Recent advancements in vision-language models (VLMs), such as CLIP, have demonstrated substantial success in self-supervised representation learning for vision tasks. However, effectively adapting VLMs to downstream applications remains challenging, as their accuracy often depends on time-intensive and expertise-demanding prompt engineering, while full model fine-tuning is costly. This is particularly true for biomedical images, which, unlike natural images, typically suffer from limited annotated datasets, unintuitive image contrasts, and nuanced visual features. Recent prompt learning techniques, such as Context Optimization (CoOp) intend to tackle these issues, but still fall short in generalizability. Meanwhile, explorations in prompt learning for biomedical image analysis are still highly limited. In this work, we propose BiomedCoOp, a novel prompt learning framework that enables efficient adaptation of BiomedCLIP for accurate and highly generalizable few-shot biomedical image classification. Our approach achieves effective prompt context learning by leveraging semantic consistency with average prompt ensembles from Large Language Models (LLMs) and knowledge distillation with a statistics-based prompt selection strategy. We conducted comprehensive validation of our proposed framework on 11 medical datasets across 9 modalities and 10 organs against existing state-of-the-art methods, demonstrating significant improvements in both accuracy and generalizability. The code will be publicly available at https://github.com/HealthX-Lab/BiomedCoOp.
Recent advancements in vision-language pre-training via contrastive learning have significantly improved performance across computer vision tasks. However, in the medical domain, obtaining multimodal data is often costly and challenging due to privacy, sensitivity, and annotation complexity. To mitigate data scarcity while boosting model performance, we introduce \textbf{Uni-Mlip}, a unified self-supervision framework specifically designed to enhance medical vision-language pre-training. Uni-Mlip seamlessly integrates cross-modality, uni-modality, and fused-modality self-supervision techniques at the data-level and the feature-level. Additionally, Uni-Mlip tailors uni-modal image self-supervision to accommodate the unique characteristics of medical images. Our experiments across datasets of varying scales demonstrate that Uni-Mlip significantly surpasses current state-of-the-art methods in three key downstream tasks: image-text retrieval, image classification, and visual question answering (VQA).
Object detectors, which are widely used in real-world applications, are vulnerable to backdoor attacks. This vulnerability arises because many users rely on datasets or pre-trained models provided by third parties due to constraints on data and resources. However, most research on backdoor attacks has focused on image classification, with limited investigation into object detection. Furthermore, the triggers for most existing backdoor attacks on object detection are manually generated, requiring prior knowledge and consistent patterns between the training and inference stages. This approach makes the attacks either easy to detect or difficult to adapt to various scenarios. To address these limitations, we propose novel twin trigger generative networks in the frequency domain to generate invisible triggers for implanting stealthy backdoors into models during training, and visible triggers for steady activation during inference, making the attack process difficult to trace. Specifically, for the invisible trigger generative network, we deploy a Gaussian smoothing layer and a high-frequency artifact classifier to enhance the stealthiness of backdoor implantation in object detectors. For the visible trigger generative network, we design a novel alignment loss to optimize the visible triggers so that they differ from the original patterns but still align with the malicious activation behavior of the invisible triggers. Extensive experimental results and analyses prove the possibility of using different triggers in the training stage and the inference stage, and demonstrate the attack effectiveness of our proposed visible trigger and invisible trigger generative networks, significantly reducing the mAP_0.5 of the object detectors by 70.0% and 84.5%, including YOLOv5 and YOLOv7 with different settings, respectively.
Machine Unlearning (MU) aims to selectively erase harmful behaviors from models while retaining the overall utility of the model. As a multi-task learning problem, MU involves balancing objectives related to forgetting specific concepts/data and preserving general performance. A naive integration of these forgetting and preserving objectives can lead to gradient conflicts, impeding MU algorithms from reaching optimal solutions. To address the gradient conflict issue, we reformulate MU as a two-player cooperative game, where the two players, namely, the forgetting player and the preservation player, contribute via their gradient proposals to maximize their overall gain. To this end, inspired by the Nash bargaining theory, we derive a closed-form solution to guide the model toward the Pareto front, effectively avoiding the gradient conflicts. Our formulation of MU guarantees an equilibrium solution, where any deviation from the final state would lead to a reduction in the overall objectives for both players, ensuring optimality in each objective. We evaluate our algorithm's effectiveness on a diverse set of tasks across image classification and image generation. Extensive experiments with ResNet, vision-language model CLIP, and text-to-image diffusion models demonstrate that our method outperforms state-of-the-art MU algorithms, achieving superior performance on several benchmarks. For example, in the challenging scenario of sample-wise forgetting, our algorithm approaches the gold standard retrain baseline. Our results also highlight improvements in forgetting precision, preservation of generalization, and robustness against adversarial attacks.
As a prominent direction of Artificial General Intelligence (AGI), Multimodal Large Language Models (MLLMs) have garnered increased attention from both industry and academia. Building upon pre-trained LLMs, this family of models further develops multimodal perception and reasoning capabilities that are impressive, such as writing code given a flow chart or creating stories based on an image. In the development process, evaluation is critical since it provides intuitive feedback and guidance on improving models. Distinct from the traditional train-eval-test paradigm that only favors a single task like image classification, the versatility of MLLMs has spurred the rise of various new benchmarks and evaluation methods. In this paper, we aim to present a comprehensive survey of MLLM evaluation, discussing four key aspects: 1) the summarised benchmarks types divided by the evaluation capabilities, including foundation capabilities, model self-analysis, and extented applications; 2) the typical process of benchmark counstruction, consisting of data collection, annotation, and precautions; 3) the systematic evaluation manner composed of judge, metric, and toolkit; 4) the outlook for the next benchmark. This work aims to offer researchers an easy grasp of how to effectively evaluate MLLMs according to different needs and to inspire better evaluation methods, thereby driving the progress of MLLM research.
Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative Adversarial Networks (GANs) to mitigate biases. We introduce DiffuBias, a novel pipeline for text-to-image generation that enhances classifier robustness by generating bias-conflict samples, without requiring training during the generation phase. Utilizing pretrained diffusion and image captioning models, DiffuBias generates images that challenge the biases of classifiers, using the top-$K$ losses from a biased classifier ($f_B$) to create more representative data samples. This method not only debiases effectively but also boosts classifier generalization capabilities. To the best of our knowledge, DiffuBias is the first approach leveraging a stable diffusion model to generate bias-conflict samples in debiasing tasks. Our comprehensive experimental evaluations demonstrate that DiffuBias achieves state-of-the-art performance on benchmark datasets. We also conduct a comparative analysis of various generative models in terms of carbon emissions and energy consumption to highlight the significance of computational efficiency.
Recent advancements in Artificial Intelligence (AI), particularly with Large Language Models (LLMs), have led to significant progress in narrow tasks such as image classification, language translation, coding, and writing. However, these models face limitations in reliability and scalability due to their siloed architectures, which are designed to handle only one data modality (data type) at a time. This single modal approach hinders their ability to integrate the complex set of data points required for real-world challenges and problem-solving tasks like medical diagnosis, quality assurance, equipment troubleshooting, and financial decision-making. Addressing these real-world challenges requires a more capable Artificial General Intelligence (AGI) system. Our primary contribution is the development of the Open General Intelligence (OGI) framework, a novel systems architecture that serves as a macro design reference for AGI. The OGI framework adopts a modular approach to the design of intelligent systems, based on the premise that cognition must occur across multiple specialized modules that can seamlessly operate as a single system. OGI integrates these modules using a dynamic processing system and a fabric interconnect, enabling real-time adaptability, multi-modal integration, and scalable processing. The OGI framework consists of three key components: (1) Overall Macro Design Guidance that directs operational design and processing, (2) a Dynamic Processing System that controls routing, primary goals, instructions, and weighting, and (3) Framework Areas, a set of specialized modules that operate cohesively to form a unified cognitive system. By incorporating known principles from human cognition into AI systems, the OGI framework aims to overcome the challenges observed in today's intelligent systems, paving the way for more holistic and context-aware problem-solving capabilities.
Few-shot learning presents a critical solution for cancer diagnosis in computational pathology (CPath), addressing fundamental limitations in data availability, particularly the scarcity of expert annotations and patient privacy constraints. A key challenge in this paradigm stems from the inherent disparity between the limited training set of whole slide images (WSIs) and the enormous number of contained patches, where a significant portion of these patches lacks diagnostically relevant information, potentially diluting the model's ability to learn and focus on critical diagnostic features. While recent works attempt to address this by incorporating additional knowledge, several crucial gaps hinder further progress: (1) despite the emergence of powerful pathology foundation models (FMs), their potential remains largely untapped, with most approaches limiting their use to basic feature extraction; (2) current language guidance mechanisms attempt to align text prompts with vast numbers of WSI patches all at once, struggling to leverage rich pathological semantic information. To this end, we introduce the knowledge-enhanced adaptive visual compression framework, dubbed FOCUS, which uniquely combines pathology FMs with language prior knowledge to enable a focused analysis of diagnostically relevant regions by prioritizing discriminative WSI patches. Our approach implements a progressive three-stage compression strategy: we first leverage FMs for global visual redundancy elimination, and integrate compressed features with language prompts for semantic relevance assessment, then perform neighbor-aware visual token filtering while preserving spatial coherence. Extensive experiments on pathological datasets spanning breast, lung, and ovarian cancers demonstrate its superior performance in few-shot pathology diagnosis. Codes are available at https://github.com/dddavid4real/FOCUS.
Derailment is one of the most frequent ways railway accidents happen. Track defects such as buckling and hogging that cause misalignment of tracks can easily lead to derailments. While railway tracks get laterally misaligned due to buckling, vertical misalignments can result from hogging. Such misalignments are visibly recognizable, and we can even automate the recognition using data-driven models. This paper discusses how we build such data-driven models. There are no public datasets available to build such models; therefore, we introduce TMD (Track Misalignment Detection) dataset. It consists of misaligned and normal track images. The problem we try to solve here is essentially a binary image classification problem, which we solve by exploring the feature extraction approach to transfer learning (TL). In this approach, we employ a pre-trained network to extract rich features, which are then supplied with annotations to a learning algorithm for building a candidate TL model. Several pre-trained networks and learning algorithms exist, resulting in many TL models; therefore, it becomes essential to identify effective ones. We propose an evaluation criterion to decide which are effective ones even before we test them. Our experiments demonstrate that the TL models selected based on our proposed evaluation criterion really perform better than other candidate TL models during testing.
In distributed optimization, the communication of model updates can be a performance bottleneck. Consequently, gradient compression has been proposed as a means of increasing optimization throughput. In general, due to information loss, compression introduces a penalty on the number of iterations needed to reach a solution. In this work, we investigate how the iteration penalty depends on the interaction between compression and problem structure, in the context of non-convex stochastic optimization. We focus on linear compression schemes, where compression and decompression can be modeled as multiplication with a random matrix. We consider several distributions of matrices, among them random orthogonal matrices and matrices with random Gaussian entries. We find that in each case, the impact of compression on convergence can be quantified in terms of the norm of the Hessian of the objective, using a norm defined by the compression scheme. The analysis reveals that in certain cases, compression performance is related to low-rank structure or other spectral properties of the problem. In these cases, our bounds predict that the penalty introduced by compression is significantly reduced compared to worst-case bounds that only consider the compression level, ignoring problem data. We verify the theoretical findings on several optimization problems, including fine-tuning an image classification model.
Explaining the decision-making processes of Artificial Intelligence (AI) models is crucial for addressing their "black box" nature, particularly in tasks like image classification. Traditional eXplainable AI (XAI) methods typically rely on unimodal explanations, either visual or textual, each with inherent limitations. Visual explanations highlight key regions but often lack rationale, while textual explanations provide context without spatial grounding. Further, both explanation types can be inconsistent or incomplete, limiting their reliability. To address these challenges, we propose a novel Multimodal Explanation-Guided Learning (MEGL) framework that leverages both visual and textual explanations to enhance model interpretability and improve classification performance. Our Saliency-Driven Textual Grounding (SDTG) approach integrates spatial information from visual explanations into textual rationales, providing spatially grounded and contextually rich explanations. Additionally, we introduce Textual Supervision on Visual Explanations to align visual explanations with textual rationales, even in cases where ground truth visual annotations are missing. A Visual Explanation Distribution Consistency loss further reinforces visual coherence by aligning the generated visual explanations with dataset-level patterns, enabling the model to effectively learn from incomplete multimodal supervision. We validate MEGL on two new datasets, Object-ME and Action-ME, for image classification with multimodal explanations. Experimental results demonstrate that MEGL outperforms previous approaches in prediction accuracy and explanation quality across both visual and textual domains. Our code will be made available upon the acceptance of the paper.
Motivated by the potential reduction in the required manual efforts in the fruit industry, this paper attempts to automate fruit maturity recognition. We study the problem from the agricultural, market, and automation perspectives, often taken at different points in the supply chain. Since different maturity states have different visual characteristics, an image classification technology can certainly help here. To develop fruit image classifiers, we need a feature extraction method and a learning algorithm. We use different pre-trained neural networks for effective feature extraction and employ different machine learning algorithms while carrying out bias/variance analysis of the learned models. The analysis helps us select the best ones for each perspective under consideration. We achieve 96%, 94%, and 86% accuracies on our novel dataset named RipeRaw from the agricultural, market, and automation perspectives, respectively.
Geometric shape features have been widely used as strong predictors for image classification. Nevertheless, most existing classifiers such as deep neural networks (DNNs) directly leverage the statistical correlations between these shape features and target variables. However, these correlations can often be spurious and unstable across different environments (e.g., in different age groups, certain types of brain changes have unstable relations with neurodegenerative disease); hence leading to biased or inaccurate predictions. In this paper, we introduce a novel framework that for the first time develops invariant shape representation learning (ISRL) to further strengthen the robustness of image classifiers. In contrast to existing approaches that mainly derive features in the image space, our model ISRL is designed to jointly capture invariant features in latent shape spaces parameterized by deformable transformations. To achieve this goal, we develop a new learning paradigm based on invariant risk minimization (IRM) to learn invariant representations of image and shape features across multiple training distributions/environments. By embedding the features that are invariant with regard to target variables in different environments, our model consistently offers more accurate predictions. We validate our method by performing classification tasks on both simulated 2D images, real 3D brain and cine cardiovascular magnetic resonance images (MRIs). Our code is publicly available at https://github.com/tonmoy-hossain/ISRL.
This study aims to optimize the few-shot image classification task and improve the model's feature extraction and classification performance by combining self-supervised learning with the deep network model ResNet-101. During the training process, we first pre-train the model with self-supervision to enable it to learn common feature expressions on a large amount of unlabeled data; then fine-tune it on the few-shot dataset Mini-ImageNet to improve the model's accuracy and generalization ability under limited data. The experimental results show that compared with traditional convolutional neural networks, ResNet-50, DenseNet, and other models, our method has achieved excellent performance of about 95.12% in classification accuracy (ACC) and F1 score, verifying the effectiveness of self-supervised learning in few-shot classification. This method provides an efficient and reliable solution for the field of few-shot image classification.
Deep learning has achieved remarkable success in image classification and segmentation tasks. However, fairness concerns persist, as models often exhibit biases that disproportionately affect demographic groups defined by sensitive attributes such as race, gender, or age. Existing bias-mitigation techniques, including Subgroup Re-balancing, Adversarial Training, and Domain Generalization, aim to balance accuracy across demographic groups, but often fail to simultaneously improve overall accuracy, group-specific accuracy, and fairness due to conflicts among these interdependent objectives. We propose the Fair Distillation (FairDi) method, a novel fairness approach that decomposes these objectives by leveraging biased ``teacher'' models, each optimized for a specific demographic group. These teacher models then guide the training of a unified ``student'' model, which distills their knowledge to maximize overall and group-specific accuracies, while minimizing inter-group disparities. Experiments on medical imaging datasets show that FairDi achieves significant gains in both overall and group-specific accuracy, along with improved fairness, compared to existing methods. FairDi is adaptable to various medical tasks, such as classification and segmentation, and provides an effective solution for equitable model performance.
Diffusion models, known for their generative capabilities, have recently shown unexpected potential in image classification tasks by using Bayes' theorem. However, most diffusion classifiers require evaluating all class labels for a single classification, leading to significant computational costs that can hinder their application in large-scale scenarios. To address this, we present a Hierarchical Diffusion Classifier (HDC) that exploits the inherent hierarchical label structure of a dataset. By progressively pruning irrelevant high-level categories and refining predictions only within relevant subcategories, i.e., leaf nodes, HDC reduces the total number of class evaluations. As a result, HDC can accelerate inference by up to 60% while maintaining and, in some cases, improving classification accuracy. Our work enables a new control mechanism of the trade-off between speed and precision, making diffusion-based classification more viable for real-world applications, particularly in large-scale image classification tasks.
Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal design of these linear models is still an open question. In this work, we attempt to answer this question by finding the best linear approximation to softmax attention from a theoretical perspective. We start by unifying existing linear complexity models as the linear attention form and then identify three conditions for the optimal linear attention design: 1) Dynamic memory ability; 2) Static approximation ability; 3) Least parameter approximation. We find that none of the current linear models meet all three conditions, resulting in suboptimal performance. Instead, we propose Meta Linear Attention (MetaLA) as a solution that satisfies these conditions. Our experiments on Multi-Query Associative Recall (MQAR) task, language modeling, image classification, and Long-Range Arena (LRA) benchmark demonstrate that MetaLA is more effective than the existing linear models.
With the development of digital imaging in medical microscopy, artificial intelligent-based analysis of pathological whole slide images (WSIs) provides a powerful tool for cancer diagnosis. Limited by the expensive cost of pixel-level annotation, current research primarily focuses on representation learning with slide-level labels, showing success in various downstream tasks. However, given the diversity of lesion types and the complex relationships between each other, these techniques still deserve further exploration in addressing advanced pathology tasks. To this end, we introduce the concept of hierarchical pathological image classification and propose a representation learning called PathTree. PathTree considers the multi-classification of diseases as a binary tree structure. Each category is represented as a professional pathological text description, which messages information with a tree-like encoder. The interactive text features are then used to guide the aggregation of hierarchical multiple representations. PathTree uses slide-text similarity to obtain probability scores and introduces two extra tree specific losses to further constrain the association between texts and slides. Through extensive experiments on three challenging hierarchical classification datasets: in-house cryosectioned lung tissue lesion identification, public prostate cancer grade assessment, and public breast cancer subtyping, our proposed PathTree is consistently competitive compared to the state-of-the-art methods and provides a new perspective on the deep learning-assisted solution for more complex WSI classification.
We propose a novel and efficient logit distillation method, Multi-perspective Contrastive Logit Distillation (MCLD), which leverages contrastive learning to distill logits from multiple perspectives in knowledge distillation. Recent research on logit distillation has primarily focused on maximizing the information learned from the teacher model's logits to enhance the performance of the student model. To this end, we propose MCLD, which consists of three key components: Instance-wise CLD, Sample-wise CLD, and Category-wise CLD. These components are designed to facilitate the transfer of more information from the teacher's logits to the student model. Comprehensive evaluations on image classification tasks using CIFAR-100 and ImageNet, alongside representation transferability assessments on STL-10 and Tiny-ImageNet, highlight the significant advantages of our method. The knowledge distillation with our MCLD, surpasses existing state-of-the-art methods.
Visual-based recognition, e.g., image classification, object detection, etc., is a long-standing challenge in computer vision and robotics communities. Concerning the roboticists, since the knowledge of the environment is a prerequisite for complex navigation tasks, visual place recognition is vital for most localization implementations or re-localization and loop closure detection pipelines within simultaneous localization and mapping (SLAM). More specifically, it corresponds to the system's ability to identify and match a previously visited location using computer vision tools. Towards developing novel techniques with enhanced accuracy and robustness, while motivated by the success presented in natural language processing methods, researchers have recently turned their attention to vision-language models, which integrate visual and textual data.