Authors: Bingying Jin, Yadong Liu, Qinlin Qian
Inspection of high-voltage power equipment is an effective way to ensure power supply reliability. Object recognition, one of the key technologies in automatic power equipment inspection, attracts attention of many researchers and engineers. Although quite a few existing models have some their own advantages, object relationship between equipment which is very important in this task is scarcely considered. This paper combining object relationship modeling and Transformer Model proposes a Relation Transformer Model. It has four parts -- backbone, encoder, decoder and prediction heads. With this structure, the proposed method shows in experiments a much better performance than other three commonly used models in object recognition in substation, largely promoting the development of automatic power equipment inspection.
Authors: Meghna Gummadi, Cassandra Kent, Karl Schmeckpeper, Eric Eaton
Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world. To improve out-of-distribution (OOD) detection for segmentation, we introduce a metacognitive approach in the form of a lightweight module that leverages entropy measures, segmentation predictions, and spatial context to characterize the segmentation model's uncertainty and detect pixel-wise OOD data in real-time. Additionally, our approach incorporates a novel method of generating synthetic OOD data in context with in-distribution data, which we use to fine-tune existing segmentation models with maximum entropy training. This further improves the metacognitive module's performance without requiring access to OOD data while enabling compatibility with established pre-trained models. Our resulting approach can reliably detect OOD instances in a scene, as shown by state-of-the-art performance on OOD detection for semantic segmentation benchmarks.
Authors: Reza Esfandiarpoor, Stephen H. Bach
A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related attributes, e.g., using brown sparrow instead of sparrow. However, current zero-shot methods select a subset of attributes regardless of commonalities between the target classes, potentially providing no useful information that would have helped to distinguish between them. For instance, they may use color instead of bill shape to distinguish between sparrows and wrens, which are both brown. We propose Follow-up Differential Descriptions (FuDD), a zero-shot approach that tailors the class descriptions to each dataset and leads to additional attributes that better differentiate the target classes. FuDD first identifies the ambiguous classes for each image, and then uses a Large Language Model (LLM) to generate new class descriptions that differentiate between them. The new class descriptions resolve the initial ambiguity and help predict the correct label. In our experiments, FuDD consistently outperforms generic description ensembles and naive LLM-generated descriptions on 12 datasets. We show that differential descriptions are an effective tool to resolve class ambiguities, which otherwise significantly degrade the performance. We also show that high quality natural language class descriptions produced by FuDD result in comparable performance to few-shot adaptation methods.
Authors: Shezheng Song, Xiaopeng Li, Shasha Li
This review paper explores Multimodal Large Language Models (MLLMs), which integrate Large Language Models (LLMs) like GPT-4 to handle multimodal data such as text and vision. MLLMs demonstrate capabilities like generating image narratives and answering image-based questions, bridging the gap towards real-world human-computer interactions and hinting at a potential pathway to artificial general intelligence. However, MLLMs still face challenges in processing the semantic gap in multimodality, which may lead to erroneous generation, posing potential risks to society. Choosing the appropriate modality alignment method is crucial, as improper methods might require more parameters with limited performance improvement. This paper aims to explore modality alignment methods for LLMs and their existing capabilities. Implementing modality alignment allows LLMs to address environmental issues and enhance accessibility. The study surveys existing modal alignment methods in MLLMs into four groups: (1) Multimodal Converters that change data into something LLMs can understand; (2) Multimodal Perceivers to improve how LLMs perceive different types of data; (3) Tools Assistance for changing data into one common format, usually text; and (4) Data-Driven methods that teach LLMs to understand specific types of data in a dataset. This field is still in a phase of exploration and experimentation, and we will organize and update various existing research methods for multimodal information alignment.
Authors: Jinyu Zhao, Jumpei Oishi, Yusuke Monno, Masatoshi Okutomi
PatchMatch Multi-View Stereo (PatchMatch MVS) is one of the popular MVS approaches, owing to its balanced accuracy and efficiency. In this paper, we propose Polarimetric PatchMatch multi-view Stereo (PolarPMS), which is the first method exploiting polarization cues to PatchMatch MVS. The key of PatchMatch MVS is to generate depth and normal hypotheses, which form local 3D planes and slanted stereo matching windows, and efficiently search for the best hypothesis based on the consistency among multi-view images. In addition to standard photometric consistency, our PolarPMS evaluates polarimetric consistency to assess the validness of a depth and normal hypothesis, motivated by the physical property that the polarimetric information is related to the object's surface normal. Experimental results demonstrate that our PolarPMS can improve the accuracy and the completeness of reconstructed 3D models, especially for texture-less surfaces, compared with state-of-the-art PatchMatch MVS methods.
Authors: Amirhossein Dadashzadeh, Shuchao Duan, Alan Whone, Majid Mirmehdi
The limited availability of labelled data in Action Quality Assessment (AQA), has forced previous works to fine-tune their models pretrained on large-scale domain-general datasets. This common approach results in weak generalisation, particularly when there is a significant domain shift. We propose a novel, parameter efficient, continual pretraining framework, PECoP, to reduce such domain shift via an additional pretraining stage. In PECoP, we introduce 3D-Adapters, inserted into the pretrained model, to learn spatiotemporal, in-domain information via self-supervised learning where only the adapter modules' parameters are updated. We demonstrate PECoP's ability to enhance the performance of recent state-of-the-art methods (MUSDL, CoRe, and TSA) applied to AQA, leading to considerable improvements on benchmark datasets, JIGSAWS ($\uparrow6.0\%$), MTL-AQA ($\uparrow0.99\%$), and FineDiving ($\uparrow2.54\%$). We also present a new Parkinson's Disease dataset, PD4T, of real patients performing four various actions, where we surpass ($\uparrow3.56\%$) the state-of-the-art in comparison. Our code, pretrained models, and the PD4T dataset are available at https://github.com/Plrbear/PECoP.
Authors: Xudong Shen, Chao Du, Tianyu Pang, Min Lin, Yongkang Wong, Mohan Kankanhalli
The rapid adoption of text-to-image diffusion models in society underscores an urgent need to address their biases. Without interventions, these biases could propagate a distorted worldview and limit opportunities for minority groups. In this work, we frame fairness as a distributional alignment problem. Our solution consists of two main technical contributions: (1) a distributional alignment loss that steers specific characteristics of the generated images towards a user-defined target distribution, and (2) biased direct finetuning of diffusion model's sampling process, which leverages a biased gradient to more effectively optimize losses defined on the generated images. Empirically, our method markedly reduces gender, racial, and their intersectional biases for occupational prompts. Gender bias is significantly reduced even when finetuning just five soft tokens. Crucially, our method supports diverse perspectives of fairness beyond absolute equality, which is demonstrated by controlling age to a $75\%$ young and $25\%$ old distribution while simultaneously debiasing gender and race. Finally, our method is scalable: it can debias multiple concepts at once by simply including these prompts in the finetuning data. We hope our work facilitates the social alignment of T2I generative AI. We will share code and various debiased diffusion model adaptors.
Authors: Mirsaeed Abdollahi, Ali Jafarizadeh, Amirhosein Ghafouri Asbagh, Navid Sobhi, Keysan Pourmoghtader, Siamak Pedrammehr, Houshyar Asadi, Roohallah Alizadehsani, Ru-San Tan, U. Rajendra Acharya
Background: Cardiovascular diseases (CVDs) continue to be the leading cause of mortality on a global scale. In recent years, the application of artificial intelligence (AI) techniques, particularly deep learning (DL), has gained considerable popularity for evaluating the various aspects of CVDs. Moreover, using fundus images and optical coherence tomography angiography (OCTA) to diagnose retinal diseases has been extensively studied. To better understand heart function and anticipate changes based on microvascular characteristics and function, researchers are currently exploring the integration of AI with non-invasive retinal scanning. Leveraging AI-assisted early detection and prediction of cardiovascular diseases on a large scale holds excellent potential to mitigate cardiovascular events and alleviate the economic burden on healthcare systems. Method: A comprehensive search was conducted across various databases, including PubMed, Medline, Google Scholar, Scopus, Web of Sciences, IEEE Xplore, and ACM Digital Library, using specific keywords related to cardiovascular diseases and artificial intelligence. Results: A total of 87 English-language publications, selected for relevance were included in the study, and additional references were considered. This study presents an overview of the current advancements and challenges in employing retinal imaging and artificial intelligence to identify cardiovascular disorders and provides insights for further exploration in this field. Conclusion: Researchers aim to develop precise disease prognosis patterns as the aging population and global CVD burden increase. AI and deep learning are transforming healthcare, offering the potential for single retinal image-based diagnosis of various CVDs, albeit with the need for accelerated adoption in healthcare systems.
Authors: Kaer Huang, Weitu Chong
Multi-Object Tracking is one of the most important technologies in maritime computer vision. Our solution tries to explore Multi-Object Tracking in maritime Unmanned Aerial vehicles (UAVs) and Unmanned Surface Vehicles (USVs) usage scenarios. Most of the current Multi-Object Tracking algorithms require complex association strategies and association information (2D location and motion, 3D motion, 3D depth, 2D appearance) to achieve better performance, which makes the entire tracking system extremely complex and heavy. At the same time, most of the current Multi-Object Tracking algorithms still require video annotation data which is costly to obtain for training. Our solution tries to explore Multi-Object Tracking in a completely unsupervised way. The scheme accomplishes instance representation learning by using self-supervision on ImageNet. Then, by cooperating with high-quality detectors, the multi-target tracking task can be completed simply and efficiently. The scheme achieved top 3 performance on both UAV-based Multi-Object Tracking with Reidentification and USV-based Multi-Object Tracking benchmarks and the solution won the championship in many multiple Multi-Object Tracking competitions. such as BDD100K MOT,MOTS, Waymo 2D MOT
Authors: Junyang Chen, Hanjiang Lai
Zero-shot composed image retrieval (ZS-CIR), which aims to retrieve a target image based on textual modifications to a reference image without triplet labeling, has gained more and more attention. Current ZS-CIR research mainly relies on two unlabeled pre-trained models: the vision-language model, e.g., CLIP, and the Pic2Word/textual inversion model. However, the pre-trained models and CIR tasks have substantial discrepancies, where the pre-trained models learn the similarities between vision and language but CIR aims to learn the modifications of the image guided by text. In this paper, we introduce a novel unlabeled and pre-trained masked tuning approach to reduce the gap between the pre-trained model and the downstream CIR task. We first reformulate the pre-trained vision-language contrastive learning as the CIR task, where we randomly mask input image patches to generate $\langle$masked image, text, image$\rangle$ triple from an image-text pair. Then, we propose a masked tuning, which uses the text and the masked image to learn the modifications of the original image. With such a simple design, it can learn to capture fine-grained text-guided modifications. Extensive experimental results demonstrate the significant superiority of our approach over the baseline models on three ZS-CIR datasets, including FashionIQ, CIRR, and CIRCO.
Authors: Juho Kim
In convolutional neural networks (CNNs), padding plays a pivotal role in preserving spatial dimensions throughout the layers. Traditional padding techniques do not explicitly distinguish between the actual image content and the padded regions, potentially causing CNNs to incorrectly interpret the boundary pixels or regions that resemble boundaries. This ambiguity can lead to suboptimal feature extraction. To address this, we propose PadChannel, a novel padding method that encodes padding statuses as an additional input channel, enabling CNNs to easily distinguish genuine pixels from padded ones. By incorporating PadChannel into several prominent CNN architectures, we observed small performance improvements and notable reductions in the variances on the ImageNet-1K image classification task at marginal increases in the computational cost. The source code is available at https://github.com/AussieSeaweed/pad-channel
Authors: Zhaojian Li, Bin Zhao, Yuan Yuan
Binaural stereo audio is recorded by imitating the way the human ear receives sound, which provides people with an immersive listening experience. Existing approaches leverage autoencoders and directly exploit visual spatial information to synthesize binaural stereo, resulting in a limited representation of visual guidance. For the first time, we propose a visually guided generative adversarial approach for generating binaural stereo audio from mono audio. Specifically, we develop a Stereo Audio Generation Model (SAGM), which utilizes shared spatio-temporal visual information to guide the generator and the discriminator to work separately. The shared visual information is updated alternately in the generative adversarial stage, allowing the generator and discriminator to deliver their respective guided knowledge while visually sharing. The proposed method learns bidirectional complementary visual information, which facilitates the expression of visual guidance in generation. In addition, spatial perception is a crucial attribute of binaural stereo audio, and thus the evaluation of stereo spatial perception is essential. However, previous metrics failed to measure the spatial perception of audio. To this end, a metric to measure the spatial perception of audio is proposed for the first time. The proposed metric is capable of measuring the magnitude and direction of spatial perception in the temporal dimension. Further, considering its function, it is feasible to utilize it instead of demanding user studies to some extent. The proposed method achieves state-of-the-art performance on 2 datasets and 5 evaluation metrics. Qualitative experiments and user studies demonstrate that the method generates space-realistic stereo audio.
Authors: Wenshuai Xu, Zhenhui Hu, Yu Lu, Jinzhou Meng, Qingjie Liu, Yunhong Wang
The pretraining-finetuning paradigm has gained popularity in various computer vision tasks. In this paradigm, the emergence of active finetuning arises due to the abundance of large-scale data and costly annotation requirements. Active finetuning involves selecting a subset of data from an unlabeled pool for annotation, facilitating subsequent finetuning. However, the use of a limited number of training samples can lead to a biased distribution, potentially resulting in model overfitting. In this paper, we propose a new method called ActiveDC for the active finetuning tasks. Firstly, we select samples for annotation by optimizing the distribution similarity between the subset to be selected and the entire unlabeled pool in continuous space. Secondly, we calibrate the distribution of the selected samples by exploiting implicit category information in the unlabeled pool. The feature visualization provides an intuitive sense of the effectiveness of our approach to distribution calibration. We conducted extensive experiments on three image classification datasets with different sampling ratios. The results indicate that ActiveDC consistently outperforms the baseline performance in all image classification tasks. The improvement is particularly significant when the sampling ratio is low, with performance gains of up to 10%. Our code will be released.
Authors: Varan Singh Rohila, Neeraj Lalwani, Lochan Basyal
Early diagnosis of the cancer cells is necessary for making an effective treatment plan and for the health and safety of a patient. Nowadays, doctors usually use a histological grade that pathologists determine by performing a semi-quantitative analysis of the histopathological and cytological features of hematoxylin-eosin (HE) stained histopathological images. This research contributes a potential classification model for cancer prognosis to efficiently utilize the valuable information underlying the HE-stained histopathological images. This work uses the PatchCamelyon benchmark datasets and trains them in a multi-layer perceptron and convolution model to observe the model's performance in terms of precision, Recall, F1 Score, Accuracy, and AUC Score. The evaluation result shows that the baseline convolution model outperforms the baseline MLP model. Also, this paper introduced ResNet50 and InceptionNet models with data augmentation, where ResNet50 is able to beat the state-of-the-art model. Furthermore, the majority vote and concatenation ensemble were evaluated and provided the future direction of using transfer learning and segmentation to understand the specific features.
Authors: Evgeny Smirnov, Vasiliy Galyuk, Evgeny Lukyanets
Prototype Memory is a powerful model for face representation learning. It enables the training of face recognition models using datasets of any size, with on-the-fly generation of prototypes (classifier weights) and efficient ways of their utilization. Prototype Memory demonstrated strong results in many face recognition benchmarks. However, the algorithm of prototype generation, used in it, is prone to the problems of imperfectly calculated prototypes in case of low-quality or poorly recognizable faces in the images, selected for the prototype creation. All images of the same person, presented in the mini-batch, used with equal weights, and the resulting averaged prototype could be contaminated with imperfect embeddings of such face images. It can lead to misdirected training signals and impair the performance of the trained face recognition models. In this paper, we propose a simple and effective way to improve Prototype Memory with quality-aware prototype generation. Quality-Aware Prototype Memory uses different weights for images of different quality in the process of prototype generation. With this improvement, prototypes get more valuable information from high-quality images and less hurt by low-quality ones. We propose and compare several methods of quality estimation and usage, perform extensive experiments on the different face recognition benchmarks and demonstrate the advantages of the proposed model compared to the basic version of Prototype Memory.
Authors: S.M. Nabil Ashraf, Md. Adyelullahil Mamun, Hasnat Md. Abdullah, Md. Golam Rabiul Alam
Chest X-rays are widely used to diagnose thoracic diseases, but the lack of detailed information about these abnormalities makes it challenging to develop accurate automated diagnosis systems, which is crucial for early detection and effective treatment. To address this challenge, we employed deep learning techniques to identify patterns in chest X-rays that correspond to different diseases. We conducted experiments on the "ChestX-ray14" dataset using various pre-trained CNNs, transformers, hybrid(CNN+Transformer) models and classical models. The best individual model was the CoAtNet, which achieved an area under the receiver operating characteristic curve (AUROC) of 84.2%. By combining the predictions of all trained models using a weighted average ensemble where the weight of each model was determined using differential evolution, we further improved the AUROC to 85.4%, outperforming other state-of-the-art methods in this field. Our findings demonstrate the potential of deep learning techniques, particularly ensemble deep learning, for improving the accuracy of automatic diagnosis of thoracic diseases from chest X-rays.
Authors: Maximilian Luz, Rohit Mohan, Ahmed Rida Sekkat, Oliver Sawade, Elmar Matthes, Thomas Brox, Abhinav Valada
Optical flow estimation is very challenging in situations with transparent or occluded objects. In this work, we address these challenges at the task level by introducing Amodal Optical Flow, which integrates optical flow with amodal perception. Instead of only representing the visible regions, we define amodal optical flow as a multi-layered pixel-level motion field that encompasses both visible and occluded regions of the scene. To facilitate research on this new task, we extend the AmodalSynthDrive dataset to include pixel-level labels for amodal optical flow estimation. We present several strong baselines, along with the Amodal Flow Quality metric to quantify the performance in an interpretable manner. Furthermore, we propose the novel AmodalFlowNet as an initial step toward addressing this task. AmodalFlowNet consists of a transformer-based cost-volume encoder paired with a recurrent transformer decoder which facilitates recurrent hierarchical feature propagation and amodal semantic grounding. We demonstrate the tractability of amodal optical flow in extensive experiments and show its utility for downstream tasks such as panoptic tracking. We make the dataset, code, and trained models publicly available at this http URL
Authors: Egemen İşgüder, Özlem Durmaz İncel
Motion sensors integrated into wearable and mobile devices provide valuable information about the device users. Machine learning and, recently, deep learning techniques have been used to characterize sensor data. Mostly, a single task, such as recognition of activities, is targeted, and the data is processed centrally at a server or in a cloud environment. However, the same sensor data can be utilized for multiple tasks and distributed machine-learning techniques can be used without the requirement of the transmission of data to a centre. This paper explores Federated Transfer Learning in a Multi-Task manner for both sensor-based human activity recognition and device position identification tasks. The OpenHAR framework is used to train the models, which contains ten smaller datasets. The aim is to obtain model(s) applicable for both tasks in different datasets, which may include only some label types. Multiple experiments are carried in the Flower federated learning environment using the DeepConvLSTM architecture. Results are presented for federated and centralized versions under different parameters and restrictions. By utilizing transfer learning and training a task-specific and personalized federated model, we obtained a similar accuracy with training each client individually and higher accuracy than a fully centralized approach.
Authors: Dota Tianai Dong, Mariya Toneva
Integrating information from multiple modalities is arguably one of the essential prerequisites for grounding artificial intelligence systems with an understanding of the real world. Recent advances in video transformers that jointly learn from vision, text, and sound over time have made some progress toward this goal, but the degree to which these models integrate information from modalities still remains unclear. In this work, we present a promising approach for probing a pre-trained multimodal video transformer model by leveraging neuroscientific evidence of multimodal information processing in the brain. Using brain recordings of participants watching a popular TV show, we analyze the effects of multi-modal connections and interactions in a pre-trained multi-modal video transformer on the alignment with uni- and multi-modal brain regions. We find evidence that vision enhances masked prediction performance during language processing, providing support that cross-modal representations in models can benefit individual modalities. However, we don't find evidence of brain-relevant information captured by the joint multi-modal transformer representations beyond that captured by all of the individual modalities. We finally show that the brain alignment of the pre-trained joint representation can be improved by fine-tuning using a task that requires vision-language inferences. Overall, our results paint an optimistic picture of the ability of multi-modal transformers to integrate vision and language in partially brain-relevant ways but also show that improving the brain alignment of these models may require new approaches.
Authors: Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr
Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user. Many solutions are proposed to resolve this catastrophic forgetting in a centralized setting. However, they do not apply directly to FL because of its unique complexities, such as privacy concerns and resource limitations. To overcome these challenges, this paper presents a framework for \textbf{federated class incremental learning} that utilizes a generative model to synthesize samples from past distributions. This data can be later exploited alongside the training data to mitigate catastrophic forgetting. To preserve privacy, the generative model is trained on the server using data-free methods at the end of each task without requesting data from clients. Moreover, our solution does not demand the users to store old data or models, which gives them the freedom to join/leave the training at any time. Additionally, we introduce SuperImageNet, a new regrouping of the ImageNet dataset specifically tailored for federated continual learning. We demonstrate significant improvements compared to existing baselines through extensive experiments on multiple datasets.
Authors: Anders Vestergaard Nørskov, Alexander Neergaard Zahid, Morten Mørup
Electroencephalography (EEG) is a prominent non-invasive neuroimaging technique providing insights into brain function. Unfortunately, EEG data exhibit a high degree of noise and variability across subjects hampering generalizable signal extraction. Therefore, a key aim in EEG analysis is to extract the underlying neural activation (content) as well as to account for the individual subject variability (style). We hypothesize that the ability to convert EEG signals between tasks and subjects requires the extraction of latent representations accounting for content and style. Inspired by recent advancements in voice conversion technologies, we propose a novel contrastive split-latent permutation autoencoder (CSLP-AE) framework that directly optimizes for EEG conversion. Importantly, the latent representations are guided using contrastive learning to promote the latent splits to explicitly represent subject (style) and task (content). We contrast CSLP-AE to conventional supervised, unsupervised (AE), and self-supervised (contrastive learning) training and find that the proposed approach provides favorable generalizable characterizations of subject and task. Importantly, the procedure also enables zero-shot conversion between unseen subjects. While the present work only considers conversion of EEG, the proposed CSLP-AE provides a general framework for signal conversion and extraction of content (task activation) and style (subject variability) components of general interest for the modeling and analysis of biological signals.
Authors: Hao Li, Han Liu, Dewei Hu, Jiacheng Wang, Ipek Oguz
Interactive segmentation model leverages prompts from users to produce robust segmentation. This advancement is facilitated by prompt engineering, where interactive prompts serve as strong priors during test-time. However, this is an inherently subjective and hard-to-reproduce process. The variability in user expertise and inherently ambiguous boundaries in medical images can lead to inconsistent prompt selections, potentially affecting segmentation accuracy. This issue has not yet been extensively explored for medical imaging. In this paper, we assess the test-time variability for interactive medical image segmentation with diverse point prompts. For a given target region, the point is classified into three sub-regions: boundary, margin, and center. Our goal is to identify a straightforward and efficient approach for optimal prompt selection during test-time based on three considerations: (1) benefits of additional prompts, (2) effects of prompt placement, and (3) strategies for optimal prompt selection. We conduct extensive experiments on the public Medical Segmentation Decathlon dataset for challenging colon tumor segmentation task. We suggest an optimal strategy for prompt selection during test-time, supported by comprehensive results. The code is publicly available at https://github.com/MedICL-VU/variability
Authors: Natasha Krell, Will Gleave, Daniel Nakada, Justin Downes, Amanda Willet, Matthew Baran
Cell phone coverage and high-speed service gaps persist in rural areas in sub-Saharan Africa, impacting public access to mobile-based financial, educational, and humanitarian services. Improving maps of telecommunications infrastructure can help inform strategies to eliminate gaps in mobile coverage. Deep neural networks, paired with remote sensing images, can be used for object detection of cell towers and eliminate the need for inefficient and burdensome manual mapping to find objects over large geographic regions. In this study, we demonstrate a partially automated workflow to train an object detection model to locate cell towers using OpenStreetMap (OSM) features and high-resolution Maxar imagery. For model fine-tuning and evaluation, we curated a diverse dataset of over 6,000 unique images of cell towers in 26 countries in eastern, southern, and central Africa using automatically generated annotations from OSM points. Our model achieves an average precision at 50% Intersection over Union (IoU) (AP@50) of 81.2 with good performance across different geographies and out-of-sample testing. Accurate localization of cell towers can yield more accurate cell coverage maps, in turn enabling improved delivery of digital services for decision-support applications.
Authors: Thao Nguyen, Simon Kornblith
Neural network representations contain structure beyond what was present in the training labels. For instance, representations of images that are visually or semantically similar tend to lie closer to each other than to dissimilar images, regardless of their labels. Clustering these representations can thus provide insights into dataset properties as well as the network internals. In this work, we study how the many design choices involved in neural network training affect the clusters formed in the hidden representations. To do so, we establish an evaluation setup based on the BREEDS hierarchy, for the task of subclass clustering after training models with only superclass information. We isolate the training dataset and architecture as important factors affecting clusterability. Datasets with labeled classes consisting of unrelated subclasses yield much better clusterability than those following a natural hierarchy. When using pretrained models to cluster representations on downstream datasets, models pretrained on subclass labels provide better clusterability than models pretrained on superclass labels, but only when there is a high degree of domain overlap between the pretraining and downstream data. Architecturally, we find that normalization strategies affect which layers yield the best clustering performance, and, surprisingly, Vision Transformers attain lower subclass clusterability than ResNets.
Authors: Hao Quan, Xinjia Li, Dayu Hu, Tianhang Nan, Xiaoyu Cui
In pathology, the rarity of certain diseases and the complexity in annotating pathological images significantly hinder the creation of extensive, high-quality datasets. This limitation impedes the progress of deep learning-assisted diagnostic systems in pathology. Consequently, it becomes imperative to devise a technology that can discern new disease categories from a minimal number of annotated examples. Such a technology would substantially advance deep learning models for rare diseases. Addressing this need, we introduce the Dual-channel Prototype Network (DCPN), rooted in the few-shot learning paradigm, to tackle the challenge of classifying pathological images with limited samples. DCPN augments the Pyramid Vision Transformer (PVT) framework for few-shot classification via self-supervised learning and integrates it with convolutional neural networks. This combination forms a dual-channel architecture that extracts multi-scale, highly precise pathological features. The approach enhances the versatility of prototype representations and elevates the efficacy of prototype networks in few-shot pathological image classification tasks. We evaluated DCPN using three publicly available pathological datasets, configuring small-sample classification tasks that mirror varying degrees of clinical scenario domain shifts. Our experimental findings robustly affirm DCPN's superiority in few-shot pathological image classification, particularly in tasks within the same domain, where it achieves the benchmarks of supervised learning.
Authors: Yunlong Zhang, Yuxuan Sun, Sunyi Zheng, Zhongyi Shui, Chenglu Zhu, Lin Yang
Although deep learning-based segmentation models have achieved impressive performance on public benchmarks, generalizing well to unseen environments remains a major challenge. To improve the model's generalization ability to the new domain during evaluation, the test-time training (TTT) is a challenging paradigm that adapts the source-pretrained model in an online fashion. Early efforts on TTT mainly focus on the image classification task. Directly extending these methods to semantic segmentation easily experiences unstable adaption due to segmentation's inherent characteristics, such as extreme class imbalance and complex decision spaces. To stabilize the adaptation process, we introduce contrastive loss (CL), known for its capability to learn robust and generalized representations. Nevertheless, the traditional CL operates in the representation space and cannot directly enhance predictions. In this paper, we resolve this limitation by adapting the CL to the output space, employing a high temperature, and simplifying the formulation, resulting in a straightforward yet effective loss function called Output Contrastive Loss (OCL). Our comprehensive experiments validate the efficacy of our approach across diverse evaluation scenarios. Notably, our method excels even when applied to models initially pre-trained using domain adaptation methods on test domain data, showcasing its resilience and adaptability.\footnote{Code and more information could be found at~ \url{https://github.com/dazhangyu123/OCL}}
Authors: Vinit Katariya, Fatema-E- Jannat, Armin Danesh Pazho, Ghazal Alinezhad Noghre, Hamed Tabkhi
Vehicle anomaly detection plays a vital role in highway safety applications such as accident prevention, rapid response, traffic flow optimization, and work zone safety. With the surge of the Internet of Things (IoT) in recent years, there has arisen a pressing demand for Artificial Intelligence (AI) based anomaly detection methods designed to meet the requirements of IoT devices. Catering to this futuristic vision, we introduce a lightweight approach to vehicle anomaly detection by utilizing the power of trajectory prediction. Our proposed design identifies vehicles deviating from expected paths, indicating highway risks from different camera-viewing angles from real-world highway datasets. On top of that, we present VegaEdge - a sophisticated AI confluence designed for real-time security and surveillance applications in modern highway settings through edge-centric IoT-embedded platforms equipped with our anomaly detection approach. Extensive testing across multiple platforms and traffic scenarios showcases the versatility and effectiveness of VegaEdge. This work also presents the Carolinas Anomaly Dataset (CAD), to bridge the existing gap in datasets tailored for highway anomalies. In real-world scenarios, our anomaly detection approach achieves an AUC-ROC of 0.94, and our proposed VegaEdge design, on an embedded IoT platform, processes 738 trajectories per second in a typical highway setting. The dataset is available at https://github.com/TeCSAR-UNCC/Carolinas_Dataset#chd-anomaly-test-set .
Authors: Minghua Liu, Ruoxi Shi, Linghao Chen, Zhuoyang Zhang, Chao Xu, Xinyue Wei, Hansheng Chen, Chong Zeng, Jiayuan Gu, Hao Su
Recent advancements in open-world 3D object generation have been remarkable, with image-to-3D methods offering superior fine-grained control over their text-to-3D counterparts. However, most existing models fall short in simultaneously providing rapid generation speeds and high fidelity to input images - two features essential for practical applications. In this paper, we present One-2-3-45++, an innovative method that transforms a single image into a detailed 3D textured mesh in approximately one minute. Our approach aims to fully harness the extensive knowledge embedded in 2D diffusion models and priors from valuable yet limited 3D data. This is achieved by initially finetuning a 2D diffusion model for consistent multi-view image generation, followed by elevating these images to 3D with the aid of multi-view conditioned 3D native diffusion models. Extensive experimental evaluations demonstrate that our method can produce high-quality, diverse 3D assets that closely mirror the original input image. Our project webpage: https://sudo-ai-3d.github.io/One2345plus_page.
Authors: Jingchen Ni, Haoru Li, Lilin Xu, Jing Liang
Constructing a high-performance target detector under the background of sea clutter is always necessary and important. In this work, we propose a RepVGGA0-CWT detector, where RepVGG is a residual network that gains a high detection accuracy. Different from traditional residual networks, RepVGG keeps an acceptable calculation speed. Giving consideration to both accuracy and speed, the RepVGGA0 is selected among all the variants of RepVGG. Also, continuous wavelet transform (CWT) is employed to extract the radar echoes' time-frequency feature effectively. In the tests, other networks (ResNet50, ResNet18 and AlexNet) and feature extraction methods (short-time Fourier transform (STFT), CWT) are combined to build detectors for comparison. The result of different datasets shows that the RepVGGA0-CWT detector performs better than those detectors in terms of low controllable false alarm rate, high training speed, high inference speed and low memory usage. This RepVGGA0-CWT detector is hardware-friendly and can be applied in real-time scenes for its high inference speed in detection.
Authors: Shashank Kotyan, Danilo Vasconcellos Vargas
Neural networks have revolutionized various domains, exhibiting remarkable accuracy in tasks like natural language processing and computer vision. However, their vulnerability to slight alterations in input samples poses challenges, particularly in safety-critical applications like autonomous driving. Current approaches, such as introducing distortions during training, fall short in addressing unforeseen corruptions. This paper proposes an innovative adversarial contrastive learning framework to enhance neural network robustness simultaneously against adversarial attacks and common corruptions. By generating instance-wise adversarial examples and optimizing contrastive loss, our method fosters representations that resist adversarial perturbations and remain robust in real-world scenarios. Subsequent contrastive learning then strengthens the similarity between clean samples and their adversarial counterparts, fostering representations resistant to both adversarial attacks and common distortions. By focusing on improving performance under adversarial and real-world conditions, our approach aims to bolster the robustness of neural networks in safety-critical applications, such as autonomous vehicles navigating unpredictable weather conditions. We anticipate that this framework will contribute to advancing the reliability of neural networks in challenging environments, facilitating their widespread adoption in mission-critical scenarios.
Authors: Chenjie Zhao, Ryan Wen Liu, Jingxiang Qu, Ruobin Gao
With the advancement of maritime unmanned aerial vehicles (UAVs) and deep learning technologies, the application of UAV-based object detection has become increasingly significant in the fields of maritime industry and ocean engineering. Endowed with intelligent sensing capabilities, the maritime UAVs enable effective and efficient maritime surveillance. To further promote the development of maritime UAV-based object detection, this paper provides a comprehensive review of challenges, relative methods, and UAV aerial datasets. Specifically, in this work, we first briefly summarize four challenges for object detection on maritime UAVs, i.e., object feature diversity, device limitation, maritime environment variability, and dataset scarcity. We then focus on computational methods to improve maritime UAV-based object detection performance in terms of scale-aware, small object detection, view-aware, rotated object detection, lightweight methods, and others. Next, we review the UAV aerial image/video datasets and propose a maritime UAV aerial dataset named MS2ship for ship detection. Furthermore, we conduct a series of experiments to present the performance evaluation and robustness analysis of object detection methods on maritime datasets. Eventually, we give the discussion and outlook on future works for maritime UAV-based object detection. The MS2ship dataset is available at \href{https://github.com/zcj234/MS2ship}{https://github.com/zcj234/MS2ship}.
Authors: Wenxi Zhang, Zhe Li, Weixi Li, Weisi Ma, Xinyi Chen, Sizhe Li
This paper introduces a robust, learning-based method for diagnosing the state of distribution network switchgear, which is crucial for maintaining the power quality for end users. Traditional diagnostic models often rely heavily on expert knowledge and lack robustness. To address this, our method incorporates an expanded feature vector that includes environmental data, temperature readings, switch position, motor operation, insulation conditions, and local discharge information. We tackle the issue of high dimensionality through feature mapping. The method introduces a decision radius to categorize unlabeled samples and updates the model parameters using a combination of supervised and unsupervised loss, along with a consistency regularization function. This approach ensures robust learning even with a limited number of labeled samples. Comparative analysis demonstrates that this method significantly outperforms existing models in both accuracy and robustness.
Authors: Martin Cubaud (LaSTIG), Arnaud Le Bris (LaSTIG), Laurence Jolivet (LaSTIG), Ana-Maria Olteanu-Raimond (LaSTIG)
Accurate land use maps, describing the territory from an anthropic utilisation point of view, are useful tools for land management and planning. To produce them, the use of optical images alone remains limited. It is therefore necessary to make use of several heterogeneous sources, each carrying complementary or contradictory information due to their imperfections or their different specifications. This study compares two different approaches i.e. a pre-classification and a post-classification fusion approach for combining several sources of spatial data in the context of land use classification. The approaches are applied on authoritative land use data located in the Gers department in the southwest of France. Pre-classification fusion, while not explicitly modeling imperfections, has the best final results, reaching an overall accuracy of 97% and a macro-mean F1 score of 88%.
Authors: Dimitri Gominski, Ankit Kariryaa, Martin Brandt, Christian Igel, Sizhuo Li, Maurice Mugabowindekwe, Rasmus Fensholt
There is a rising interest in mapping trees using satellite or aerial imagery, but there is no standardized evaluation protocol for comparing and enhancing methods. In dense canopy areas, the high variability of tree sizes and their spatial proximity makes it arduous to define the quality of the predictions. Concurrently, object-centric approaches such as bounding box detection usuallyperform poorly on small and dense objects. It thus remains unclear what is the ideal framework for individual tree mapping, in regards to detection and segmentation approaches, convolutional neural networks and transformers. In this paper, we introduce an evaluation framework suited for individual tree mapping in any physical environment, with annotation costs and applicative goals in mind. We review and compare different approaches and deep architectures, and introduce a new method that we experimentally prove to be a good compromise between segmentation and detection.
Authors: Dalong Zheng, Zebin Wu, Jia Liu, Chih-Cheng Hung, Zhihui Wei
Change detection has always been a concerned task in the interpretation of remote sensing images. It is essentially a unique binary classification task with two inputs, and there is a change relationship between these two inputs. At present, the mining of change relationship features is usually implicit in the network architectures that contain single-branch or two-branch encoders. However, due to the lack of artificial prior design for change relationship features, these networks cannot learn enough change semantic information and lose more accurate change detection performance. So we propose a network architecture NAME for the explicit mining of change relation features. In our opinion, the change features of change detection should be divided into pre-changed image features, post-changed image features and change relation features. In order to fully mine these three kinds of change features, we propose the triple branch network combining the transformer and convolutional neural network (CNN) to extract and fuse these change features from two perspectives of global information and local information, respectively. In addition, we design the continuous change relation (CCR) branch to further obtain the continuous and detail change relation features to improve the change discrimination capability of the model. The experimental results show that our network performs better, in terms of F1, IoU, and OA, than those of the existing advanced networks for change detection on four public very high-resolution (VHR) remote sensing datasets. Our source code is available at https://github.com/DalongZ/NAME.
Authors: Zhihang Zhong, Gurunandan Krishnan, Xiao Sun, Yu Qiao, Sizhuo Ma, Jian Wang
Existing video frame interpolation (VFI) methods blindly predict where each object is at a specific timestep t ("time indexing"), which struggles to predict precise object movements. Given two images of a baseball, there are infinitely many possible trajectories: accelerating or decelerating, straight or curved. This often results in blurry frames as the method averages out these possibilities. Instead of forcing the network to learn this complicated time-to-location mapping implicitly together with predicting the frames, we provide the network with an explicit hint on how far the object has traveled between start and end frames, a novel approach termed "distance indexing". This method offers a clearer learning goal for models, reducing the uncertainty tied to object speeds. We further observed that, even with this extra guidance, objects can still be blurry especially when they are equally far from both input frames (i.e., halfway in-between), due to the directional ambiguity in long-range motion. To solve this, we propose an iterative reference-based estimation strategy that breaks down a long-range prediction into several short-range steps. When integrating our plug-and-play strategies into state-of-the-art learning-based models, they exhibit markedly sharper outputs and superior perceptual quality in arbitrary time interpolations, using a uniform distance indexing map in the same format as time indexing. Additionally, distance indexing can be specified pixel-wise, which enables temporal manipulation of each object independently, offering a novel tool for video editing tasks like re-timing.
Authors: Jiarui Hu, Mao Mao, Hujun Bao, Guofeng Zhang, Zhaopeng Cui
This paper presents a collaborative implicit neural simultaneous localization and mapping (SLAM) system with RGB-D image sequences, which consists of complete front-end and back-end modules including odometry, loop detection, sub-map fusion, and global refinement. In order to enable all these modules in a unified framework, we propose a novel neural point based 3D scene representation in which each point maintains a learnable neural feature for scene encoding and is associated with a certain keyframe. Moreover, a distributed-to-centralized learning strategy is proposed for the collaborative implicit SLAM to improve consistency and cooperation. A novel global optimization framework is also proposed to improve the system accuracy like traditional bundle adjustment. Experiments on various datasets demonstrate the superiority of the proposed method in both camera tracking and mapping.
Authors: Tao Song, Ruizhi Hou, Lisong Dai, Lei Xiang
Image quality assessment (IQA) plays a critical role in optimizing radiation dose and developing novel medical imaging techniques in computed tomography (CT). Traditional IQA methods relying on hand-crafted features have limitations in summarizing the subjective perceptual experience of image quality. Recent deep learning-based approaches have demonstrated strong modeling capabilities and potential for medical IQA, but challenges remain regarding model generalization and perceptual accuracy. In this work, we propose a multi-scale distributions regression approach to predict quality scores by constraining the output distribution, thereby improving model generalization. Furthermore, we design a dual-branch alignment network to enhance feature extraction capabilities. Additionally, semi-supervised learning is introduced by utilizing pseudo-labels for unlabeled data to guide model training. Extensive qualitative experiments demonstrate the effectiveness of our proposed method for advancing the state-of-the-art in deep learning-based medical IQA. Code is available at: https://github.com/zunzhumu/MD-IQA.
Authors: Wenyun Li, Chi-Man Pun
Glaucoma is a chronic neurodegenerative condition that can lead to blindness. Early detection and curing are very important in stopping the disease from getting worse for glaucoma patients. The 2D fundus images and optical coherence tomography(OCT) are useful for ophthalmologists in diagnosing glaucoma. There are many methods based on the fundus images or 3D OCT volumes; however, the mining for multi-modality, including both fundus images and data, is less studied. In this work, we propose an end-to-end local and global multi-modal fusion framework for glaucoma grading, named ELF for short. ELF can fully utilize the complementary information between fundus and OCT. In addition, unlike previous methods that concatenate the multi-modal features together, which lack exploring the mutual information between different modalities, ELF can take advantage of local-wise and global-wise mutual information. The extensive experiment conducted on the multi-modal glaucoma grading GAMMA dataset can prove the effiectness of ELF when compared with other state-of-the-art methods.
Authors: Pierre-François De Plaen, Nicola Marinello, Marc Proesmans, Tinne Tuytelaars, Luc Van Gool
The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to perform Multi-Object Tracking (MOT), resulting in more complicated architectures. We instead show how DETR can be turned into a MOT model by employing an instance-level contrastive loss, a revised sampling strategy and a lightweight assignment method. Our training scheme learns object appearances while preserving detection capabilities and with little overhead. Its performance surpasses the previous state-of-the-art by +2.6 mMOTA on the challenging BDD100K dataset and is comparable to existing transformer-based methods on the MOT17 dataset.
Authors: Peng Jin, Ryuichi Takanobu, Caiwan Zhang, Xiaochun Cao, Li Yuan
Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a unified vision-language model capable of comprehending and engaging in conversations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to efficiently utilize a limited number of visual tokens to simultaneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level semantic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Extensive experimental results demonstrate that Chat-UniVi, as a unified model, consistently outperforms even existing methods exclusively designed for either images or videos.
Authors: Melaku N. Getahun, Oleg Y. Rogov, Dmitry V. Dylov, Andrey Somov, Ahmed Bouridane, Rifat Hamoudi
Retinal vascular segmentation, is a widely researched subject in biomedical image processing, aims to relieve ophthalmologists' workload when treating and detecting retinal disorders. However, segmenting retinal vessels has its own set of challenges, with prior techniques failing to generate adequate results when segmenting branches and microvascular structures. The neural network approaches used recently are characterized by the inability to keep local and global properties together and the failure to capture tiny end vessels make it challenging to attain the desired result. To reduce this retinal vessel segmentation problem, we propose a full-scale micro-vessel extraction mechanism based on an encoder-decoder neural network architecture, sigmoid smoothing, and an adaptive threshold method. The network consists of of residual, encoder booster, bottleneck enhancement, squeeze, and excitation building blocks. All of these blocks together help to improve the feature extraction and prediction of the segmentation map. The proposed solution has been evaluated using the DRIVE, CHASE-DB1, and STARE datasets, and competitive results are obtained when compared with previous studies. The AUC and accuracy on the DRIVE dataset are 0.9884 and 0.9702, respectively. On the CHASE-DB1 dataset, the scores are 0.9903 and 0.9755, respectively. On the STARE dataset, the scores are 0.9916 and 0.9750, respectively. The performance achieved is one step ahead of what has been done in previous studies, and this results in a higher chance of having this solution in real-life diagnostic centers that seek ophthalmologists attention.
Authors: Hongyang Jiang, Mengdi Gao, Zirong Liu, Chen Tang, Xiaoqing Zhang, Shuai Jiang, Wu Yuan, Jiang Liu
Early-stage diabetic retinopathy (DR) presents challenges in clinical diagnosis due to inconspicuous and minute microangioma lesions, resulting in limited research in this area. Additionally, the potential of emerging foundation models, such as the segment anything model (SAM), in medical scenarios remains rarely explored. In this work, we propose a human-in-the-loop, label-free early DR diagnosis framework called GlanceSeg, based on SAM. GlanceSeg enables real-time segmentation of microangioma lesions as ophthalmologists review fundus images. Our human-in-the-loop framework integrates the ophthalmologist's gaze map, allowing for rough localization of minute lesions in fundus images. Subsequently, a saliency map is generated based on the located region of interest, which provides prompt points to assist the foundation model in efficiently segmenting microangioma lesions. Finally, a domain knowledge filter refines the segmentation of minute lesions. We conducted experiments on two newly-built public datasets, i.e., IDRiD and Retinal-Lesions, and validated the feasibility and superiority of GlanceSeg through visualized illustrations and quantitative measures. Additionally, we demonstrated that GlanceSeg improves annotation efficiency for clinicians and enhances segmentation performance through fine-tuning using annotations. This study highlights the potential of GlanceSeg-based annotations for self-model optimization, leading to enduring performance advancements through continual learning.
Authors: Virmarie Maquiling, Sean Anthony Byrne, Diederick C. Niehorster, Marcus Nyström, Enkelejda Kasneci
The advent of foundation models signals a new era in artificial intelligence. The Segment Anything Model (SAM) is the first foundation model for image segmentation. In this study, we evaluate SAM's ability to segment features from eye images recorded in virtual reality setups. The increasing requirement for annotated eye-image datasets presents a significant opportunity for SAM to redefine the landscape of data annotation in gaze estimation. Our investigation centers on SAM's zero-shot learning abilities and the effectiveness of prompts like bounding boxes or point clicks. Our results are consistent with studies in other domains, demonstrating that SAM's segmentation effectiveness can be on-par with specialized models depending on the feature, with prompts improving its performance, evidenced by an IoU of 93.34% for pupil segmentation in one dataset. Foundation models like SAM could revolutionize gaze estimation by enabling quick and easy image segmentation, reducing reliance on specialized models and extensive manual annotation.
Authors: Kaiming Cui, D. J. Armstrong, Fabo Feng
Vast amounts of astronomical photometric data are generated from various projects, requiring significant efforts to identify variable stars and other object classes. In light of this, a general, widely applicable classification framework would simplify the task of designing custom classifiers. We present a novel deep learning framework for classifying light curves using a weakly supervised object detection model. Our framework identifies the optimal windows for both light curves and power spectra automatically, and zooms in on their corresponding data. This allows for automatic feature extraction from both time and frequency domains, enabling our model to handle data across different scales and sampling intervals. We train our model on datasets obtained from both space-based and ground-based multi-band observations of variable stars and transients. We achieve an accuracy of 87% for combined variables and transient events, which is comparable to the performance of previous feature-based models. Our trained model can be utilized directly to other missions, such as ASAS-SN, without requiring any retraining or fine-tuning. To address known issues with miscalibrated predictive probabilities, we apply conformal prediction to generate robust predictive sets that guarantee true label coverage with a given probability. Additionally, we incorporate various anomaly detection algorithms to empower our model with the ability to identify out-of-distribution objects. Our framework is implemented in the Deep-LC toolkit, which is an open-source Python package hosted on Github and PyPI.
Authors: Luca H. Thoms, Karel A. Veldkamp, Hannes Rosenbusch, Claire E. Stevenson
Analogical reasoning derives information from known relations and generalizes this information to similar yet unfamiliar situations. One of the first generalized ways in which deep learning models were able to solve verbal analogies was through vector arithmetic of word embeddings, essentially relating words that were mapped to a vector space (e.g., king - man + woman = __?). In comparison, most attempts to solve visual analogies are still predominantly task-specific and less generalizable. This project focuses on visual analogical reasoning and applies the initial generalized mechanism used to solve verbal analogies to the visual realm. Taking the Abstraction and Reasoning Corpus (ARC) as an example to investigate visual analogy solving, we use a variational autoencoder (VAE) to transform ARC items into low-dimensional latent vectors, analogous to the word embeddings used in the verbal approaches. Through simple vector arithmetic, underlying rules of ARC items are discovered and used to solve them. Results indicate that the approach works well on simple items with fewer dimensions (i.e., few colors used, uniform shapes), similar input-to-output examples, and high reconstruction accuracy on the VAE. Predictions on more complex items showed stronger deviations from expected outputs, although, predictions still often approximated parts of the item's rule set. Error patterns indicated that the model works as intended. On the official ARC paradigm, the model achieved a score of 2% (cf. current world record is 21%) and on ConceptARC it scored 8.8%. Although the methodology proposed involves basic dimensionality reduction techniques and standard vector arithmetic, this approach demonstrates promising outcomes on ARC and can easily be generalized to other abstract visual reasoning tasks.
Authors: Ozge Oztimur Karadag
Skeleton-based action recognition receives the attention of many researchers as it is robust to viewpoint and illumination changes, and its processing is much more efficient than video frames. With the emergence of deep learning models, it has become very popular to represent the skeleton data in pseudo-image form and apply Convolutional Neural Networks for action recognition. Thereafter, studies concentrated on finding effective methods for forming pseudo-images. Recently, attention networks, more specifically transformers have provided promising results in various vision problems. In this study, the effectiveness of vision transformers for skeleton-based action recognition is examined and its robustness on the pseudo-image representation scheme is investigated. To this end, a three-level architecture, Act-VIT is proposed, which forms a set of pseudo images apply a classifier on each of the representation and combine their results to find the final action class. The classifiers of Act-VIT are first realized by CNNs and then by VITs and their performances are compared. Experimental studies reveal that the vision transformer is less sensitive to the initial pseudo-image representation compared to CNN. Nevertheless, even with the vision transformer, the recognition performance can be further improved by consensus of classifiers.
Authors: Zhili Chen, Maosheng Ye, Shuangjie Xu, Tongyi Cao, Qifeng Chen
Motion planning is a computational problem that finds a sequence of valid trajectories, often based on surrounding agents' forecasting, environmental understanding, and historical and future contexts. It can also be viewed as a game in which agents continuously plan their next move according to other agents' intentions and the encountering environment, further achieving their ultimate goals through incremental actions. To model the dynamic planning and interaction process, we propose a novel framework, DeepEMplanner, which takes the stepwise interaction into account for fine-grained behavior learning. The ego vehicle maximizes each step motion to reach its eventual driving outcome based on the stepwise expectation from agents and its upcoming road conditions. On the other hand, the agents also follow the same philosophy to maximize their stepwise behavior under the encountering environment and the expectations from ego and other agents. Our DeepEMplanner models the interactions among ego, agents, and the dynamic environment in an autoregressive manner by interleaving the Expectation and Maximization processes. Further, we design ego-to-agents, ego-to-map, and ego-to-BEV interaction mechanisms with hierarchical dynamic key objects attention to better model the interactions. Experiments on the nuScenes benchmark show that our approach achieves state-of-the-art results.
Authors: Jingbiao Mei, Jinghong Chen, Weizhe Lin, Bill Byrne, Marcus Tomalin
Hateful memes have emerged as a significant concern on the Internet. These memes, which are a combination of image and text, often convey messages vastly different from their individual meanings. Thus, detecting hateful memes requires the system to jointly understand the visual and textual modalities. However, our investigation reveals that the embedding space of existing CLIP-based systems lacks sensitivity to subtle differences in memes that are vital for correct hatefulness classification. To address this issue, we propose constructing a hatefulness-aware embedding space through retrieval-guided contrastive training. Specifically, we add an auxiliary loss that utilizes hard negative and pseudo-gold samples to train the embedding space. Our approach achieves state-of-the-art performance on the HatefulMemes dataset with an AUROC of 86.7. Notably, our approach outperforms much larger fine-tuned Large Multimodal Models like Flamingo and LLaVA. Finally, we demonstrate a retrieval-based hateful memes detection system, which is capable of making hatefulness classification based on data unseen in training from a database. This allows developers to update the hateful memes detection system by simply adding new data without retraining, a desirable feature for real services in the constantly-evolving landscape of hateful memes on the Internet.
Authors: Langqing Shi, Ping Zhou
Light field cameras have a wide range of uses due to their ability to simultaneously record light intensity and direction. The angular resolution of light fields is important for downstream tasks such as depth estimation, yet is often difficult to improve due to hardware limitations. Conventional methods tend to perform poorly against the challenge of large disparity in sparse light fields, while general CNNs have difficulty extracting spatial and angular features coupled together in 4D light fields. The light field disentangling mechanism transforms the 4D light field into 2D image format, which is more favorable for CNN for feature extraction. In this paper, we propose a Deep Disentangling Mechanism, which inherits the principle of the light field disentangling mechanism and further develops the design of the feature extractor and adds advanced network structure. We design a light-field reconstruction network (i.e., DDASR) on the basis of the Deep Disentangling Mechanism, and achieve SOTA performance in the experiments. In addition, we design a Block Traversal Angular Super-Resolution Strategy for the practical application of depth estimation enhancement where the input views is often higher than 2x2 in the experiments resulting in a high memory usage, which can reduce the memory usage while having a better reconstruction performance.
Authors: Jinpei Guo, Shaofeng Zhang, Runzhong Wang, Chang Liu, Junchi Yan
Vision transformers (ViTs) have recently been used for visual matching beyond object detection and segmentation. However, the original grid dividing strategy of ViTs neglects the spatial information of the keypoints, limiting the sensitivity to local information. Therefore, we propose \textbf{QueryTrans} (Query Transformer), which adopts a cross-attention module and keypoints-based center crop strategy for better spatial information extraction. We further integrate the graph attention module and devise a transformer-based graph matching approach \textbf{GMTR} (Graph Matching TRansformers) whereby the combinatorial nature of GM is addressed by a graph transformer neural GM solver. On standard GM benchmarks, GMTR shows competitive performance against the SOTA frameworks. Specifically, on Pascal VOC, GMTR achieves $\mathbf{83.6\%}$ accuracy, $\mathbf{0.9\%}$ higher than the SOTA framework. On Spair-71k, GMTR shows great potential and outperforms most of the previous works. Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80.1\%$ to $\mathbf{83.3\%}$, and BBGM from $79.0\%$ to $\mathbf{84.5\%}$. On Spair-71k, QueryTrans improves NGMv2 from $80.6\%$ to $\mathbf{82.5\%}$, and BBGM from $82.1\%$ to $\mathbf{83.9\%}$. Source code will be made publicly available.
Authors: G. N. Kimani, P. Oluwadara, P. Fashingabo, M. Busogi, E. Luhanga, K. Sowon, L. Chacha ((1) CyLab-Africa / Upanzi Network, (2) Carnegie Mellon University Africa and (3) Carnegie Mellon University Pittsburgh)
Traditional animal identification methods such as ear-tagging, ear notching, and branding have been effective but pose risks to the animal and have scalability issues. Electrical methods offer better tracking and monitoring but require specialized equipment and are susceptible to attacks. Biometric identification using time-immutable dermatoglyphic features such as muzzle prints and iris patterns is a promising solution. This project explores cattle identification using 4923 muzzle images collected from 268 beef cattle. Two deep learning classification models are implemented - wide ResNet50 and VGG16\_BN and image compression is done to lower the image quality and adapt the models to work for the African context. From the experiments run, a maximum accuracy of 99.5\% is achieved while using the wide ResNet50 model with a compression retaining 25\% of the original image. From the study, it is noted that the time required by the models to train and converge as well as recognition time are dependent on the machine used to run the model.
Authors: Yating Xu, Conghui Hu, Gim Hee Lee
Existing works on weakly-supervised audio-visual video parsing adopt hybrid attention network (HAN) as the multi-modal embedding to capture the cross-modal context. It embeds the audio and visual modalities with a shared network, where the cross-attention is performed at the input. However, such an early fusion method highly entangles the two non-fully correlated modalities and leads to sub-optimal performance in detecting single-modality events. To deal with this problem, we propose the messenger-guided mid-fusion transformer to reduce the uncorrelated cross-modal context in the fusion. The messengers condense the full cross-modal context into a compact representation to only preserve useful cross-modal information. Furthermore, due to the fact that microphones capture audio events from all directions, while cameras only record visual events within a restricted field of view, there is a more frequent occurrence of unaligned cross-modal context from audio for visual event predictions. We thus propose cross-audio prediction consistency to suppress the impact of irrelevant audio information on visual event prediction. Experiments consistently illustrate the superior performance of our framework compared to existing state-of-the-art methods.
Authors: Mirgahney Mohamed, Lourdes Agapito
We propose DynamicSurf, a model-free neural implicit surface reconstruction method for high-fidelity 3D modelling of non-rigid surfaces from monocular RGB-D video. To cope with the lack of multi-view cues in monocular sequences of deforming surfaces, one of the most challenging settings for 3D reconstruction, DynamicSurf exploits depth, surface normals, and RGB losses to improve reconstruction fidelity and optimisation time. DynamicSurf learns a neural deformation field that maps a canonical representation of the surface geometry to the current frame. We depart from current neural non-rigid surface reconstruction models by designing the canonical representation as a learned feature grid which leads to faster and more accurate surface reconstruction than competing approaches that use a single MLP. We demonstrate DynamicSurf on public datasets and show that it can optimize sequences of varying frames with $6\times$ speedup over pure MLP-based approaches while achieving comparable results to the state-of-the-art methods. Project is available at https://mirgahney.github.io//DynamicSurf.io/.
Authors: Chen Li, Yixiao Ge, Dian Li, Ying Shan
Instruction tuning is an essential supervised training phase for Large Language Models (LLMs), with the goal of enhancing LLMs' capacity to generalize instruction execution and adapt to user preferences. With the growing incorporation of multi-modal data into LLMs, there is an increasing interest in the performance of vision-language instruction tuning which presents more complex features in comparison to pure text instructions. In this paper, we systematically review the latest vision-language instruction tuning settings and datasets in multi-modal LLMs and summarize the characteristics that high-quality vision-language tuning data should have. We consider these characteristics as the foundational principles for constructing vision-language instruction data and propose a complete construction pipeline consisting of data collection, instruction generation, and quality control modules that incorporate meticulously designed instruction property evaluation indicators. We perform vision-language instruction tuning on three widely used multi-modal LLMs based on the instruction data we constructed and conduct extensive experiments on the corresponding metrics to demonstrate the rationality of the construction principles proposed in this paper. The code and dataset related to this paper have been open-sourced at \url{https://github.com/palchenli/VL-Instruction-Tuning}.
Authors: Jingru Fu, Daniel Ferreira, Örjan Smedby, Rodrigo Moreno
Alzheimer's Disease and normal aging are both characterized by brain atrophy. The question of whether AD-related brain atrophy represents accelerated aging or a neurodegeneration process distinct from that in normal aging remains unresolved. Moreover, precisely disentangling AD-related brain atrophy from normal aging in a clinical context is complex. In this study, we propose a deformation-based morphometry framework to estimate normal aging and AD-specific atrophy patterns of subjects from morphological MRI scans. We first leverage deep-learning-based methods to create age-dependent templates of cognitively normal (CN) subjects. These templates model the normal aging atrophy patterns in a CN population. Then, we use the learned diffeomorphic registration to estimate the one-year normal aging pattern at the voxel level. We register the testing image to the 60-year-old CN template in the second step. Finally, normal aging and AD-specific scores are estimated by measuring the alignment of this registration with the one-year normal aging pattern. The methodology was developed and evaluated on the OASIS3 dataset with 1,014 T1-weighted MRI scans. Of these, 326 scans were from CN subjects, and 688 scans were from individuals clinically diagnosed with AD at different stages of clinical severity defined by clinical dementia rating (CDR) scores. The results show that ventricles predominantly follow an accelerated normal aging pattern in subjects with AD. In turn, hippocampi and amygdala regions were affected by both normal aging and AD-specific factors. Interestingly, hippocampi and amygdala regions showed more of an accelerated normal aging pattern for subjects during the early clinical stages of the disease, while the AD-specific score increases in later clinical stages. Our code is freely available at https://github.com/Fjr9516/DBM_with_DL.
Authors: Yinuo Wang, Kai Chen, Weimin Yuan, Cai Meng, XiangZhi Bai
Segment Anything Model (SAM), a vision foundation model trained on large-scale annotations, has recently continued raising awareness within medical image segmentation. Despite the impressive capabilities of SAM on natural scenes, it struggles with performance decline when confronted with medical images, especially those involving blurry boundaries and highly irregular regions of low contrast. In this paper, a SAM-based parameter-efficient fine-tuning method, called SAMIHS, is proposed for intracranial hemorrhage segmentation, which is a crucial and challenging step in stroke diagnosis and surgical planning. Distinguished from previous SAM and SAM-based methods, SAMIHS incorporates parameter-refactoring adapters into SAM's image encoder and considers the efficient and flexible utilization of adapters' parameters. Additionally, we employ a combo loss that combines binary cross-entropy loss and boundary-sensitive loss to enhance SAMIHS's ability to recognize the boundary regions. Our experimental results on two public datasets demonstrate the effectiveness of our proposed method. Code is available at https://github.com/mileswyn/SAMIHS .
Authors: Robert Harb, Thomas Pock, Heimo Müller
We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment training datasets to enhance the performance of many computational pathology applications. They allow the creation of synthesized copies of datasets that can be shared without violating privacy regulations. Or they can facilitate learning representations of WSIs without requiring data annotations. Despite this variety of applications, no existing deep-learning-based method generates WSIs at their typically high resolutions. Mainly due to the high computational complexity. Therefore, we propose a novel coarse-to-fine sampling scheme to tackle image generation of high-resolution WSIs. In this scheme, we increase the resolution of an initial low-resolution image to a high-resolution WSI. Particularly, a diffusion model sequentially adds fine details to images and increases their resolution. In our experiments, we train our method with WSIs from the TCGA-BRCA dataset. Additionally to quantitative evaluations, we also performed a user study with pathologists. The study results suggest that our generated WSIs resemble the structure of real WSIs.
Authors: Xinwei Li, Li Lin, Shuai Wang, Chen Qian
Recently, multi-modal content generation has attracted lots of attention from researchers by investigating the utilization of visual instruction tuning based on large language models (LLMs). To enhance the performance and generalization ability of such LLMs, the practice of distilling knowledge from pretrained multi-modal models (a.k.a. teachers) to more compact multi-modal LLMs (students) has gained considerable interest. However, the prevailing paradigm of instructiontuning in multi-modal LLMs knowledge distillation is resource-intensive and unidirectional, neglecting the potential for mutual feedback between the student and teacher models. Thus, we propose an innovative Competitive Multi-modal Distillation framework (CoMD), which captures bidirectional feedback between teacher and student models and continually updates the multi-modal capabilities that the student model has learned. It comprises two stages: multi-modal pre-training and multi-modal competitive distillation. The first stage pre-trains the student model on a large number of filtered multi-modal datasets. The second stage facilitates a bidirectional knowledge transfer between the student and teacher models. Our experimental analysis of diverse datasets shows that our knowledge transfer method consistently improves the capabilities of the student model. Finally, the 7B-sized student model after four distillations surpassed the current state-of-the-art model LLaVA-13B on the ScienceQA and LLaVA Test dataset, also outperforms other strong baselines in the zero-shot setting.
Authors: Ziqiang Li, Chaoyue Wang, Xue Rui, Chao Xue, Jiaxu Leng, Bin Li
Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate images that closely resemble the training data while Transfer Learning (TL) methods try to improve performance by leveraging prior knowledge from GANs pre-trained on large-scale datasets. However, current TL methods may not allow for sufficient control over the degree of knowledge preservation from the source model, making them unsuitable for setups where the source and target domains are not closely related. To address this, we propose a novel pipeline called Peer is your Pillar (PIP), which combines a target few-shot dataset with a peer dataset to create a data-unbalanced conditional generation. Our approach includes a class embedding method that separates the class space from the latent space, and we use a direction loss based on pre-trained CLIP to improve image diversity. Experiments on various few-shot datasets demonstrate the advancement of the proposed PIP, especially reduces the training requirements of few-shot image generation.
Authors: Ting Wang, Weidong Chen, Yuanhe Tian, Yan Song, Zhendong Mao
Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly. Although promising results on concept prediction were obtained, the aforementioned studies normally ignore the relationship among concepts, which relies on not only objects in the image, but also word dependencies in the text, so that offers a considerable potential for improving the process of generating good descriptions. In this paper, we propose a structured concept predictor (SCP) to predict concepts and their structures, then we integrate them into captioning, so as to enhance the contribution of visual signals in this task via concepts and further use their relations to distinguish cross-modal semantics for better description generation. Particularly, we design weighted graph convolutional networks (W-GCN) to depict concept relations driven by word dependencies, and then learns differentiated contributions from these concepts for following decoding process. Therefore, our approach captures potential relations among concepts and discriminatively learns different concepts, so that effectively facilitates image captioning with inherited information across modalities. Extensive experiments and their results demonstrate the effectiveness of our approach as well as each proposed module in this work.
Authors: Zhiyun Song, Zengxin Qi, Xin Wang, Xiangyu Zhao, Zhenrong Shen, Sheng Wang, Manman Fei, Zhe Wang, Di Zang, Dongdong Chen, Linlin Yao, Qian Wang, Xuehai Wu, Lichi Zhang
Cross-modality synthesis (CMS), super-resolution (SR), and their combination (CMSR) have been extensively studied for magnetic resonance imaging (MRI). Their primary goals are to enhance the imaging quality by synthesizing the desired modality and reducing the slice thickness. Despite the promising synthetic results, these techniques are often tailored to specific tasks, thereby limiting their adaptability to complex clinical scenarios. Therefore, it is crucial to build a unified network that can handle various image synthesis tasks with arbitrary requirements of modality and resolution settings, so that the resources for training and deploying the models can be greatly reduced. However, none of the previous works is capable of performing CMS, SR, and CMSR using a unified network. Moreover, these MRI reconstruction methods often treat alias frequencies improperly, resulting in suboptimal detail restoration. In this paper, we propose a Unified Co-Modulated Alias-free framework (Uni-COAL) to accomplish the aforementioned tasks with a single network. The co-modulation design of the image-conditioned and stochastic attribute representations ensures the consistency between CMS and SR, while simultaneously accommodating arbitrary combinations of input/output modalities and thickness. The generator of Uni-COAL is also designed to be alias-free based on the Shannon-Nyquist signal processing framework, ensuring effective suppression of alias frequencies. Additionally, we leverage the semantic prior of Segment Anything Model (SAM) to guide Uni-COAL, ensuring a more authentic preservation of anatomical structures during synthesis. Experiments on three datasets demonstrate that Uni-COAL outperforms the alternatives in CMS, SR, and CMSR tasks for MR images, which highlights its generalizability to wide-range applications.
Authors: Yitao Zhu, Zhenrong Shen, Zihao Zhao, Sheng Wang, Xin Wang, Xiangyu Zhao, Dinggang Shen, Qian Wang
The common practice in developing computer-aided diagnosis (CAD) models based on transformer architectures usually involves fine-tuning from ImageNet pre-trained weights. However, with recent advances in large-scale pre-training and the practice of scaling laws, Vision Transformers (ViT) have become much larger and less accessible to medical imaging communities. Additionally, in real-world scenarios, the deployments of multiple CAD models can be troublesome due to problems such as limited storage space and time-consuming model switching. To address these challenges, we propose a new method MeLo (Medical image Low-rank adaptation), which enables the development of a single CAD model for multiple clinical tasks in a lightweight manner. It adopts low-rank adaptation instead of resource-demanding fine-tuning. By fixing the weight of ViT models and only adding small low-rank plug-ins, we achieve competitive results on various diagnosis tasks across different imaging modalities using only a few trainable parameters. Specifically, our proposed method achieves comparable performance to fully fine-tuned ViT models on four distinct medical imaging datasets using about 0.17% trainable parameters. Moreover, MeLo adds only about 0.5MB of storage space and allows for extremely fast model switching in deployment and inference. Our source code and pre-trained weights are available on our website (https://absterzhu.github.io/melo.github.io/).
Authors: Anna Reithmeir, Julia A. Schnabel, Veronika A. Zimmer
Medical image registration aims at identifying the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy. To date, the majority of the deep learning-based registration methods employ regularizers that enforce global spatial smoothness, e.g., the diffusion regularizer. However, such regularizers are not tailored to the data and might not be capable of reflecting the complex underlying deformation. In contrast, physics-inspired regularizers promote physically plausible deformations. One such regularizer is the linear elastic regularizer which models the deformation of elastic material. These regularizers are driven by parameters that define the material's physical properties. For biological tissue, a wide range of estimations of such parameters can be found in the literature and it remains an open challenge to identify suitable parameter values for successful registration. To overcome this problem and to incorporate physical properties into learning-based registration, we propose to use a hypernetwork that learns the effect of the physical parameters of a physics-inspired regularizer on the resulting spatial deformation field. In particular, we adapt the HyperMorph framework to learn the effect of the two elasticity parameters of the linear elastic regularizer. Our approach enables the efficient discovery of suitable, data-specific physical parameters at test time.
Authors: Yunjiao Zhou, Jianfei Yang, Han Zou, Lihua Xie
Recent achievements in language models have showcased their extraordinary capabilities in bridging visual information with semantic language understanding. This leads us to a novel question: can language models connect textual semantics with IoT sensory signals to perform recognition tasks, e.g., Human Activity Recognition (HAR)? If so, an intelligent HAR system with human-like cognition can be built, capable of adapting to new environments and unseen categories. This paper explores its feasibility with an innovative approach, IoT-sEnsors-language alignmEnt pre-Training (TENT), which jointly aligns textual embeddings with IoT sensor signals, including camera video, LiDAR, and mmWave. Through the IoT-language contrastive learning, we derive a unified semantic feature space that aligns multi-modal features with language embeddings, so that the IoT data corresponds to specific words that describe the IoT data. To enhance the connection between textual categories and their IoT data, we propose supplementary descriptions and learnable prompts that bring more semantic information into the joint feature space. TENT can not only recognize actions that have been seen but also ``guess'' the unseen action by the closest textual words from the feature space. We demonstrate TENT achieves state-of-the-art performance on zero-shot HAR tasks using different modalities, improving the best vision-language models by over 12%.
Authors: Dana Weitzner, Raja Giryes
The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input.
In this work, we aim at explaining this vulnerability through the framework of sparsity.
We show the connection between adversarial attacks and sparse representations, with a focus on explaining the universality and transferability of adversarial examples in neural networks.
To this end, we show that sparse coding algorithms, and the neural network-based learned iterative shrinkage thresholding algorithm (LISTA) among them, suffer from this sensitivity, and that common attacks on neural networks can be expressed as attacks on the sparse representation of the input image. The phenomenon that we observe holds true also when the network is agnostic to the sparse representation and dictionary, and thus can provide a possible explanation for the universality and transferability of adversarial attacks.
The code is available at https://github.com/danawr/adversarial_attacks_and_sparse_representations.
Authors: Nodar Gogoberidze, Beth A. Cimini
Segmentation, or the outlining of objects within images, is a critical step in the measurement and analysis of cells within microscopy images. While improvements continue to be made in tools that rely on classical methods for segmentation, deep learning-based tools increasingly dominate advances in the technology. Specialist models such as Cellpose continue to improve in accuracy and user-friendliness, and segmentation challenges such as the Multi-Modality Cell Segmentation Challenge continue to push innovation in accuracy across widely-varying test data as well as efficiency and usability. Increased attention on documentation, sharing, and evaluation standards are leading to increased user-friendliness and acceleration towards the goal of a truly universal method.
Authors: James Baker
We propose a novel method for generating abstract art. First an autoencoder is trained to encode and decode the style representations of images, which are extracted from source images with a pretrained VGG network. Then, the decoder component of the autoencoder is extracted and used as a generator in a GAN. The generator works with an ensemble of discriminators. Each discriminator takes different style representations of the same images, and the generator is trained to create images that create convincing style representations in order to deceive all of the generators. The generator is also trained to maximize a diversity term. The resulting images had a surreal, geometric quality. We call our approach ARTEMIS (ARTistic Encoder- Multi- Discriminators Including Self-Attention), as it uses the self-attention layers and an encoder-decoder architecture.
Authors: Dennis Grinwald, Kirill Bykov, Shinichi Nakajima, Marina M.-C. Höhne
Explainable Artificial Intelligence (XAI) aims to make learning machines less opaque, and offers researchers and practitioners various tools to reveal the decision-making strategies of neural networks. In this work, we investigate how XAI methods can be used for exploring and visualizing the diversity of feature representations learned by Bayesian Neural Networks (BNNs). Our goal is to provide a global understanding of BNNs by making their decision-making strategies a) visible and tangible through feature visualizations and b) quantitatively measurable with a distance measure learned by contrastive learning. Our work provides new insights into the \emph{posterior} distribution in terms of human-understandable feature information with regard to the underlying decision making strategies. The main findings of our work are the following: 1) global XAI methods can be applied to explain the diversity of decision-making strategies of BNN instances, 2) Monte Carlo dropout with commonly used Dropout rates exhibit increased diversity in feature representations compared to the multimodal posterior approximation of MultiSWAG, 3) the diversity of learned feature representations highly correlates with the uncertainty estimate for the output and 4) the inter-mode diversity of the multimodal posterior decreases as the network width increases, while the intra mode diversity increases. These findings are consistent with the recent Deep Neural Networks theory, providing additional intuitions about what the theory implies in terms of humanly understandable concepts.
Authors: Daniele Ravi (for the Alzheimer's Disease Neuroimaging Initiative), Frederik Barkhof, Daniel C. Alexander, Lemuel Puglisi, Geoffrey JM Parker, Arman Eshaghi
Large medical imaging data sets are becoming increasingly available, but ensuring sample quality without significant artefacts is challenging. Existing methods for identifying imperfections in medical imaging rely on data-intensive approaches, compounded by a scarcity of artefact-rich scans for training machine learning models in clinical research. To tackle this problem, we propose a framework with four main components: 1) artefact generators inspired by magnetic resonance physics to corrupt brain MRI scans and augment a training dataset, 2) abstract and engineered features to represent images compactly, 3) a feature selection process depending on the artefact class to improve classification, and 4) SVM classifiers to identify artefacts. Our contributions are threefold: first, physics-based artefact generators produce synthetic brain MRI scans with controlled artefacts for data augmentation. This will avoid the labour-intensive collection and labelling process of scans with rare artefacts. Second, we propose a pool of abstract and engineered image features to identify 9 different artefacts for structural MRI. Finally, we use an artefact-based feature selection block that, for each class of artefacts, finds the set of features providing the best classification performance. We performed validation experiments on a large data set of scans with artificially-generated artefacts, and in a multiple sclerosis clinical trial where real artefacts were identified by experts, showing that the proposed pipeline outperforms traditional methods. In particular, our data augmentation increases performance by up to 12.5 percentage points on accuracy, precision, and recall. The computational efficiency of our pipeline enables potential real-time deployment, promising high-throughput clinical applications through automated image-processing pipelines driven by quality control systems.
Authors: Rushi Jiao, Yichi Zhang, Le Ding, Rong Cai, Jicong Zhang
Medical image segmentation is a fundamental and critical step in many image-guided clinical approaches. Recent success of deep learning-based segmentation methods usually relies on a large amount of labeled data, which is particularly difficult and costly to obtain especially in the medical imaging domain where only experts can provide reliable and accurate annotations. Semi-supervised learning has emerged as an appealing strategy and been widely applied to medical image segmentation tasks to train deep models with limited annotations. In this paper, we present a comprehensive review of recently proposed semi-supervised learning methods for medical image segmentation and summarized both the technical novelties and empirical results. Furthermore, we analyze and discuss the limitations and several unsolved problems of existing approaches. We hope this review could inspire the research community to explore solutions for this challenge and further promote the developments in medical image segmentation field.
Authors: Minghui Zhang, Guang-Zhong Yang, Yun Gu
Detailed pulmonary airway segmentation is a clinically important task for endobronchial intervention and treatment of peripheral located lung cancer lesions. Convolutional Neural Networks (CNNs) are promising tools for medical image analysis but have been performing poorly for cases when existing a significant imbalanced feature distribution, which is true for the airway data as the trachea and principal bronchi dominate most of the voxels whereas the lobar bronchi and distal segmental bronchi occupy a small proportion. In this paper, we propose a Differentiable Topology-Preserved Distance Transform (DTPDT) framework to improve the performance of airway segmentation. A Topology-Preserved Surrogate (TPS) learning strategy is first proposed to balance the training progress within-class distribution. Furthermore, a Convolutional Distance Transform (CDT) is designed to identify the breakage phenomenon with superior sensitivity and minimize the variation of the distance map between the predictionand ground-truth. The proposed method is validated with the publically available reference airway segmentation datasets. The detected rate of branch and length on public EXACT'09 and BAS datasets are 82.1%/79.6% and 96.5%/91.5% respectively, demonstrating the reliability and efficiency of the method in terms of improving the topology completeness of the segmentation performance while maintaining the overall topology accuracy.
Authors: Ananda Padhmanabhan Suresh, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly, Ukrit Watchareeruetai, Aubin Samacoits
In recent years, language-driven artistic style transfer has emerged as a new type of style transfer technique, eliminating the need for a reference style image by using natural language descriptions of the style. The first model to achieve this, called CLIPstyler, has demonstrated impressive stylisation results. However, its lengthy optimisation procedure at runtime for each query limits its suitability for many practical applications. In this work, we present FastCLIPstyler, a generalised text-based image style transfer model capable of stylising images in a single forward pass for arbitrary text inputs. Furthermore, we introduce EdgeCLIPstyler, a lightweight model designed for compatibility with resource-constrained devices. Through quantitative and qualitative comparisons with state-of-the-art approaches, we demonstrate that our models achieve superior stylisation quality based on measurable metrics while offering significantly improved runtime efficiency, particularly on edge devices.
Authors: Chenyang Lei, Xudong Jiang, Qifeng Chen
We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. This flash-only image is visually reflection-free and thus can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR. We extend our approach to handheld photography to address the misalignment between the flash and no-flash pair. With misaligned training data and the alignment module, our aligned model outperforms our previous version by more than 3.19dB in PSNR on a misaligned dataset. We also study using linear RGB images as training data. Our source code and dataset are publicly available at https://github.com/ChenyangLEI/flash-reflection-removal.
Authors: Jingang Qu, Thibault Faney, Ze Wang, Patrick Gallinari, Soleiman Yousef, Jean-Charles de Hemptinne
Due to domain shifts, machine learning systems typically struggle to generalize well to new domains that differ from those of training data, which is what domain generalization (DG) aims to address. Although a variety of DG methods have been proposed, most of them fall short in interpretability and require domain labels, which are not available in many real-world scenarios. This paper presents a novel DG method, called HMOE: Hypernetwork-based Mixture of Experts (MoE), which does not rely on domain labels and is more interpretable. MoE proves effective in identifying heterogeneous patterns in data. For the DG problem, heterogeneity arises exactly from domain shifts. HMOE employs hypernetworks taking vectors as input to generate the weights of experts, which promotes knowledge sharing among experts and enables the exploration of their similarities in a low-dimensional vector space. We benchmark HMOE against other DG methods under a fair evaluation framework -- DomainBed. Our extensive experiments show that HMOE can effectively separate mixed-domain data into distinct clusters that are surprisingly more consistent with human intuition than original domain labels. Using self-learned domain information, HMOE achieves state-of-the-art results on most datasets and significantly surpasses other DG methods in average accuracy across all datasets.
Authors: Kenan Jiang, Xuehai He, Ruize Xu, Xin Eric Wang
Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text matching -- a more challenging image and text matching task requiring the model understanding of compositional word concepts and visual components. Towards better compositional generalization in zero-shot image and text matching, in this paper, we study the problem from a causal perspective: the erroneous semantics of individual entities are essentially confounders that cause the matching failure. Therefore, we propose a novel \textbf{\textit{training-free}} compositional CLIP model (ComCLIP). ComCLIP disentangles input images into subjects, objects, and action sub-images and composes CLIP's vision encoder and text encoder to perform evolving matching over compositional text embedding and sub-image embeddings. In this way, ComCLIP can mitigate spurious correlations introduced by the pretrained CLIP models and dynamically evaluate the importance of each component. Experiments on four compositional image-text matching datasets: SVO, ComVG, Winoground, and VL-checklist, and two general image-text retrieval datasets: Flick30K, and MSCOCO demonstrate the effectiveness of our plug-and-play method, which boosts the \textbf{\textit{zero-shot}} inference ability of CLIP, SLIP, and BLIP2 even without further training or fine-tuning. Our codes can be found at https://github.com/eric-ai-lab/ComCLIP.
Authors: Jiaqi Guo, Amy R. Reibman, Edward J. Delp
Unsupervised domain adaptive (UDA) person re-identification (re-ID) aims to learn identity information from labeled images in source domains and apply it to unlabeled images in a target domain. One major issue with many unsupervised re-identification methods is that they do not perform well relative to large domain variations such as illumination, viewpoint, and occlusions. In this paper, we propose a Synthesis Model Bank (SMB) to deal with illumination variation in unsupervised person re-ID. The proposed SMB consists of several convolutional neural networks (CNN) for feature extraction and Mahalanobis matrices for distance metrics. They are trained using synthetic data with different illumination conditions such that their synergistic effect makes the SMB robust against illumination variation. To better quantify the illumination intensity and improve the quality of synthetic images, we introduce a new 3D virtual-human dataset for GAN-based image synthesis. From our experiments, the proposed SMB outperforms other synthesis methods on several re-ID benchmarks.
Authors: Bo Han, Yitong Fu, Yixuan Shen
Semantic-driven 3D shape generation aims to generate 3D objects conditioned on text. Previous works face problems with single-category generation, low-frequency 3D details, and requiring a large number of paired datasets for training. To tackle these challenges, we propose a multi-category conditional diffusion model. Specifically, 1) to alleviate the problem of lack of large-scale paired data, we bridge the text, 2D image and 3D shape based on the pre-trained CLIP model, and 2) to obtain the multi-category 3D shape feature, we apply the conditional flow model to generate 3D shape vector conditioned on CLIP embedding. 3) to generate multi-category 3D shape, we employ the hidden-layer diffusion model conditioned on the multi-category shape vector, which greatly reduces the training time and memory consumption.
Authors: Hongkang Li, Meng Wang, Sijia Liu, Pin-yu Chen
Vision Transformers (ViTs) with self-attention modules have recently achieved great empirical success in many vision tasks. Due to non-convex interactions across layers, however, theoretical learning and generalization analysis is mostly elusive. Based on a data model characterizing both label-relevant and label-irrelevant tokens, this paper provides the first theoretical analysis of training a shallow ViT, i.e., one self-attention layer followed by a two-layer perceptron, for a classification task. We characterize the sample complexity to achieve a zero generalization error. Our sample complexity bound is positively correlated with the inverse of the fraction of label-relevant tokens, the token noise level, and the initial model error. We also prove that a training process using stochastic gradient descent (SGD) leads to a sparse attention map, which is a formal verification of the general intuition about the success of attention. Moreover, this paper indicates that a proper token sparsification can improve the test performance by removing label-irrelevant and/or noisy tokens, including spurious correlations. Empirical experiments on synthetic data and CIFAR-10 dataset justify our theoretical results and generalize to deeper ViTs.
Authors: Dejun Feng, Hongyu Chen, Suning Liu, Ziyang Liao, Xingyu Shen, Yakun Xie, Jun Zhu
With the increasing application of deep learning in various domains, salient object detection in optical remote sensing images (ORSI-SOD) has attracted significant attention. However, most existing ORSI-SOD methods predominantly rely on local information from low-level features to infer salient boundary cues and supervise them using boundary ground truth, but fail to sufficiently optimize and protect the local information, and almost all approaches ignore the potential advantages offered by the last layer of the decoder to maintain the integrity of saliency maps. To address these issues, we propose a novel method named boundary-semantic collaborative guidance network (BSCGNet) with dual-stream feedback mechanism. First, we propose a boundary protection calibration (BPC) module, which effectively reduces the loss of edge position information during forward propagation and suppresses noise in low-level features without relying on boundary ground truth. Second, based on the BPC module, a dual feature feedback complementary (DFFC) module is proposed, which aggregates boundary-semantic dual features and provides effective feedback to coordinate features across different layers, thereby enhancing cross-scale knowledge communication. Finally, to obtain more complete saliency maps, we consider the uniqueness of the last layer of the decoder for the first time and propose the adaptive feedback refinement (AFR) module, which further refines feature representation and eliminates differences between features through a unique feedback mechanism. Extensive experiments on three benchmark datasets demonstrate that BSCGNet exhibits distinct advantages in challenging scenarios and outperforms the 17 state-of-the-art (SOTA) approaches proposed in recent years. Codes and results have been released on GitHub: https://github.com/YUHsss/BSCGNet.
Authors: Chao Wang
Multi-turn compositional image generation (M-CIG) is a challenging task that aims to iteratively manipulate a reference image given a modification text. While most of the existing methods for M-CIG are based on generative adversarial networks (GANs), recent advances in image generation have demonstrated the superiority of diffusion models over GANs. In this paper, we propose a diffusion-based method for M-CIG named conditional denoising diffusion with image compositional matching (CDD-ICM). We leverage CLIP as the backbone of image and text encoders, and incorporate a gated fusion mechanism, originally proposed for question answering, to compositionally fuse the reference image and the modification text at each turn of M-CIG. We introduce a conditioning scheme to generate the target image based on the fusion results. To prioritize the semantic quality of the generated target image, we learn an auxiliary image compositional match (ICM) objective, along with the conditional denoising diffusion (CDD) objective in a multi-task learning framework. Additionally, we also perform ICM guidance and classifier-free guidance to improve performance. Experimental results show that CDD-ICM achieves state-of-the-art results on two benchmark datasets for M-CIG, i.e., CoDraw and i-CLEVR.
Authors: Weihang Mao, Bo Han, Zihao Wang
Sketch-guided image editing aims to achieve local fine-tuning of the image based on the sketch information provided by the user, while maintaining the original status of the unedited areas. Due to the high cost of acquiring human sketches, previous works mostly relied on edge maps as a substitute for sketches, but sketches possess more rich structural information. In this paper, we propose a sketch generation scheme that can preserve the main contours of an image and closely adhere to the actual sketch style drawn by the user. Simultaneously, current image editing methods often face challenges such as image distortion, training cost, and loss of fine details in the sketch. To address these limitations, We propose a conditional diffusion model (SketchFFusion) based on the sketch structure vector. We evaluate the generative performance of our model and demonstrate that it outperforms existing methods.
Authors: Rui-Yang Ju, Weiming Cai
Hospital emergency departments frequently receive lots of bone fracture cases, with pediatric wrist trauma fracture accounting for the majority of them. Before pediatric surgeons perform surgery, they need to ask patients how the fracture occurred and analyze the fracture situation by interpreting X-ray images. The interpretation of X-ray images often requires a combination of techniques from radiologists and surgeons, which requires time-consuming specialized training. With the rise of deep learning in the field of computer vision, network models applying for fracture detection has become an important research topic. In this paper, we use data augmentation to improve the model performance of YOLOv8 algorithm (the latest version of You Only Look Once) on a pediatric wrist trauma X-ray dataset (GRAZPEDWRI-DX), which is a public dataset. The experimental results show that our model has reached the state-of-the-art (SOTA) mean average precision (mAP 50). Specifically, mAP 50 of our model is 0.638, which is significantly higher than the 0.634 and 0.636 of the improved YOLOv7 and original YOLOv8 models. To enable surgeons to use our model for fracture detection on pediatric wrist trauma X-ray images, we have designed the application "Fracture Detection Using YOLOv8 App" to assist surgeons in diagnosing fractures, reducing the probability of error analysis, and providing more useful information for surgery.
Authors: Fabio Hellmann, Silvan Mertes, Mohamed Benouis, Alexander Hustinx, Tzung-Chien Hsieh, Cristina Conati, Peter Krawitz, Elisabeth André
In recent years, the increasing availability of personal data has raised concerns regarding privacy and security. One of the critical processes to address these concerns is data anonymization, which aims to protect individual privacy and prevent the release of sensitive information. This research focuses on the importance of face anonymization. Therefore, we introduce GANonymization, a novel face anonymization framework with facial expression-preserving abilities. Our approach is based on a high-level representation of a face, which is synthesized into an anonymized version based on a generative adversarial network (GAN). The effectiveness of the approach was assessed by evaluating its performance in removing identifiable facial attributes to increase the anonymity of the given individual face. Additionally, the performance of preserving facial expressions was evaluated on several affect recognition datasets and outperformed the state-of-the-art methods in most categories. Finally, our approach was analyzed for its ability to remove various facial traits, such as jewelry, hair color, and multiple others. Here, it demonstrated reliable performance in removing these attributes. Our results suggest that GANonymization is a promising approach for anonymizing faces while preserving facial expressions.
Authors: Corinne Stucker, Vivien Sainte Fare Garnot, Konrad Schindler
Satellite image time series in the optical and infrared spectrum suffer from frequent data gaps due to cloud cover, cloud shadows, and temporary sensor outages. It has been a long-standing problem of remote sensing research how to best reconstruct the missing pixel values and obtain complete, cloud-free image sequences. We approach that problem from the perspective of representation learning and develop U-TILISE, an efficient neural model that is able to implicitly capture spatio-temporal patterns of the spectral intensities, and that can therefore be trained to map a cloud-masked input sequence to a cloud-free output sequence. The model consists of a convolutional spatial encoder that maps each individual frame of the input sequence to a latent encoding; an attention-based temporal encoder that captures dependencies between those per-frame encodings and lets them exchange information along the time dimension; and a convolutional spatial decoder that decodes the latent embeddings back into multi-spectral images. We experimentally evaluate the proposed model on EarthNet2021, a dataset of Sentinel-2 time series acquired all over Europe, and demonstrate its superior ability to reconstruct the missing pixels. Compared to a standard interpolation baseline, it increases the PSNR by 1.8 dB at previously seen locations and by 1.3 dB at unseen locations.
Authors: Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
Recent breakthroughs in generative modeling have sparked interest in practical single-model attribution. Such methods predict whether a sample was generated by a specific generator or not, for instance, to prove intellectual property theft. However, previous works are either limited to the closed-world setting or require undesirable changes to the generative model. We address these shortcomings by, first, viewing single-model attribution through the lens of anomaly detection. Arising from this change of perspective, we propose FLIPAD, a new approach for single-model attribution in the open-world setting based on final-layer inversion and anomaly detection. We show that the utilized final-layer inversion can be reduced to a convex lasso optimization problem, making our approach theoretically sound and computationally efficient. The theoretical findings are accompanied by an experimental study demonstrating the effectiveness of our approach and its flexibility to various domains.
Authors: Kazuki Shimada, Archontis Politis, Parthasaarathy Sudarsanam, Daniel Krause, Kengo Uchida, Sharath Adavanne, Aapo Hakala, Yuichiro Koyama, Naoya Takahashi, Shusuke Takahashi, Tuomas Virtanen, Yuki Mitsufuji
While direction of arrival (DOA) of sound events is generally estimated from multichannel audio data recorded in a microphone array, sound events usually derive from visually perceptible source objects, e.g., sounds of footsteps come from the feet of a walker. This paper proposes an audio-visual sound event localization and detection (SELD) task, which uses multichannel audio and video information to estimate the temporal activation and DOA of target sound events. Audio-visual SELD systems can detect and localize sound events using signals from a microphone array and audio-visual correspondence. We also introduce an audio-visual dataset, Sony-TAu Realistic Spatial Soundscapes 2023 (STARSS23), which consists of multichannel audio data recorded with a microphone array, video data, and spatiotemporal annotation of sound events. Sound scenes in STARSS23 are recorded with instructions, which guide recording participants to ensure adequate activity and occurrences of sound events. STARSS23 also serves human-annotated temporal activation labels and human-confirmed DOA labels, which are based on tracking results of a motion capture system. Our benchmark results demonstrate the benefits of using visual object positions in audio-visual SELD tasks. The data is available at https://zenodo.org/record/7880637.
Authors: Yujin Lee, Harin Lim, Seoyoon Jang, Hyunsoo Yoon
Visual anomaly detection aims to learn normality from normal images, but existing approaches are fragmented across various tasks: defect detection, semantic anomaly detection, multi-class anomaly detection, and anomaly clustering. This one-task-one-model approach is resource-intensive and incurs high maintenance costs as the number of tasks increases. We present UniFormaly, a universal and powerful anomaly detection framework. We emphasize the necessity of our off-the-shelf approach by pointing out a suboptimal issue in online encoder-based methods. We introduce Back Patch Masking (BPM) and top k-ratio feature matching to achieve unified anomaly detection. BPM eliminates irrelevant background regions using a self-attention map from self-supervised ViTs. This operates in a task-agnostic manner and alleviates memory storage consumption, scaling to tasks with large-scale datasets. Top k-ratio feature matching unifies anomaly levels and tasks by casting anomaly scoring into multiple instance learning. Finally, UniFormaly achieves outstanding results on various tasks and datasets. Codes are available at https://github.com/YoojLee/Uniformaly.
Authors: Hongxiang Li, Meng Cao, Xuxin Cheng, Yaowei Li, Zhihong Zhu, Yuexian Zou
The recent video grounding works attempt to introduce vanilla contrastive learning into video grounding. However, we claim that this naive solution is suboptimal. Contrastive learning requires two key properties: (1) \emph{alignment} of features of similar samples, and (2) \emph{uniformity} of the induced distribution of the normalized features on the hypersphere. Due to two annoying issues in video grounding: (1) the co-existence of some visual entities in both ground truth and other moments, \ie semantic overlapping; (2) only a few moments in the video are annotated, \ie sparse annotation dilemma, vanilla contrastive learning is unable to model the correlations between temporally distant moments and learned inconsistent video representations. Both characteristics lead to vanilla contrastive learning being unsuitable for video grounding. In this paper, we introduce Geodesic and Game Localization (G2L), a semantically aligned and uniform video grounding framework via geodesic and game theory. We quantify the correlations among moments leveraging the geodesic distance that guides the model to learn the correct cross-modal representations. Furthermore, from the novel perspective of game theory, we propose semantic Shapley interaction based on geodesic distance sampling to learn fine-grained semantic alignment in similar moments. Experiments on three benchmarks demonstrate the effectiveness of our method.
Authors: M. M. Amaan Valiuddin, Christiaan G. A. Viviers, Ruud J. G. van Sloun, Peter H. N. de With, Fons van der Sommen
Data uncertainties, such as sensor noise or occlusions, can introduce irreducible ambiguities in images, which result in varying, yet plausible, semantic hypotheses. In Machine Learning, this ambiguity is commonly referred to as aleatoric uncertainty. Latent density models can be utilized to address this problem in image segmentation. The most popular approach is the Probabilistic U-Net (PU-Net), which uses latent Normal densities to optimize the conditional data log-likelihood Evidence Lower Bound. In this work, we demonstrate that the PU- Net latent space is severely inhomogenous. As a result, the effectiveness of gradient descent is inhibited and the model becomes extremely sensitive to the localization of the latent space samples, resulting in defective predictions. To address this, we present the Sinkhorn PU-Net (SPU-Net), which uses the Sinkhorn Divergence to promote homogeneity across all latent dimensions, effectively improving gradient-descent updates and model robustness. Our results show that by applying this on public datasets of various clinical segmentation problems, the SPU-Net receives up to 11% performance gains compared against preceding latent variable models for probabilistic segmentation on the Hungarian-Matched metric. The results indicate that by encouraging a homogeneous latent space, one can significantly improve latent density modeling for medical image segmentation.
Authors: Huilin Zhang, Sumei Li, Haoxiang Chang, Peiming Lin
Stereo image quality assessment (SIQA) plays a crucial role in evaluating and improving the visual experience of 3D content. Existing visual properties-based methods for SIQA have achieved promising performance. However, these approaches ignore the top-down philosophy, leading to a lack of a comprehensive grasp of the human visual system (HVS) and SIQA. This paper presents a novel Stereo AttenTion Network (SATNet), which employs a top-down perspective to guide the quality assessment process. Specifically, our generalized Stereo AttenTion (SAT) structure adapts components and input/output for stereo scenarios. It leverages the fusion-generated attention map as a higher-level binocular modulator to influence two lower-level monocular features, allowing progressive recalibration of both throughout the pipeline. Additionally, we introduce an Energy Coefficient (EC) to flexibly tune the magnitude of binocular response, accounting for the fact that binocular responses in the primate primary visual cortex are less than the sum of monocular responses. To extract the most discriminative quality information from the summation and subtraction of the two branches of monocular features, we utilize a dual-pooling strategy that applies min-pooling and max-pooling operations to the respective branches. Experimental results highlight the superiority of our top-down method in advancing the state-of-the-art in the SIQA field. The code is available at https://github.com/Fanning-Zhang/SATNet.
Authors: Brian B. Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel
This work introduces "You Only Diffuse Areas" (YODA), a novel method for partial diffusion in Single-Image Super-Resolution (SISR). The core idea is to utilize diffusion selectively on spatial regions based on attention maps derived from the low-resolution image and the current time step in the diffusion process. This time-dependent targeting enables a more effective conversion to high-resolution outputs by focusing on areas that benefit the most from the iterative refinement process, i.e., detail-rich objects. We empirically validate YODA by extending leading diffusion-based SISR methods SR3 and SRDiff. Our experiments demonstrate new state-of-the-art performance gains in face and general SR across PSNR, SSIM, and LPIPS metrics. A notable finding is YODA's stabilization effect on training by reducing color shifts, especially when induced by small batch sizes, potentially contributing to resource-constrained scenarios. The proposed spatial and temporal adaptive diffusion mechanism opens promising research directions, including developing enhanced attention map extraction techniques and optimizing inference latency based on sparser diffusion.
Authors: Robert Graf, Joachim Schmitt, Sarah Schlaeger, Hendrik Kristian Möller, Vasiliki Sideri-Lampretsa, Anjany Sekuboyina, Sandro Manuel Krieg, Benedikt Wiestler, Bjoern Menze, Daniel Rueckert, Jan Stefan Kirschke
Background: Automated segmentation of spinal MR images plays a vital role both scientifically and clinically. However, accurately delineating posterior spine structures presents challenges.
Methods: This retrospective study, approved by the ethical committee, involved translating T1w and T2w MR image series into CT images in a total of n=263 pairs of CT/MR series. Landmark-based registration was performed to align image pairs. We compared 2D paired (Pix2Pix, denoising diffusion implicit models (DDIM) image mode, DDIM noise mode) and unpaired (contrastive unpaired translation, SynDiff) image-to-image translation using "peak signal to noise ratio" (PSNR) as quality measure. A publicly available segmentation network segmented the synthesized CT datasets, and Dice scores were evaluated on in-house test sets and the "MRSpineSeg Challenge" volumes. The 2D findings were extended to 3D Pix2Pix and DDIM.
Results: 2D paired methods and SynDiff exhibited similar translation performance and Dice scores on paired data. DDIM image mode achieved the highest image quality. SynDiff, Pix2Pix, and DDIM image mode demonstrated similar Dice scores (0.77). For craniocaudal axis rotations, at least two landmarks per vertebra were required for registration. The 3D translation outperformed the 2D approach, resulting in improved Dice scores (0.80) and anatomically accurate segmentations in a higher resolution than the original MR image.
Conclusion: Two landmarks per vertebra registration enabled paired image-to-image translation from MR to CT and outperformed all unpaired approaches. The 3D techniques provided anatomically correct segmentations, avoiding underprediction of small structures like the spinous process.
Authors: Katharina Prasse, Steffen Jung, Yuxuan Zhou, Margret Keuper
Hand action recognition is essential. Communication, human-robot interactions, and gesture control are dependent on it. Skeleton-based action recognition traditionally includes hands, which belong to the classes which remain challenging to correctly recognize to date. We propose a method specifically designed for hand action recognition which uses relative angular embeddings and local Spherical Harmonics to create novel hand representations. The use of Spherical Harmonics creates rotation-invariant representations which make hand action recognition even more robust against inter-subject differences and viewpoint changes. We conduct extensive experiments on the hand joints in the First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations, and on the NTU RGB+D 120 dataset, demonstrating the benefit of using Local Spherical Harmonics Representations. Our code is available at https://github.com/KathPra/LSHR_LSHT.
Authors: Binh Duong Nguyen, Pavlo Potapenko, Aytekin Dermici, Kishan Govind, Sébastien Bompas, Stefan Sandfeld
Determining, understanding, and predicting the so-called structure-property relation is an important task in many scientific disciplines, such as chemistry, biology, meteorology, physics, engineering, and materials science. Structure refers to the spatial distribution of, e.g., substances, material, or matter in general, while property is a resulting characteristic that usually depends in a non-trivial way on spatial details of the structure. Traditionally, forward simulations models have been used for such tasks. Recently, several machine learning algorithms have been applied in these scientific fields to enhance and accelerate simulation models or as surrogate models. In this work, we develop and investigate the applications of six machine learning techniques based on two different datasets from the domain of materials science: data from a two-dimensional Ising model for predicting the formation of magnetic domains and data representing the evolution of dual-phase microstructures from the Cahn-Hilliard model. We analyze the accuracy and robustness of all models and elucidate the reasons for the differences in their performances. The impact of including domain knowledge through tailored features is studied, and general recommendations based on the availability and quality of training data are derived from this.
Authors: Aryaman Gupta, Kaustav Chakraborty, Somil Bansal
Autonomous systems, such as self-driving cars and drones, have made significant strides in recent years by leveraging visual inputs and machine learning for decision-making and control. Despite their impressive performance, these vision-based controllers can make erroneous predictions when faced with novel or out-of-distribution inputs. Such errors can cascade to catastrophic system failures and compromise system safety. In this work, we introduce a run-time anomaly monitor to detect and mitigate such closed-loop, system-level failures. Specifically, we leverage a reachability-based framework to stress-test the vision-based controller offline and mine its system-level failures. This data is then used to train a classifier that is leveraged online to flag inputs that might cause system breakdowns. The anomaly detector highlights issues that transcend individual modules and pertain to the safety of the overall system. We also design a fallback controller that robustly handles these detected anomalies to preserve system safety. We validate the proposed approach on an autonomous aircraft taxiing system that uses a vision-based controller for taxiing. Our results show the efficacy of the proposed approach in identifying and handling system-level anomalies, outperforming methods such as prediction error-based detection, and ensembling, thereby enhancing the overall safety and robustness of autonomous systems.
Authors: Yuan-Ming Li, Ling-An Zeng, Jing-Ke Meng, Wei-Shi Zheng
Action Quality Assessment (AQA) is a task that tries to answer how well an action is carried out. While remarkable progress has been achieved, existing works on AQA assume that all the training data are visible for training in one time, but do not enable continual learning on assessing new technical actions. In this work, we address such a Continual Learning problem in AQA (Continual-AQA), which urges a unified model to learn AQA tasks sequentially without forgetting. Our idea for modeling Continual-AQA is to sequentially learn a task-consistent score-discriminative feature distribution, in which the latent features express a strong correlation with the score labels regardless of the task or action types. From this perspective, we aim to mitigate the forgetting in Continual-AQA from two aspects. Firstly, to fuse the features of new and previous data into a score-discriminative distribution, a novel Feature-Score Correlation-Aware Rehearsal is proposed to store and reuse data from previous tasks with limited memory size. Secondly, an Action General-Specific Graph is developed to learn and decouple the action-general and action-specific knowledge so that the task-consistent score-discriminative features can be better extracted across various tasks. Extensive experiments are conducted to evaluate the contributions of proposed components. The comparisons with the existing continual learning methods additionally verify the effectiveness and versatility of our approach.
Authors: Razieh Faghihpirayesh, Davood Karimi, Deniz Erdoğmuş, Ali Gholipour
Fetal brain extraction is a necessary first step in most computational fetal brain MRI pipelines. However, it has been a very challenging task due to non-standard fetal head pose, fetal movements during examination, and vastly heterogeneous appearance of the developing fetal brain and the neighboring fetal and maternal anatomy across various sequences and scanning conditions. Development of a machine learning method to effectively address this task requires a large and rich labeled dataset that has not been previously available. As a result, there is currently no method for accurate fetal brain extraction on various fetal MRI sequences. In this work, we first built a large annotated dataset of approximately 72,000 2D fetal brain MRI images. Our dataset covers the three common MRI sequences including T2-weighted, diffusion-weighted, and functional MRI acquired with different scanners. Moreover, it includes normal and pathological brains. Using this dataset, we developed and validated deep learning methods, by exploiting the power of the U-Net style architectures, the attention mechanism, multi-contrast feature learning, and data augmentation for fast, accurate, and generalizable automatic fetal brain extraction. Our approach leverages the rich information from multi-contrast (multi-sequence) fetal MRI data, enabling precise delineation of the fetal brain structures. Evaluations on independent test data show that our method achieves accurate brain extraction on heterogeneous test data acquired with different scanners, on pathological brains, and at various gestational stages. This robustness underscores the potential utility of our deep learning model for fetal brain imaging and image analysis.
Authors: Tushar Choudhary, Vikrant Dewangan, Shivam Chandhok, Shubham Priyadarshan, Anushka Jain, Arun K. Singh, Siddharth Srivastava, Krishna Murthy Jatavallabhula, K. Madhava Krishna
Talk2BEV is a large vision-language model (LVLM) interface for bird's-eye view (BEV) maps in autonomous driving contexts. While existing perception systems for autonomous driving scenarios have largely focused on a pre-defined (closed) set of object categories and driving scenarios, Talk2BEV blends recent advances in general-purpose language and vision models with BEV-structured map representations, eliminating the need for task-specific models. This enables a single system to cater to a variety of autonomous driving tasks encompassing visual and spatial reasoning, predicting the intents of traffic actors, and decision-making based on visual cues. We extensively evaluate Talk2BEV on a large number of scene understanding tasks that rely on both the ability to interpret free-form natural language queries, and in grounding these queries to the visual context embedded into the language-enhanced BEV map. To enable further research in LVLMs for autonomous driving scenarios, we develop and release Talk2BEV-Bench, a benchmark encompassing 1000 human-annotated BEV scenarios, with more than 20,000 questions and ground-truth responses from the NuScenes dataset.
Authors: Songyan Zhang, Xinyu Sun, Hao Chen, Bo Li, Chunhua Shen
Finding corresponding pixels within a pair of images is a fundamental computer vision task with various applications. Due to the specific requirements of different tasks like optical flow estimation and local feature matching, previous works are primarily categorized into dense matching and sparse feature matching focusing on specialized architectures along with task-specific datasets, which may somewhat hinder the generalization performance of specialized models. In this paper, we propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching). In particular, we elaborately design a cascaded GRU module for refinement by exploring the geometric similarity iteratively at multiple scales following an additional uncertainty estimation module for sparsification. To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth by generating optical flow supervision with greater intervals. As such, we are able to mix up various dense and sparse matching datasets, significantly improving the training diversity. The generalization capacity of our proposed RGM is greatly improved by learning the matching and uncertainty estimation in a two-stage manner on the large, mixed data. Superior performance is achieved for zero-shot matching and downstream geometry estimation across multiple datasets, outperforming the previous methods by a large margin.
Authors: Weiyi Wu, Chongyang Gao, Joseph DiPalma, Soroush Vosoughi, Saeed Hassanpour
Recent advances in whole-slide image (WSI) scanners and computational capabilities have significantly propelled the application of artificial intelligence in histopathology slide analysis. While these strides are promising, current supervised learning approaches for WSI analysis come with the challenge of exhaustively labeling high-resolution slides - a process that is both labor-intensive and time-consuming. In contrast, self-supervised learning (SSL) pretraining strategies are emerging as a viable alternative, given that they don't rely on explicit data annotations. These SSL strategies are quickly bridging the performance disparity with their supervised counterparts. In this context, we introduce an SSL framework. This framework aims for transferable representation learning and semantically meaningful clustering by synergizing invariance loss and clustering loss in WSI analysis. Notably, our approach outperforms common SSL methods in downstream classification and clustering tasks, as evidenced by tests on the Camelyon16 and a pancreatic cancer dataset.
Authors: Guanqun Sun, Yizhi Pan, Weikun Kong, Zichang Xu, Jianhua Ma, Teeradaj Racharak, Le-Minh Nguyen, Junyi Xin
Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional Unet architectures and their transformer-integrated variants excel in automated segmentation tasks. However, they lack the ability to harness the intrinsic position and channel features of image. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transformers. To address these issues, this study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to integrate the Transformer and dual attention block(DA-Block) into the traditional U-shaped architecture. Unlike earlier transformer-based U-net models, DA-TransUNet utilizes Transformers and DA-Block to integrate not only global and local features, but also image-specific positional and channel features, improving the performance of medical image segmentation. By incorporating a DA-Block at the embedding layer and within each skip connection layer, we substantially enhance feature extraction capabilities and improve the efficiency of the encoder-decoder structure. DA-TransUNet demonstrates superior performance in medical image segmentation tasks, consistently outperforming state-of-the-art techniques across multiple datasets. In summary, DA-TransUNet offers a significant advancement in medical image segmentation, providing an effective and powerful alternative to existing techniques. Our architecture stands out for its ability to improve segmentation accuracy, thereby advancing the field of automated medical image diagnostics. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet.
Authors: Joana Palés Huix, Adithya Raju Ganeshan, Johan Fredin Haslum, Magnus Söderberg, Christos Matsoukas, Kevin Smith
The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has become common practice within the field of natural language processing, progress has been slower in computer vision. In this paper we attempt to address this issue by investigating the transferability of various state-of-the-art foundation models to medical image classification tasks. Specifically, we evaluate the performance of five foundation models, namely SAM, SEEM, DINOv2, BLIP, and OpenCLIP across four well-established medical imaging datasets. We explore different training settings to fully harness the potential of these models. Our study shows mixed results. DINOv2 consistently outperforms the standard practice of ImageNet pretraining. However, other foundation models failed to consistently beat this established baseline indicating limitations in their transferability to medical image classification tasks.
Authors: Hao Li, Han Liu, Dewei Hu, Jiacheng Wang, Ipek Oguz
To address prevalent issues in medical imaging, such as data acquisition challenges and label availability, transfer learning from natural to medical image domains serves as a viable strategy to produce reliable segmentation results. However, several existing barriers between domains need to be broken down, including addressing contrast discrepancies, managing anatomical variability, and adapting 2D pretrained models for 3D segmentation tasks. In this paper, we propose ProMISe,a prompt-driven 3D medical image segmentation model using only a single point prompt to leverage knowledge from a pretrained 2D image foundation model. In particular, we use the pretrained vision transformer from the Segment Anything Model (SAM) and integrate lightweight adapters to extract depth-related (3D) spatial context without updating the pretrained weights. For robust results, a hybrid network with complementary encoders is designed, and a boundary-aware loss is proposed to achieve precise boundaries. We evaluate our model on two public datasets for colon and pancreas tumor segmentations, respectively. Compared to the state-of-the-art segmentation methods with and without prompt engineering, our proposed method achieves superior performance. The code is publicly available at https://github.com/MedICL-VU/ProMISe.
Authors: Hao Zhang, Cong Xu, Shuaijie Zhang
With the rapid development of detectors, Bounding Box Regression (BBR) loss function has constantly updated and optimized. However, the existing IoU-based BBR still focus on accelerating convergence by adding new loss terms, ignoring the limitations of IoU loss term itself. Although theoretically IoU loss can effectively describe the state of bounding box regression,in practical applications, it cannot adjust itself according to different detectors and detection tasks, and does not have strong generalization. Based on the above, we first analyzed the BBR model and concluded that distinguishing different regression samples and using different scales of auxiliary bounding boxes to calculate losses can effectively accelerate the bounding box regression process. For high IoU samples, using smaller auxiliary bounding boxes to calculate losses can accelerate convergence, while larger auxiliary bounding boxes are suitable for low IoU samples. Then, we propose Inner-IoU loss, which calculates IoU loss through auxiliary bounding boxes. For different datasets and detectors, we introduce a scaling factor ratio to control the scale size of the auxiliary bounding boxes for calculating losses. Finally, integrate Inner-IoU into the existing IoU-based loss functions for simulation and comparative experiments. The experiment result demonstrate a further enhancement in detection performance with the utilization of the method proposed in this paper, verifying the effectiveness and generalization ability of Inner-IoU loss. Code is available at https://github.com/malagoutou/Inner-IoU.
Authors: Matteo Destro, Michael Gygli
Analyzing periodic video sequences is a key topic in applications such as automatic production systems, remote sensing, medical applications, or physical training. An example is counting repetitions of a physical exercise. Due to the distinct characteristics of periodic data, self-supervised methods designed for standard image datasets do not capture changes relevant to the progression of the cycle and fail to ignore unrelated noise. They thus do not work well on periodic data. In this paper, we propose CycleCL, a self-supervised learning method specifically designed to work with periodic data. We start from the insight that a good visual representation for periodic data should be sensitive to the phase of a cycle, but be invariant to the exact repetition, i.e. it should generate identical representations for a specific phase throughout all repetitions. We exploit the repetitions in videos to design a novel contrastive learning method based on a triplet loss that optimizes for these desired properties. Our method uses pre-trained features to sample pairs of frames from approximately the same phase and negative pairs of frames from different phases. Then, we iterate between optimizing a feature encoder and resampling triplets, until convergence. By optimizing a model this way, we are able to learn features that have the mentioned desired properties. We evaluate CycleCL on an industrial and multiple human actions datasets, where it significantly outperforms previous video-based self-supervised learning methods on all tasks.
Authors: Zhen Zhou, Yunkai Ma, Junfeng Fan, Zhaoyang Liu, Fengshui Jing, Min Tan
In oriented object detection, current representations of oriented bounding boxes (OBBs) often suffer from boundary discontinuity problem. Methods of designing continuous regression losses do not essentially solve this problem. Although Gaussian bounding box (GBB) representation avoids this problem, directly regressing GBB is susceptible to numerical instability. We propose linear GBB (LGBB), a novel OBB representation. By linearly transforming the elements of GBB, LGBB avoids the boundary discontinuity problem and has high numerical stability. In addition, existing convolution-based rotation-sensitive feature extraction methods only have local receptive fields, resulting in slow feature aggregation. We propose ring-shaped rotated convolution (RRC), which adaptively rotates feature maps to arbitrary orientations to extract rotation-sensitive features under a ring-shaped receptive field, rapidly aggregating features and contextual information. Experimental results demonstrate that LGBB and RRC achieve state-of-the-art performance. Furthermore, integrating LGBB and RRC into various models effectively improves detection accuracy.
Authors: Saurav Sengupta, Donald E. Brown
Deep learning for histopathology has been successfully used for disease classification, image segmentation and more. However, combining image and text modalities using current state-of-the-art methods has been a challenge due to the high resolution of histopathology images. Automatic report generation for histopathology images is one such challenge. In this work, we show that using an existing pre-trained Vision Transformer in a two-step process of first using it to encode 4096x4096 sized patches of the Whole Slide Image (WSI) and then using it as the encoder and an LSTM decoder for report generation, we can build a fairly performant and portable report generation mechanism that takes into account the whole of the high resolution image, instead of just the patches. We are also able to use representations from an existing powerful pre-trained hierarchical vision transformer and show its usefulness in not just zero shot classification but also for report generation.
Authors: Johannes Kopp, Dominik Kellner, Aldi Piroli, Vinzenz Dallabetta, Klaus Dietmayer
The unique properties of radar sensors, such as their robustness to adverse weather conditions, make them an important part of the environment perception system of autonomous vehicles. One of the first steps during the processing of radar point clouds is often the detection of clutter, i.e. erroneous points that do not correspond to real objects. Another common objective is the semantic segmentation of moving road users. These two problems are handled strictly separate from each other in literature. The employed neural networks are always focused entirely on only one of the tasks. In contrast to this, we examine ways to solve both tasks at the same time with a single jointly used model. In addition to a new augmented multi-head architecture, we also devise a method to represent a network's predictions for the two tasks with only one output value. This novel approach allows us to solve the tasks simultaneously with the same inference time as a conventional task-specific model. In an extensive evaluation, we show that our setup is highly effective and outperforms every existing network for semantic segmentation on the RadarScenes dataset.
Authors: Seongyun Lee, Sue Hyun Park, Yongrae Jo, Minjoon Seo
Large multimodal models (LMMs) suffer from multimodal hallucination, where they provide incorrect responses misaligned with the given visual information. Recent works have conjectured that one of the reasons behind multimodal hallucination might be due to the vision encoder failing to ground on the image properly. To mitigate this issue, we propose a novel approach that leverages self-feedback as visual cues. Building on this approach, we introduce Volcano, a multimodal self-feedback guided revision model. Volcano generates natural language feedback to its initial response based on the provided visual information and utilizes this feedback to self-revise its initial response. Volcano effectively reduces multimodal hallucination and achieves state-of-the-art on MMHal-Bench, POPE, and GAVIE. It also improves on general multimodal abilities and outperforms previous models on MM-Vet and MMBench. Through a qualitative analysis, we show that Volcano's feedback is properly grounded on the image than the initial response. This indicates that Volcano can provide itself with richer visual information, helping alleviate multimodal hallucination. We publicly release Volcano models of 7B and 13B sizes along with the data and code at https://github.com/kaistAI/Volcano.
Authors: Brian Moser, Stanislav Frolov, Federico Raue, Sebastian Palacio, Andreas Dengel
This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR). It leverages the strengths of Denoising Diffusion Probabilistic Models (DDPMs) and Discrete Wavelet Transformation (DWT). By enabling DDPMs to operate in the DWT domain, our DDPM models effectively hallucinate high-frequency information for super-resolved images on the wavelet spectrum, resulting in high-quality and detailed reconstructions in image space. Quantitatively, we outperform state-of-the-art diffusion-based SISR methods, namely SR3 and SRDiff, regarding PSNR, SSIM, and LPIPS on both face (8x scaling) and general (4x scaling) SR benchmarks. Meanwhile, using DWT enabled us to use fewer parameters than the compared models: 92M parameters instead of 550M compared to SR3 and 9.3M instead of 12M compared to SRDiff. Additionally, our method outperforms other state-of-the-art generative methods on classical general SR datasets while saving inference time. Finally, our work highlights its potential for various applications.
Authors: Shunfeng Wang, Yueyang Li, Haichi Luo, Chenyang Bi
In the anomaly detection field, the scarcity of anomalous samples has directed the current research emphasis towards unsupervised anomaly detection. While these unsupervised anomaly detection methods offer convenience, they also overlook the crucial prior information embedded within anomalous samples. Moreover, among numerous deep learning methods, supervised methods generally exhibit superior performance compared to unsupervised methods. Considering the reasons mentioned above, we propose a self-supervised anomaly detection approach that combines contrastive learning with 2D-Flow to achieve more precise detection outcomes and expedited inference processes. On one hand, we introduce a novel approach to anomaly synthesis, yielding anomalous samples in accordance with authentic industrial scenarios, alongside their surrogate annotations. On the other hand, having obtained a substantial number of anomalous samples, we enhance the 2D-Flow framework by incorporating contrastive learning, leveraging diverse proxy tasks to fine-tune the network. Our approach enables the network to learn more precise mapping relationships from self-generated labels while retaining the lightweight characteristics of the 2D-Flow. Compared to mainstream unsupervised approaches, our self-supervised method demonstrates superior detection accuracy, fewer additional model parameters, and faster inference speed. Furthermore, the entire training and inference process is end-to-end. Our approach showcases new state-of-the-art results, achieving a performance of 99.6\% in image-level AUROC on the MVTecAD dataset and 96.8\% in image-level AUROC on the BTAD dataset.