentation labels. A loss weighting mechanism, wBackMix, is also proposed to increase the contribution of the augmented examples. We validate our method on both in-distribution and out-of-distribution datasets, demonstrating significant improvements in classification accuracy, region focus and generalisability. Our source code is available at: https://github.com/kitbransby/BackMix
Recently, cyber-attacks have been extensively seen due to the everlasting increase of malware in the cyber world. These attacks cause irreversible damage not only to end-users but also to corporate computer systems. Ransomware attacks such as WannaCry and Petya specifically targets to make critical infrastructures such as airports and rendered operational processes inoperable. Hence, it has attracted increasing attention in terms of volume, versatility, and intricacy. The most important feature of this type of malware is that they change shape as they propagate from one computer to another. Since standard signature-based detection software fails to identify this type of malware because they have different characteristics on each contaminated computer. This paper aims at providing an image augmentation enhanced deep convolutional neural network (CNN) models for the detection of malware families in a metamorphic malware environment. The main contributions of the paper's model structure consist of three components, including image generation from malware samples, image augmentation, and the last one is classifying the malware families by using a convolutional neural network model. In the first component, the collected malware samples are converted binary representation to 3-channel images using windowing technique. The second component of the system create the augmented version of the images, and the last component builds a classification model. In this study, five different deep convolutional neural network model for malware family detection is used.
Recent work has shown the potential of transformers for computer vision applications. An image is first partitioned into patches, which are then used as input tokens for the attention mechanism. Due to the expensive quadratic cost of the attention mechanism, either a large patch size is used, resulting in coarse-grained global interactions, or alternatively, attention is applied only on a local region of the image, at the expense of long-range interactions. In this work, we propose an approach that allows for both coarse global interactions and fine-grained local interactions already at early layers of a vision transformer. At the core of our method is the application of local and global attention layers. In the local attention layer, we apply attention to each patch and its local shifts, resulting in virtually located local patches, which are not bound to a single, specific location. These virtually located patches are then used in a global attention layer. The separation of the attention layer into local and global counterparts allows for a low computational cost in the number of patches, while still supporting data-dependent localization already at the first layer, as opposed to the static positioning in other visual transformers. Our method is shown to be superior to both convolutional and transformer-based methods for image classification on CIFAR10, CIFAR100, and ImageNet. Code is available at: https://github.com/shellysheynin/Locally-SAG-Transformer.
Undoubtedly breast cancer identifies itself as one of the most widespread and terrifying cancers across the globe. Millions of women are getting affected each year from it. Breast cancer remains the major one for being the reason of largest number of demise of women. In the recent time of research, Medical Image Computing and Processing has been playing a significant role for detecting and classifying breast cancers from ultrasound images and mammograms, along with the celestial touch of deep neural networks. In this research, we focused mostly on our rigorous implementations and iterative result analysis of different cutting-edge modified versions of EfficientNet architectures namely EfficientNet-V1 (b0-b7) and EfficientNet-V2 (b0-b3) with ultrasound image, named as CEIMVEN. We utilized transfer learning approach here for using the pre-trained models of EfficientNet versions. We activated the hyper-parameter tuning procedures, added fully connected layers, discarded the unprecedented outliers and recorded the accuracy results from our custom modified EfficientNet architectures. Our deep learning model training approach was related to both identifying the cancer affected areas with region of interest (ROI) techniques and multiple classifications (benign, malignant and normal). The approximate testing accuracies we got from the modified versions of EfficientNet-V1 (b0- 99.15%, b1- 98.58%, b2- 98.43%, b3- 98.01%, b4- 98.86%, b5- 97.72%, b6- 97.72%, b7- 98.72%) and EfficientNet-V2 (b0- 99.29%, b1- 99.01%, b2- 98.72%, b3- 99.43%) are showing very bright future and strong potentials of deep learning approach for the successful detection and classification of breast cancers from the ultrasound images at a very early stage. The code for this research is available here: https://github.com/ac005sheekar/CEIMVEN-Breast.
The availability of curated large-scale training data is a crucial factor for the development of well-generalizing deep learning methods for the extraction of geoinformation from multi-sensor remote sensing imagery. While quite some datasets have already been published by the community, most of them suffer from rather strong limitations, e.g. regarding spatial coverage, diversity or simply number of available samples. Exploiting the freely available data acquired by the Sentinel satellites of the Copernicus program implemented by the European Space Agency, as well as the cloud computing facilities of Google Earth Engine, we provide a dataset consisting of 180,662 triplets of dual-pol synthetic aperture radar (SAR) image patches, multi-spectral Sentinel-2 image patches, and MODIS land cover maps. With all patches being fully georeferenced at a 10 m ground sampling distance and covering all inhabited continents during all meteorological seasons, we expect the dataset to support the community in developing sophisticated deep learning-based approaches for common tasks such as scene classification or semantic segmentation for land cover mapping.