Convolutional Neural Networks (CNNs) are pivotal in image classification tasks due to their robust feature extraction capabilities. However, their high computational and memory requirements pose challenges for deployment in resource-constrained environments. This paper introduces a methodology to construct lightweight CNNs while maintaining competitive accuracy. The approach integrates two stages of training; dual-input-output model and transfer learning with progressive unfreezing. The dual-input-output model train on original and augmented datasets, enhancing robustness. Progressive unfreezing is applied to the unified model to optimize pre-learned features during fine-tuning, enabling faster convergence and improved model accuracy. The methodology was evaluated on three benchmark datasets; handwritten digit MNIST, fashion MNIST, and CIFAR-10. The proposed model achieved a state-of-the-art accuracy of 99% on the handwritten digit MNIST and 89% on fashion MNIST, with only 14,862 parameters and a model size of 0.17 MB. While performance on CIFAR-10 was comparatively lower (65% with less than 20,00 parameters), the results highlight the scalability of this method. The final model demonstrated fast inference times and low latency, making it suitable for real-time applications. Future directions include exploring advanced augmentation techniques, improving architectural scalability for complex datasets, and extending the methodology to tasks beyond classification. This research underscores the potential for creating efficient, scalable, and task-specific CNNs for diverse applications.
Vision Transformers (ViTs) have recently taken computer vision by storm. However, the softmax attention underlying ViTs comes with a quadratic complexity in time and memory, hindering the application of ViTs to high-resolution images. We revisit the attention design and propose a linear attention method to address the limitation, which doesn't sacrifice ViT's core advantage of capturing global representation like existing methods (e.g. local window attention of Swin). We further investigate the key difference between linear attention and softmax attention. Our empirical results suggest that linear attention lacks a fundamental property of concentrating the distribution of the attention matrix. Inspired by this observation, we introduce a local concentration module to enhance linear attention. By incorporating enhanced linear global attention and local window attention, we propose a new ViT architecture, dubbed L$^2$ViT. Notably, L$^2$ViT can effectively capture both global interactions and local representations while enjoying linear computational complexity. Extensive experiments demonstrate the strong performance of L$^2$ViT. On image classification, L$^2$ViT achieves 84.4% Top-1 accuracy on ImageNet-1K without any extra training data or label. By further pre-training on ImageNet-22k, it attains 87.0% when fine-tuned with resolution 384$^2$. For downstream tasks, L$^2$ViT delivers favorable performance as a backbone on object detection as well as semantic segmentation.
Visual reprogramming (VR) reuses pre-trained vision models for downstream image classification tasks by adding trainable noise patterns to inputs. When applied to vision-language models (e.g., CLIP), existing VR approaches follow the same pipeline used in vision models (e.g., ResNet, ViT), where ground-truth class labels are inserted into fixed text templates to guide the optimization of VR patterns. This label-based approach, however, overlooks the rich information and diverse attribute-guided textual representations that CLIP can exploit, which may lead to the misclassification of samples. In this paper, we propose Attribute-based Visual Reprogramming (AttrVR) for CLIP, utilizing descriptive attributes (DesAttrs) and distinctive attributes (DistAttrs), which respectively represent common and unique feature descriptions for different classes. Besides, as images of the same class may reflect different attributes after VR, AttrVR iteratively refines patterns using the $k$-nearest DesAttrs and DistAttrs for each image sample, enabling more dynamic and sample-specific optimization. Theoretically, AttrVR is shown to reduce intra-class variance and increase inter-class separation. Empirically, it achieves superior performance in 12 downstream tasks for both ViT-based and ResNet-based CLIP. The success of AttrVR facilitates more effective integration of VR from unimodal vision models into vision-language models. Our code is available at https://github.com/tmlr-group/AttrVR.
Spiking Neural Networks (SNNs) hold promise for energy-efficient, biologically inspired computing. We identify substantial informatio loss during spike transmission, linked to temporal dependencies in traditional Leaky Integrate-and-Fire (LIF) neuron-a key factor potentially limiting SNN performance. Existing SNN architectures also underutilize modern GPUs, constrained by single-bit spike storage and isolated weight-spike operations that restrict computational efficiency. We introduce ${SpikePack}$, a neuron model designed to reduce transmission loss while preserving essential features like membrane potential reset and leaky integration. ${SpikePack}$ achieves constant $\mathcal{O}(1)$ time and space complexity, enabling efficient parallel processing on GPUs and also supporting serial inference on existing SNN hardware accelerators. Compatible with standard Artificial Neural Network (ANN) architectures, ${SpikePack}$ facilitates near-lossless ANN-to-SNN conversion across various networks. Experimental results on tasks such as image classification, detection, and segmentation show ${SpikePack}$ achieves significant gains in accuracy and efficiency for both directly trained and converted SNNs over state-of-the-art models. Tests on FPGA-based platforms further confirm cross-platform flexibility, delivering high performance and enhanced sparsity. By enhancing information flow and rethinking SNN-ANN integration, ${SpikePack}$ advances efficient SNN deployment across diverse hardware platforms.
Batch normalization (BatchNorm) is a popular layer normalization technique used when training deep neural networks. It has been shown to enhance the training speed and accuracy of deep learning models. However, the mechanics by which BatchNorm achieves these benefits is an active area of research, and different perspectives have been proposed. In this paper, we investigate the effect of BatchNorm on the resulting hidden representations, that is, the vectors of activation values formed as samples are processed at each hidden layer. Specifically, we consider the sparsity of these representations, as well as their implicit clustering -- the creation of groups of representations that are similar to some extent. We contrast image classification models trained with and without batch normalization and highlight consistent differences observed. These findings highlight that BatchNorm's effect on representational sparsity is not a significant factor affecting generalization, while the representations of models trained with BatchNorm tend to show more advantageous clustering characteristics.
Machine learning methods are solving very successfully a plethora of tasks, but they have the disadvantage of not providing any information about their decision. Consequently, estimating the reasoning of the system provides additional information. For this, Layer-Wise Relevance Propagation (LRP) is one of the methods in eXplainable Machine Learning (XML). Its purpose is to provide contributions of any neural network output in the domain of its input. The main drawback of current methods is mainly due to division by small values. To overcome this problem, we provide a new definition called Relative LRP where the classical conservation law is satisfied up to a multiplicative factor but without divisions by small values except for Resnet skip connection. In this article, we will focus on image classification. This allows us to visualize the contributions of a pixel to the predictions of a multi-layer neural network. Pixel contributions provide a focus to further analysis on regions of potential interest. R-LRP can be applied for any dense, CNN or residual neural networks. Moreover, R-LRP doesn't need any hyperparameters to tune contrary to other LRP methods. We then compare the R-LRP method on different datasets with simple CNN, VGG16, VGG19 and Resnet50 networks.
The scheme of adaptation via meta-learning is seen as an ingredient for solving the problem of data shortage or distribution shift in real-world applications, but it also brings the new risk of inappropriate updates of the model in the user environment, which increases the demand for explainability. Among the various types of XAI methods, establishing a method of explanation based on past experience in meta-learning requires special consideration due to its bi-level structure of training, which has been left unexplored. In this work, we propose influence functions for explaining meta-learning that measure the sensitivities of training tasks to adaptation and inference. We also argue that the approximation of the Hessian using the Gauss-Newton matrix resolves computational barriers peculiar to meta-learning. We demonstrate the adequacy of the method through experiments on task distinction and task distribution distinction using image classification tasks with MAML and Prototypical Network.
Long-tailed classification is challenging due to its heavy imbalance in class probabilities. While existing methods often focus on overall accuracy or accuracy for tail classes, they overlook a critical aspect: certain types of errors can carry greater risks than others in real-world long-tailed problems. For example, misclassifying patients (a tail class) as healthy individuals (a head class) entails far more serious consequences than the reverse scenario. To address this critical issue, we introduce Making Reliable and Flexible Decisions in Long-tailed Classification (RF-DLC), a novel framework aimed at reliable predictions in long-tailed problems. Leveraging Bayesian Decision Theory, we introduce an integrated gain to seamlessly combine long-tailed data distributions and the decision-making procedure. We further propose an efficient variational optimization strategy for the decision risk objective. Our method adapts readily to diverse utility matrices, which can be designed for specific tasks, ensuring its flexibility for different problem settings. In empirical evaluation, we design a new metric, False Head Rate, to quantify tail-sensitivity risk, along with comprehensive experiments on multiple real-world tasks, including large-scale image classification and uncertainty quantification, to demonstrate the reliability and flexibility of our method.
Hyperspectral images offer extensive spectral information about ground objects across multiple spectral bands. However, the large volume of data can pose challenges during processing. Typically, adjacent bands in hyperspectral data are highly correlated, leading to the use of only a few selected bands for various applications. In this work, we present a correlation-based band selection approach for hyperspectral image classification. Our approach calculates the average correlation between bands using correlation coefficients to identify the relationships among different bands. Afterward, we select a subset of bands by analyzing the average correlation and applying a threshold-based method. This allows us to isolate and retain bands that exhibit lower inter-band dependencies, ensuring that the selected bands provide diverse and non-redundant information. We evaluate our proposed approach on two standard benchmark datasets: Pavia University (PA) and Salinas Valley (SA), focusing on image classification tasks. The experimental results demonstrate that our method performs competitively with other standard band selection approaches.
Foundation models are widely employed in medical image analysis, due to their high adaptability and generalizability for downstream tasks. With the increasing number of foundation models being released, model selection has become an important issue. In this work, we study the capabilities of foundation models in medical image classification tasks by conducting a benchmark study on the MedMNIST dataset. Specifically, we adopt various foundation models ranging from convolutional to Transformer-based models and implement both end-to-end training and linear probing for all classification tasks. The results demonstrate the significant potential of these pre-trained models when transferred for medical image classification. We further conduct experiments with different image sizes and various sizes of training data. By analyzing all the results, we provide preliminary, yet useful insights and conclusions on this topic.
Few-shot learning (FSL) is a challenging task in machine learning, demanding a model to render discriminative classification by using only a few labeled samples. In the literature of FSL, deep models are trained in a manner of metric learning to provide metric in a feature space which is well generalizable to classify samples of novel classes; in the space, even a few amount of labeled training examples can construct an effective classifier. In this paper, we propose a novel FSL loss based on \emph{geometric mean} to embed discriminative metric into deep features. In contrast to the other losses such as utilizing arithmetic mean in softmax-based formulation, the proposed method leverages geometric mean to aggregate pair-wise relationships among samples for enhancing discriminative metric across class categories. The proposed loss is not only formulated in a simple form but also is thoroughly analyzed in theoretical ways to reveal its favorable characteristics which are favorable for learning feature metric in FSL. In the experiments on few-shot image classification tasks, the method produces competitive performance in comparison to the other losses.
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Learning agent to add minimum distortion to input images while still causing misclassification by the target model. The agent uses a novel dual-action method to explore the input image at each step to identify sensitive regions for adding distortions while removing noises that have less impact on the target model. This dual action leads to faster and more efficient convergence of the attack. The platform can also be used to measure the robustness of image classification models against specific distortion types. Also, retraining the model with adversarial samples significantly improved robustness when evaluated on benchmark datasets. The proposed platform outperforms state-of-the-art methods in terms of the average number of queries required to cause misclassification. This advances trustworthiness with a positive social impact.
Modern neural networks (NNs) often do not generalize well in the presence of a "covariate shift"; that is, in situations where the training and test data distributions differ, but the conditional distribution of classification labels remains unchanged. In such cases, NN generalization can be reduced to a problem of learning more domain-invariant features. Domain adaptation (DA) methods include a range of techniques aimed at achieving this; however, these methods have struggled with the need for extensive hyperparameter tuning, which then incurs significant computational costs. In this work, we introduce SIDDA, an out-of-the-box DA training algorithm built upon the Sinkhorn divergence, that can achieve effective domain alignment with minimal hyperparameter tuning and computational overhead. We demonstrate the efficacy of our method on multiple simulated and real datasets of varying complexity, including simple shapes, handwritten digits, and real astronomical observations. SIDDA is compatible with a variety of NN architectures, and it works particularly well in improving classification accuracy and model calibration when paired with equivariant neural networks (ENNs). We find that SIDDA enhances the generalization capabilities of NNs, achieving up to a $\approx40\%$ improvement in classification accuracy on unlabeled target data. We also study the efficacy of DA on ENNs with respect to the varying group orders of the dihedral group $D_N$, and find that the model performance improves as the degree of equivariance increases. Finally, we find that SIDDA enhances model calibration on both source and target data--achieving over an order of magnitude improvement in the ECE and Brier score. SIDDA's versatility, combined with its automated approach to domain alignment, has the potential to advance multi-dataset studies by enabling the development of highly generalizable models.
I introduce two novel loss functions for classification in deep learning. The two loss functions extend standard cross entropy loss by regularizing it with minimum entropy and Kullback-Leibler (K-L) divergence terms. The first of the two novel loss functions is termed mixed entropy loss (MIX-ENT for short), while the second one is termed minimum entropy regularized cross-entropy loss (MIN-ENT for short). The MIX-ENT function introduces a regularizer that can be shown to be equivalent to the sum of a minimum entropy term and a K-L divergence term. However, it should be noted that the K-L divergence term here is different from that in the standard cross-entropy loss function, in the sense that it swaps the roles of the target probability and the hypothesis probability. The MIN-ENT function simply adds a minimum entropy regularizer to the standard cross entropy loss function. In both MIX-ENT and MIN-ENT, the minimum entropy regularizer minimizes the entropy of the hypothesis probability distribution which is output by the neural network. Experiments on the EMNIST-Letters dataset shows that my implementation of MIX-ENT and MIN-ENT lets the VGG model climb from its previous 3rd position on the paperswithcode leaderboard to reach the 2nd position on the leaderboard, outperforming the Spinal-VGG model in so doing. Specifically, using standard cross-entropy, VGG achieves 95.86% while Spinal-VGG achieves 95.88% classification accuracies, whereas using VGG (without Spinal-VGG) our MIN-ENT achieved 95.933%, while our MIX-ENT achieved 95.927% accuracies. The pre-trained models for both MIX-ENT and MIN-ENT are at https://github.com/rahmanoladi/minimum entropy project.
Parking space occupation detection using deep learning frameworks has seen significant advancements over the past few years. While these approaches effectively detect partial obstructions and adapt to varying lighting conditions, their performance significantly diminishes when haze is present. This paper proposes a novel hybrid model with a pre-trained feature extractor and a Pinball Generalized Twin Support Vector Machine (Pin-GTSVM) classifier, which removes the need for a dehazing system from the current State-of-The-Art hazy parking slot classification systems and is also insensitive to any atmospheric noise. The proposed system can seamlessly integrate with conventional smart parking infrastructures, leveraging a minimal number of cameras to monitor and manage hundreds of parking spaces efficiently. Its effectiveness has been evaluated against established parking space detection methods using the CNRPark Patches, PKLot, and a custom dataset specific to hazy parking scenarios. Furthermore, empirical results indicate a significant improvement in accuracy on a hazy parking system, thus emphasizing efficient atmospheric noise handling.
Robust training with noisy labels is a critical challenge in image classification, offering the potential to reduce reliance on costly clean-label datasets. Real-world datasets often contain a mix of in-distribution (ID) and out-of-distribution (OOD) instance-dependent label noise, a challenge that is rarely addressed simultaneously by existing methods and is further compounded by the lack of comprehensive benchmarking datasets. Furthermore, even though current noisy-label learning approaches attempt to find noisy-label samples during training, these methods do not aim to estimate ID and OOD noise rates to promote their effectiveness in the selection of such noisy-label samples, and they are often represented by inefficient multi-stage learning algorithms. We propose the Adaptive Estimation of Instance-Dependent In-Distribution and Out-of-Distribution Label Noise (AEON) approach to address these research gaps. AEON is an efficient one-stage noisy-label learning methodology that dynamically estimates instance-dependent ID and OOD label noise rates to enhance robustness to complex noise settings. Additionally, we introduce a new benchmark reflecting real-world ID and OOD noise scenarios. Experiments demonstrate that AEON achieves state-of-the-art performance on both synthetic and real-world datasets
Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy loss on class logits. Since they focus on classifying images with considering class labels, these methods may struggle to learn various \emph{aspects} of classes (e.g., natural positions and shape changes). Rethinking the previous approach from a novel view, we propose a multi-aspect knowledge distillation method using Multimodal Large Language Models (MLLMs). Our approach involves: 1) querying Large Language Model with multi-aspect questions relevant to the knowledge we want to transfer to the model, 2) extracting corresponding logits from MLLM, and 3) expanding the model's output dimensions to distill these multi-aspect logits. We then apply cross-entropy loss to class logits and binary cross-entropy loss to multi-aspect logits. Through our method, the model can learn not only the knowledge about visual aspects but also the abstract and complex aspects that require a deeper understanding. We primarily apply our method to image classification, and to explore the potential for extending our model, we expand it to other tasks, such as object detection. In all experimental results, our method improves the performance of the baselines. Additionally, we analyze the effect of multi-aspect knowledge distillation. These results demonstrate that our method can transfer knowledge about various aspects to the model and the aspect knowledge can enhance model performance in computer vision tasks. This paper demonstrates the great potential of multi-aspect knowledge distillation, and we believe it offers a promising direction for future research in computer vision and beyond.
Data augmentation is a widely used and effective technique to improve the generalization performance of deep neural networks. Yet, despite often facing limited data availability when working with medical images, it is frequently underutilized. This appears to come from a gap in our collective understanding of the efficacy of different augmentation techniques across different tasks and modalities. One modality where this is especially true is ultrasound imaging. This work addresses this gap by analyzing the effectiveness of different augmentation techniques at improving model performance across a wide range of ultrasound image analysis tasks. To achieve this, we introduce a new standardized benchmark of 14 ultrasound image classification and semantic segmentation tasks from 10 different sources and covering 11 body regions. Our results demonstrate that many of the augmentations commonly used for tasks on natural images are also effective on ultrasound images, even more so than augmentations developed specifically for ultrasound images in some cases. We also show that diverse augmentation using TrivialAugment, which is widely used for natural images, is also effective for ultrasound images. Moreover, our proposed methodology represents a structured approach for assessing various data augmentations that can be applied to other contexts and modalities.
This expository paper introduces a simplified approach to image-based quality inspection in manufacturing using OpenAI's CLIP (Contrastive Language-Image Pretraining) model adapted for few-shot learning. While CLIP has demonstrated impressive capabilities in general computer vision tasks, its direct application to manufacturing inspection presents challenges due to the domain gap between its training data and industrial applications. We evaluate CLIP's effectiveness through five case studies: metallic pan surface inspection, 3D printing extrusion profile analysis, stochastic textured surface evaluation, automotive assembly inspection, and microstructure image classification. Our results show that CLIP can achieve high classification accuracy with relatively small learning sets (50-100 examples per class) for single-component and texture-based applications. However, the performance degrades with complex multi-component scenes. We provide a practical implementation framework that enables quality engineers to quickly assess CLIP's suitability for their specific applications before pursuing more complex solutions. This work establishes CLIP-based few-shot learning as an effective baseline approach that balances implementation simplicity with robust performance, demonstrated in several manufacturing quality control applications.
Conformal Prediction (CP) is a method to control prediction uncertainty by producing a small prediction set, ensuring a predetermined probability that the true class lies within this set. This is commonly done by defining a score, based on the model predictions, and setting a threshold on this score using a validation set. In this study, we address the problem of CP calibration when we only have access to a validation set with noisy labels. We show how we can estimate the noise-free conformal threshold based on the noisy labeled data. Our solution is flexible and can accommodate various modeling assumptions regarding the label contamination process, without needing any information about the underlying data distribution or the internal mechanisms of the machine learning classifier. We develop a coverage guarantee for uniform noise that is effective even in tasks with a large number of classes. We dub our approach Noise-Aware Conformal Prediction (NACP) and show on several natural and medical image classification datasets, including ImageNet, that it significantly outperforms current noisy label methods and achieves results comparable to those obtained with a clean validation set.