Activation functions are crucial in deep learning models since they introduce non-linearity into the networks, allowing them to learn from errors and make adjustments, which is essential for learning complex patterns. The essential purpose of activation functions is to transform unprocessed input signals into significant output activations, promoting information transmission throughout the neural network. In this study, we propose a new activation function called Sqish, which is a non-monotonic and smooth function and an alternative to existing ones. We showed its superiority in classification, object detection, segmentation tasks, and adversarial robustness experiments. We got an 8.21% improvement over ReLU on the CIFAR100 dataset with the ShuffleNet V2 model in the FGSM adversarial attack. We also got a 5.87% improvement over ReLU on image classification on the CIFAR100 dataset with the ShuffleNet V2 model.
The Wilson-Cowan model for metapopulation, a Neural Mass Network Model, treats different subcortical regions of the brain as connected nodes, with connections representing various types of structural, functional, or effective neuronal connectivity between these regions. Each region comprises interacting populations of excitatory and inhibitory cells, consistent with the standard Wilson-Cowan model. By incorporating stable attractors into such a metapopulation model's dynamics, we transform it into a learning algorithm capable of achieving high image and text classification accuracy. We test it on MNIST and Fashion MNIST, in combination with convolutional neural networks, on CIFAR-10 and TF-FLOWERS, and, in combination with a transformer architecture (BERT), on IMDB, always showing high classification accuracy. These numerical evaluations illustrate that minimal modifications to the Wilson-Cowan model for metapopulation can reveal unique and previously unobserved dynamics.
Diffusion Tensor Imaging (DTI) tractography offers detailed insights into the structural connectivity of the brain, but presents challenges in effective representation and interpretation in deep learning models. In this work, we propose a novel 2D representation of DTI tractography that encodes tract-level fractional anisotropy (FA) values into a 9x9 grayscale image. This representation is processed through a Beta-Total Correlation Variational Autoencoder with a Spatial Broadcast Decoder to learn a disentangled and interpretable latent embedding. We evaluate the quality of this embedding using supervised and unsupervised representation learning strategies, including auxiliary classification, triplet loss, and SimCLR-based contrastive learning. Compared to the 1D Group deep neural network (DNN) baselines, our approach improves the F1 score in a downstream sex classification task by 15.74% and shows a better disentanglement than the 3D representation.
Camera traps are important tools in animal ecology for biodiversity monitoring and conservation. However, their practical application is limited by issues such as poor generalization to new and unseen locations. Images are typically associated with diverse forms of context, which may exist in different modalities. In this work, we exploit the structured context linked to camera trap images to boost out-of-distribution generalization for species classification tasks in camera traps. For instance, a picture of a wild animal could be linked to details about the time and place it was captured, as well as structured biological knowledge about the animal species. While often overlooked by existing studies, incorporating such context offers several potential benefits for better image understanding, such as addressing data scarcity and enhancing generalization. However, effectively incorporating such heterogeneous context into the visual domain is a challenging problem. To address this, we propose a novel framework that transforms species classification as link prediction in a multimodal knowledge graph (KG). This framework enables the seamless integration of diverse multimodal contexts for visual recognition. We apply this framework for out-of-distribution species classification on the iWildCam2020-WILDS and Snapshot Mountain Zebra datasets and achieve competitive performance with state-of-the-art approaches. Furthermore, our framework enhances sample efficiency for recognizing under-represented species.
The detection and classification of power quality disturbances (PQDs) carries significant importance for power systems. In response to this imperative, numerous intelligent diagnostic methods have been developed. However, existing identification methods usually concentrate on single-type signals or on complex signals with two types, rendering them susceptible to noisy labels and environmental effects. This study proposes a novel method for the classification of PQDs, termed ST-GSResNet, which utilizes the S-Transform and an improved residual neural network (ResNet) with a channel attention mechanism. The ST-GSResNet approach initially uses the S-Transform to transform a time-series signal into a 2D time-frequency image for feature enhancement. Then, an improved ResNet model is introduced, which employs grouped convolution instead of the traditional convolution operation. This improvement aims to facilitate learning with a block-diagonal structured sparsity on the channel dimension, the highly-correlated filters are learned in a more structured way in the networks with filter groups. By reducing the number of parameters in the network in this significant manner, the model becomes less prone to overfitting. Furthermore, the SE module concentrates on primary components, which enhances the model's robustness in recognition and immunity to noise. Experimental results demonstrate that, compared to existing deep learning models, our approach has advantages in computational efficiency and classification accuracy.
Accurate classification of blood cells is of vital significance in the diagnosis of hematological disorders. However, in real-world scenarios, domain shifts caused by the variability in laboratory procedures and settings, result in a rapid deterioration of the model's generalization performance. To address this issue, we propose a novel framework of domain-invariant representation learning (DoRL) via segment anything model (SAM) for blood cell classification. The DoRL comprises two main components: a LoRA-based SAM (LoRA-SAM) and a cross-domain autoencoder (CAE). The advantage of DoRL is that it can extract domain-invariant representations from various blood cell datasets in an unsupervised manner. Specifically, we first leverage the large-scale foundation model of SAM, fine-tuned with LoRA, to learn general image embeddings and segment blood cells. Additionally, we introduce CAE to learn domain-invariant representations across different-domain datasets while mitigating images' artifacts. To validate the effectiveness of domain-invariant representations, we employ five widely used machine learning classifiers to construct blood cell classification models. Experimental results on two public blood cell datasets and a private real dataset demonstrate that our proposed DoRL achieves a new state-of-the-art cross-domain performance, surpassing existing methods by a significant margin. The source code can be available at the URL (https://github.com/AnoK3111/DoRL).
Sky-image-based solar forecasting using deep learning has been recognized as a promising approach in reducing the uncertainty in solar power generation. However, one of the biggest challenges is the lack of massive and diversified sky image samples. In this study, we present a comprehensive survey of open-source ground-based sky image datasets for very short-term solar forecasting (i.e., forecasting horizon less than 30 minutes), as well as related research areas which can potentially help improve solar forecasting methods, including cloud segmentation, cloud classification and cloud motion prediction. We first identify 72 open-source sky image datasets that satisfy the needs of machine/deep learning. Then a database of information about various aspects of the identified datasets is constructed. To evaluate each surveyed datasets, we further develop a multi-criteria ranking system based on 8 dimensions of the datasets which could have important impacts on usage of the data. Finally, we provide insights on the usage of these datasets for different applications. We hope this paper can provide an overview for researchers who are looking for datasets for very short-term solar forecasting and related areas.
Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object detection data remains an underexplored area, where not only image-level perceptual quality but also geometric conditions such as bounding boxes and camera views are essential. Previous studies have utilized either copy-paste synthesis or layout-to-image (L2I) generation with specifically designed modules to encode the semantic layouts. In this paper, we propose the GeoDiffusion, a simple framework that can flexibly translate various geometric conditions into text prompts and empower pre-trained text-to-image (T2I) diffusion models for high-quality detection data generation. Unlike previous L2I methods, our GeoDiffusion is able to encode not only the bounding boxes but also extra geometric conditions such as camera views in self-driving scenes. Extensive experiments demonstrate GeoDiffusion outperforms previous L2I methods while maintaining 4x training time faster. To the best of our knowledge, this is the first work to adopt diffusion models for layout-to-image generation with geometric conditions and demonstrate that L2I-generated images can be beneficial for improving the performance of object detectors.
In recent years, Deep Neural Networks (DNN) have emerged as a practical method for image recognition. The raw data, which contain sensitive information, are generally exploited within the training process. However, when the training process is outsourced to a third-party organization, the raw data should be desensitized before being transferred to protect sensitive information. Although masks are widely applied to hide important sensitive information, preventing inpainting masked images is critical, which may restore the sensitive information. The corresponding models should be adjusted for the masked images to reduce the degradation of the performance for recognition or classification tasks due to the desensitization of images. In this paper, we propose a mask-based image desensitization approach while supporting recognition. This approach consists of a mask generation algorithm and a model adjustment method. We propose exploiting an interpretation algorithm to maintain critical information for the recognition task in the mask generation algorithm. In addition, we propose a feature selection masknet as the model adjustment method to improve the performance based on the masked images. Extensive experimentation results based on multiple image datasets reveal significant advantages (up to 9.34% in terms of accuracy) of our approach for image desensitization while supporting recognition.
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.
Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from the view of a camera. Methods to improve performance under occlusion, including data augmentation, part-based clustering, and more inherently robust architectures, including Vision Transformer (ViT) models, have, to some extent, been evaluated on their ability to classify objects under partial occlusion. However, evaluations of these methods have largely relied on images containing artificial occlusion, which are typically computer-generated and therefore inexpensive to label. Additionally, methods are rarely compared against each other, and many methods are compared against early, now outdated, deep learning models. We contribute the Image Recognition Under Occlusion (IRUO) dataset, based on the recently developed Occluded Video Instance Segmentation (OVIS) dataset (arXiv:2102.01558). IRUO utilizes real-world and artificially occluded images to test and benchmark leading methods' robustness to partial occlusion in visual recognition tasks. In addition, we contribute the design and results of a human study using images from IRUO that evaluates human classification performance at multiple levels and types of occlusion. We find that modern CNN-based models show improved recognition accuracy on occluded images compared to earlier CNN-based models, and ViT-based models are more accurate than CNN-based models on occluded images, performing only modestly worse than human accuracy. We also find that certain types of occlusion, including diffuse occlusion, where relevant objects are seen through "holes" in occluders such as fences and leaves, can greatly reduce the accuracy of deep recognition models as compared to humans, especially those with CNN backbones.
Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes. In this paper, we propose a new ZSL algorithm using coupled dictionary learning. The core idea is that the visual features and the semantic attributes of an image can share the same sparse representation in an intermediate space. We use images from seen classes and semantic attributes from seen and unseen classes to learn two dictionaries that can represent sparsely the visual and semantic feature vectors of an image. In the ZSL testing stage and in the absence of labeled data, images from unseen classes can be mapped into the attribute space by finding the joint sparse representation using solely the visual data. The image is then classified in the attribute space given semantic descriptions of unseen classes. We also provide an attribute-aware formulation to tackle domain shift and hubness problems in ZSL. Extensive experiments are provided to demonstrate the superior performance of our approach against the state of the art ZSL algorithms on benchmark ZSL datasets.
Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the perspectives of data and model architecture. To address the prevalence of noisy data and enhance the quality of large-scale image-text data crawled from the internet, we introduce a diverse description generation framework that can leverage Large Language Models (LLMs) to synthesize and refine content from web-based texts, synthetic captions, and detection tags. Furthermore, we propose RWKV-CLIP, the first RWKV-driven vision-language representation learning model that combines the effective parallel training of transformers with the efficient inference of RNNs. Comprehensive experiments across various model scales and pre-training datasets demonstrate that RWKV-CLIP is a robust and efficient vision-language representation learner, it achieves state-of-the-art performance in several downstream tasks, including linear probe, zero-shot classification, and zero-shot image-text retrieval. To facilitate future research, the code and pre-trained models are released at https://github.com/deepglint/RWKV-CLIP
The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely uninterpretable models exhibit glaring security vulnerabilities in the presence of an adversary. In this work, we develop a powerful untargeted adversarial attack for action recognition systems in both white-box and black-box settings. Action recognition models differ from image-classification models in that their inputs contain a temporal dimension, which we explicitly target in the attack. Drawing inspiration from image classifier attacks, we create new attacks which achieve state-of-the-art success rates on a two-stream classifier trained on the UCF-101 dataset. We find that our attacks can significantly degrade a model's performance with sparsely and imperceptibly perturbed examples. We also demonstrate the transferability of our attacks to black-box action recognition systems.
Cross-modal representation learning allows to integrate information from different modalities into one representation. At the same time, research on generative models tends to focus on the visual domain with less emphasis on other domains, such as audio or text, potentially missing the benefits of shared representations. Studies successfully linking more than one modality in the generative setting are rare. In this context, we verify the possibility to train variational autoencoders (VAEs) to reconstruct image archetypes from audio data. Specifically, we consider VAEs in an adversarial training framework in order to ensure more variability in the generated data and find that there is a trade-off between the consistency and diversity of the generated images - this trade-off can be governed by scaling the reconstruction loss up or down, respectively. Our results further suggest that even in the case when the generated images are relatively inconsistent (diverse), features that are critical for proper image classification are preserved.
Large-scale image databases remain largely biased towards objects and activities encountered in a select few cultures. This absence of culturally-diverse images, which we refer to as the hidden tail, limits the applicability of pre-trained neural networks and inadvertently excludes researchers from under-represented regions. To begin remedying this issue, we curate Turath-150K, a database of images of the Arab world that reflect objects, activities, and scenarios commonly found there. In the process, we introduce three benchmark databases, Turath Standard, Art, and UNESCO, specialised subsets of the Turath dataset. After demonstrating the limitations of existing networks pre-trained on ImageNet when deployed on such benchmarks, we train and evaluate several networks on the task of image classification. As a consequence of Turath, we hope to engage machine learning researchers in under-represented regions, and to inspire the release of additional culture-focused databases. The database can be accessed here: danikiyasseh.github.io/Turath.
Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense prediction tasks such as semantic segmentation. In this work, we propose a pixel-wise contrastive learning method called CP2 (Copy-Paste Contrastive Pretraining), which facilitates both image- and pixel-level representation learning and therefore is more suitable for downstream dense prediction tasks. In detail, we copy-paste a random crop from an image (the foreground) onto different background images and pretrain a semantic segmentation model with the objective of 1) distinguishing the foreground pixels from the background pixels, and 2) identifying the composed images that share the same foreground.Experiments show the strong performance of CP2 in downstream semantic segmentation: By finetuning CP2 pretrained models on PASCAL VOC 2012, we obtain 78.6% mIoU with a ResNet-50 and 79.5% with a ViT-S.
We perform a comprehensive benchmarking of contrastive frameworks for learning multimodal representations in the medical domain. Through this study, we aim to answer the following research questions: (i) How transferable are general-domain representations to the medical domain? (ii) Is multimodal contrastive training sufficient, or does it benefit from unimodal training as well? (iii) What is the impact of feature granularity on the effectiveness of multimodal medical representation learning? To answer these questions, we investigate eight contrastive learning approaches under identical training setups, and train them on 2.8 million image-text pairs from four datasets, and evaluate them on 25 downstream tasks, including classification (zero-shot and linear probing), image-to-text and text-to-image retrieval, and visual question-answering. Our findings suggest a positive answer to the first question, a negative answer to the second question, and the benefit of learning fine-grained features. Finally, we make our code publicly available.
Variational autoencoder (VAE) is one of the most common techniques in the field of medical image generation, where this architecture has shown advanced researchers in recent years and has developed into various architectures. VAE has advantages including improving datasets by adding samples in smaller datasets and in datasets with imbalanced classes, and this is how data augmentation works. This paper provides a comprehensive review of studies on VAE in medical imaging, with a special focus on their ability to create synthetic images close to real data so that they can be used for data augmentation. This study reviews important architectures and methods used to develop VAEs for medical images and provides a comparison with other generative models such as GANs on issues such as image quality, and low diversity of generated samples. We discuss recent developments and applications in several medical fields highlighting the ability of VAEs to improve segmentation and classification accuracy.
Few-shot learning in medical image classification presents a significant challenge due to the limited availability of annotated data and the complex nature of medical imagery. In this work, we propose Adaptive Vision-Language Fine-tuning with Hierarchical Contrastive Alignment (HiCA), a novel framework that leverages the capabilities of Large Vision-Language Models (LVLMs) for medical image analysis. HiCA introduces a two-stage fine-tuning strategy, combining domain-specific pretraining and hierarchical contrastive learning to align visual and textual representations at multiple levels. We evaluate our approach on two benchmark datasets, Chest X-ray and Breast Ultrasound, achieving state-of-the-art performance in both few-shot and zero-shot settings. Further analyses demonstrate the robustness, generalizability, and interpretability of our method, with substantial improvements in performance compared to existing baselines. Our work highlights the potential of hierarchical contrastive strategies in adapting LVLMs to the unique challenges of medical imaging tasks.