Developing artificial intelligence (AI) and machine learning (ML) models for medical imaging typically involves extensive training and testing on large datasets, consuming significant computational time, energy, and resources. There is a need for more efficient methods that can achieve comparable or superior diagnostic performance without the associated resource burden. We investigated the feasibility of replacing conventional training procedures with an embedding-based approach that leverages concise and semantically meaningful representations of medical images. Using pre-trained foundational models-specifically, convolutional neural networks (CNN) like ResNet and multimodal models like Contrastive Language-Image Pre-training (CLIP)-we generated image embeddings for multi-class classification tasks. Simple linear classifiers were then applied to these embeddings. The approach was evaluated across diverse medical imaging modalities, including retinal images, mammography, dermatoscopic images, and chest radiographs. Performance was compared to benchmark models trained and tested using traditional methods. The embedding-based models surpassed the benchmark area under the receiver operating characteristic curve (AUC-ROC) scores by up to 87 percentage in multi-class classification tasks across the various medical imaging modalities. Notably, CLIP embedding models achieved the highest AUC-ROC scores, demonstrating superior classification performance while significantly reducing computational demands. Our study indicates that leveraging embeddings from pre-trained foundational models can effectively replace conventional, resource-intensive training and testing procedures in medical image analysis. This embedding-based approach offers a more efficient alternative for image segmentation, classification, and prediction, potentially accelerating AI technology integration into clinical practice.
Modern sensors produce increasingly rich streams of high-resolution data. Due to resource constraints, machine learning systems discard the vast majority of this information via resolution reduction. Compressed-domain learning allows models to operate on compact latent representations, allowing higher effective resolution for the same budget. However, existing compression systems are not ideal for compressed learning. Linear transform coding and end-to-end learned compression systems reduce bitrate, but do not uniformly reduce dimensionality; thus, they do not meaningfully increase efficiency. Generative autoencoders reduce dimensionality, but their adversarial or perceptual objectives lead to significant information loss. To address these limitations, we introduce WaLLoC (Wavelet Learned Lossy Compression), a neural codec architecture that combines linear transform coding with nonlinear dimensionality-reducing autoencoders. WaLLoC sandwiches a shallow, asymmetric autoencoder and entropy bottleneck between an invertible wavelet packet transform. Across several key metrics, WaLLoC outperforms the autoencoders used in state-of-the-art latent diffusion models. WaLLoC does not require perceptual or adversarial losses to represent high-frequency detail, providing compatibility with modalities beyond RGB images and stereo audio. WaLLoC's encoder consists almost entirely of linear operations, making it exceptionally efficient and suitable for mobile computing, remote sensing, and learning directly from compressed data. We demonstrate WaLLoC's capability for compressed-domain learning across several tasks, including image classification, colorization, document understanding, and music source separation. Our code, experiments, and pre-trained audio and image codecs are available at https://ut-sysml.org/walloc
Recent advancement in deep-neural network performance led to the development of new state-of-the-art approaches in numerous areas. However, the black-box nature of neural networks often prohibits their use in areas where model explainability and model transparency are crucial. Over the years, researchers proposed many algorithms to aid neural network understanding and provide additional information to the human expert. One of the most popular methods being Layer-Wise Relevance Propagation (LRP). This method assigns local relevance based on the pixel-wise decomposition of nonlinear classifiers. With the rise of attribution method research, there has emerged a pressing need to assess and evaluate their performance. Numerous metrics have been proposed, each assessing an individual property of attribution methods such as faithfulness, robustness or localization. Unfortunately, no single metric is deemed optimal for every case, and researchers often use several metrics to test the quality of the attribution maps. In this work, we address the shortcomings of the current LRP formulations and introduce a novel method for determining the relevance of input neurons through layer-wise relevance propagation. Furthermore, we apply this approach to the recently developed Vision Transformer architecture and evaluate its performance against existing methods on two image classification datasets, namely ImageNet and PascalVOC. Our results clearly demonstrate the advantage of our proposed method. Furthermore, we discuss the insufficiencies of current evaluation metrics for attribution-based explainability and propose a new evaluation metric that combines the notions of faithfulness, robustness and contrastiveness. We utilize this new metric to evaluate the performance of various attribution-based methods. Our code is available at: https://github.com/davor10105/relative-absolute-magnitude-propagation
Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition, learning task-specific weights while compressing parameter size. However, such approaches predominantly manipulate within the original feature space utilizing a single-branch structure, which might be suboptimal for decoupling the learned representations and patterns. In this paper, we propose ALoRE, a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts using a multi-branch paradigm, disentangling the learned cognitive patterns during training. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone via re-parameterization in a sequential manner, avoiding additional inference latency. We conduct extensive experiments on 24 image classification tasks using various backbone variants. Experimental results demonstrate that ALoRE outperforms the full fine-tuning strategy and other state-of-the-art PETL methods in terms of performance and parameter efficiency. For instance, ALoRE obtains 3.06% and 9.97% Top-1 accuracy improvement on average compared to full fine-tuning on the FGVC datasets and VTAB-1k benchmark by only updating 0.15M parameters.
Internet of Things (IoT) based healthcare systems offer significant potential for improving the delivery of healthcare services in humanitarian engineering, providing essential healthcare services to millions of underserved people in remote areas worldwide. However, these areas have poor network infrastructure, making communications difficult for traditional IoT. This paper presents a real-time chest X-ray classification system for hospitals in remote areas using FastDDS real-time middleware, offering reliable real-time communication. We fine-tuned a ResNet50 neural network to an accuracy of 88.61%, a precision of 88.76%, and a recall of 88.49\%. Our system results mark an average throughput of 3.2 KB/s and an average latency of 65 ms. The proposed system demonstrates how middleware-based systems can assist doctors in remote locations.
Since pioneering work of Hinton et al., knowledge distillation based on Kullback-Leibler Divergence (KL-Div) has been predominant, and recently its variants have achieved compelling performance. However, KL-Div only compares probabilities of the corresponding category between the teacher and student while lacking a mechanism for cross-category comparison. Besides, KL-Div is problematic when applied to intermediate layers, as it cannot handle non-overlapping distributions and is unaware of geometry of the underlying manifold. To address these downsides, we propose a methodology of Wasserstein Distance (WD) based knowledge distillation. Specifically, we propose a logit distillation method called WKD-L based on discrete WD, which performs cross-category comparison of probabilities and thus can explicitly leverage rich interrelations among categories. Moreover, we introduce a feature distillation method called WKD-F, which uses a parametric method for modeling feature distributions and adopts continuous WD for transferring knowledge from intermediate layers. Comprehensive evaluations on image classification and object detection have shown (1) for logit distillation WKD-L outperforms very strong KL-Div variants; (2) for feature distillation WKD-F is superior to the KL-Div counterparts and state-of-the-art competitors. The source code is available at https://peihuali.org/WKD
The application of TensorFlow pre-trained models in deep learning is explored, with an emphasis on practical guidance for tasks such as image classification and object detection. The study covers modern architectures, including ResNet, MobileNet, and EfficientNet, and demonstrates the effectiveness of transfer learning through real-world examples and experiments. A comparison of linear probing and model fine-tuning is presented, supplemented by visualizations using techniques like PCA, t-SNE, and UMAP, allowing for an intuitive understanding of the impact of these approaches. The work provides complete example code and step-by-step instructions, offering valuable insights for both beginners and advanced users. By integrating theoretical concepts with hands-on practice, the paper equips readers with the tools necessary to address deep learning challenges efficiently.
This study investigates the applicability of Singular Value Decomposition for the image classification of specific breeds of cats and dogs using fur color as the primary identifying feature. Sequential Quadratic Programming (SQP) is employed to construct optimally weighted templates. The proposed method achieves 69% accuracy using the Frobenius norm at rank 10. The results partially validate the assumption that dominant features, such as fur color, can be effectively captured through low-rank approximations. However, the accuracy suggests that additional features or methods may be required for more robust classification, highlighting the trade-off between simplicity and performance in resource-constrained environments.
Low-light conditions have an adverse impact on machine cognition, limiting the performance of computer vision systems in real life. Since low-light data is limited and difficult to annotate, we focus on image processing to enhance low-light images and improve the performance of any downstream task model, instead of fine-tuning each of the models which can be prohibitively expensive. We propose to improve the existing zero-reference low-light enhancement by leveraging the CLIP model to capture image prior and for semantic guidance. Specifically, we propose a data augmentation strategy to learn an image prior via prompt learning, based on image sampling, to learn the image prior without any need for paired or unpaired normal-light data. Next, we propose a semantic guidance strategy that maximally takes advantage of existing low-light annotation by introducing both content and context cues about the image training patches. We experimentally show, in a qualitative study, that the proposed prior and semantic guidance help to improve the overall image contrast and hue, as well as improve background-foreground discrimination, resulting in reduced over-saturation and noise over-amplification, common in related zero-reference methods. As we target machine cognition, rather than rely on assuming the correlation between human perception and downstream task performance, we conduct and present an ablation study and comparison with related zero-reference methods in terms of task-based performance across many low-light datasets, including image classification, object and face detection, showing the effectiveness of our proposed method.
Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource constrained devices. Quantization is one technique that aims to alleviate these large storage requirements and speed up the inference process by reducing the precision of model parameters to lower-bit representations. In this paper, we introduce a novel post-training quantization method for model weights. Our method finds optimal clipping thresholds and scaling factors along with mathematical guarantees that our method minimizes quantization noise. Empirical results on Real World Datasets demonstrate that our quantization scheme significantly reduces model size and computational requirements while preserving model accuracy.
This study focuses on enhancing rice leaf disease image classification algorithms, which have traditionally relied on Convolutional Neural Network (CNN) models. We employed transfer learning with MobileViTV2_050 using ImageNet-1k weights, a lightweight model that integrates CNN's local feature extraction with Vision Transformers' global context learning through a separable self-attention mechanism. Our approach resulted in a significant 15.66% improvement in classification accuracy for MobileViTV2_050-A, our first enhanced model trained on the baseline dataset, achieving 93.14%. Furthermore, MobileViTV2_050-B, our second enhanced model trained on a broader rice leaf dataset, demonstrated a 22.12% improvement, reaching 99.6% test accuracy. Additionally, MobileViTV2-A attained an F1-score of 93% across four rice labels and a Receiver Operating Characteristic (ROC) curve ranging from 87% to 97%. In terms of resource consumption, our enhanced models reduced the total parameters of the baseline CNN model by up to 92.50%, from 14 million to 1.1 million. These results indicate that MobileViTV2_050 not only improves computational efficiency through its separable self-attention mechanism but also enhances global context learning. Consequently, it offers a lightweight and robust solution suitable for mobile deployment, advancing the interpretability and practicality of models in precision agriculture.
The project aims to develop differentially private deep learning models for image classification on CIFAR-10 datasets \cite{cifar10} and analyze the impact of various privacy parameters on model accuracy. We have implemented five different deep learning models, namely ConvNet, ResNet18, EfficientNet, ViT, and DenseNet121 and three supervised classifiers namely K-Nearest Neighbors, Naive Bayes Classifier and Support Vector Machine. We evaluated the performance of these models under varying settings. Our best performing model to date is EfficientNet with test accuracy of $59.63\%$ with the following parameters (Adam optimizer, batch size 256, epoch size 100, epsilon value 5.0, learning rate $1e-3$, clipping threshold 1.0, and noise multiplier 0.912).
This paper addresses the challenge of spectral-spatial feature extraction for hyperspectral image classification by introducing a novel tensor-based framework. The proposed approach incorporates circular convolution into a tensor structure to effectively capture and integrate both spectral and spatial information. Building upon this framework, the traditional Principal Component Analysis (PCA) technique is extended to its tensor-based counterpart, referred to as Tensor Principal Component Analysis (TPCA). The proposed TPCA method leverages the inherent multi-dimensional structure of hyperspectral data, thereby enabling more effective feature representation. Experimental results on benchmark hyperspectral datasets demonstrate that classification models using TPCA features consistently outperform those using traditional PCA and other state-of-the-art techniques. These findings highlight the potential of the tensor-based framework in advancing hyperspectral image analysis.
Semantic communications provide significant performance gains over traditional communications by transmitting task-relevant semantic features through wireless channels. However, most existing studies rely on end-to-end (E2E) training of neural-type encoders and decoders to ensure effective transmission of these semantic features. To enable semantic communications without relying on E2E training, this paper presents a vision transformer (ViT)-based semantic communication system with importance-aware quantization (IAQ) for wireless image transmission. The core idea of the presented system is to leverage the attention scores of a pretrained ViT model to quantify the importance levels of image patches. Based on this idea, our IAQ framework assigns different quantization bits to image patches based on their importance levels. This is achieved by formulating a weighted quantization error minimization problem, where the weight is set to be an increasing function of the attention score. Then, an optimal incremental allocation method and a low-complexity water-filling method are devised to solve the formulated problem. Our framework is further extended for realistic digital communication systems by modifying the bit allocation problem and the corresponding allocation methods based on an equivalent binary symmetric channel (BSC) model. Simulations on single-view and multi-view image classification tasks show that our IAQ framework outperforms conventional image compression methods in both error-free and realistic communication scenarios.
We propose a novel approach to image classification inspired by complex nonlinear biological visual processing, whereby classical convolutional neural networks (CNNs) are equipped with learnable higher-order convolutions. Our model incorporates a Volterra-like expansion of the convolution operator, capturing multiplicative interactions akin to those observed in early and advanced stages of biological visual processing. We evaluated this approach on synthetic datasets by measuring sensitivity to testing higher-order correlations and performance in standard benchmarks (MNIST, FashionMNIST, CIFAR10, CIFAR100 and Imagenette). Our architecture outperforms traditional CNN baselines, and achieves optimal performance with expansions up to 3rd/4th order, aligning remarkably well with the distribution of pixel intensities in natural images. Through systematic perturbation analysis, we validate this alignment by isolating the contributions of specific image statistics to model performance, demonstrating how different orders of convolution process distinct aspects of visual information. Furthermore, Representational Similarity Analysis reveals distinct geometries across network layers, indicating qualitatively different modes of visual information processing. Our work bridges neuroscience and deep learning, offering a path towards more effective, biologically inspired computer vision models. It provides insights into visual information processing and lays the groundwork for neural networks that better capture complex visual patterns, particularly in resource-constrained scenarios.
Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new Sparse Autoencoder (SAE) for the CLIP vision transformer, named PatchSAE, to extract interpretable concepts at granular levels (e.g. shape, color, or semantics of an object) and their patch-wise spatial attributions. We explore how these concepts influence the model output in downstream image classification tasks and investigate how recent state-of-the-art prompt-based adaptation techniques change the association of model inputs to these concepts. While activations of concepts slightly change between adapted and non-adapted models, we find that the majority of gains on common adaptation tasks can be explained with the existing concepts already present in the non-adapted foundation model. This work provides a concrete framework to train and use SAEs for Vision Transformers and provides insights into explaining adaptation mechanisms.
Vision-language models (VLMs) like CLIP have been cherished for their ability to perform zero-shot visual recognition on open-vocabulary concepts. This is achieved by selecting the object category whose textual representation bears the highest similarity with the query image. While successful in some domains, this method struggles with identifying fine-grained entities as well as generalizing to unseen concepts that are not captured by the training distribution. Recent works attempt to mitigate these challenges by integrating category descriptions at test time, albeit yielding modest improvements. We attribute these limited gains to a fundamental misalignment between image and description representations, which is rooted in the pretraining structure of CLIP. In this paper, we propose GRAIN, a new pretraining strategy aimed at aligning representations at both fine and coarse levels simultaneously. Our approach learns to jointly ground textual descriptions in image regions along with aligning overarching captions with global image representations. To drive this pre-training, we leverage frozen Multimodal Large Language Models (MLLMs) to derive large-scale synthetic annotations. We demonstrate the enhanced zero-shot performance of our model compared to current state-of-the art methods across 11 diverse image classification datasets. Additionally, we introduce Products-2023, a newly curated, manually labeled dataset featuring novel concepts, and showcase our model's ability to recognize these concepts by benchmarking on it. Significant improvements achieved by our model on other downstream tasks like retrieval further highlight the superior quality of representations learned by our approach. Code available at https://github.com/shaunak27/grain-clip .
Federated Learning (FL) marks a transformative approach to distributed model training by combining locally optimized models from various clients into a unified global model. While FL preserves data privacy by eliminating centralized storage, it encounters significant challenges such as performance degradation, slower convergence, and reduced robustness of the global model due to the heterogeneity in client data distributions. Among the various forms of data heterogeneity, label skew emerges as a particularly formidable and prevalent issue, especially in domains such as image classification. To address these challenges, we begin with comprehensive experiments to pinpoint the underlying issues in the FL training process. Based on our findings, we then introduce an innovative dual-strategy approach designed to effectively resolve these issues. First, we introduce an adaptive loss function for client-side training, meticulously crafted to preserve previously acquired knowledge while maintaining an optimal equilibrium between local optimization and global model coherence. Secondly, we develop a dynamic aggregation strategy for aggregating client models at the server. This approach adapts to each client's unique learning patterns, effectively addressing the challenges of diverse data across the network. Our comprehensive evaluation, conducted across three diverse real-world datasets, coupled with theoretical convergence guarantees, demonstrates the superior efficacy of our method compared to several established state-of-the-art approaches.
Domain shift in the field of histopathological imaging is a common phenomenon due to the intra- and inter-hospital variability of staining and digitization protocols. The implementation of robust models, capable of creating generalized domains, represents a need to be solved. In this work, a new domain adaptation method to deal with the variability between histopathological images from multiple centers is presented. In particular, our method adds a training constraint to the supervised contrastive learning approach to achieve domain adaptation and improve inter-class separability. Experiments performed on domain adaptation and classification of whole-slide images of six skin cancer subtypes from two centers demonstrate the method's usefulness. The results reflect superior performance compared to not using domain adaptation after feature extraction or staining normalization.
Deep learning techniques have proven highly effective in image classification, but their deployment in resourceconstrained environments remains challenging due to high computational demands. Furthermore, their interpretability is of high importance which demands even more available resources. In this work, we introduce an approach that combines saliency-guided training with quantization techniques to create an interpretable and resource-efficient model without compromising accuracy. We utilize Parameterized Clipping Activation (PACT) to perform quantization-aware training, specifically targeting activations and weights to optimize precision while minimizing resource usage. Concurrently, saliency-guided training is employed to enhance interpretability by iteratively masking features with low gradient values, leading to more focused and meaningful saliency maps. This training procedure helps in mitigating noisy gradients and yields models that provide clearer, more interpretable insights into their decision-making processes. To evaluate the impact of our approach, we conduct experiments using famous Convolutional Neural Networks (CNN) architecture on the MNIST and CIFAR-10 benchmark datasets as two popular datasets. We compare the saliency maps generated by standard and quantized models to assess the influence of quantization on both interpretability and classification accuracy. Our results demonstrate that the combined use of saliency-guided training and PACT-based quantization not only maintains classification performance but also produces models that are significantly more efficient and interpretable, making them suitable for deployment in resource-limited settings.