Shortcut learning is a phenomenon where machine learning models prioritize learning simple, potentially misleading cues from data that do not generalize well beyond the training set. While existing research primarily investigates this in the realm of image classification, this study extends the exploration of shortcut learning into medical image segmentation. We demonstrate that clinical annotations such as calipers, and the combination of zero-padded convolutions and center-cropped training sets in the dataset can inadvertently serve as shortcuts, impacting segmentation accuracy. We identify and evaluate the shortcut learning on two different but common medical image segmentation tasks. In addition, we suggest strategies to mitigate the influence of shortcut learning and improve the generalizability of the segmentation models. By uncovering the presence and implications of shortcuts in medical image segmentation, we provide insights and methodologies for evaluating and overcoming this pervasive challenge and call for attention in the community for shortcuts in segmentation. Our code is public at https://github.com/nina-weng/shortcut_skinseg .
It is common to view people in real applications walking in arbitrary directions, holding items, or wearing heavy coats. These factors are challenges in gait-based application methods because they significantly change a person's appearance. This paper proposes a novel method for classifying human gender in real time using gait information. The use of an average gait image (AGI), rather than a gait energy image (GEI), allows this method to be computationally efficient and robust against view changes. A viewpoint (VP) model is created for automatically determining the viewing angle during the testing phase. A distance signal (DS) model is constructed to remove any areas with an attachment (carried items, worn coats) from a silhouette to reduce the interference in the resulting classification. Finally, the human gender is classified using multiple view-dependent classifiers trained using a support vector machine. Experiment results confirm that the proposed method achieves a high accuracy of 98.8% on the CASIA Dataset B and outperforms the recent state-of-the-art methods.
Label hierarchies widely exist in many vision-related problems, ranging from explicit label hierarchies existed in image classification to latent label hierarchies existed in semantic segmentation. Nevertheless, state-of-the-art methods often deploy cross-entropy loss that implicitly assumes class labels to be exclusive and thus independence from each other. Motivated by the fact that classes from the same parental category usually share certain similarity, we design a new training diagram called Hierarchical Complement Objective Training (HCOT) that leverages the information from label hierarchy. HCOT maximizes the probability of the ground truth class, and at the same time, neutralizes the probabilities of rest of the classes in a hierarchical fashion, making the model take advantage of the label hierarchy explicitly. The proposed HCOT is evaluated on both image classification and semantic segmentation tasks. Experimental results confirm that HCOT outperforms state-of-the-art models in CIFAR-100, ImageNet-2012, and PASCAL-Context. The study further demonstrates that HCOT can be applied on tasks with latent label hierarchies, which is a common characteristic in many machine learning tasks.
Research on automated, image based identification of clothing categories and fashion landmarks has recently gained significant interest due to its potential impact on areas such as robotic clothing manipulation, automated clothes sorting and recycling, and online shopping. Several public and annotated fashion datasets have been created to facilitate research advances in this direction. In this work, we make the first step towards leveraging the data and techniques developed for fashion image analysis in vision-based robotic clothing manipulation tasks. We focus on techniques that can generalize from large-scale fashion datasets to less structured, small datasets collected in a robotic lab. Specifically, we propose training data augmentation methods such as elastic warping, and model adjustments such as rotation invariant convolutions to make the model generalize better. Our experiments demonstrate that our approach outperforms stateof-the art models with respect to clothing category classification and fashion landmark detection when tested on previously unseen datasets. Furthermore, we present experimental results on a new dataset composed of images where a robot holds different garments, collected in our lab.
Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are suffering from a catastrophic forgetting problem, which is not studied extensively. In this paper, we make the first attempt to tackle the catastrophic forgetting problem in the mainstream self-supervised methods, i.e., contrastive learning methods. Specifically, we first develop a rehearsal-based framework combined with a novel sampling strategy and a self-supervised knowledge distillation to transfer information over time efficiently. Then, we propose an extra sample queue to help the network separate the feature representations of old and new data in the embedding space. Experimental results show that compared with the naive self-supervised baseline, which learns tasks one by one without taking any technique, we improve the image classification accuracy by 1.60% on CIFAR-100, 2.86% on ImageNet-Sub, and 1.29% on ImageNet-Full under 10 incremental steps setting. Our code will be available at https://github.com/VDIGPKU/ContinualContrastiveLearning.
The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field. However, a persistent issue remains unsolved during experiments: the interferential technical noise caused by systematic errors (e.g., temperature, reagent concentration, and well location) is always mixed up with the real biological signals, leading to misinterpretation of any conclusion drawn. Here, we show a mean teacher based deep learning model (DeepNoise) that can disentangle biological signals from the experimental noise. Specifically, we aim to classify the phenotypic impact of 1,108 different genetic perturbations screened from 125,510 fluorescent microscopy images, which are totally unrecognizable by human eye. We validate our model by participating in the Recursion Cellular Image Classification Challenge, and our proposed method achieves an extremely high classification score (Acc: 99.596%), ranking the 2nd place among 866 participating groups. This promising result indicates the successful separation of biological and technical factors, which might help decrease the cost of treatment development and expedite the drug discovery process.
Convolutional Neural Networks have played a significant role in various medical imaging tasks like classification and segmentation. They provide state-of-the-art performance compared to classical image processing algorithms. However, the major downside of these methods is the high computational complexity, reliance on high-performance hardware like GPUs and the inherent black-box nature of the model. In this paper, we propose quantised stand-alone self-attention based models as an alternative to traditional CNNs. In the proposed class of networks, convolutional layers are replaced with stand-alone self-attention layers, and the network parameters are quantised after training. We experimentally validate the performance of our method on classification and segmentation tasks. We observe a $50-80\%$ reduction in model size, $60-80\%$ lesser number of parameters, $40-85\%$ fewer FLOPs and $65-80\%$ more energy efficiency during inference on CPUs. The code will be available at \href {https://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Network}{https://github.com/Rakshith2597/Quantised-Self-Attentive-Deep-Neural-Network}.
Training deep learning models on medical datasets that perform well for all classes is a challenging task. It is often the case that a suboptimal performance is obtained on some classes due to the natural class imbalance issue that comes with medical data. An effective way to tackle this problem is by using targeted active learning, where we iteratively add data points to the training data that belong to the rare classes. However, existing active learning methods are ineffective in targeting rare classes in medical datasets. In this work, we propose Clinical (targeted aCtive Learning for ImbalaNced medICal imAge cLassification) a framework that uses submodular mutual information functions as acquisition functions to mine critical data points from rare classes. We apply our framework to a wide-array of medical imaging datasets on a variety of real-world class imbalance scenarios - namely, binary imbalance and long-tail imbalance. We show that Clinical outperforms the state-of-the-art active learning methods by acquiring a diverse set of data points that belong to the rare classes.
Transformers were initially introduced for natural language processing (NLP) tasks, but fast they were adopted by most deep learning fields, including computer vision. They measure the relationships between pairs of input tokens (words in the case of text strings, parts of images for visual Transformers), termed attention. The cost is exponential with the number of tokens. For image classification, the most common Transformer Architecture uses only the Transformer Encoder in order to transform the various input tokens. However, there are also numerous other applications in which the decoder part of the traditional Transformer Architecture is also used. Here, we first introduce the Attention mechanism (Section 1), and then the Basic Transformer Block including the Vision Transformer (Section 2). Next, we discuss some improvements of visual Transformers to account for small datasets or less computation(Section 3). Finally, we introduce Visual Transformers applied to tasks other than image classification, such as detection, segmentation, generation and training without labels (Section 4) and other domains, such as video or multimodality using text or audio data (Section 5).
Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation. This deficiency is often attributed to the absence of localization cues in captions and the intertwined nature of the learning process, which encompasses both image representation learning and cross-modality alignment. To tackle these issues, we propose SimZSS, a Simple framework for open-vocabulary Zero-Shot Segmentation. The method is founded on two key principles: i) leveraging frozen vision-only models that exhibit spatial awareness while exclusively aligning the text encoder and ii) exploiting the discrete nature of text and linguistic knowledge to pinpoint local concepts within captions. By capitalizing on the quality of the visual representations, our method requires only image-caption pairs datasets and adapts to both small curated and large-scale noisy datasets. When trained on COCO Captions across 8 GPUs, SimZSS achieves state-of-the-art results on 7 out of 8 benchmark datasets in less than 15 minutes.
Automatic cell tracking in dense environments is plagued by inaccurate correspondences and misidentification of parent-offspring relationships. In this paper, we introduce a novel cell tracking algorithm named DenseTrack, which integrates deep learning with mathematical model-based strategies to effectively establish correspondences between consecutive frames and detect cell division events in crowded scenarios. We formulate the cell tracking problem as a deep learning-based temporal sequence classification task followed by solving a constrained one-to-one matching optimization problem exploiting the classifier's confidence scores. Additionally, we present an eigendecomposition-based cell division detection strategy that leverages knowledge of cellular geometry. The performance of the proposed approach has been evaluated by tracking densely packed cells in 3D time-lapse image sequences of bacterial biofilm development. The experimental results on simulated as well as experimental fluorescence image sequences suggest that the proposed tracking method achieves superior performance in terms of both qualitative and quantitative evaluation measures compared to recent state-of-the-art cell tracking approaches.
Deep convolutional neural networks(CNNs) have been successful for a wide range of computer vision tasks, including image classification. A specific area of the application lies in digital pathology for pattern recognition in the tissue-based diagnosis of gastrointestinal(GI) diseases. This domain can utilize CNNs to translate histopathological images into precise diagnostics. This is challenging since these complex biopsies are heterogeneous and require multiple levels of assessment. This is mainly due to structural similarities in different parts of the GI tract and shared features among different gut diseases. Addressing this problem with a flat model that assumes all classes (parts of the gut and their diseases) are equally difficult to distinguish leads to an inadequate assessment of each class. Since the hierarchical model restricts classification error to each sub-class, it leads to a more informative model than a flat model. In this paper, we propose to apply the hierarchical classification of biopsy images from different parts of the GI tract and the receptive diseases within each. We embedded a class hierarchy into the plain VGGNet to take advantage of its layers' hierarchical structure. The proposed model was evaluated using an independent set of image patches from 373 whole slide images. The results indicate that the hierarchical model can achieve better results than the flat model for multi-category diagnosis of GI disorders using histopathological images.
Recently, the amount of GI tract datasets is introduced more and more by gathering from contests and challenges. The most common task needs to solve that is to classify images from the GI tract into various classes. However, the contributions of the existing approaches exhibit lots of limitations. In this paper, we aim to develop a computer-aided diagnosis system to classify the pathological findings in endoscopy images, the system can classify some common pathologies including polyps, esophagitis, and ulcerative -- colitis. To evaluate the proposed work, we use the public dataset which is Hyper--Kvasir instead of gathering the data. The key idea of our system is to develop self-supervised learning based on the Barlow Twins framework with a downstream task which is an endoscopy image classification integrated with triplet loss and focal loss functions. The self-supervision framework and focal loss function are used to overcome class-imbalanced data, while the triplet loss function is to tackle the domain-specific properties in endoscopy images which are inter/intra-class problems. An extensive experimental study on the pathological finding images in the Hyper--Kvasir dataset has shown that our proposed system is in general better than the compared methods, whereas using a simple neural network model. This means the proposed system can be used efficiently and capable of accurately for the classification of pathology images in the GI tract.
Recent advances in capsule endoscopy systems have introduced new methods and capabilities. The capsule endoscopy system, by observing the entire digestive tract, has significantly improved diagnosing gastrointestinal disorders and diseases. The system has challenges such as the need to enhance the quality of the transmitted images, low frame rates of transmission, and battery lifetime that need to be addressed. One of the important parts of a capsule endoscopy system is the image compression unit. Better compression of images increases the frame rate and hence improves the diagnosis process. In this paper a high precision compression algorithm with high compression ratio is proposed. In this algorithm we use the similarity between frames to compress the data more efficiently.
We discuss two potentially challenging problems faced by the ecommerce industry. One relates to the problem faced by sellers while uploading pictures of products on the platform for sale and the consequent manual tagging involved. It gives rise to misclassifications leading to its absence from search results. The other problem concerns with the potential bottleneck in placing orders when a customer may not know the right keywords but has a visual impression of an image. An image based search algorithm can unleash the true potential of ecommerce by enabling customers to click a picture of an object and search for similar products without the need for typing. In this paper, we explore machine learning algorithms which can help us solve both these problems.
We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task. Our differentiable layer can be added as a preprocessing block to existing task networks and trained altogether in an end-to-end fashion. The effect of the layer is to efficiently estimate how to sample from the original data in order to boost task performance. For example, for an image classification task in which the original data might range in size up to several megapixels, but where the desired input images to the task network are much smaller, our layer learns how best to sample from the underlying high resolution data in a manner which preserves task-relevant information better than uniform downsampling. This has the effect of creating distorted, caricature-like intermediate images, in which idiosyncratic elements of the image that improve task performance are zoomed and exaggerated. Unlike alternative approaches such as spatial transformer networks, our proposed layer is inspired by image saliency, computed efficiently from uniformly downsampled data, and degrades gracefully to a uniform sampling strategy under uncertainty. We apply our layer to improve existing networks for the tasks of human gaze estimation and fine-grained object classification. Code for our method is available in: http://github.com/recasens/Saliency-Sampler
Vision transformer (ViT) has recently shown its strong capability in achieving comparable results to convolutional neural networks (CNNs) on image classification. However, vanilla ViT simply inherits the same architecture from the natural language processing directly, which is often not optimized for vision applications. Motivated by this, in this paper, we propose a new architecture that adopts the pyramid structure and employ a novel regional-to-local attention rather than global self-attention in vision transformers. More specifically, our model first generates regional tokens and local tokens from an image with different patch sizes, where each regional token is associated with a set of local tokens based on the spatial location. The regional-to-local attention includes two steps: first, the regional self-attention extract global information among all regional tokens and then the local self-attention exchanges the information among one regional token and the associated local tokens via self-attention. Therefore, even though local self-attention confines the scope in a local region but it can still receive global information. Extensive experiments on four vision tasks, including image classification, object and keypoint detection, semantics segmentation and action recognition, show that our approach outperforms or is on par with state-of-the-art ViT variants including many concurrent works. Our source codes and models are available at https://github.com/ibm/regionvit.
Fine-grained recognition involves the classification of images from subordinate macro-categories, and it is challenging due to small inter-class differences. To overcome this, most methods perform discriminative feature selection enabled by a feature extraction backbone followed by a high-level feature refinement step. Recently, many studies have shown the potential behind vision transformers as a backbone for fine-grained recognition, but their usage of its attention mechanism to select discriminative tokens can be computationally expensive. In this work, we propose a novel and computationally inexpensive metric to identify discriminative regions in an image. We compare the similarity between the global representation of an image given by the CLS token, a learnable token used by transformers for classification, and the local representation of individual patches. We select the regions with the highest similarity to obtain crops, which are forwarded through the same transformer encoder. Finally, high-level features of the original and cropped representations are further refined together in order to make more robust predictions. Through extensive experimental evaluation we demonstrate the effectiveness of our proposed method, obtaining favorable results in terms of accuracy across a variety of datasets. Furthermore, our method achieves these results at a much lower computational cost compared to the alternatives. Code and checkpoints are available at: \url{https://github.com/arkel23/GLSim}.
In the computer vision community, Convolutional Neural Networks (CNNs), first proposed in the 1980's, have become the standard visual classification model. Recently, as alternatives to CNNs, Capsule Networks (CapsNets) and Vision Transformers (ViTs) have been proposed. CapsNets, which were inspired by the information processing of the human brain, are considered to have more inductive bias than CNNs, whereas ViTs are considered to have less inductive bias than CNNs. All three classification models have received great attention since they can serve as backbones for various downstream tasks. However, these models are far from being perfect. As pointed out by the community, there are two weaknesses in standard Deep Neural Networks (DNNs). One of the limitations of DNNs is the lack of explainability. Even though they can achieve or surpass human expert performance in the image classification task, the DNN-based decisions are difficult to understand. In many real-world applications, however, individual decisions need to be explained. The other limitation of DNNs is adversarial vulnerability. Concretely, the small and imperceptible perturbations of inputs can mislead DNNs. The vulnerability of deep neural networks poses challenges to current visual classification models. The potential threats thereof can lead to unacceptable consequences. Besides, studying model adversarial vulnerability can lead to a better understanding of the underlying models. Our research aims to address the two limitations of DNNs. Specifically, we focus on deep visual classification models, especially the core building parts of each classification model, e.g. dynamic routing in CapsNets and self-attention module in ViTs.
Deep convolutional neural networks have been proven to be very effective in image related analysis and tasks, such as image segmentation, image classification, image generation, etc. Recently many sophisticated CNN based architectures have been proposed for the purpose of image segmentation. Some of these newly designed networks are used for the specific purpose of medical image segmentation, models like V-Net, U-Net and their variants. It has been shown that U-Net produces very promising results in the domain of medical image segmentation.However, in this paper, we argue that the architecture of U-Net, when combined with a supervised training strategy at the bottleneck layer, can produce comparable results with the original U-Net architecture. More specifically, we introduce a fully supervised FC layers based pixel-wise loss at the bottleneck of the encoder branch of U-Net. The two layer based FC sub-net will train the bottleneck representation to contain more semantic information, which will be used by the decoder layers to predict the final segmentation map. The FC layer based sub-net is trained by employing the pixel-wise cross entropy loss, while the U-Net architectures trained by using L1 loss.