The escalating frequency and scale of recent malware attacks underscore the urgent need for swift and precise malware classification in the ever-evolving cybersecurity landscape. Key challenges include accurately categorizing closely related malware families. To tackle this evolving threat landscape, this paper proposes a novel architecture LeViT-MC which produces state-of-the-art results in malware detection and classification. LeViT-MC leverages a vision transformer-based architecture, an image-based visualization approach, and advanced transfer learning techniques. Experimental results on multi-class malware classification using the MaleVis dataset indicate LeViT-MC's significant advantage over existing models. This study underscores the critical importance of combining image-based and transfer learning techniques, with vision transformers at the forefront of the ongoing battle against evolving cyber threats. We propose a novel architecture LeViT-MC which not only achieves state of the art results on image classification but is also more time efficient.
Merging has become a widespread way to cheaply combine individual models into a single model that inherits their capabilities and attains better performance. This popularity has spurred rapid development of many new merging methods, which are typically validated in disparate experimental settings and frequently differ in the assumptions made about model architecture, data availability, and computational budget. In this work, we characterize the relative merits of different merging methods by evaluating them in a shared experimental setting and precisely identifying the practical requirements of each method. Specifically, our setting focuses on using merging for compositional generalization of capabilities in image classification, image generation, and natural language processing. Additionally, we measure the computational costs of different merging methods as well as how they perform when scaling the number of models being merged. Taken together, our results clarify the state of the field of model merging and provide a comprehensive and rigorous experimental setup to test new methods.
Stability in recurrent neural models poses a significant challenge, particularly in developing biologically plausible neurodynamical models that can be seamlessly trained. Traditional cortical circuit models are notoriously difficult to train due to expansive nonlinearities in the dynamical system, leading to an optimization problem with nonlinear stability constraints that are difficult to impose. Conversely, recurrent neural networks (RNNs) excel in tasks involving sequential data but lack biological plausibility and interpretability. In this work, we address these challenges by linking dynamic divisive normalization (DN) to the stability of ORGaNICs, a biologically plausible recurrent cortical circuit model that dynamically achieves DN and that has been shown to simulate a wide range of neurophysiological phenomena. By using the indirect method of Lyapunov, we prove the remarkable property of unconditional local stability for an arbitrary-dimensional ORGaNICs circuit when the recurrent weight matrix is the identity. We thus connect ORGaNICs to a system of coupled damped harmonic oscillators, which enables us to derive the circuit's energy function, providing a normative principle of what the circuit, and individual neurons, aim to accomplish. Further, for a generic recurrent weight matrix, we prove the stability of the 2D model and demonstrate empirically that stability holds in higher dimensions. Finally, we show that ORGaNICs can be trained by backpropagation through time without gradient clipping/scaling, thanks to its intrinsic stability property and adaptive time constants, which address the problems of exploding, vanishing, and oscillating gradients. By evaluating the model's performance on RNN benchmarks, we find that ORGaNICs outperform alternative neurodynamical models on static image classification tasks and perform comparably to LSTMs on sequential tasks.
Prompt learning has surfaced as an effective approach to enhance the performance of Vision-Language Models (VLMs) like CLIP when applied to downstream tasks. However, current learnable prompt tokens are primarily used for the single phase of adapting to tasks (i.e., adapting prompt), easily leading to overfitting risks. In this work, we propose a novel Cascade Prompt Learning CasPL framework to enable prompt learning to serve both generic and specific expertise (i.e., boosting and adapting prompt) simultaneously. Specifically, CasPL is a new learning paradigm comprising two distinct phases of learnable prompts: the first boosting prompt is crafted to extract domain-general knowledge from a senior larger CLIP teacher model by aligning their predicted logits using extensive unlabeled domain images. The second adapting prompt is then cascaded with the frozen first set to fine-tune the downstream tasks, following the approaches employed in prior research. In this manner, CasPL can effectively capture both domain-general and task-specific representations into explicitly different gradual groups of prompts, thus potentially alleviating overfitting issues in the target domain. It's worth noting that CasPL serves as a plug-and-play module that can seamlessly integrate into any existing prompt learning approach. CasPL achieves a significantly better balance between performance and inference speed, which is especially beneficial for deploying smaller VLM models in resource-constrained environments. Compared to the previous state-of-the-art method PromptSRC, CasPL shows an average improvement of 1.85% for base classes, 3.44% for novel classes, and 2.72% for the harmonic mean over 11 image classification datasets. Code is publicly available at: https://github.com/megvii-research/CasPL.
Artificial Intelligence (AI), with its multiplier effect and wide applications in multiple areas, could potentially be an important application of quantum computing. Since modern AI systems are often built on neural networks, the design of quantum neural networks becomes a key challenge in integrating quantum computing into AI. To provide a more fine-grained characterisation of the impact of quantum components on the performance of neural networks, we propose a framework where classical neural network layers are gradually replaced by quantum layers that have the same type of input and output while keeping the flow of information between layers unchanged, different from most current research in quantum neural network, which favours an end-to-end quantum model. We start with a simple three-layer classical neural network without any normalisation layers or activation functions, and gradually change the classical layers to the corresponding quantum versions. We conduct numerical experiments on image classification datasets such as the MNIST, FashionMNIST and CIFAR-10 datasets to demonstrate the change of performance brought by the systematic introduction of quantum components. Through this framework, our research sheds new light on the design of future quantum neural network models where it could be more favourable to search for methods and frameworks that harness the advantages from both the classical and quantum worlds.
Multi-modal large language models (MLLMs) have shown impressive capabilities as a general-purpose interface for various visual and linguistic tasks. However, building a unified MLLM for multi-task learning in the medical field remains a thorny challenge. To mitigate the tug-of-war problem of multi-modal multi-task optimization in MLLMs, recent advances primarily focus on improving the LLM components, while neglecting the connector that bridges the gap between modalities. In this paper, we introduce Uni-Med, a novel medical generalist foundation model which consists of a universal visual feature extraction module, a connector mixture-of-experts (CMoE) module, and an LLM. Benefiting from the proposed CMoE that leverages a well-designed router with a mixture of projection experts at the connector, Uni-Med achieves efficient solution to the tug-of-war problem and can perform six different medical tasks including question answering, visual question answering, report generation, referring expression comprehension, referring expression generation and image classification. To the best of our knowledge, Uni-Med is the first effort to tackle multi-task interference at the connector in MLLMs. Extensive ablation experiments validate the effectiveness of introducing CMoE under any configuration, with up to an average 8% performance gains. We further provide interpretation analysis of the tug-of-war problem from the perspective of gradient optimization and parameter statistics. Compared to previous state-of-the-art medical MLLMs, Uni-Med achieves competitive or superior evaluation metrics on diverse tasks. Code and resources are available at https://github.com/tsinghua-msiip/Uni-Med.
Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by eliminating the central server, thereby enhancing scalability and robustness through the avoidance of a single point of failure. However, DFL faces significant challenges in optimizing security, as most Byzantine-robust algorithms proposed in the literature are designed for centralized scenarios. In this paper, we present a novel Byzantine-robust aggregation algorithm to enhance the security of Decentralized Federated Learning environments, coined WFAgg. This proposal handles the adverse conditions and strength robustness of dynamic decentralized topologies at the same time by employing multiple filters to identify and mitigate Byzantine attacks. Experimental results demonstrate the effectiveness of the proposed algorithm in maintaining model accuracy and convergence in the presence of various Byzantine attack scenarios, outperforming state-of-the-art centralized Byzantine-robust aggregation schemes (such as Multi-Krum or Clustering). These algorithms are evaluated on an IID image classification problem in both centralized and decentralized scenarios.
Deep neural networks (DNNs) are powerful for cognitive tasks such as image classification, object detection, and scene segmentation. One drawback however is the significant high computational complexity and memory consumption, which makes them unfeasible to run real-time on embedded platforms because of the limited hardware resources. Block floating point (BFP) quantization is one of the representative compression approaches for reducing the memory and computational burden owing to their capability to effectively capture the broad data distribution of DNN models. Unfortunately, prior works on BFP-based quantization empirically choose the block size and the precision that preserve accuracy. In this paper, we develop a BFP-based bitwidth-aware analytical modeling framework (called ``BitQ'') for the best BFP implementation of DNN inference on embedded platforms. We formulate and resolve an optimization problem to identify the optimal BFP block size and bitwidth distribution by the trade-off of both accuracy and performance loss. Experimental results show that compared with an equal bitwidth setting, the BFP DNNs with optimized bitwidth allocation provide efficient computation, preserving accuracy on famous benchmarks. The source code and data are available at https://github.com/Cheliosoops/BitQ.
Data representation in non-Euclidean spaces has proven effective for capturing hierarchical and complex relationships in real-world datasets. Hyperbolic spaces, in particular, provide efficient embeddings for hierarchical structures. This paper introduces the Hyperbolic Vision Transformer (HVT), a novel extension of the Vision Transformer (ViT) that integrates hyperbolic geometry. While traditional ViTs operate in Euclidean space, our method enhances the self-attention mechanism by leveraging hyperbolic distance and M\"obius transformations. This enables more effective modeling of hierarchical and relational dependencies in image data. We present rigorous mathematical formulations, showing how hyperbolic geometry can be incorporated into attention layers, feed-forward networks, and optimization. We offer improved performance for image classification using the ImageNet dataset.
While convolutional neural networks (CNNs) excel at clean image classification, they struggle to classify images corrupted with different common corruptions, limiting their real-world applicability. Recent work has shown that incorporating a CNN front-end block that simulates some features of the primate primary visual cortex (V1) can improve overall model robustness. Here, we expand on this approach by introducing two novel biologically-inspired CNN model families that incorporate a new front-end block designed to simulate pre-cortical visual processing. RetinaNet, a hybrid architecture containing the novel front-end followed by a standard CNN back-end, shows a relative robustness improvement of 12.3% when compared to the standard model; and EVNet, which further adds a V1 block after the pre-cortical front-end, shows a relative gain of 18.5%. The improvement in robustness was observed for all the different corruption categories, though accompanied by a small decrease in clean image accuracy, and generalized to a different back-end architecture. These findings show that simulating multiple stages of early visual processing in CNN early layers provides cumulative benefits for model robustness.
Histopathology image classification is crucial for the accurate identification and diagnosis of various diseases but requires large and diverse datasets. Obtaining such datasets, however, is often costly and time-consuming due to the need for expert annotations and ethical constraints. To address this, we examine the suitability of different generative models and image selection approaches to create realistic synthetic histopathology image patches conditioned on class labels. Our findings highlight the importance of selecting an appropriate generative model type and architecture to enhance performance. Our experiments over the PCam dataset show that diffusion models are effective for transfer learning, while GAN-generated samples are better suited for augmentation. Additionally, transformer-based generative models do not require image filtering, in contrast to those derived from Convolutional Neural Networks (CNNs), which benefit from realism score-based selection. Therefore, we show that synthetic images can effectively augment existing datasets, ultimately improving the performance of the downstream histopathology image classification task.
The loss landscape of neural networks is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we investigate how the loss surface changes when the sample size increases, a previously unexplored issue. We theoretically analyze the convergence of the loss landscape in a fully connected neural network and derive upper bounds for the difference in loss function values when adding a new object to the sample. Our empirical study confirms these results on various datasets, demonstrating the convergence of the loss function surface for image classification tasks. Our findings provide insights into the local geometry of neural loss landscapes and have implications for the development of sample size determination techniques.
Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model. Integrating KANs into transformers, however, is no easy feat, especially when scaled up. Specifically, we identify three key challenges: (C1) Base function. The standard B-spline function used in KANs is not optimized for parallel computing on modern hardware, resulting in slower inference speeds. (C2) Parameter and Computation Inefficiency. KAN requires a unique function for each input-output pair, making the computation extremely large. (C3) Weight initialization. The initialization of weights in KANs is particularly challenging due to their learnable activation functions, which are critical for achieving convergence in deep neural networks. To overcome the aforementioned challenges, we propose three key solutions: (S1) Rational basis. We replace B-spline functions with rational functions to improve compatibility with modern GPUs. By implementing this in CUDA, we achieve faster computations. (S2) Group KAN. We share the activation weights through a group of neurons, to reduce the computational load without sacrificing performance. (S3) Variance-preserving initialization. We carefully initialize the activation weights to make sure that the activation variance is maintained across layers. With these designs, KAT scales effectively and readily outperforms traditional MLP-based transformers.
Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering, and grounding, often in zero-shot settings. Comics Understanding, a complex and multifaceted field, stands to greatly benefit from these advances. Comics, as a medium, combine rich visual and textual narratives, challenging AI models with tasks that span image classification, object detection, instance segmentation, and deeper narrative comprehension through sequential panels. However, the unique structure of comics -- characterized by creative variations in style, reading order, and non-linear storytelling -- presents a set of challenges distinct from those in other visual-language domains. In this survey, we present a comprehensive review of Comics Understanding from both dataset and task perspectives. Our contributions are fivefold: (1) We analyze the structure of the comics medium, detailing its distinctive compositional elements; (2) We survey the widely used datasets and tasks in comics research, emphasizing their role in advancing the field; (3) We introduce the Layer of Comics Understanding (LoCU) framework, a novel taxonomy that redefines vision-language tasks within comics and lays the foundation for future work; (4) We provide a detailed review and categorization of existing methods following the LoCU framework; (5) Finally, we highlight current research challenges and propose directions for future exploration, particularly in the context of vision-language models applied to comics. This survey is the first to propose a task-oriented framework for comics intelligence and aims to guide future research by addressing critical gaps in data availability and task definition. A project associated with this survey is available at https://github.com/emanuelevivoli/awesome-comics-understanding.
We present a novel frequency-based Self-Supervised Learning (SSL) approach that significantly enhances its efficacy for pre-training. Prior work in this direction masks out pre-defined frequencies in the input image and employs a reconstruction loss to pre-train the model. While achieving promising results, such an implementation has two fundamental limitations as identified in our paper. First, using pre-defined frequencies overlooks the variability of image frequency responses. Second, pre-trained with frequency-filtered images, the resulting model needs relatively more data to adapt to naturally looking images during fine-tuning. To address these drawbacks, we propose FOurier transform compression with seLf-Knowledge distillation (FOLK), integrating two dedicated ideas. First, inspired by image compression, we adaptively select the masked-out frequencies based on image frequency responses, creating more suitable SSL tasks for pre-training. Second, we employ a two-branch framework empowered by knowledge distillation, enabling the model to take both the filtered and original images as input, largely reducing the burden of downstream tasks. Our experimental results demonstrate the effectiveness of FOLK in achieving competitive performance to many state-of-the-art SSL methods across various downstream tasks, including image classification, few-shot learning, and semantic segmentation.
Vision-language models (VLMs) such as CLIP are trained via contrastive learning between text and image pairs, resulting in aligned image and text embeddings that are useful for many downstream tasks. A notable drawback of CLIP, however, is that the resulting embedding space seems to lack some of the structure of their purely text-based alternatives. For instance, while text embeddings have been long noted to satisfy \emph{analogies} in embedding space using vector arithmetic, CLIP has no such property. In this paper, we propose an approach to natively train CLIP in a contrastive manner to reason about differences in embedding space. We finetune CLIP so that the differences in image embedding space correspond to \emph{text descriptions of the image differences}, which we synthetically generate with large language models on image-caption paired datasets. We first demonstrate that our approach yields significantly improved capabilities in ranking images by a certain attribute (e.g., elephants are larger than cats), which is useful in retrieval or constructing attribute-based classifiers, and improved zeroshot classification performance on many downstream image classification tasks. In addition, our approach enables a new mechanism for inference that we refer to as comparative prompting, where we leverage prior knowledge of text descriptions of differences between classes of interest, achieving even larger performance gains in classification. Finally, we illustrate that the resulting embeddings obey a larger degree of geometric properties in embedding space, such as in text-to-image generation.
Due to the capability of dynamic state space models (SSMs) in capturing long-range dependencies with linear-time computational complexity, Mamba has shown notable performance in NLP tasks. This has inspired the rapid development of Mamba-based vision models, resulting in promising results in visual recognition tasks. However, such models are not capable of distilling features across layers through feature aggregation, interaction, and selection. Moreover, existing cross-layer feature aggregation methods designed for CNNs or ViTs are not practical in Mamba-based models due to high computational costs. Therefore, this paper aims to introduce an efficient cross-layer feature aggregation mechanism for vision backbone networks. Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX to effectively improve cross-layer feature interaction and reuse. Specifically, we build two different types of network layers: ganglion layers and normal layers. The former has higher connectivity and complexity, enabling multi-layer feature aggregation and interaction in an input-dependent manner. In contrast, the latter has lower connectivity and complexity. By interleaving these two types of layers, we design a new family of vision backbone networks with sparsely cross-connected layers, achieving an excellent trade-off among model size, computational cost, memory cost, and accuracy in comparison to its counterparts. For instance, with fewer parameters, SparX-Mamba-T improves the top-1 accuracy of VMamba-T from 82.5\% to 83.5\%, while SparX-Swin-T achieves a 1.3\% increase in top-1 accuracy compared to Swin-T. Extensive experimental results demonstrate that our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based DeFender framework that leverages the power of a text-guided diffusion model to counter adversarial patch attacks. At the core of our approach is the discovery of the Adversarial Anomaly Perception (AAP) phenomenon, which enables the diffusion model to accurately detect and locate adversarial patches by analyzing distributional anomalies. DIFFender seamlessly integrates the tasks of patch localization and restoration within a unified diffusion model framework, enhancing defense efficacy through their close interaction. Additionally, DIFFender employs an efficient few-shot prompt-tuning algorithm, facilitating the adaptation of the pre-trained diffusion model to defense tasks without the need for extensive retraining. Our comprehensive evaluation, covering image classification and face recognition tasks, as well as real-world scenarios, demonstrates DIFFender's robust performance against adversarial attacks. The framework's versatility and generalizability across various settings, classifiers, and attack methodologies mark a significant advancement in adversarial patch defense strategies. Except for the popular visible domain, we have identified another advantage of DIFFender: its capability to easily expand into the infrared domain. Consequently, we demonstrate the good flexibility of DIFFender, which can defend against both infrared and visible adversarial patch attacks alternatively using a universal defense framework.
We propose an approach for anytime continual learning (AnytimeCL) for open vocabulary image classification. The AnytimeCL problem aims to break away from batch training and rigid models by requiring that a system can predict any set of labels at any time and efficiently update and improve when receiving one or more training samples at any time. Despite the challenging goal, we achieve substantial improvements over recent methods. We propose a dynamic weighting between predictions of a partially fine-tuned model and a fixed open vocabulary model that enables continual improvement when training samples are available for a subset of a task's labels. We also propose an attention-weighted PCA compression of training features that reduces storage and computation with little impact to model accuracy. Our methods are validated with experiments that test flexibility of learning and inference. Code is available at https://github.com/jessemelpolio/AnytimeCL.
Earth observation (EO) plays a crucial role in creating and sustaining a resilient and prosperous society that has far reaching consequences for all life and the planet itself. Remote sensing platforms like satellites, airborne platforms, and more recently dones and UAVs are used for EO. They collect large amounts of data and this needs to be downlinked to Earth for further processing and analysis. Bottleneck for such high throughput acquisition is the downlink bandwidth. Data-centric solutions to image compression is required to address this deluge. In this work, semantic compression is studied through a compressed learning framework that utilizes only fast and sparse matrix-vector multiplication to encode the data. Camera noise and a communication channel are the considered sources of distortion. The complete semantic communication pipeline then consists of a learned low-complexity compression matrix that acts on the noisy camera output to generate onboard a vector of observations that is downlinked through a communication channel, processed through an unrolled network and then fed to a deep learning model performing the necessary downstream tasks; image classification is studied. Distortions are compensated by unrolling layers of NA-ALISTA with a wavelet sparsity prior. Decoding is thus a plug-n-play approach designed according to the camera/environment information and downstream task. The deep learning model for the downstream task is jointly fine-tuned with the compression matrix and the unrolled network through the loss function in an end-to-end fashion. It is shown that addition of a recovery loss along with the task dependent losses improves the downstream performance in noisy settings at low compression ratios.