Transformers, particularly Vision Transformers (ViTs), have achieved state-of-the-art performance in large-scale image classification. However, they often require large amounts of data and can exhibit biases that limit their robustness and generalizability. This paper introduces ForAug, a novel data augmentation scheme that addresses these challenges and explicitly includes inductive biases, which commonly are part of the neural network architecture, into the training data. ForAug is constructed by using pretrained foundation models to separate and recombine foreground objects with different backgrounds, enabling fine-grained control over image composition during training. It thus increases the data diversity and effective number of training samples. We demonstrate that training on ForNet, the application of ForAug to ImageNet, significantly improves the accuracy of ViTs and other architectures by up to 4.5 percentage points (p.p.) on ImageNet and 7.3 p.p. on downstream tasks. Importantly, ForAug enables novel ways of analyzing model behavior and quantifying biases. Namely, we introduce metrics for background robustness, foreground focus, center bias, and size bias and show that training on ForNet substantially reduces these biases compared to training on ImageNet. In summary, ForAug provides a valuable tool for analyzing and mitigating biases, enabling the development of more robust and reliable computer vision models. Our code and dataset are publicly available at https://github.com/tobna/ForAug.
Test-time adaptation with pre-trained vision-language models, such as CLIP, aims to adapt the model to new, potentially out-of-distribution test data. Existing methods calculate the similarity between visual embedding and learnable class embeddings, which are initialized by text embeddings, for zero-shot image classification. In this work, we first analyze this process based on Bayes theorem, and observe that the core factors influencing the final prediction are the likelihood and the prior. However, existing methods essentially focus on adapting class embeddings to adapt likelihood, but they often ignore the importance of prior. To address this gap, we propose a novel approach, \textbf{B}ayesian \textbf{C}lass \textbf{A}daptation (BCA), which in addition to continuously updating class embeddings to adapt likelihood, also uses the posterior of incoming samples to continuously update the prior for each class embedding. This dual updating mechanism allows the model to better adapt to distribution shifts and achieve higher prediction accuracy. Our method not only surpasses existing approaches in terms of performance metrics but also maintains superior inference rates and memory usage, making it highly efficient and practical for real-world applications.
Vision Transformer models exhibit immense power yet remain opaque to human understanding, posing challenges and risks for practical applications. While prior research has attempted to demystify these models through input attribution and neuron role analysis, there's been a notable gap in considering layer-level information and the holistic path of information flow across layers. In this paper, we investigate the significance of influential neuron paths within vision Transformers, which is a path of neurons from the model input to output that impacts the model inference most significantly. We first propose a joint influence measure to assess the contribution of a set of neurons to the model outcome. And we further provide a layer-progressive neuron locating approach that efficiently selects the most influential neuron at each layer trying to discover the crucial neuron path from input to output within the target model. Our experiments demonstrate the superiority of our method finding the most influential neuron path along which the information flows, over the existing baseline solutions. Additionally, the neuron paths have illustrated that vision Transformers exhibit some specific inner working mechanism for processing the visual information within the same image category. We further analyze the key effects of these neurons on the image classification task, showcasing that the found neuron paths have already preserved the model capability on downstream tasks, which may also shed some lights on real-world applications like model pruning. The project website including implementation code is available at https://foundation-model-research.github.io/NeuronPath/.
Due to their effective performance, Convolutional Neural Network (CNN) and Vision Transformer (ViT) architectures have become the standard for solving computer vision tasks. Such architectures require large data sets and rely on convolution and self-attention operations. In 2021, MLP-Mixer emerged, an architecture that relies only on Multilayer Perceptron (MLP) and achieves extremely competitive results when compared to CNNs and ViTs. Despite its good performance in computer vision tasks, the MLP-Mixer architecture may not be suitable for refined feature extraction in images. Recently, the Kolmogorov-Arnold Network (KAN) was proposed as a promising alternative to MLP models. KANs promise to improve accuracy and interpretability when compared to MLPs. Therefore, the present work aims to design a new mixer-based architecture, called KAN-Mixers, using KANs as main layers and evaluate its performance, in terms of several performance metrics, in the image classification task. As main results obtained, the KAN-Mixers model was superior to the MLP, MLP-Mixer and KAN models in the Fashion-MNIST and CIFAR-10 datasets, with 0.9030 and 0.6980 of average accuracy, respectively.
Despite the potential of federated learning in medical applications, inconsistent imaging quality across institutions-stemming from lower-quality data from a minority of clients-biases federated models toward more common high-quality images. This raises significant fairness concerns. Existing fair federated learning methods have demonstrated some effectiveness in solving this problem by aligning a single 0th- or 1st-order state of convergence (e.g., training loss or sharpness). However, we argue in this work that fairness based on such a single state is still not an adequate surrogate for fairness during testing, as these single metrics fail to fully capture the convergence characteristics, making them suboptimal for guiding fair learning. To address this limitation, we develop a generalized framework. Specifically, we propose assessing convergence using multiple states, defined as sharpness or perturbed loss computed at varying search distances. Building on this comprehensive assessment, we propose promoting fairness for these states across clients to achieve our ultimate fairness objective. This is accomplished through the proposed method, FedISM+. In FedISM+, the search distance evolves over time, progressively focusing on different states. We then incorporate two components in local training and global aggregation to ensure cross-client fairness for each state. This gradually makes convergence equitable for all states, thereby improving fairness during testing. Our empirical evaluations, performed on the well-known RSNA ICH and ISIC 2019 datasets, demonstrate the superiority of FedISM+ over existing state-of-the-art methods for fair federated learning. The code is available at https://github.com/wnn2000/FFL4MIA.
Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of base-point. The choice of base-point is not a priori obvious and can lead to drastically different explanations. There is a longstanding hypothesis that data lies on a low dimensional Riemannian manifold. The quality of explanations on a manifold can be measured by the extent to which an explanation for a point lies in its tangent space. In this work, we propose that the base-point should be chosen such that it maximises the tangential alignment of the explanation. We formalise the notion of tangential alignment and provide theoretical conditions under which a base-point choice will provide explanations lying in the tangent space. We demonstrate how to approximate the optimal base-point on several well-known image classification datasets. Furthermore, we compare the optimal base-point choice with common base-points and three gradient explainability models.
Climate change is one of the most pressing challenges of the 21st century, sparking widespread discourse across social media platforms. Activists, policymakers, and researchers seek to understand public sentiment and narratives while access to social media data has become increasingly restricted in the post-API era. In this study, we analyze a dataset of climate change-related tweets from X (formerly Twitter) shared in 2019, containing 730k tweets along with the shared images. Our approach integrates statistical analysis, image classification, object detection, and sentiment analysis to explore visual narratives in climate discourse. Additionally, we introduce a graphical user interface (GUI) to facilitate interactive data exploration. Our findings reveal key themes in climate communication, highlight sentiment divergence between images and text, and underscore the strengths and limitations of foundation models in analyzing social media imagery. By releasing our code and tools, we aim to support future research on the intersection of climate change, social media, and computer vision.
The Mixture-of-Experts (MoE) model has succeeded in deep learning (DL). However, its complex architecture and advantages over dense models in image classification remain unclear. In previous studies, MoE performance has often been affected by noise and outliers in the input space. Some approaches incorporate input clustering for training MoE models, but most clustering algorithms lack access to labeled data, limiting their effectiveness. This paper introduces the Double-stage Feature-level Clustering and Pseudo-labeling-based Mixture of Experts (DFCP-MoE) framework, which consists of input feature extraction, feature-level clustering, and a computationally efficient pseudo-labeling strategy. This approach reduces the impact of noise and outliers while leveraging a small subset of labeled data to label a large portion of unlabeled inputs. We propose a conditional end-to-end joint training method that improves expert specialization by training the MoE model on well-labeled, clustered inputs. Unlike traditional MoE and dense models, the DFCP-MoE framework effectively captures input space diversity, leading to competitive inference results. We validate our approach on three benchmark datasets for multi-class classification tasks.
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether it was used to train a machine learning model. While state-of-the-art attacks achieve a significant privacy leakage, their requirements are not feasible enough, hindering their role as practical tools to assess the magnitude of the privacy risk. Moreover, the most appropriate evaluation metric of MIA, the True Positive Rate at low False Positive Rate lacks interpretability. We claim that the incorporation of Few-Shot Learning techniques to the MIA field and a proper qualitative and quantitative privacy evaluation measure should deal with these issues. In this context, our proposal is twofold. We propose a Few-Shot learning based MIA, coined as the FeS-MIA model, which eases the evaluation of the privacy breach of a deep learning model by significantly reducing the number of resources required for the purpose. Furthermore, we propose an interpretable quantitative and qualitative measure of privacy, referred to as Log-MIA measure. Jointly, these proposals provide new tools to assess the privacy leakage and to ease the evaluation of the training data integrity of deep learning models, that is, to analyze the privacy breach of a deep learning model. Experiments carried out with MIA over image classification and language modeling tasks and its comparison to the state-of-the-art show that our proposals excel at reporting the privacy leakage of a deep learning model with little extra information.
To improve trust and transparency, it is crucial to be able to interpret the decisions of Deep Neural classifiers (DNNs). Instance-level examinations, such as attribution techniques, are commonly employed to interpret the model decisions. However, when interpreting misclassified decisions, human intervention may be required. Analyzing the attribu tions across each class within one instance can be particularly labor intensive and influenced by the bias of the human interpreter. In this paper, we present a novel framework to uncover the weakness of the classifier via counterfactual examples. A prober is introduced to learn the correctness of the classifier's decision in terms of binary code-hit or miss. It enables the creation of the counterfactual example concerning the prober's decision. We test the performance of our prober's misclassification detection and verify its effectiveness on the image classification benchmark datasets. Furthermore, by generating counterfactuals that penetrate the prober, we demonstrate that our framework effectively identifies vulnerabilities in the target classifier without relying on label information on the MNIST dataset.
Model merging is a technique that combines multiple finetuned models into a single model without additional training, allowing a free-rider to cheaply inherit specialized capabilities. This study investigates methodologies to suppress unwanted model merging by free-riders. Existing methods such as model watermarking or fingerprinting can only detect merging in hindsight. In contrast, we propose a first proactive defense against model merging. Specifically, our defense method modifies the model parameters so that the model is disrupted if the model is merged with any other model, while its functionality is kept unchanged if not merged with others. Our approach consists of two modules, rearranging MLP parameters and scaling attention heads, which push the model out of the shared basin in parameter space, causing the merging performance with other models to degrade significantly. We conduct extensive experiments on image classification, image generation, and text classification to demonstrate that our defense severely disrupts merging while retaining the functionality of the post-protect model. Moreover, we analyze potential adaptive attacks and further propose a dropout-based pruning to improve our proposal's robustness.
Foundation models pretrained on large-scale natural images have been widely used to adapt to medical image analysis through finetuning. This is largely attributed to pretrained representations capturing universal, robust, and generalizable features, which can be reutilized by downstream tasks. However, these representations are later found to gradually vanish during finetuning, accompanied by a degradation of foundation model's original abilities, e.g., generalizability. In this paper, we argue that pretrained representations can be well preserved while still effectively adapting to downstream tasks. We study this by proposing a new finetuning method RepSim, which minimizes the distance between pretrained and finetuned representations via constraining learnable orthogonal manifold based on similarity invariance. Compared to standard finetuning methods, e.g., full finetuning, our method improves representation similarity by over 30% while maintaining competitive accuracy, and reduces sharpness by 42% across five medical image classification datasets. The code will be released.
Zero-shot learning (ZSL) aims to train a model on seen classes and recognize unseen classes by knowledge transfer through shared auxiliary information. Recent studies reveal that documents from encyclopedias provide helpful auxiliary information. However, existing methods align noisy documents, entangled in visual and non-visual descriptions, with image regions, yet solely depend on implicit learning. These models fail to filter non-visual noise reliably and incorrectly align non-visual words to image regions, which is harmful to knowledge transfer. In this work, we propose a novel multi-attribute document supervision framework to remove noises at both document collection and model learning stages. With the help of large language models, we introduce a novel prompt algorithm that automatically removes non-visual descriptions and enriches less-described documents in multiple attribute views. Our proposed model, MADS, extracts multi-view transferable knowledge with information decoupling and semantic interactions for semantic alignment at local and global levels. Besides, we introduce a model-agnostic focus loss to explicitly enhance attention to visually discriminative information during training, also improving existing methods without additional parameters. With comparable computation costs, MADS consistently outperforms the SOTA by 7.2% and 8.2% on average in three benchmarks for document-based ZSL and GZSL settings, respectively. Moreover, we qualitatively offer interpretable predictions from multiple attribute views.
Multi-modal fusion holds great promise for integrating information from different modalities. However, due to a lack of consideration for modal consistency, existing multi-modal fusion methods in the field of remote sensing still face challenges of incomplete semantic information and low computational efficiency in their fusion designs. Inspired by the observation that the visual language pre-training model CLIP can effectively extract strong semantic information from visual features, we propose M$^3$amba, a novel end-to-end CLIP-driven Mamba model for multi-modal fusion to address these challenges. Specifically, we introduce CLIP-driven modality-specific adapters in the fusion architecture to avoid the bias of understanding specific domains caused by direct inference, making the original CLIP encoder modality-specific perception. This unified framework enables minimal training to achieve a comprehensive semantic understanding of different modalities, thereby guiding cross-modal feature fusion. To further enhance the consistent association between modality mappings, a multi-modal Mamba fusion architecture with linear complexity and a cross-attention module Cross-SS2D are designed, which fully considers effective and efficient information interaction to achieve complete fusion. Extensive experiments have shown that M$^3$amba has an average performance improvement of at least 5.98\% compared with the state-of-the-art methods in multi-modal hyperspectral image classification tasks in the remote sensing field, while also demonstrating excellent training efficiency, achieving a double improvement in accuracy and efficiency. The code is released at https://github.com/kaka-Cao/M3amba.
Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge. Existing methods aim to tackle this problem by locating and aligning relevant local features. However, the high intra-class variability in real-world images poses significant challenges in locating semantically relevant local regions under few-shot settings. Drawing inspiration from the human's complementary learning system, which excels at rapidly capturing and integrating semantic features from limited examples, we propose the generalization-optimized Systems Consolidation Adaptive Memory Dual-Network, SCAM-Net. This approach simulates the systems consolidation of complementary learning system with an adaptive memory module, which successfully addresses the difficulty of identifying meaningful features in few-shot scenarios. Specifically, we construct a Hippocampus-Neocortex dual-network that consolidates structured representation of each category, the structured representation is then stored and adaptively regulated following the generalization optimization principle in a long-term memory inside Neocortex. Extensive experiments on benchmark datasets show that the proposed model has achieved state-of-the-art performance.
Zero-shot learning (ZL) is crucial for tasks involving unseen categories, such as natural language processing, image classification, and cross-lingual transfer. Current applications often fail to accurately infer and handle new relations or entities involving unseen categories, severely limiting their scalability and practicality in open-domain scenarios. ZL learning faces the challenge of effectively transferring semantic information of unseen categories in multi-modal knowledge graph (MMKG) embedding representation learning. In this paper, we propose ZSLLM, a framework for zero-shot embedding learning of MMKGs using large language models (LLMs). We leverage textual modality information of unseen categories as prompts to fully utilize the reasoning capabilities of LLMs, enabling semantic information transfer across different modalities for unseen categories. Through model-based learning, the embedding representation of unseen categories in MMKG is enhanced. Extensive experiments conducted on multiple real-world datasets demonstrate the superiority of our approach compared to state-of-the-art methods.
Growing evidence suggests that layer attention mechanisms, which enhance interaction among layers in deep neural networks, have significantly advanced network architectures. However, existing layer attention methods suffer from redundancy, as attention weights learned by adjacent layers often become highly similar. This redundancy causes multiple layers to extract nearly identical features, reducing the model's representational capacity and increasing training time. To address this issue, we propose a novel approach to quantify redundancy by leveraging the Kullback-Leibler (KL) divergence between adjacent layers. Additionally, we introduce an Enhanced Beta Quantile Mapping (EBQM) method that accurately identifies and skips redundant layers, thereby maintaining model stability. Our proposed Efficient Layer Attention (ELA) architecture, improves both training efficiency and overall performance, achieving a 30% reduction in training time while enhancing performance in tasks such as image classification and object detection.
Minimally invasive surgery (MIS) has transformed clinical practice by reducing recovery times, minimizing complications, and enhancing precision. Nonetheless, MIS inherently relies on indirect visualization and precise instrument control, posing unique challenges. Recent advances in artificial intelligence have enabled real-time surgical scene understanding through techniques such as image classification, object detection, and segmentation, with scene reconstruction emerging as a key element for enhanced intraoperative guidance. Although neural radiance fields (NeRFs) have been explored for this purpose, their substantial data requirements and slow rendering inhibit real-time performance. In contrast, 3D Gaussian Splatting (3DGS) offers a more efficient alternative, achieving state-of-the-art performance in dynamic surgical scene reconstruction. In this work, we introduce Feature-EndoGaussian (FEG), an extension of 3DGS that integrates 2D segmentation cues into 3D rendering to enable real-time semantic and scene reconstruction. By leveraging pretrained segmentation foundation models, FEG incorporates semantic feature distillation within the Gaussian deformation framework, thereby enhancing both reconstruction fidelity and segmentation accuracy. On the EndoNeRF dataset, FEG achieves superior performance (SSIM of 0.97, PSNR of 39.08, and LPIPS of 0.03) compared to leading methods. Additionally, on the EndoVis18 dataset, FEG demonstrates competitive class-wise segmentation metrics while balancing model size and real-time performance.
In histopathology, intelligent diagnosis of Whole Slide Images (WSIs) is essential for automating and objectifying diagnoses, reducing the workload of pathologists. However, diagnostic models often face the challenge of forgetting previously learned data during incremental training on datasets from different sources. To address this issue, we propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification. Our framework introduces two key components into the common MIL model architecture. First, it leverages microscopic pathological prior to select more accurate and diverse representative patches for MIL. Secondly, it trains separate classification heads for each task and uses macroscopic pathological prior knowledge, treating the thumbnail as a prompt guide (PG) to select the appropriate classification head. We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets. PaGMIL achieves a better balance between the performance of the current task and the retention of previous tasks, outperforming other continual learning methods. Our code will be open-sourced upon acceptance.
Quantum vision transformers (QViTs) build on vision transformers (ViTs) by replacing linear layers within the self-attention mechanism with parameterised quantum neural networks (QNNs), harnessing quantum mechanical properties to improve feature representation. This hybrid approach aims to achieve superior performance, with significantly reduced model complexity as a result of the enriched feature representation, requiring fewer parameters. This paper proposes a novel QViT model for biomedical image classification and investigates its performance against comparable ViTs across eight diverse datasets, encompassing various modalities and classification tasks. We assess models trained from scratch and those pre-trained using knowledge distillation (KD) from high-quality teacher models. Our findings demonstrate that QViTs outperform comparable ViTs with average ROC AUC (0.863 vs 0.846) and accuracy (0.710 vs 0.687) when trained from scratch, and even compete with state-of-the-art classical models in multiple tasks, whilst being significantly more efficient (89% reduction in GFLOPs and 99.99% in parameter number). Additionally, we find that QViTs and ViTs respond equally well to KD, with QViT pre-training performance scaling with model complexity. This is the first investigation into the efficacy of deploying QViTs with KD for computer-aided diagnosis. Our results highlight the enormous potential of quantum machine learning (QML) in biomedical image analysis.