The visual examination of tissue biopsy sections is fundamental for cancer diagnosis, with pathologists analyzing sections at multiple magnifications to discern tumor cells and their subtypes. However, existing attention-based multiple instance learning (MIL) models used for analyzing Whole Slide Images (WSIs) in cancer diagnostics often overlook the contextual information of tumor and neighboring tiles, leading to misclassifications. To address this, we propose the Context-Aware Multiple Instance Learning (CAMIL) architecture. CAMIL incorporates neighbor-constrained attention to consider dependencies among tiles within a WSI and integrates contextual constraints as prior knowledge into the MIL model. We evaluated CAMIL on subtyping non-small cell lung cancer (TCGA-NSCLC) and detecting lymph node (CAMELYON16 and CAMELYON17) metastasis, achieving test AUCs of 97.5\%, 95.9\%, and 88.1\%, respectively, outperforming other state-of-the-art methods. Additionally, CAMIL enhances model interpretability by identifying regions of high diagnostic value.
Quantum processing units (QPUs) are currently exclusively available from cloud vendors. However, with recent advancements, hosting QPUs is soon possible everywhere. Existing work has yet to draw from research in edge computing to explore systems exploiting mobile QPUs, or how hybrid applications can benefit from distributed heterogeneous resources. Hence, this work presents an architecture for Quantum Computing in the edge-cloud continuum. We discuss the necessity, challenges, and solution approaches for extending existing work on classical edge computing to integrate QPUs. We describe how warm-starting allows defining workflows that exploit the hierarchical resources spread across the continuum. Then, we introduce a distributed inference engine with hybrid classical-quantum neural networks (QNNs) to aid system designers in accommodating applications with complex requirements that incur the highest degree of heterogeneity. We propose solutions focusing on classical layer partitioning and quantum circuit cutting to demonstrate the potential of utilizing classical and quantum computation across the continuum. To evaluate the importance and feasibility of our vision, we provide a proof of concept that exemplifies how extending a classical partition method to integrate quantum circuits can improve the solution quality. Specifically, we implement a split neural network with optional hybrid QNN predictors. Our results show that extending classical methods with QNNs is viable and promising for future work.
In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical 2D images. In this context, 3D point clouds (PCs), whether obtained through LiDAR or photogrammetric techniques, provide valuable information. While recent studies showed the considerable benefit of using deep learning-based methods to detect and characterize changes into raw 3D PCs, these studies rely on large annotated training data to obtain accurate results. The collection of these annotations are tricky and time-consuming. The availability of unsupervised or weakly supervised approaches is then of prime interest. In this paper, we propose an unsupervised method, called DeepCluster 3D Change Detection (DC3DCD), to detect and categorize multiclass changes at point level. We classify our approach in the unsupervised family given the fact that we extract in a completely unsupervised way a number of clusters associated with potential changes. Let us precise that in the end of the process, the user has only to assign a label to each of these clusters to derive the final change map. Our method builds upon the DeepCluster approach, originally designed for image classification, to handle complex raw 3D PCs and perform change segmentation task. An assessment of the method on both simulated and real public dataset is provided. The proposed method allows to outperform fully-supervised traditional machine learning algorithm and to be competitive with fully-supervised deep learning networks applied on rasterization of 3D PCs with a mean of IoU over classes of change of 57.06\% and 66.69\% for the simulated and the real datasets, respectively.
In creative design, where aesthetics play a crucial role in determining the quality of outcomes, there are often multiple worthwhile possibilities, rather than a single ``best'' design. This challenge is compounded in the use of computational generative systems, where the sheer number of potential outcomes can be overwhelming. This paper introduces a method that combines evolutionary optimisation with AI-based image classification to perform quality-diversity search, allowing for the creative exploration of complex design spaces. The process begins by randomly sampling the genotype space, followed by mapping the generated phenotypes to a reduced representation of the solution space, as well as evaluating them based on their visual characteristics. This results in an elite group of diverse outcomes that span the solution space. The elite is then progressively updated via sampling and simple mutation. We tested our method on a generative system that produces abstract drawings. The results demonstrate that the system can effectively evolve populations of phenotypes with high aesthetic value and greater visual diversity compared to traditional optimisation-focused evolutionary approaches.
Vision transformers (ViTs) that model an image as a sequence of partitioned patches have shown notable performance in diverse vision tasks. Because partitioning patches eliminates the image structure, to reflect the order of patches, ViTs utilize an explicit component called positional embedding. However, we claim that the use of positional embedding does not simply guarantee the order-awareness of ViT. To support this claim, we analyze the actual behavior of ViTs using an effective receptive field. We demonstrate that during training, ViT acquires an understanding of patch order from the positional embedding that is trained to be a specific pattern. Based on this observation, we propose explicitly adding a Gaussian attention bias that guides the positional embedding to have the corresponding pattern from the beginning of training. We evaluated the influence of Gaussian attention bias on the performance of ViTs in several image classification, object detection, and semantic segmentation experiments. The results showed that proposed method not only facilitates ViTs to understand images but also boosts their performance on various datasets, including ImageNet, COCO 2017, and ADE20K.
Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning to help researchers and organizations with limited computation power. We also present a methodology for selecting background images and discuss potential future improvements. We apply our approach to several datasets and achieve improved generalization with much lower computation. Through the class activation mappings (CAMs) of the trained models, we observed the tendency towards looking at a bigger picture with the proposed model training methodology. Applying the vision transformer with the proposed background class, we receive state-of-the-art (SOTA) performance on CIFAR-10C, Caltech-101, and CINIC-10 datasets. Example scripts are available in the `CAM' folder of the following GitHub Repository: github.com/dipuk0506/UQ
Although data augmentation is a powerful technique for improving the performance of image classification tasks, it is difficult to identify the best augmentation policy. The optimal augmentation policy, which is the latent variable, cannot be directly observed. To address this problem, this study proposes $\textit{LatentAugment}$, which estimates the latent probability of optimal augmentation. The proposed method is appealing in that it can dynamically optimize the augmentation strategies for each input and model parameter in learning iterations. Theoretical analysis shows that LatentAugment is a general model that includes other augmentation methods as special cases, and it is simple and computationally efficient in comparison with existing augmentation methods. Experimental results show that the proposed LatentAugment has higher test accuracy than previous augmentation methods on the CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets.
Although contrastive learning methods have shown prevailing performance on a variety of representation learning tasks, they encounter difficulty when the training dataset is long-tailed. Many researchers have combined contrastive learning and a logit adjustment technique to address this problem, but the combinations are done ad-hoc and a theoretical background has not yet been provided. The goal of this paper is to provide the background and further improve the performance. First, we show that the fundamental reason contrastive learning methods struggle with long-tailed tasks is that they try to maximize the mutual information maximization between latent features and input data. As ground-truth labels are not considered in the maximization, they are not able to address imbalances between class labels. Rather, we interpret the long-tailed recognition task as a mutual information maximization between latent features and ground-truth labels. This approach integrates contrastive learning and logit adjustment seamlessly to derive a loss function that shows state-of-the-art performance on long-tailed recognition benchmarks. It also demonstrates its efficacy in image segmentation tasks, verifying its versatility beyond image classification.
Limited training data and severe class imbalance impose significant challenges to developing clinically robust deep learning models. Federated learning (FL) addresses the former by enabling different medical clients to collaboratively train a deep model without sharing data. However, the class imbalance problem persists due to inter-client class distribution variations. To overcome this, we propose federated classifier anchoring (FCA) by adding a personalized classifier at each client to guide and debias the federated model through consistency learning. Additionally, FCA debiases the federated classifier and each client's personalized classifier based on their respective class distributions, thus mitigating divergence. With FCA, the federated feature extractor effectively learns discriminative features suitably globally for federation as well as locally for all participants. In clinical practice, the federated model is expected to be both generalized, performing well across clients, and specialized, benefiting each individual client from collaboration. According to this, we propose a novel evaluation metric to assess models' generalization and specialization performance globally on an aggregated public test set and locally at each client. Through comprehensive comparison and evaluation, FCA outperforms the state-of-the-art methods with large margins for federated long-tailed skin lesion classification and intracranial hemorrhage classification, making it a more feasible solution in clinical settings.
Digital pathology based on whole slide images (WSIs) plays a key role in cancer diagnosis and clinical practice. Due to the high resolution of the WSI and the unavailability of patch-level annotations, WSI classification is usually formulated as a weakly supervised problem, which relies on multiple instance learning (MIL) based on patches of a WSI. In this paper, we aim to learn an optimal patch-level feature space by integrating prototype learning with MIL. To this end, we develop a Trainable Prototype enhanced deep MIL (TPMIL) framework for weakly supervised WSI classification. In contrast to the conventional methods which rely on a certain number of selected patches for feature space refinement, we softly cluster all the instances by allocating them to their corresponding prototypes. Additionally, our method is able to reveal the correlations between different tumor subtypes through distances between corresponding trained prototypes. More importantly, TPMIL also enables to provide a more accurate interpretability based on the distance of the instances from the trained prototypes which serves as an alternative to the conventional attention score-based interpretability. We test our method on two WSI datasets and it achieves a new SOTA. GitHub repository: https://github.com/LitaoYang-Jet/TPMIL
Through prompting, large-scale pre-trained models have become more expressive and powerful, gaining significant attention in recent years. Though these big models have zero-shot capabilities, in general, labeled data are still required to adapt them to downstream tasks. To overcome this critical limitation, we propose an unsupervised fine-tuning framework to directly fine-tune the model or prompt on the unlabeled target data. We demonstrate how to apply our method to both language-augmented vision and masked-language models by aligning the discrete distributions extracted from the prompts and target data. To verify our approach's applicability, we conduct extensive experiments on image classification, sentiment analysis, and natural language inference tasks. Across 13 image-related tasks and 15 language-related ones, the proposed approach achieves consistent improvements over the baselines.
In the last few years, the success of Transformers in computer vision has stimulated the discovery of many alternative models that compete with Transformers, such as the MLP-Mixer. Despite their weak inductive bias, these models have achieved performance comparable to well-studied convolutional neural networks. Recent studies on modern Hopfield networks suggest the correspondence between certain energy-based associative memory models and Transformers or MLP-Mixer, and shed some light on the theoretical background of the Transformer-type architectures design. In this paper, we generalize the correspondence to the recently introduced hierarchical Hopfield network, and find iMixer, a novel generalization of MLP-Mixer model. Unlike ordinary feedforward neural networks, iMixer involves MLP layers that propagate forward from the output side to the input side. We characterize the module as an example of invertible, implicit, and iterative mixing module. We evaluate the model performance with various datasets on image classification tasks, and find that iMixer, despite its unique architecture, exhibits stable learning capabilities and achieves performance comparable to or better than the baseline vanilla MLP-Mixer. The results imply that the correspondence between the Hopfield networks and the Mixer models serves as a principle for understanding a broader class of Transformer-like architecture designs.
Self-supervised learning (SSL) techniques have recently been integrated into the few-shot learning (FSL) framework and have shown promising results in improving the few-shot image classification performance. However, existing SSL approaches used in FSL typically seek the supervision signals from the global embedding of every single image. Therefore, during the episodic training of FSL, these methods cannot capture and fully utilize the local visual information in image samples and the data structure information of the whole episode, which are beneficial to FSL. To this end, we propose to augment the few-shot learning objective with a novel self-supervised Episodic Spatial Pretext Task (ESPT). Specifically, for each few-shot episode, we generate its corresponding transformed episode by applying a random geometric transformation to all the images in it. Based on these, our ESPT objective is defined as maximizing the local spatial relationship consistency between the original episode and the transformed one. With this definition, the ESPT-augmented FSL objective promotes learning more transferable feature representations that capture the local spatial features of different images and their inter-relational structural information in each input episode, thus enabling the model to generalize better to new categories with only a few samples. Extensive experiments indicate that our ESPT method achieves new state-of-the-art performance for few-shot image classification on three mainstay benchmark datasets. The source code will be available at: https://github.com/Whut-YiRong/ESPT.
With the development of Vision-Language Pre-training Models (VLPMs) represented by CLIP and ALIGN, significant breakthroughs have been achieved for association-based visual tasks such as image classification and image-text retrieval by the zero-shot capability of CLIP without fine-tuning. However, CLIP is hard to apply to generation-based tasks. This is due to the lack of decoder architecture and pre-training tasks for generation. Although previous works have created generation capacity for CLIP through additional language models, a modality gap between the CLIP representations of different modalities and the inability of CLIP to model the offset of this gap, which fails the concept to transfer across modalities. To solve the problem, we try to map images/videos to the language modality and generate captions from the language modality. In this paper, we propose the K-nearest-neighbor Cross-modality Mapping (Knight), a zero-shot method from association to generation. With text-only unsupervised training, Knight achieves State-of-the-Art performance in zero-shot methods for image captioning and video captioning. Our code is available at https://github.com/junyangwang0410/Knight.
Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV's ability to promptly comprehend the crisis and optimally utilize its limited power and processing resources to narrow down search areas is crucial. Therefore, developing an efficient and lightweight method for scene classification is of utmost importance. However, current approaches tend to prioritize accuracy on benchmark datasets at the expense of computational efficiency. To address this shortcoming, we introduce the Wider ATTENTION EfficientNet (WATT-EffNet), a novel method that achieves higher accuracy with a more lightweight architecture compared to the baseline EfficientNet. The WATT-EffNet leverages width-wise incremental feature modules and attention mechanisms over width-wise features to ensure the network structure remains lightweight. We evaluate our method on a UAV-based aerial disaster image classification dataset and demonstrate that it outperforms the baseline by up to 15 times in terms of classification accuracy and 38.3% in terms of computing efficiency as measured by Floating Point Operations per second (FLOPs). Additionally, we conduct an ablation study to investigate the effect of varying the width of WATT-EffNet on accuracy and computational efficiency. Our code is available at \url{https://github.com/TanmDL/WATT-EffNet}.
Meta-learning, also known as ``learning to learn'', enables models to acquire great generalization abilities by learning from various tasks. Recent advancements have made these models applicable across various fields without data constraints, offering new opportunities for general artificial intelligence. However, applying these models can be challenging due to their often task-specific, standalone nature and the technical barriers involved. To address this challenge, we develop AwesomeMeta+, a prototyping and learning system designed to standardize the key components of meta-learning within the context of systems engineering. It standardizes different components of meta-learning and uses a building block metaphor to assist in model construction. By employing a modular, building-block approach, AwesomeMeta+ facilitates the construction of meta-learning models that can be adapted and optimized for specific application needs in real-world systems. The system is developed to support the full lifecycle of meta-learning system engineering, from design to deployment, by enabling users to assemble compatible algorithmic modules. We evaluate AwesomeMeta+ through feedback from 50 researchers and a series of machine-based tests and user studies. The results demonstrate that AwesomeMeta+ enhances users' understanding of meta-learning principles, accelerates system engineering processes, and provides valuable decision-making support for efficient deployment of meta-learning systems in complex application scenarios.
Bayesian optimization (BO) has contributed greatly to improving model performance by suggesting promising hyperparameter configurations iteratively based on observations from multiple training trials. However, only partial knowledge (i.e., the measured performances of trained models and their hyperparameter configurations) from previous trials is transferred. On the other hand, Self-Distillation (SD) only transfers partial knowledge learned by the task model itself. To fully leverage the various knowledge gained from all training trials, we propose the BOSS framework, which combines BO and SD. BOSS suggests promising hyperparameter configurations through BO and carefully selects pre-trained models from previous trials for SD, which are otherwise abandoned in the conventional BO process. BOSS achieves significantly better performance than both BO and SD in a wide range of tasks including general image classification, learning with noisy labels, semi-supervised learning, and medical image analysis tasks.
The recently proposed data augmentation TransMix employs attention labels to help visual transformers (ViT) achieve better robustness and performance. However, TransMix is deficient in two aspects: 1) The image cropping method of TransMix may not be suitable for ViTs. 2) At the early stage of training, the model produces unreliable attention maps. TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model. To address the aforementioned issues, we propose MaskMix and Progressive Attention Labeling (PAL) in image and label space, respectively. In detail, from the perspective of image space, we design MaskMix, which mixes two images based on a patch-like grid mask. In particular, the size of each mask patch is adjustable and is a multiple of the image patch size, which ensures each image patch comes from only one image and contains more global contents. From the perspective of label space, we design PAL, which utilizes a progressive factor to dynamically re-weight the attention weights of the mixed attention label. Finally, we combine MaskMix and Progressive Attention Labeling as our new data augmentation method, named MixPro. The experimental results show that our method can improve various ViT-based models at scales on ImageNet classification (73.8\% top-1 accuracy based on DeiT-T for 300 epochs). After being pre-trained with MixPro on ImageNet, the ViT-based models also demonstrate better transferability to semantic segmentation, object detection, and instance segmentation. Furthermore, compared to TransMix, MixPro also shows stronger robustness on several benchmarks. The code is available at https://github.com/fistyee/MixPro.
Feature distillation makes the student mimic the intermediate features of the teacher. Nearly all existing feature-distillation methods use L2 distance or its slight variants as the distance metric between teacher and student features. However, while L2 distance is isotropic w.r.t. all dimensions, the neural network's operation on different dimensions is usually anisotropic, i.e., perturbations with the same 2-norm but in different dimensions of intermediate features lead to changes in the final output with largely different magnitude. Considering this, we argue that the similarity between teacher and student features should not be measured merely based on their appearance (i.e., L2 distance), but should, more importantly, be measured by their difference in function, namely how later layers of the network will read, decode, and process them. Therefore, we propose Function-Consistent Feature Distillation (FCFD), which explicitly optimizes the functional similarity between teacher and student features. The core idea of FCFD is to make teacher and student features not only numerically similar, but more importantly produce similar outputs when fed to the later part of the same network. With FCFD, the student mimics the teacher more faithfully and learns more from the teacher. Extensive experiments on image classification and object detection demonstrate the superiority of FCFD to existing methods. Furthermore, we can combine FCFD with many existing methods to obtain even higher accuracy. Our codes are available at https://github.com/LiuDongyang6/FCFD.
The paper discusses the use of the Absolute activation function in classification neural networks. An examples are shown of using this activation function in simple and more complex problems. Using as a baseline LeNet-5 network for solving the MNIST problem, the efficiency of Absolute activation function is shown in comparison with the use of Tanh, ReLU and SeLU activations. It is shown that in deep networks Absolute activation does not cause vanishing and exploding gradients, and therefore Absolute activation can be used in both simple and deep neural networks. Due to high volatility of training networks with Absolute activation, a special modification of ADAM training algorithm is used, that estimates lower bound of accuracy at any test dataset using validation dataset analysis at each training epoch, and uses this value to stop/decrease learning rate, and re-initializes ADAM algorithm between these steps. It is shown that solving the MNIST problem with the LeNet-like architectures based on Absolute activation allows to significantly reduce the number of trained parameters in the neural network with improving the prediction accuracy.