Images shared on social media help crisis managers gain situational awareness and assess incurred damages, among other response tasks. As the volume and velocity of such content are typically high, real-time image classification has become an urgent need for a faster disaster response. Recent advances in computer vision and deep neural networks have enabled the development of models for real-time image classification for a number of tasks, including detecting crisis incidents, filtering irrelevant images, classifying images into specific humanitarian categories, and assessing the severity of the damage. To develop robust real-time models, it is necessary to understand the capability of the publicly available pre-trained models for these tasks, which remains to be under-explored in the crisis informatics literature. In this study, we address such limitations by investigating ten different network architectures for four different tasks using the largest publicly available datasets for these tasks. We also explore various data augmentation strategies, semi-supervised techniques, and a multitask learning setup. In our extensive experiments, we achieve promising results.
Generalizability is the ultimate goal of Machine Learning (ML) image classifiers, for which noise and limited dataset size are among the major concerns. We tackle these challenges through utilizing the framework of deep Multitask Learning (dMTL) and incorporating image depth estimation as an auxiliary task. On a customized and depth-augmented derivation of the MNIST dataset, we show a) multitask loss functions are the most effective approach of implementing dMTL, b) limited dataset size primarily contributes to classification inaccuracy, and c) depth estimation is mostly impacted by noise. In order to further validate the results, we manually labeled the NYU Depth V2 dataset for scene classification tasks. As a contribution to the field, we have made the data in python native format publicly available as an open-source dataset and provided the scene labels. Our experiments on MNIST and NYU-Depth-V2 show dMTL improves generalizability of the classifiers when the dataset is noisy and the number of examples is limited.
We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness. We first developed new gradient-based XAI methods for object detection models to generate object-specific explanations by extending the current methods for image classification models. Interestingly, while these gradient-based methods worked well for explaining image classification models, when being used for explaining object detection models, the resulting saliency maps generally had lower faithfulness than human attention maps when performing the same task. We then developed Human Attention-Guided XAI (HAG-XAI) to learn from human attention how to best combine explanatory information from the models to enhance explanation plausibility by using trainable activation functions and smoothing kernels to maximize XAI saliency map's similarity to human attention maps. While for image classification models, HAG-XAI enhanced explanation plausibility at the expense of faithfulness, for object detection models it enhanced plausibility and faithfulness simultaneously and outperformed existing methods. The learned functions were model-specific, well generalizable to other databases.
In the field of out-of-distribution (OOD) detection, a previous method that use auxiliary data as OOD data has shown promising performance. However, the method provides an equal loss to all auxiliary data to differentiate them from inliers. However, based on our observation, in various tasks, there is a general imbalance in the distribution of the auxiliary OOD data across classes. We propose a balanced energy regularization loss that is simple but generally effective for a variety of tasks. Our balanced energy regularization loss utilizes class-wise different prior probabilities for auxiliary data to address the class imbalance in OOD data. The main concept is to regularize auxiliary samples from majority classes, more heavily than those from minority classes. Our approach performs better for OOD detection in semantic segmentation, long-tailed image classification, and image classification than the prior energy regularization loss. Furthermore, our approach achieves state-of-the-art performance in two tasks: OOD detection in semantic segmentation and long-tailed image classification. Code is available at https://github.com/hyunjunChhoi/Balanced_Energy.
We propose a planning and perception mechanism for a robot (agent), that can only observe the underlying environment partially, in order to solve an image classification problem. A three-layer architecture is suggested that consists of a meta-layer that decides the intermediate goals, an action-layer that selects local actions as the agent navigates towards a goal, and a classification-layer that evaluates the reward and makes a prediction. We design and implement these layers using deep reinforcement learning. A generalized policy gradient algorithm is utilized to learn the parameters of these layers to maximize the expected reward. Our proposed methodology is tested on the MNIST dataset of handwritten digits, which provides us with a level of explainability while interpreting the agent's intermediate goals and course of action.
Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant yet in a task-specific manner. The proposed model improves the final feature's interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance compared to the baseline and standard ResNet models while substantially improving interpretability.
Machine-learning algorithms have shown outstanding image recognition or classification performance for computer vision applications. However, the compute and energy requirement for implementing such classifier models for large-scale problems is quite high. In this paper, we propose Feature Driven Selective Classification (FALCON) inspired by the biological visual attention mechanism in the brain to optimize the energy-efficiency of machine-learning classifiers. We use the consensus in the characteristic features (color/texture) across images in a dataset to decompose the original classification problem and construct a tree of classifiers (nodes) with a generic-to-specific transition in the classification hierarchy. The initial nodes of the tree separate the instances based on feature information and selectively enable the latter nodes to perform object specific classification. The proposed methodology allows selective activation of only those branches and nodes of the classification tree that are relevant to the input while keeping the remaining nodes idle. Additionally, we propose a programmable and scalable Neuromorphic Engine (NeuE) that utilizes arrays of specialized neural computational elements to execute the FALCON based classifier models for diverse datasets. The structure of FALCON facilitates the reuse of nodes while scaling up from small classification problems to larger ones thus allowing us to construct classifier implementations that are significantly more efficient. We evaluate our approach for a 12-object classification task on the Caltech101 dataset and 10-object task on CIFAR-10 dataset by constructing FALCON models on the NeuE platform in 45nm technology. Our results demonstrate significant improvement in energy-efficiency and training time for minimal loss in output quality.
This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised learning methods, DINO and data2vec, were evaluated and compared for their representation learning of vehicle images. The former contrasts local and global views while the latter uses masked prediction on multi-layered representations. In the latter case, supervised learning is employed to finetune a pretrained YOLOR object detector for detecting vehicle wheels, from which definitive wheel positional features are retrieved. The representations learned from these self-supervised learning methods were combined with the wheel positional features for the vehicle classification task. Particularly, a random wheel masking strategy was utilized to finetune the previously learned representations in harmony with the wheel positional features during the training of the classifier. Our experiments show that the data2vec-distilled representations, which are consistent with our wheel masking strategy, outperformed the DINO counterpart, resulting in a celebrated Top-1 classification accuracy of 97.2% for classifying the 13 vehicle classes defined by the Federal Highway Administration.
Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and addresses these issues from the perspective of multi-instance learning. However, these methods neglect the correlation between patches and suffer from a low efficiency in the model optimization and inference. Meanwhile, Swin Transformer is able to address both of these issues with its unique strengths. Built upon Swin Transformer, we present a vision Transformer named \textbf{P}avement \textbf{I}mage \textbf{C}lassification \textbf{T}ransformer (\textbf{PicT}) for pavement distress classification. In order to better exploit the discriminative information of pavement images at the patch level, the \textit{Patch Labeling Teacher} is proposed to leverage a teacher model to dynamically generate pseudo labels of patches from image labels during each iteration, and guides the model to learn the discriminative features of patches. The broad classification head of Swin Transformer may dilute the discriminative features of distressed patches in the feature aggregation step due to the small distressed area ratio of the pavement image. To overcome this drawback, we present a \textit{Patch Refiner} to cluster patches into different groups and only select the highest distress-risk group to yield a slim head for the final image classification. We evaluate our method on CQU-BPDD. Extensive results show that \textbf{PicT} outperforms the second-best performed model by a large margin of $+2.4\%$ in P@R on detection task, $+3.9\%$ in $F1$ on recognition task, and 1.8x throughput, while enjoying 7x faster training speed using the same computing resources. Our codes and models have been released on \href{https://github.com/DearCaat/PicT}{https://github.com/DearCaat/PicT}.
In recent years, colorectal cancer has become one of the most significant diseases that endanger human health. Deep learning methods are increasingly important for the classification of colorectal histopathology images. However, existing approaches focus more on end-to-end automatic classification using computers rather than human-computer interaction. In this paper, we propose an IL-MCAM framework. It is based on attention mechanisms and interactive learning. The proposed IL-MCAM framework includes two stages: automatic learning (AL) and interactivity learning (IL). In the AL stage, a multi-channel attention mechanism model containing three different attention mechanism channels and convolutional neural networks is used to extract multi-channel features for classification. In the IL stage, the proposed IL-MCAM framework continuously adds misclassified images to the training set in an interactive approach, which improves the classification ability of the MCAM model. We carried out a comparison experiment on our dataset and an extended experiment on the HE-NCT-CRC-100K dataset to verify the performance of the proposed IL-MCAM framework, achieving classification accuracies of 98.98% and 99.77%, respectively. In addition, we conducted an ablation experiment and an interchangeability experiment to verify the ability and interchangeability of the three channels. The experimental results show that the proposed IL-MCAM framework has excellent performance in the colorectal histopathological image classification tasks.
Data augmentation has been established as an efficacious approach to supplement useful information for low-resource datasets. Traditional augmentation techniques such as noise injection and image transformations have been widely used. In addition, generative data augmentation (GDA) has been shown to produce more diverse and flexible data. While generative adversarial networks (GANs) have been frequently used for GDA, they lack diversity and controllability compared to text-to-image diffusion models. In this paper, we propose TTIDA (Text-to-Text-to-Image Data Augmentation) to leverage the capabilities of large-scale pre-trained Text-to-Text (T2T) and Text-to-Image (T2I) generative models for data augmentation. By conditioning the T2I model on detailed descriptions produced by T2T models, we are able to generate photo-realistic labeled images in a flexible and controllable manner. Experiments on in-domain classification, cross-domain classification, and image captioning tasks show consistent improvements over other data augmentation baselines. Analytical studies in varied settings, including few-shot, long-tail, and adversarial, further reinforce the effectiveness of TTIDA in enhancing performance and increasing robustness.
Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting targeted attacks that aim to misclassify into a specific target class is particularly challenging due to narrow decision regions. Current state-of-the-art methods often exploit the geometric properties of the decision boundary separating a source image and a target image rather than incorporating information from the images themselves. In contrast, we propose Targeted Edge-informed Attack (TEA), a novel attack that utilizes edge information from the target image to carefully perturb it, thereby producing an adversarial image that is closer to the source image while still achieving the desired target classification. Our approach consistently outperforms current state-of-the-art methods across different models in low query settings (nearly 70\% fewer queries are used), a scenario especially relevant in real-world applications with limited queries and black-box access. Furthermore, by efficiently generating a suitable adversarial example, TEA provides an improved target initialization for established geometry-based attacks.
Linear synthesis model based dictionary learning framework has achieved remarkable performances in image classification in the last decade. Behaved as a generative feature model, it however suffers from some intrinsic deficiencies. In this paper, we propose a novel parametric nonlinear analysis cosparse model (NACM) with which a unique feature vector will be much more efficiently extracted. Additionally, we derive a deep insight to demonstrate that NACM is capable of simultaneously learning the task adapted feature transformation and regularization to encode our preferences, domain prior knowledge and task oriented supervised information into the features. The proposed NACM is devoted to the classification task as a discriminative feature model and yield a novel discriminative nonlinear analysis operator learning framework (DNAOL). The theoretical analysis and experimental performances clearly demonstrate that DNAOL will not only achieve the better or at least competitive classification accuracies than the state-of-the-art algorithms but it can also dramatically reduce the time complexities in both training and testing phases.
Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.
Witnessed the development of deep learning in recent years, increasing number of researches try to adopt deep learning model for medical image analysis. However, the usage of deep learning networks for the pathological image analysis encounters several challenges, e.g. high resolution (gigapixel) of pathological images and lack of annotations of cancer areas. To address the challenges, we proposed a complete framework for the pathological image classification, which consists of a novel training strategy, namely reversed active learning (RAL), and an advanced network, namely atrous DenseNet (ADN). The proposed RAL can remove the mislabel patches in the training set. The refined training set can then be used to train widely used deep learning networks, e.g. VGG-16, ResNets, etc. A novel deep learning network, i.e. atrous DenseNet (ADN), is also proposed for the classification of pathological images. The proposed ADN achieves multi-scale feature extraction by integrating the atrous convolutions to the Dense Block. The proposed RAL and ADN have been evaluated on two pathological datasets, i.e. BACH and CCG. The experimental results demonstrate the excellent performance of the proposed ADN + RAL framework, i.e. the average patch-level ACAs of 94.10% and 92.05% on BACH and CCG validation sets were achieved.
Ordinal classification models assign higher penalties to predictions further away from the true class. As a result, they are appropriate for relevant diagnostic tasks like disease progression prediction or medical image grading. The consensus for assessing their categorical predictions dictates the use of distance-sensitive metrics like the Quadratic-Weighted Kappa score or the Expected Cost. However, there has been little discussion regarding how to measure performance of probabilistic predictions for ordinal classifiers. In conventional classification, common measures for probabilistic predictions are Proper Scoring Rules (PSR) like the Brier score, or Calibration Errors like the ECE, yet these are not optimal choices for ordinal classification. A PSR named Ranked Probability Score (RPS), widely popular in the forecasting field, is more suitable for this task, but it has received no attention in the image analysis community. This paper advocates the use of the RPS for image grading tasks. In addition, we demonstrate a counter-intuitive and questionable behavior of this score, and propose a simple fix for it. Comprehensive experiments on four large-scale biomedical image grading problems over three different datasets show that the RPS is a more suitable performance metric for probabilistic ordinal predictions. Code to reproduce our experiments can be found at https://github.com/agaldran/prob_ord_metrics .
Large vision-language representation learning models like CLIP have demonstrated impressive performance for zero-shot transfer to downstream tasks while largely benefiting from inter-modal (image-text) alignment via contrastive objectives. This downstream performance can further be enhanced by full-scale fine-tuning which is often compute intensive, requires large labelled data, and can reduce out-of-distribution (OOD) robustness. Furthermore, sole reliance on inter-modal alignment might overlook the rich information embedded within each individual modality. In this work, we introduce a sample-efficient domain adaptation strategy for CLIP, termed Domain Aligned CLIP (DAC), which improves both intra-modal (image-image) and inter-modal alignment on target distributions without fine-tuning the main model. For intra-modal alignment, we introduce a lightweight adapter that is specifically trained with an intra-modal contrastive objective. To improve inter-modal alignment, we introduce a simple framework to modulate the precomputed class text embeddings. The proposed few-shot fine-tuning framework is computationally efficient, robust to distribution shifts, and does not alter CLIP's parameters. We study the effectiveness of DAC by benchmarking on 11 widely used image classification tasks with consistent improvements in 16-shot classification upon strong baselines by about 2.3% and demonstrate competitive performance on 4 OOD robustness benchmarks.
Recent developments in vision language models (VLM) have shown great potential for diverse applications related to image understanding. In this study, we have explored state-of-the-art VLM models for vision-based transportation engineering tasks such as image classification and object detection. The image classification task involves congestion detection and crack identification, whereas, for object detection, helmet violations were identified. We have applied open-source models such as CLIP, BLIP, OWL-ViT, Llava-Next, and closed-source GPT-4o to evaluate the performance of these state-of-the-art VLM models to harness the capabilities of language understanding for vision-based transportation tasks. These tasks were performed by applying zero-shot prompting to the VLM models, as zero-shot prompting involves performing tasks without any training on those tasks. It eliminates the need for annotated datasets or fine-tuning for specific tasks. Though these models gave comparative results with benchmark Convolutional Neural Networks (CNN) models in the image classification tasks, for object localization tasks, it still needs improvement. Therefore, this study provides a comprehensive evaluation of the state-of-the-art VLM models highlighting the advantages and limitations of the models, which can be taken as the baseline for future improvement and wide-scale implementation.
The colorectal polyps classification is a critical clinical examination. To improve the classification accuracy, most computer-aided diagnosis algorithms recognize colorectal polyps by adopting Narrow-Band Imaging (NBI). However, the NBI usually suffers from missing utilization in real clinic scenarios since the acquisition of this specific image requires manual switching of the light mode when polyps have been detected by using White-Light (WL) images. To avoid the above situation, we propose a novel method to directly achieve accurate white-light colonoscopy image classification by conducting structured cross-modal representation consistency. In practice, a pair of multi-modal images, i.e. NBI and WL, are fed into a shared Transformer to extract hierarchical feature representations. Then a novel designed Spatial Attention Module (SAM) is adopted to calculate the similarities between the class token and patch tokens %from multi-levels for a specific modality image. By aligning the class tokens and spatial attention maps of paired NBI and WL images at different levels, the Transformer achieves the ability to keep both global and local representation consistency for the above two modalities. Extensive experimental results illustrate the proposed method outperforms the recent studies with a margin, realizing multi-modal prediction with a single Transformer while greatly improving the classification accuracy when only with WL images.
Existing multi-modal approaches primarily focus on enhancing multi-label skin lesion classification performance through advanced fusion modules, often neglecting the associated rise in parameters. In clinical settings, both clinical and dermoscopy images are captured for diagnosis; however, dermoscopy images exhibit more crucial visual features for multi-label skin lesion classification. Motivated by this observation, we introduce a novel asymmetric multi-modal fusion method in this paper for efficient multi-label skin lesion classification. Our fusion method incorporates two innovative schemes. Firstly, we validate the effectiveness of our asymmetric fusion structure. It employs a light and simple network for clinical images and a heavier, more complex one for dermoscopy images, resulting in significant parameter savings compared to the symmetric fusion structure using two identical networks for both modalities. Secondly, in contrast to previous approaches using mutual attention modules for interaction between image modalities, we propose an asymmetric attention module. This module solely leverages clinical image information to enhance dermoscopy image features, considering clinical images as supplementary information in our pipeline. We conduct the extensive experiments on the seven-point checklist dataset. Results demonstrate the generality of our proposed method for both networks and Transformer structures, showcasing its superiority over existing methods We will make our code publicly available.