Authors: Wonjoong Kim, Sangwu Park, Yeonjun In, Seokwon Han, Chanyoung Park
Abstract: Recently, interpreting complex charts with logical reasoning have emerged as challenges due to the development of vision-language models. A prior state-of-the-art (SOTA) model, Deplot, has presented an end-to-end method that leverages the vision-language model to convert charts into table format utilizing Large Language Models (LLMs) for reasoning. However, unlike natural images, charts contain a mix of essential and irrelevant information required for chart reasoning, and we discover that this characteristic can lower the performance of chart-to-table extraction. In this paper, we introduce SIMPLOT, a method designed to extract only the elements necessary for chart reasoning. The proposed method involves two steps: 1) training to mimic a simple plot that contains only the essential information from a complex chart for table extraction, followed by 2) performing reasoning based on the table. Our model enables accurate chart reasoning without the need for additional annotations or datasets, and its effectiveness is demonstrated through various experiments. Furthermore, we propose a novel prompt addressing the shortcoming of recent SOTA model, ignoring visual attributes such as color. Our source code is available at https://github.com/sangwu99/Simplot.
Authors: A. Hossam, A. Ramadan, M. Magdy, R. Abdelwahab, S. Ashraf, Z. Mohamed
Abstract: In response to the significant challenges facing the retail sector, including inefficient queue management, poor demand forecasting, and ineffective marketing, this paper introduces an innovative approach utilizing cutting-edge machine learning technologies. We aim to create an advanced smart retail analytics system (SRAS), leveraging these technologies to enhance retail efficiency and customer engagement. To enhance customer tracking capabilities, a new hybrid architecture is proposed integrating several predictive models. In the first stage of the proposed hybrid architecture for customer tracking, we fine-tuned the YOLOV8 algorithm using a diverse set of parameters, achieving exceptional results across various performance metrics. This fine-tuning process utilized actual surveillance footage from retail environments, ensuring its practical applicability. In the second stage, we explored integrating two sophisticated object-tracking models, BOT-SORT and ByteTrack, with the labels detected by YOLOV8. This integration is crucial for tracing customer paths within stores, which facilitates the creation of accurate visitor counts and heat maps. These insights are invaluable for understanding consumer behavior and improving store operations. To optimize inventory management, we delved into various predictive models, optimizing and contrasting their performance against complex retail data patterns. The GRU model, with its ability to interpret time-series data with long-range temporal dependencies, consistently surpassed other models like Linear Regression, showing 2.873% and 29.31% improvements in R2-score and mAPE, respectively.
Authors: Md. Shohanur Islam Sobuj, Md. Imran Hossen, Md. Foysal Mahmud, Mahbub Ul Islam Khan
Abstract: Rice disease classification is a critical task in agricultural research, and in this study, we rigorously evaluate the impact of integrating feature extraction methodologies within pre-trained convolutional neural networks (CNNs). Initial investigations into baseline models, devoid of feature extraction, revealed commendable performance with ResNet-50 and ResNet-101 achieving accuracies of 91% and 92%, respectively. Subsequent integration of Histogram of Oriented Gradients (HOG) yielded substantial improvements across architectures, notably propelling the accuracy of EfficientNet-B7 from 92\% to an impressive 97%. Conversely, the application of Local Binary Patterns (LBP) demonstrated more conservative performance enhancements. Moreover, employing Gradient-weighted Class Activation Mapping (Grad-CAM) unveiled that HOG integration resulted in heightened attention to disease-specific features, corroborating the performance enhancements observed. Visual representations further validated HOG's notable influence, showcasing a discernible surge in accuracy across epochs due to focused attention on disease-affected regions. These results underscore the pivotal role of feature extraction, particularly HOG, in refining representations and bolstering classification accuracy. The study's significant highlight was the achievement of 97% accuracy with EfficientNet-B7 employing HOG and Grad-CAM, a noteworthy advancement in optimizing pre-trained CNN-based rice disease identification systems. The findings advocate for the strategic integration of advanced feature extraction techniques with cutting-edge pre-trained CNN architectures, presenting a promising avenue for substantially augmenting the precision and effectiveness of image-based disease classification systems in agricultural contexts.
Authors: Wen Cao, Ehsan Miandji, Jonas Unger
Abstract: This paper considers a compressive multi-spectral light field camera model that utilizes a one-hot spectralcoded mask and a microlens array to capture spatial, angular, and spectral information using a single monochrome sensor. We propose a model that employs compressed sensing techniques to reconstruct the complete multi-spectral light field from undersampled measurements. Unlike previous work where a light field is vectorized to a 1D signal, our method employs a 5D basis and a novel 5D measurement model, hence, matching the intrinsic dimensionality of multispectral light fields. We mathematically and empirically show the equivalence of 5D and 1D sensing models, and most importantly that the 5D framework achieves orders of magnitude faster reconstruction while requiring a small fraction of the memory. Moreover, our new multidimensional sensing model opens new research directions for designing efficient visual data acquisition algorithms and hardware.
Authors: Alex Kim, Jia Huang, Rob Monarch, Jerry Kwac, Anikesh Kamath, Parmeshwar Khurd, Kailash Thiyagarajan, Goodman Gu
Abstract: Application developers advertise their Apps by creating product pages with App images, and bidding on search terms. It is then crucial for App images to be highly relevant with the search terms. Solutions to this problem require an image-text matching model to predict the quality of the match between the chosen image and the search terms. In this work, we present a novel approach to matching an App image to search terms based on fine-tuning a pre-trained LXMERT model. We show that compared to the CLIP model and a baseline using a Transformer model for search terms, and a ResNet model for images, we significantly improve the matching accuracy. We evaluate our approach using two sets of labels: advertiser associated (image, search term) pairs for a given application, and human ratings for the relevance between (image, search term) pairs. Our approach achieves 0.96 AUC score for advertiser associated ground truth, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 8% and 14%. For human labeled ground truth, our approach achieves 0.95 AUC score, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 16% and 17%.
Authors: Aditya V. Jonnalagadda, Hashim A. Hashim
Abstract: This research addresses the pressing challenge of enhancing processing times and detection capabilities in Unmanned Aerial Vehicle (UAV)/drone imagery for global wildfire detection, despite limited datasets. Proposing a Segmented Neural Network (SegNet) selection approach, we focus on reducing feature maps to boost both time resolution and accuracy significantly advancing processing speeds and accuracy in real-time wildfire detection. This paper contributes to increased processing speeds enabling real-time detection capabilities for wildfire, increased detection accuracy of wildfire, and improved detection capabilities of early wildfire, through proposing a new direction for image classification of amorphous objects like fire, water, smoke, etc. Employing Convolutional Neural Networks (CNNs) for image classification, emphasizing on the reduction of irrelevant features vital for deep learning processes, especially in live feed data for fire detection. Amidst the complexity of live feed data in fire detection, our study emphasizes on image feed, highlighting the urgency to enhance real-time processing. Our proposed algorithm combats feature overload through segmentation, addressing challenges arising from diverse features like objects, colors, and textures. Notably, a delicate balance of feature map size and dataset adequacy is pivotal. Several research papers use smaller image sizes, compromising feature richness which necessitating a new approach. We illuminate the critical role of pixel density in retaining essential details, especially for early wildfire detection. By carefully selecting number of filters during training, we underscore the significance of higher pixel density for proper feature selection. The proposed SegNet approach is rigorously evaluated using real-world dataset obtained by a drone flight and compared to state-of-the-art literature.
Authors: Justin Engelmann, Miguel O. Bernabeu
Abstract: Artificial Intelligence holds tremendous potential in medicine, but is traditionally limited by the lack of massive datasets to train models on. Foundation models, pre-trained models that can be adapted to downstream tasks with small datasets, could alleviate this problem. Researchers at Moorfields Eye Hospital (MEH) proposed RETFound-MEH, a foundation model for retinal imaging that was trained on 900,000 images, including private hospital data. Recently, data-efficient DERETFound was proposed that provides comparable performance while being trained on only 150,000 images that are all publicly available. However, both these models required very substantial resources to train initially and are resource-intensive in downstream use. We propose a novel Token Reconstruction objective that we use to train RETFound-Green, a retinal foundation model trained using only 75,000 publicly available images and 400 times less compute. We estimate the cost of training RETFound-MEH and DERETFound at $10,000 and $14,000, respectively, while RETFound-Green could be trained for less than $100, with equally reduced environmental impact. RETFound-Green is also far more efficient in downstream use: it can be downloaded 14 times faster, computes vector embeddings 2.7 times faster which then require 2.6 times less storage space. Despite this, RETFound-Green does not perform systematically worse. In fact, it performs best on 14 tasks, compared to six for DERETFound and two for RETFound-MEH. Our results suggest that RETFound-Green is a very efficient, high-performance retinal foundation model. We anticipate that our Token Reconstruction objective could be scaled up for even higher performance and be applied to other domains beyond retinal imaging.
Authors: Skylar Chan, Pranav Kulkarni, Paul H. Yi, Vishwa S. Parekh
Abstract: Quantum machine learning (QML) has the potential for improving the multi-label classification of rare, albeit critical, diseases in large-scale chest x-ray (CXR) datasets due to theoretical quantum advantages over classical machine learning (CML) in sample efficiency and generalizability. While prior literature has explored QML with CXRs, it has focused on binary classification tasks with small datasets due to limited access to quantum hardware and computationally expensive simulations. To that end, we implemented a Jax-based framework that enables the simulation of medium-sized qubit architectures with significant improvements in wall-clock time over current software offerings. We evaluated the performance of our Jax-based framework in terms of efficiency and performance for hybrid quantum transfer learning for long-tailed classification across 8, 14, and 19 disease labels using large-scale CXR datasets. The Jax-based framework resulted in up to a 58% and 95% speed-up compared to PyTorch and TensorFlow implementations, respectively. However, compared to CML, QML demonstrated slower convergence and an average AUROC of 0.70, 0.73, and 0.74 for the classification of 8, 14, and 19 CXR disease labels. In comparison, the CML models had an average AUROC of 0.77, 0.78, and 0.80 respectively. In conclusion, our work presents an accessible implementation of hybrid quantum transfer learning for long-tailed CXR classification with a computationally efficient Jax-based framework.
Authors: Zhangyong Tang, Tianyang Xu, Zhenhua Feng, Xuefeng Zhu, He Wang, Pengcheng Shao, Chunyang Cheng, Xiao-Jun Wu, Muhammad Awais, Sara Atito, Josef Kittler
Abstract: RGBT tracking draws increasing attention due to its robustness in multi-modality warranting (MMW) scenarios, such as nighttime and bad weather, where relying on a single sensing modality fails to ensure stable tracking results. However, the existing benchmarks predominantly consist of videos collected in common scenarios where both RGB and thermal infrared (TIR) information are of sufficient quality. This makes the data unrepresentative of severe imaging conditions, leading to tracking failures in MMW scenarios. To bridge this gap, we present a new benchmark, MV-RGBT, captured specifically in MMW scenarios. In contrast with the existing datasets, MV-RGBT comprises more object categories and scenes, providing a diverse and challenging benchmark. Furthermore, for severe imaging conditions of MMW scenarios, a new problem is posed, namely \textit{when to fuse}, to stimulate the development of fusion strategies for such data. We propose a new method based on a mixture of experts, namely MoETrack, as a baseline fusion strategy. In MoETrack, each expert generates independent tracking results along with the corresponding confidence score, which is used to control the fusion process. Extensive experimental results demonstrate the significant potential of MV-RGBT in advancing RGBT tracking and elicit the conclusion that fusion is not always beneficial, especially in MMW scenarios. Significantly, the proposed MoETrack method achieves new state-of-the-art results not only on MV-RGBT, but also on standard benchmarks, such as RGBT234, LasHeR, and the short-term split of VTUAV (VTUAV-ST). More information of MV-RGBT and the source code of MoETrack will be released at https://github.com/Zhangyong-Tang/MoETrack.
Authors: Hang Du, Sicheng Zhang, Binzhu Xie, Guoshun Nan, Jiayang Zhang, Junrui Xu, Hangyu Liu, Sicong Leng, Jiangming Liu, Hehe Fan, Dajiu Huang, Jing Feng, Linli Chen, Can Zhang, Xuhuan Li, Hao Zhang, Jianhang Chen, Qimei Cui, Xiaofeng Tao
Abstract: Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily concentrate on anomaly detection and localization, our focus is on more practicality, prompting us to raise the following crucial questions: "what anomaly occurred?", "why did it happen?", and "how severe is this abnormal event?". In pursuit of these answers, we present a comprehensive benchmark for Causation Understanding of Video Anomaly (CUVA). Specifically, each instance of the proposed benchmark involves three sets of human annotations to indicate the "what", "why" and "how" of an anomaly, including 1) anomaly type, start and end times, and event descriptions, 2) natural language explanations for the cause of an anomaly, and 3) free text reflecting the effect of the abnormality. In addition, we also introduce MMEval, a novel evaluation metric designed to better align with human preferences for CUVA, facilitating the measurement of existing LLMs in comprehending the underlying cause and corresponding effect of video anomalies. Finally, we propose a novel prompt-based method that can serve as a baseline approach for the challenging CUVA. We conduct extensive experiments to show the superiority of our evaluation metric and the prompt-based approach. Our code and dataset are available at https://github.com/fesvhtr/CUVA.
Authors: Tahira Shehzadi, Shalini Sarode, Didier Stricker, Muhammad Zeshan Afzal
Abstract: Table detection within document images is a crucial task in document processing, involving the identification and localization of tables. Recent strides in deep learning have substantially improved the accuracy of this task, but it still heavily relies on large labeled datasets for effective training. Several semi-supervised approaches have emerged to overcome this challenge, often employing CNN-based detectors with anchor proposals and post-processing techniques like non-maximal suppression (NMS). However, recent advancements in the field have shifted the focus towards transformer-based techniques, eliminating the need for NMS and emphasizing object queries and attention mechanisms. Previous research has focused on two key areas to improve transformer-based detectors: refining the quality of object queries and optimizing attention mechanisms. However, increasing object queries can introduce redundancy, while adjustments to the attention mechanism can increase complexity. To address these challenges, we introduce a semi-supervised approach employing SAM-DETR, a novel approach for precise alignment between object queries and target features. Our approach demonstrates remarkable reductions in false positives and substantial enhancements in table detection performance, particularly in complex documents characterized by diverse table structures. This work provides more efficient and accurate table detection in semi-supervised settings.
Authors: Diangarti Tariang, Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
Abstract: In this work we present an overview of approaches for the detection and attribution of synthetic images and highlight their strengths and weaknesses. We also point out and discuss hot topics in this field and outline promising directions for future research.
Authors: David Geissb\"uhler, Hatef Otroshi Shahreza, S\'ebastien Marcel
Abstract: Face Recognition (FR) models are trained on large-scale datasets, which have privacy and ethical concerns. Lately, the use of synthetic data to complement or replace genuine data for the training of FR models has been proposed. While promising results have been obtained, it still remains unclear if generative models can yield diverse enough data for such tasks. In this work, we introduce a new method, inspired by the physical motion of soft particles subjected to stochastic Brownian forces, allowing us to sample identities distributions in a latent space under various constraints. With this in hands, we generate several face datasets and benchmark them by training FR models, showing that data generated with our method exceeds the performance of previously GAN-based datasets and achieves competitive performance with state-of-the-art diffusion-based synthetic datasets. We also show that this method can be used to mitigate leakage from the generator's training set and explore the ability of generative models to generate data beyond it.
Authors: Diego Porres, Yi Xiao, Gabriel Villalonga, Alexandre Levy, Antonio M. L\'opez
Abstract: Vision-based end-to-end driving models trained by imitation learning can lead to affordable solutions for autonomous driving. However, training these well-performing models usually requires a huge amount of data, while still lacking explicit and intuitive activation maps to reveal the inner workings of these models while driving. In this paper, we study how to guide the attention of these models to improve their driving quality and obtain more intuitive activation maps by adding a loss term during training using salient semantic maps. In contrast to previous work, our method does not require these salient semantic maps to be available during testing time, as well as removing the need to modify the model's architecture to which it is applied. We perform tests using perfect and noisy salient semantic maps with encouraging results in both, the latter of which is inspired by possible errors encountered with real data. Using CIL++ as a representative state-of-the-art model and the CARLA simulator with its standard benchmarks, we conduct experiments that show the effectiveness of our method in training better autonomous driving models, especially when data and computational resources are scarce.
Authors: Yong Shu, Liquan Shen, Xiangyu Hu, Mengyao Li, Zihao Zhou
Abstract: As an important and practical way to obtain high dynamic range (HDR) video, HDR video reconstruction from sequences with alternating exposures is still less explored, mainly due to the lack of large-scale real-world datasets. Existing methods are mostly trained on synthetic datasets, which perform poorly in real scenes. In this work, to facilitate the development of real-world HDR video reconstruction, we present Real-HDRV, a large-scale real-world benchmark dataset for HDR video reconstruction, featuring various scenes, diverse motion patterns, and high-quality labels. Specifically, our dataset contains 500 LDRs-HDRs video pairs, comprising about 28,000 LDR frames and 4,000 HDR labels, covering daytime, nighttime, indoor, and outdoor scenes. To our best knowledge, our dataset is the largest real-world HDR video reconstruction dataset. Correspondingly, we propose an end-to-end network for HDR video reconstruction, where a novel two-stage strategy is designed to perform alignment sequentially. Specifically, the first stage performs global alignment with the adaptively estimated global offsets, reducing the difficulty of subsequent alignment. The second stage implicitly performs local alignment in a coarse-to-fine manner at the feature level using the adaptive separable convolution. Extensive experiments demonstrate that: (1) models trained on our dataset can achieve better performance on real scenes than those trained on synthetic datasets; (2) our method outperforms previous state-of-the-art methods. Our dataset is available at https://github.com/yungsyu99/Real-HDRV.
Authors: Narayanan Elavathur Ranganatha, Hengyuan Zhang, Shashank Venkatramani, Jing-Yan Liao, Henrik I. Christensen
Abstract: Vector maps are essential in autonomous driving for tasks like localization and planning, yet their creation and maintenance are notably costly. While recent advances in online vector map generation for autonomous vehicles are promising, current models lack adaptability to different sensor configurations. They tend to overfit to specific sensor poses, leading to decreased performance and higher retraining costs. This limitation hampers their practical use in real-world applications. In response to this challenge, we propose a modular pipeline for vector map generation with improved generalization to sensor configurations. The pipeline leverages probabilistic semantic mapping to generate a bird's-eye-view (BEV) semantic map as an intermediate representation. This intermediate representation is then converted to a vector map using the MapTRv2 decoder. By adopting a BEV semantic map robust to different sensor configurations, our proposed approach significantly improves the generalization performance. We evaluate the model on datasets with sensor configurations not used during training. Our evaluation sets includes larger public datasets, and smaller scale private data collected on our platform. Our model generalizes significantly better than the state-of-the-art methods.
Authors: Dylan Green, William Harvey, Saeid Naderiparizi, Matthew Niedoba, Yunpeng Liu, Xiaoxuan Liang, Jonathan Lavington, Ke Zhang, Vasileios Lioutas, Setareh Dabiri, Adam Scibior, Berend Zwartsenberg, Frank Wood
Abstract: Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames. While such approaches have led to significant progress on standard benchmarks, they struggle with tasks that require the synthesis of novel content that is not present in other frames. In this paper we reframe video inpainting as a conditional generative modeling problem and present a framework for solving such problems with conditional video diffusion models. We highlight the advantages of using a generative approach for this task, showing that our method is capable of generating diverse, high-quality inpaintings and synthesizing new content that is spatially, temporally, and semantically consistent with the provided context.
Authors: Bo Li, Haoke Xiao, Lv Tang
Abstract: In the evolving landscape of computer vision, foundation models have emerged as pivotal tools, exhibiting exceptional adaptability to a myriad of tasks. Among these, the Segment Anything Model (SAM) by Meta AI has distinguished itself in image segmentation. However, SAM, like its counterparts, encounters limitations in specific niche applications, prompting a quest for enhancement strategies that do not compromise its inherent capabilities. This paper introduces ASAM, a novel methodology that amplifies SAM's performance through adversarial tuning. We harness the potential of natural adversarial examples, inspired by their successful implementation in natural language processing. By utilizing a stable diffusion model, we augment a subset (1%) of the SA-1B dataset, generating adversarial instances that are more representative of natural variations rather than conventional imperceptible perturbations. Our approach maintains the photorealism of adversarial examples and ensures alignment with original mask annotations, thereby preserving the integrity of the segmentation task. The fine-tuned ASAM demonstrates significant improvements across a diverse range of segmentation tasks without necessitating additional data or architectural modifications. The results of our extensive evaluations confirm that ASAM establishes new benchmarks in segmentation tasks, thereby contributing to the advancement of foundational models in computer vision. Our project page is in https://asam2024.github.io/.
Authors: Yamato Okamoto, Youngmin Baek, Geewook Kim, Ryota Nakao, DongHyun Kim, Moon Bin Yim, Seunghyun Park, Bado Lee
Abstract: In this study, we formulate an OCR-free sequence generation model for visual document understanding (VDU). Our model not only parses text from document images but also extracts the spatial coordinates of the text based on the multi-head architecture. Named as Coordinate-aware End-to-end Document Parser (CREPE), our method uniquely integrates these capabilities by introducing a special token for OCR text, and token-triggered coordinate decoding. We also proposed a weakly-supervised framework for cost-efficient training, requiring only parsing annotations without high-cost coordinate annotations. Our experimental evaluations demonstrate CREPE's state-of-the-art performances on document parsing tasks. Beyond that, CREPE's adaptability is further highlighted by its successful usage in other document understanding tasks such as layout analysis, document visual question answering, and so one. CREPE's abilities including OCR and semantic parsing not only mitigate error propagation issues in existing OCR-dependent methods, it also significantly enhance the functionality of sequence generation models, ushering in a new era for document understanding studies.
Authors: David R. Treadwell IV, Derek Jacoby, Will Parkinson, Bruce Maxwell, Yvonne Coady
Abstract: Identifying terrain within satellite image data is a key issue in geographical information sciences, with numerous environmental and safety implications. Many techniques exist to derive classifications from spectral data captured by satellites. However, the ability to reliably classify vegetation remains a challenge. In particular, no precise methods exist for classifying forest vs. non-forest vegetation in high-level satellite images. This paper provides an initial proposal for a static, algorithmic process to identify forest regions in satellite image data through texture features created from detected edges and the NDVI ratio captured by Sentinel-2 satellite images. With strong initial results, this paper also identifies the next steps to improve the accuracy of the classification and verification processes.
Authors: Rajat Sahay, Andreas Savakis
Abstract: The emergence of foundation models, such as the Segment Anything Model (SAM), has sparked interest in Parameter-Efficient Fine-Tuning (PEFT) methods that tailor these large models to application domains outside their training data. However, different PEFT techniques modify the representation of a model differently, making it a non-trivial task to select the most appropriate method for the domain of interest. We propose a new framework, Mixture-of-PEFTs methods (MoPEFT), that is inspired by traditional Mixture-of-Experts (MoE) methodologies and is utilized for fine-tuning SAM. Our MoPEFT framework incorporates three different PEFT techniques as submodules and dynamically learns to activate the ones that are best suited for a given data-task setup. We test our method on the Segment Anything Model and show that MoPEFT consistently outperforms other fine-tuning methods on the MESS benchmark.
Authors: Peyman Gholami, Robert Xiao
Abstract: Denoising diffusion models have recently gained prominence as powerful tools for a variety of image generation and manipulation tasks. Building on this, we propose a novel tool for real-time editing of images that provides users with fine-grained region-targeted supervision in addition to existing prompt-based controls. Our novel editing technique, termed Layered Diffusion Brushes, leverages prompt-guided and region-targeted alteration of intermediate denoising steps, enabling precise modifications while maintaining the integrity and context of the input image. We provide an editor based on Layered Diffusion Brushes modifications, which incorporates well-known image editing concepts such as layer masks, visibility toggles, and independent manipulation of layers; regardless of their order. Our system renders a single edit on a 512x512 image within 140 ms using a high-end consumer GPU, enabling real-time feedback and rapid exploration of candidate edits. We validated our method and editing system through a user study involving both natural images (using inversion) and generated images, showcasing its usability and effectiveness compared to existing techniques such as InstructPix2Pix and Stable Diffusion Inpainting for refining images. Our approach demonstrates efficacy across a range of tasks, including object attribute adjustments, error correction, and sequential prompt-based object placement and manipulation, demonstrating its versatility and potential for enhancing creative workflows.
Authors: Ziyi Chen, Xiaolong Wu, Yu Zhang
Abstract: State-of-the-art neural implicit surface representations have achieved impressive results in indoor scene reconstruction by incorporating monocular geometric priors as additional supervision. However, we have observed that multi-view inconsistency between such priors poses a challenge for high-quality reconstructions. In response, we present NC-SDF, a neural signed distance field (SDF) 3D reconstruction framework with view-dependent normal compensation (NC). Specifically, we integrate view-dependent biases in monocular normal priors into the neural implicit representation of the scene. By adaptively learning and correcting the biases, our NC-SDF effectively mitigates the adverse impact of inconsistent supervision, enhancing both the global consistency and local details in the reconstructions. To further refine the details, we introduce an informative pixel sampling strategy to pay more attention to intricate geometry with higher information content. Additionally, we design a hybrid geometry modeling approach to improve the neural implicit representation. Experiments on synthetic and real-world datasets demonstrate that NC-SDF outperforms existing approaches in terms of reconstruction quality.
Authors: Bin Zhao, Chunshi Wang, Shuxue Ding
Abstract: Semi-supervised learning for medical image segmentation presents a unique challenge of efficiently using limited labeled data while leveraging abundant unlabeled data. Despite advancements, existing methods often do not fully exploit the potential of the unlabeled data for enhancing model robustness and accuracy. In this paper, we introduce CrossMatch, a novel framework that integrates knowledge distillation with dual perturbation strategies-image-level and feature-level-to improve the model's learning from both labeled and unlabeled data. CrossMatch employs multiple encoders and decoders to generate diverse data streams, which undergo self-knowledge distillation to enhance consistency and reliability of predictions across varied perturbations. Our method significantly surpasses other state-of-the-art techniques in standard benchmarks by effectively minimizing the gap between training on labeled and unlabeled data and improving edge accuracy and generalization in medical image segmentation. The efficacy of CrossMatch is demonstrated through extensive experimental validations, showing remarkable performance improvements without increasing computational costs. Code for this implementation is made available at https://github.com/AiEson/CrossMatch.git.
Authors: Huy H. Nguyen, Junichi Yamagishi, Isao Echizen
Abstract: This paper investigates the effectiveness of self-supervised pre-trained transformers compared to supervised pre-trained transformers and conventional neural networks (ConvNets) for detecting various types of deepfakes. We focus on their potential for improved generalization, particularly when training data is limited. Despite the notable success of large vision-language models utilizing transformer architectures in various tasks, including zero-shot and few-shot learning, the deepfake detection community has still shown some reluctance to adopt pre-trained vision transformers (ViTs), especially large ones, as feature extractors. One concern is their perceived excessive capacity, which often demands extensive data, and the resulting suboptimal generalization when training or fine-tuning data is small or less diverse. This contrasts poorly with ConvNets, which have already established themselves as robust feature extractors. Additionally, training and optimizing transformers from scratch requires significant computational resources, making this accessible primarily to large companies and hindering broader investigation within the academic community. Recent advancements in using self-supervised learning (SSL) in transformers, such as DINO and its derivatives, have showcased significant adaptability across diverse vision tasks and possess explicit semantic segmentation capabilities. By leveraging DINO for deepfake detection with modest training data and implementing partial fine-tuning, we observe comparable adaptability to the task and the natural explainability of the detection result via the attention mechanism. Moreover, partial fine-tuning of transformers for deepfake detection offers a more resource-efficient alternative, requiring significantly fewer computational resources.
Authors: Hanyang Chi, Jian Pang, Bingfeng Zhang, Weifeng Liu
Abstract: Consistency learning is a central strategy to tackle unlabeled data in semi-supervised medical image segmentation (SSMIS), which enforces the model to produce consistent predictions under the perturbation. However, most current approaches solely focus on utilizing a specific single perturbation, which can only cope with limited cases, while employing multiple perturbations simultaneously is hard to guarantee the quality of consistency learning. In this paper, we propose an Adaptive Bidirectional Displacement (ABD) approach to solve the above challenge. Specifically, we first design a bidirectional patch displacement based on reliable prediction confidence for unlabeled data to generate new samples, which can effectively suppress uncontrollable regions and still retain the influence of input perturbations. Meanwhile, to enforce the model to learn the potentially uncontrollable content, a bidirectional displacement operation with inverse confidence is proposed for the labeled images, which generates samples with more unreliable information to facilitate model learning. Extensive experiments show that ABD achieves new state-of-the-art performances for SSMIS, significantly improving different baselines. Source code is available at https://github.com/chy-upc/ABD.
Authors: Konstantinos Apostolidis, Jakob Abesser, Luca Cuccovillo, Vasileios Mezaris
Abstract: This paper presents a baseline approach and an experimental protocol for a specific content verification problem: detecting discrepancies between the audio and video modalities in multimedia content. We first design and optimize an audio-visual scene classifier, to compare with existing classification baselines that use both modalities. Then, by applying this classifier separately to the audio and the visual modality, we can detect scene-class inconsistencies between them. To facilitate further research and provide a common evaluation platform, we introduce an experimental protocol and a benchmark dataset simulating such inconsistencies. Our approach achieves state-of-the-art results in scene classification and promising outcomes in audio-visual discrepancies detection, highlighting its potential in content verification applications.
Authors: Martin Ki\v{s}\v{s}, Michal Hradi\v{s}
Abstract: In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them. Therefore, methods utilizing unlabeled data are researched. We study self-supervised pre-training methods based on masked label prediction using three different approaches -- Feature Quantization, VQ-VAE, and Post-Quantized AE. We also investigate joint-embedding approaches with VICReg and NT-Xent objectives, for which we propose an image shifting technique to prevent model collapse where it relies solely on positional encoding while completely ignoring the input image. We perform our experiments on historical handwritten (Bentham) and historical printed datasets mainly to investigate the benefits of the self-supervised pre-training techniques with different amounts of annotated target domain data. We use transfer learning as strong baselines. The evaluation shows that the self-supervised pre-training on data from the target domain is very effective, but it struggles to outperform transfer learning from closely related domains. This paper is one of the first researches exploring self-supervised pre-training in document text recognition, and we believe that it will become a cornerstone for future research in this area. We made our implementation of the investigated methods publicly available at https://github.com/DCGM/pero-pretraining.
Authors: Zihan Wang, Ziliang Xiong, Hongying Tang, Xiaobing Yuan
Abstract: Recent years have witnessed the prosperity of reference-based image super-resolution (Ref-SR). By importing the high-resolution (HR) reference images into the single image super-resolution (SISR) approach, the ill-posed nature of this long-standing field has been alleviated with the assistance of texture transferred from reference images. Although the significant improvement in quantitative and qualitative results has verified the superiority of Ref-SR methods, the presence of misalignment before texture transfer indicates room for further performance improvement. Existing methods tend to neglect the significance of details in the context of comparison, therefore not fully leveraging the information contained within low-resolution (LR) images. In this paper, we propose a Detail-Enhancing Framework (DEF) for reference-based super-resolution, which introduces the diffusion model to generate and enhance the underlying detail in LR images. If corresponding parts are present in the reference image, our method can facilitate rigorous alignment. In cases where the reference image lacks corresponding parts, it ensures a fundamental improvement while avoiding the influence of the reference image. Extensive experiments demonstrate that our proposed method achieves superior visual results while maintaining comparable numerical outcomes.
Authors: Xujie Zhang, Ente Lin, Xiu Li, Yuxuan Luo, Michael Kampffmeyer, Xin Dong, Xiaodan Liang
Abstract: This paper introduces MMTryon, a multi-modal multi-reference VIrtual Try-ON (VITON) framework, which can generate high-quality compositional try-on results by taking as inputs a text instruction and multiple garment images. Our MMTryon mainly addresses two problems overlooked in prior literature: 1) Support of multiple try-on items and dressing styleExisting methods are commonly designed for single-item try-on tasks (e.g., upper/lower garments, dresses) and fall short on customizing dressing styles (e.g., zipped/unzipped, tuck-in/tuck-out, etc.) 2) Segmentation Dependency. They further heavily rely on category-specific segmentation models to identify the replacement regions, with segmentation errors directly leading to significant artifacts in the try-on results. For the first issue, our MMTryon introduces a novel multi-modality and multi-reference attention mechanism to combine the garment information from reference images and dressing-style information from text instructions. Besides, to remove the segmentation dependency, MMTryon uses a parsing-free garment encoder and leverages a novel scalable data generation pipeline to convert existing VITON datasets to a form that allows MMTryon to be trained without requiring any explicit segmentation. Extensive experiments on high-resolution benchmarks and in-the-wild test sets demonstrate MMTryon's superiority over existing SOTA methods both qualitatively and quantitatively. Besides, MMTryon's impressive performance on multi-items and style-controllable virtual try-on scenarios and its ability to try on any outfit in a large variety of scenarios from any source image, opens up a new avenue for future investigation in the fashion community.
Authors: Jun Shi, Shulan Ruan, Ziqi Zhu, Minfan Zhao, Hong An, Xudong Xue, Bing Yan
Abstract: Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images. However, most existing methods suffer from unreliable uncertainty assessment and the struggle to balance diversity and informativeness, leading to poor performance in segmentation tasks. In response, we propose an efficient Predictive Accuracy-based Active Learning (PAAL) method for medical image segmentation, first introducing predictive accuracy to define uncertainty. Specifically, PAAL mainly consists of an Accuracy Predictor (AP) and a Weighted Polling Strategy (WPS). The former is an attached learnable module that can accurately predict the segmentation accuracy of unlabeled samples relative to the target model with the predicted posterior probability. The latter provides an efficient hybrid querying scheme by combining predicted accuracy and feature representation, aiming to ensure the uncertainty and diversity of the acquired samples. Extensive experiment results on multiple datasets demonstrate the superiority of PAAL. PAAL achieves comparable accuracy to fully annotated data while reducing annotation costs by approximately 50% to 80%, showcasing significant potential in clinical applications. The code is available at https://github.com/shijun18/PAAL-MedSeg.
Authors: Haozhe Liu, Wentian Zhang, Bing Li, Bernard Ghanem, J\"urgen Schmidhuber
Abstract: Foundational generative models should be traceable to protect their owners and facilitate safety regulation. To achieve this, traditional approaches embed identifiers based on supervisory trigger-response signals, which are commonly known as backdoor watermarks. They are prone to failure when the model is fine-tuned with nontrigger data. Our experiments show that this vulnerability is due to energetic changes in only a few 'busy' layers during fine-tuning. This yields a novel arbitrary-in-arbitrary-out (AIAO) strategy that makes watermarks resilient to fine-tuning-based removal. The trigger-response pairs of AIAO samples across various neural network depths can be used to construct watermarked subpaths, employing Monte Carlo sampling to achieve stable verification results. In addition, unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths, where a mask-controlled trigger function is proposed to preserve the generation performance and ensure the invisibility of the embedded backdoor. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO; while the verification rates of other trigger-based methods fall from ~90% to ~70% after fine-tuning, those of our method remain consistently above 90%.
Authors: Jincheng Zhang, Qijun Zhao, Tie Liu
Abstract: To facilitate the re-identification (Re-ID) of individual animals, existing methods primarily focus on maximizing feature similarity within the same individual and enhancing distinctiveness between different individuals. However, most of them still rely on supervised learning and require substantial labeled data, which is challenging to obtain. To avoid this issue, we propose a Feature-Aware Noise Contrastive Learning (FANCL) method to explore an unsupervised learning solution, which is then validated on the task of red panda re-ID. FANCL employs a Feature-Aware Noise Addition module to produce noised images that conceal critical features and designs two contrastive learning modules to calculate the losses. Firstly, a feature consistency module is designed to bridge the gap between the original and noised features. Secondly, the neural networks are trained through a cluster contrastive learning module. Through these more challenging learning tasks, FANCL can adaptively extract deeper representations of red pandas. The experimental results on a set of red panda images collected in both indoor and outdoor environments prove that FANCL outperforms several related state-of-the-art unsupervised methods, achieving high performance comparable to supervised learning methods.
Authors: Zhilin Zhang
Abstract: Visual Question Answering (VQA) has emerged as a highly engaging field in recent years, attracting increasing research efforts aiming to enhance VQA accuracy through the deployment of advanced models such as Transformers. Despite this growing interest, there has been limited exploration into the comparative analysis and impact of textual modalities within VQA, particularly in terms of model complexity and its effect on performance. In this work, we conduct a comprehensive comparison between complex textual models that leverage long dependency mechanisms and simpler models focusing on local textual features within a well-established VQA framework. Our findings reveal that employing complex textual encoders is not invariably the optimal approach for the VQA-v2 dataset. Motivated by this insight, we introduce an improved model, ConvGRU, which incorporates convolutional layers to enhance the representation of question text. Tested on the VQA-v2 dataset, ConvGRU achieves better performance without substantially increasing parameter complexity.
Authors: Wei-Han Wang, Chin-Yuan Yeh, Hsi-Wen Chen, De-Nian Yang, Ming-Syan Chen
Abstract: As deep generative models advance, we anticipate deepfakes achieving "perfection"-generating no discernible artifacts or noise. However, current deepfake detectors, intentionally or inadvertently, rely on such artifacts for detection, as they are exclusive to deepfakes and absent in genuine examples. To bridge this gap, we introduce the Rebalanced Deepfake Detection Protocol (RDDP) to stress-test detectors under balanced scenarios where genuine and forged examples bear similar artifacts. We offer two RDDP variants: RDDP-WHITEHAT uses white-hat deepfake algorithms to create 'self-deepfakes,' genuine portrait videos with the resemblance of the underlying identity, yet carry similar artifacts to deepfake videos; RDDP-SURROGATE employs surrogate functions (e.g., Gaussian noise) to process both genuine and forged examples, introducing equivalent noise, thereby sidestepping the need of deepfake algorithms. Towards detecting perfect deepfake videos that aligns with genuine ones, we present ID-Miner, a detector that identifies the puppeteer behind the disguise by focusing on motion over artifacts or appearances. As an identity-based detector, it authenticates videos by comparing them with reference footage. Equipped with the artifact-agnostic loss at frame-level and the identity-anchored loss at video-level, ID-Miner effectively singles out identity signals amidst distracting variations. Extensive experiments comparing ID-Miner with 12 baseline detectors under both conventional and RDDP evaluations with two deepfake datasets, along with additional qualitative studies, affirm the superiority of our method and the necessity for detectors designed to counter perfect deepfakes.
Authors: Delong Chen, Samuel Cahyawijaya, Etsuko Ishii, Ho Shu Chan, Yejin Bang, Pascale Fung
Abstract: We introduce a formal information-theoretic framework for image captioning by regarding it as a representation learning task. Our framework defines three key objectives: task sufficiency, minimal redundancy, and human interpretability. Building upon this foundation, we propose a novel Pyramid of Captions (PoCa) method, which constructs caption pyramids by generating localized captions for zoomed-in image patches and integrating them with global caption information using large language models. This approach leverages intuition that the detailed examination of local patches can reduce error risks and address inaccuracies in global captions, either by correcting the hallucination or adding missing details. Based on our theoretical framework, we formalize this intuition and provide formal proof demonstrating the effectiveness of PoCa under certain assumptions. Empirical tests with various image captioning models and large language models show that PoCa consistently yields more informative and semantically aligned captions, maintaining brevity and interpretability.
Authors: Zhinan Yu, Zheng Qin, Yijie Tang, Yongjun Wang, Renjiao Yi, Chenyang Zhu, Kai Xu
Abstract: This paper focuses on training a robust RGB-D registration model without ground-truth pose supervision. Existing methods usually adopt a pairwise training strategy based on differentiable rendering, which enforces the photometric and the geometric consistency between the two registered frames as supervision. However, this frame-to-frame framework suffers from poor multi-view consistency due to factors such as lighting changes, geometry occlusion and reflective materials. In this paper, we present NeRF-UR, a novel frame-to-model optimization framework for unsupervised RGB-D registration. Instead of frame-to-frame consistency, we leverage the neural radiance field (NeRF) as a global model of the scene and use the consistency between the input and the NeRF-rerendered frames for pose optimization. This design can significantly improve the robustness in scenarios with poor multi-view consistency and provides better learning signal for the registration model. Furthermore, to bootstrap the NeRF optimization, we create a synthetic dataset, Sim-RGBD, through a photo-realistic simulator to warm up the registration model. By first training the registration model on Sim-RGBD and later unsupervisedly fine-tuning on real data, our framework enables distilling the capability of feature extraction and registration from simulation to reality. Our method outperforms the state-of-the-art counterparts on two popular indoor RGB-D datasets, ScanNet and 3DMatch. Code and models will be released for paper reproduction.
Authors: Sizhuo Li, Dimitri Gominski, Martin Brandt, Xiaoye Tong, Philippe Ciais
Abstract: Image-level regression is an important task in Earth observation, where visual domain and label shifts are a core challenge hampering generalization. However, cross-domain regression with remote sensing data remains understudied due to the absence of suited datasets. We introduce a new dataset with aerial and satellite imagery in five countries with three forest-related regression tasks. To match real-world applicative interests, we compare methods through a restrictive setup where no prior on the target domain is available during training, and models are adapted with limited information during testing. Building on the assumption that ordered relationships generalize better, we propose manifold diffusion for regression as a strong baseline for transduction in low-data regimes. Our comparison highlights the comparative advantages of inductive and transductive methods in cross-domain regression.
Authors: Young Kyun Jang, Dat Huynh, Ashish Shah, Wen-Kai Chen, Ser-Nam Lim
Abstract: Composed Image Retrieval (CIR) is a complex task that retrieves images using a query, which is configured with an image and a caption that describes desired modifications to that image. Supervised CIR approaches have shown strong performance, but their reliance on expensive manually-annotated datasets restricts their scalability and broader applicability. To address these issues, previous studies have proposed pseudo-word token-based Zero-Shot CIR (ZS-CIR) methods, which utilize a projection module to map images to word tokens. However, we conjecture that this approach has a downside: the projection module distorts the original image representation and confines the resulting composed embeddings to the text-side. In order to resolve this, we introduce a novel ZS-CIR method that uses Spherical Linear Interpolation (Slerp) to directly merge image and text representations by identifying an intermediate embedding of both. Furthermore, we introduce Text-Anchored-Tuning (TAT), a method that fine-tunes the image encoder while keeping the text encoder fixed. TAT closes the modality gap between images and text, making the Slerp process much more effective. Notably, the TAT method is not only efficient in terms of the scale of the training dataset and training time, but it also serves as an excellent initial checkpoint for training supervised CIR models, thereby highlighting its wider potential. The integration of the Slerp-based ZS-CIR with a TAT-tuned model enables our approach to deliver state-of-the-art retrieval performance across CIR benchmarks.
Authors: Deng Li, Xin Liu, Bohao Xing, Baiqiang Xia, Yuan Zong, Bihan Wen, Heikki K\"alvi\"ainen
Abstract: Emotion AI is the ability of computers to understand human emotional states. Existing works have achieved promising progress, but two limitations remain to be solved: 1) Previous studies have been more focused on short sequential video emotion analysis while overlooking long sequential video. However, the emotions in short sequential videos only reflect instantaneous emotions, which may be deliberately guided or hidden. In contrast, long sequential videos can reveal authentic emotions; 2) Previous studies commonly utilize various signals such as facial, speech, and even sensitive biological signals (e.g., electrocardiogram). However, due to the increasing demand for privacy, developing Emotion AI without relying on sensitive signals is becoming important. To address the aforementioned limitations, in this paper, we construct a dataset for Emotion Analysis in Long-sequential and De-identity videos called EALD by collecting and processing the sequences of athletes' post-match interviews. In addition to providing annotations of the overall emotional state of each video, we also provide the Non-Facial Body Language (NFBL) annotations for each player. NFBL is an inner-driven emotional expression and can serve as an identity-free clue to understanding the emotional state. Moreover, we provide a simple but effective baseline for further research. More precisely, we evaluate the Multimodal Large Language Models (MLLMs) with de-identification signals (e.g., visual, speech, and NFBLs) to perform emotion analysis. Our experimental results demonstrate that: 1) MLLMs can achieve comparable, even better performance than the supervised single-modal models, even in a zero-shot scenario; 2) NFBL is an important cue in long sequential emotion analysis. EALD will be available on the open-source platform.
Authors: Yian Zhao, Kehan Li, Zesen Cheng, Pengchong Qiao, Xiawu Zheng, Rongrong Ji, Chang Liu, Li Yuan, Jie Chen
Abstract: Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity output and multi-granularity output. The latter aims to alleviate the spatial ambiguity present in the former. However, the multi-granularity output pipeline suffers from limited interaction flexibility and produces redundant results. In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing additional parameters to input. This enhances the customization of the interactive system and eliminates redundancy while resolving ambiguity. Nevertheless, the exorbitant cost of annotating multi-granularity masks and the lack of available datasets with granularity annotations make it difficult for models to acquire the necessary guidance to control output granularity. To address this problem, we design an any-granularity mask generator that exploits the semantic property of the pre-trained IS model to automatically generate abundant mask-granularity pairs without requiring additional manual annotation. Based on these pairs, we propose a granularity-controllable learning strategy that efficiently imparts the granularity controllability to the IS model. Extensive experiments on intricate scenarios at object and part levels demonstrate that our GraCo has significant advantages over previous methods. This highlights the potential of GraCo to be a flexible annotation tool, capable of adapting to diverse segmentation scenarios. The project page: https://zhao-yian.github.io/GraCo.
Authors: Antonio Ruiz, Andrew Melnik, Dong Wang, Helge Ritter
Abstract: The lane graph is a key component for building high-definition (HD) maps and crucial for downstream tasks such as autonomous driving or navigation planning. Previously, He et al. (2022) explored the extraction of the lane-level graph from aerial imagery utilizing a segmentation based approach. However, segmentation networks struggle to achieve perfect segmentation masks resulting in inaccurate lane graph extraction. We explore additional enhancements to refine this segmentation-based approach and extend it with a diffusion probabilistic model (DPM) component. This combination further improves the GEO F1 and TOPO F1 scores, which are crucial indicators of the quality of a lane graph, in the undirected graph in non-intersection areas. We conduct experiments on a publicly available dataset, demonstrating that our method outperforms the previous approach, particularly in enhancing the connectivity of such a graph, as measured by the TOPO F1 score. Moreover, we perform ablation studies on the individual components of our method to understand their contribution and evaluate their effectiveness.
Authors: Zhihao Guo, Peng Wang
Abstract: Neural Radiance Fields (NeRF) have shown impressive results in 3D reconstruction and generating novel views. A key challenge within NeRF is the editing of reconstructed scenes, such as object removal, which requires maintaining consistency across multiple views and ensuring high-quality synthesised perspectives. Previous studies have incorporated depth priors, typically from LiDAR or sparse depth measurements provided by COLMAP, to improve the performance of object removal in NeRF. However, these methods are either costly or time-consuming. In this paper, we propose a novel approach that integrates monocular depth estimates with NeRF-based object removal models to significantly reduce time consumption and enhance the robustness and quality of scene generation and object removal. We conducted a thorough evaluation of COLMAP's dense depth reconstruction on the KITTI dataset to verify its accuracy in depth map generation. Our findings suggest that COLMAP can serve as an effective alternative to a ground truth depth map where such information is missing or costly to obtain. Additionally, we integrated various monocular depth estimation methods into the removal NeRF model, i.e., SpinNeRF, to assess their capacity to improve object removal performance. Our experimental results highlight the potential of monocular depth estimation to substantially improve NeRF applications.
Authors: Assefa Seyoum Wahd
Abstract: In this paper, we present a novel approach that combines deep metric learning and synthetic data generation using diffusion models for out-of-distribution (OOD) detection. One popular approach for OOD detection is outlier exposure, where models are trained using a mixture of in-distribution (ID) samples and ``seen" OOD samples. For the OOD samples, the model is trained to minimize the KL divergence between the output probability and the uniform distribution while correctly classifying the in-distribution (ID) data. In this paper, we propose a label-mixup approach to generate synthetic OOD data using Denoising Diffusion Probabilistic Models (DDPMs). Additionally, we explore recent advancements in metric learning to train our models. In the experiments, we found that metric learning-based loss functions perform better than the softmax. Furthermore, the baseline models (including softmax, and metric learning) show a significant improvement when trained with the generated OOD data. Our approach outperforms strong baselines in conventional OOD detection metrics.
Authors: Whie Jung, Jaehoon Yoo, Sungjin Ahn, Seunghoon Hong
Abstract: Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, most of the existing approaches rely on auto-encoding objective, while the compositionality is implicitly imposed by the architectural or algorithmic bias in the encoder. This misalignment between auto-encoding objective and learning compositionality often results in failure of capturing meaningful object representations. In this study, we propose a novel objective that explicitly encourages compositionality of the representations. Built upon the existing object-centric learning framework (e.g., slot attention), our method incorporates additional constraints that an arbitrary mixture of object representations from two images should be valid by maximizing the likelihood of the composite data. We demonstrate that incorporating our objective to the existing framework consistently improves the objective-centric learning and enhances the robustness to the architectural choices.
Authors: Colton R. Crum, Samuel Webster, Adam Czajka
Abstract: Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic samples. After the initial collection phase, human visual saliency (e.g., eye-tracking data, or handwritten annotations) can be integrated into model training through attention mechanisms, augmented training samples, or through human perception-related components of loss functions. Despite their successes, a vital, but seemingly neglected, aspect of any saliency-based training is the level of salience granularity (e.g., bounding boxes, single saliency maps, or saliency aggregated from multiple subjects) necessary to find a balance between reaping the full benefits of human saliency and the cost of its collection. In this paper, we explore several different levels of salience granularity and demonstrate that increased generalization capabilities of PAD and synthetic face detection can be achieved by using simple yet effective saliency post-processing techniques across several different CNNs.
Authors: Zheng Zeng, Valentin Deschaintre, Iliyan Georgiev, Yannick Hold-Geoffroy, Yiwei Hu, Fujun Luan, Ling-Qi Yan, Milo\v{s} Ha\v{s}an
Abstract: The three areas of realistic forward rendering, per-pixel inverse rendering, and generative image synthesis may seem like separate and unrelated sub-fields of graphics and vision. However, recent work has demonstrated improved estimation of per-pixel intrinsic channels (albedo, roughness, metallicity) based on a diffusion architecture; we call this the RGB$\rightarrow$X problem. We further show that the reverse problem of synthesizing realistic images given intrinsic channels, X$\rightarrow$RGB, can also be addressed in a diffusion framework. Focusing on the image domain of interior scenes, we introduce an improved diffusion model for RGB$\rightarrow$X, which also estimates lighting, as well as the first diffusion X$\rightarrow$RGB model capable of synthesizing realistic images from (full or partial) intrinsic channels. Our X$\rightarrow$RGB model explores a middle ground between traditional rendering and generative models: we can specify only certain appearance properties that should be followed, and give freedom to the model to hallucinate a plausible version of the rest. This flexibility makes it possible to use a mix of heterogeneous training datasets, which differ in the available channels. We use multiple existing datasets and extend them with our own synthetic and real data, resulting in a model capable of extracting scene properties better than previous work and of generating highly realistic images of interior scenes.
Authors: Andrei Chubarau, Hyunjin Yoo, Tara Akhavan, James Clark
Abstract: Conventional image quality metrics (IQMs), such as PSNR and SSIM, are designed for perceptually uniform gamma-encoded pixel values and cannot be directly applied to perceptually non-uniform linear high-dynamic-range (HDR) colors. Similarly, most of the available datasets consist of standard-dynamic-range (SDR) images collected in standard and possibly uncontrolled viewing conditions. Popular pre-trained neural networks are likewise intended for SDR inputs, restricting their direct application to HDR content. On the other hand, training HDR models from scratch is challenging due to limited available HDR data. In this work, we explore more effective approaches for training deep learning-based models for image quality assessment (IQA) on HDR data. We leverage networks pre-trained on SDR data (source domain) and re-target these models to HDR (target domain) with additional fine-tuning and domain adaptation. We validate our methods on the available HDR IQA datasets, demonstrating that models trained with our combined recipe outperform previous baselines, converge much quicker, and reliably generalize to HDR inputs.
Authors: Runyi Yang, Zhenxin Zhu, Zhou Jiang, Baijun Ye, Xiaoxue Chen, Yifei Zhang, Yuantao Chen, Jian Zhao, Hao Zhao
Abstract: Recently, 3D Gaussian Splatting, as a novel 3D representation, has garnered attention for its fast rendering speed and high rendering quality. However, this comes with high memory consumption, e.g., a well-trained Gaussian field may utilize three million Gaussian primitives and over 700 MB of memory. We credit this high memory footprint to the lack of consideration for the relationship between primitives. In this paper, we propose a memory-efficient Gaussian field named SUNDAE with spectral pruning and neural compensation. On one hand, we construct a graph on the set of Gaussian primitives to model their relationship and design a spectral down-sampling module to prune out primitives while preserving desired signals. On the other hand, to compensate for the quality loss of pruning Gaussians, we exploit a lightweight neural network head to mix splatted features, which effectively compensates for quality losses while capturing the relationship between primitives in its weights. We demonstrate the performance of SUNDAE with extensive results. For example, SUNDAE can achieve 26.80 PSNR at 145 FPS using 104 MB memory while the vanilla Gaussian splatting algorithm achieves 25.60 PSNR at 160 FPS using 523 MB memory, on the Mip-NeRF360 dataset. Codes are publicly available at https://runyiyang.github.io/projects/SUNDAE/.
Authors: Amarjeet Kumar, Hongxu Jiang, Muhammad Imran, Cyndi Valdes, Gabriela Leon, Dahyun Kang, Parvathi Nataraj, Yuyin Zhou, Michael D. Weiss, Wei Shao
Abstract: Deep learning has become the de facto method for medical image segmentation, with 3D segmentation models excelling in capturing complex 3D structures and 2D models offering high computational efficiency. However, segmenting 2.5D images, which have high in-plane but low through-plane resolution, is a relatively unexplored challenge. While applying 2D models to individual slices of a 2.5D image is feasible, it fails to capture the spatial relationships between slices. On the other hand, 3D models face challenges such as resolution inconsistencies in 2.5D images, along with computational complexity and susceptibility to overfitting when trained with limited data. In this context, 2.5D models, which capture inter-slice correlations using only 2D neural networks, emerge as a promising solution due to their reduced computational demand and simplicity in implementation. In this paper, we introduce CSA-Net, a flexible 2.5D segmentation model capable of processing 2.5D images with an arbitrary number of slices through an innovative Cross-Slice Attention (CSA) module. This module uses the cross-slice attention mechanism to effectively capture 3D spatial information by learning long-range dependencies between the center slice (for segmentation) and its neighboring slices. Moreover, CSA-Net utilizes the self-attention mechanism to understand correlations among pixels within the center slice. We evaluated CSA-Net on three 2.5D segmentation tasks: (1) multi-class brain MRI segmentation, (2) binary prostate MRI segmentation, and (3) multi-class prostate MRI segmentation. CSA-Net outperformed leading 2D and 2.5D segmentation methods across all three tasks, demonstrating its efficacy and superiority. Our code is publicly available at https://github.com/mirthAI/CSA-Net.
Authors: Trinath Sai Subhash Reddy Pittala, Uma Maheswara R Meleti, Manasa Thatipamula
Abstract: In this project, we have explored machine learning approaches for predicting hearing loss thresholds on the brain's gray matter 3D images. We have solved the problem statement in two phases. In the first phase, we used a 3D CNN model to reduce high-dimensional input into latent space and decode it into an original image to represent the input in rich feature space. In the second phase, we utilized this model to reduce input into rich features and used these features to train standard machine learning models for predicting hearing thresholds. We have experimented with autoencoders and variational autoencoders in the first phase for dimensionality reduction and explored random forest, XGBoost and multi-layer perceptron for regressing the thresholds. We split the given data set into training and testing sets and achieved an 8.80 range and 22.57 range for PT500 and PT4000 on the test set, respectively. We got the lowest RMSE using multi-layer perceptron among the other models. Our approach leverages the unique capabilities of VAEs to capture complex, non-linear relationships within high-dimensional neuroimaging data. We rigorously evaluated the models using various metrics, focusing on the root mean squared error (RMSE). The results highlight the efficacy of the multi-layer neural network model, which outperformed other techniques in terms of accuracy. This project advances the application of data mining in medical diagnostics and enhances our understanding of age-related hearing loss through innovative machine-learning frameworks.
Authors: Jialiang Wei, Anne-Lise Courbis, Thomas Lambolais, Binbin Xu, Pierre Louis Bernard, G\'erard Dray, Walid Maalej
Abstract: App developers use the Graphical User Interface (GUI) of other apps as an important source of inspiration to design and improve their own apps. In recent years, research suggested various approaches to retrieve GUI designs that fit a certain text query from screenshot datasets acquired through automated GUI exploration. However, such text-to-GUI retrieval approaches only leverage the textual information of the GUI elements in the screenshots, neglecting visual information such as icons or background images. In addition, the retrieved screenshots are not steered by app developers and often lack important app features, e.g. whose UI pages require user authentication. To overcome these limitations, this paper proposes GUing, a GUI search engine based on a vision-language model called UIClip, which we trained specifically for the app GUI domain. For this, we first collected app introduction images from Google Play, which usually display the most representative screenshots selected and often captioned (i.e. labeled) by app vendors. Then, we developed an automated pipeline to classify, crop, and extract the captions from these images. This finally results in a large dataset which we share with this paper: including 303k app screenshots, out of which 135k have captions. We used this dataset to train a novel vision-language model, which is, to the best of our knowledge, the first of its kind in GUI retrieval. We evaluated our approach on various datasets from related work and in manual experiment. The results demonstrate that our model outperforms previous approaches in text-to-GUI retrieval achieving a Recall@10 of up to 0.69 and a HIT@10 of 0.91. We also explored the performance of UIClip for other GUI tasks including GUI classification and Sketch-to-GUI retrieval with encouraging results.
Authors: Longlong Jing, Ruichi Yu, Xu Chen, Zhengli Zhao, Shiwei Sheng, Colin Graber, Qi Chen, Qinru Li, Shangxuan Wu, Han Deng, Sangjin Lee, Chris Sweeney, Qiurui He, Wei-Chih Hung, Tong He, Xingyi Zhou, Farshid Moussavi, Zijian Guo, Yin Zhou, Mingxing Tan, Weilong Yang, Congcong Li
Abstract: Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. Existing works frequently focus on the association task while either neglecting the model performance on state estimation or deploying complex heuristics to predict the states. In this paper, we propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately. STT consumes rich appearance, geometry, and motion signals through long term history of detections and is jointly optimized for both data association and state estimation tasks. Since the standard tracking metrics like MOTA and MOTP do not capture the combined performance of the two tasks in the wider spectrum of object states, we extend them with new metrics called S-MOTA and MOTPS that address this limitation. STT achieves competitive real-time performance on the Waymo Open Dataset.
Authors: Shadab Ahamed, Yixi Xu, Arman Rahmim
Abstract: Minimizing the need for pixel-level annotated data for training PET anomaly segmentation networks is crucial, particularly due to time and cost constraints related to expert annotations. Current un-/weakly-supervised anomaly detection methods rely on autoencoder or generative adversarial networks trained only on healthy data, although these are more challenging to train. In this work, we present a weakly supervised and Implicitly guided COuNterfactual diffusion model for Detecting Anomalies in PET images, branded as IgCONDA-PET. The training is conditioned on image class labels (healthy vs. unhealthy) along with implicit guidance to generate counterfactuals for an unhealthy image with anomalies. The counterfactual generation process synthesizes the healthy counterpart for a given unhealthy image, and the difference between the two facilitates the identification of anomaly locations. The code is available at: https://github.com/igcondapet/IgCONDA-PET.git
Authors: Dayou Du, Gu Gong, Xiaowen Chu
Abstract: Vision Transformers (ViTs) have recently garnered considerable attention, emerging as a promising alternative to convolutional neural networks (CNNs) in several vision-related applications. However, their large model sizes and high computational and memory demands hinder deployment, especially on resource-constrained devices. This underscores the necessity of algorithm-hardware co-design specific to ViTs, aiming to optimize their performance by tailoring both the algorithmic structure and the underlying hardware accelerator to each other's strengths. Model quantization, by converting high-precision numbers to lower-precision, reduces the computational demands and memory needs of ViTs, allowing the creation of hardware specifically optimized for these quantized algorithms, boosting efficiency. This article provides a comprehensive survey of ViTs quantization and its hardware acceleration. We first delve into the unique architectural attributes of ViTs and their runtime characteristics. Subsequently, we examine the fundamental principles of model quantization, followed by a comparative analysis of the state-of-the-art quantization techniques for ViTs. Additionally, we explore the hardware acceleration of quantized ViTs, highlighting the importance of hardware-friendly algorithm design. In conclusion, this article will discuss ongoing challenges and future research paths. We consistently maintain the related open-source materials at https://github.com/DD-DuDa/awesome-vit-quantization-acceleration.
URLs: https://github.com/DD-DuDa/awesome-vit-quantization-acceleration.
Authors: Jens Egholm Pedersen, J\"org Conradt, Tony Lindeberg
Abstract: Biological nervous systems constitute important sources of inspiration towards computers that are faster, cheaper, and more energy efficient. Neuromorphic disciplines view the brain as a coevolved system, simultaneously optimizing the hardware and the algorithms running on it. There are clear efficiency gains when bringing the computations into a physical substrate, but we presently lack theories to guide efficient implementations. Here, we present a principled computational model for neuromorphic systems in terms of spatio-temporal receptive fields, based on affine Gaussian kernels over space and leaky-integrator and leaky integrate-and-fire models over time. Our theory is provably covariant to spatial affine and temporal scaling transformations, and with close similarities to the visual processing in mammalian brains. We use these spatio-temporal receptive fields as a prior in an event-based vision task, and show that this improves the training of spiking networks, which otherwise is known as problematic for event-based vision. This work combines efforts within scale-space theory and computational neuroscience to identify theoretically well-founded ways to process spatio-temporal signals in neuromorphic systems. Our contributions are immediately relevant for signal processing and event-based vision, and can be extended to other processing tasks over space and time, such as memory and control.
Authors: Zidong Cao, Zhan Wang, Yexin Liu, Yan-Pei Cao, Ying Shan, Wei Zeng, Lin Wang
Abstract: Viewing omnidirectional images (ODIs) in virtual reality (VR) represents a novel form of media that provides immersive experiences for users to navigate and interact with digital content. Nonetheless, this sense of immersion can be greatly compromised by a blur effect that masks details and hampers the user's ability to engage with objects of interest. In this paper, we present a novel system, called OmniVR, designed to enhance visual clarity during VR navigation. Our system enables users to effortlessly locate and zoom in on the objects of interest in VR. It captures user commands for navigation and zoom, converting these inputs into parameters for the Mobius transformation matrix. Leveraging these parameters, the ODI is refined using a learning-based algorithm. The resultant ODI is presented within the VR media, effectively reducing blur and increasing user engagement. To verify the effectiveness of our system, we first evaluate our algorithm with state-of-the-art methods on public datasets, which achieves the best performance. Furthermore, we undertake a comprehensive user study to evaluate viewer experiences across diverse scenarios and to gather their qualitative feedback from multiple perspectives. The outcomes reveal that our system enhances user engagement by improving the viewers' recognition, reducing discomfort, and improving the overall immersive experience. Our system makes the navigation and zoom more user-friendly.
Authors: Xia Li, Muheng Li, Antony Lomax, Joachim Buhmann, Ye Zhang
Abstract: Background and purpose: Deformable image registration (DIR) is a crucial tool in radiotherapy for extracting and modelling organ motion. However, when significant changes and sliding boundaries are present, it faces compromised accuracy and uncertainty, determining the subsequential contour propagation and dose accumulation procedures. Materials and methods: We propose an implicit neural representation (INR)-based approach modelling motion continuously in both space and time, named Continues-sPatial-Temporal DIR (CPT-DIR). This method uses a multilayer perception (MLP) network to map 3D coordinate (x,y,z) to its corresponding velocity vector (vx,vy,vz). The displacement vectors (dx,dy,dz) are then calculated by integrating velocity vectors over time. The MLP's parameters can rapidly adapt to new cases without pre-training, enhancing optimisation. The DIR's performance was tested on the DIR-Lab dataset of 10 lung 4DCT cases, using metrics of landmark accuracy (TRE), contour conformity (Dice) and image similarity (MAE). Results: The proposed CPT-DIR can reduce landmark TRE from 2.79mm to 0.99mm, outperforming B-splines' results for all cases. The MAE of the whole-body region improves from 35.46HU to 28.99HU. Furthermore, CPT-DIR surpasses B-splines for accuracy in the sliding boundary region, lowering MAE and increasing Dice coefficients for the ribcage from 65.65HU and 90.41% to 42.04HU and 90.56%, versus 75.40HU and 89.30% without registration. Meanwhile, CPT-DIR offers significant speed advantages, completing in under 15 seconds compared to a few minutes with the conventional B-splines method. Conclusion: Leveraging the continuous representations, the CPT-DIR method significantly enhances registration accuracy, automation and speed, outperforming traditional B-splines in landmark and contour precision, particularly in the challenging areas.
Authors: Zhaojin Fu, Zheng Chen, Jinjiang Li, Lu Ren
Abstract: Deep learning has made important contributions to the development of medical image segmentation. Convolutional neural networks, as a crucial branch, have attracted strong attention from researchers. Through the tireless efforts of numerous researchers, convolutional neural networks have yielded numerous outstanding algorithms for processing medical images. The ideas and architectures of these algorithms have also provided important inspiration for the development of later technologies.Through extensive experimentation, we have found that currently mainstream deep learning algorithms are not always able to achieve ideal results when processing complex datasets and different types of datasets. These networks still have room for improvement in lesion localization and feature extraction. Therefore, we have created the Dense Multiscale Attention and Depth-Supervised Network (DmADs-Net).We use ResNet for feature extraction at different depths and create a Multi-scale Convolutional Feature Attention Block to improve the network's attention to weak feature information. The Local Feature Attention Block is created to enable enhanced local feature attention for high-level semantic information. In addition, in the feature fusion phase, a Feature Refinement and Fusion Block is created to enhance the fusion of different semantic information.We validated the performance of the network using five datasets of varying sizes and types. Results from comparative experiments show that DmADs-Net outperformed mainstream networks. Ablation experiments further demonstrated the effectiveness of the created modules and the rationality of the network architecture.
Authors: Weijian Sun, Yanbo Jia, Qi Zeng, Zihao Liu, Jiang Liao, Yue Li, Xianfeng Li, Bolin Zhao
Abstract: Deep-learning-based techniques have been widely adopted for autonomous driving software stacks for mass production in recent years, focusing primarily on perception modules, with some work extending this method to prediction modules. However, the downstream planning and control modules are still designed with hefty handcrafted rules, dominated by optimization-based methods such as quadratic programming or model predictive control. This results in a performance bottleneck for autonomous driving systems in that corner cases simply cannot be solved by enumerating hand-crafted rules. We present a deep-learning-based approach that brings prediction, decision, and planning modules together with the attempt to overcome the rule-based methods' deficiency in real-world applications of autonomous driving, especially for urban scenes. The DNN model we proposed is solely trained with 10 hours of human driver data, and it supports all mass-production ADAS features available on the market to date. This method is deployed onto a Jiyue test car with no modification to its factory-ready sensor set and compute platform. the feasibility, usability, and commercial potential are demonstrated in this article.
Authors: Ruiquan Ge, Zhaojie Fang, Pengxue Wei, Zhanghao Chen, Hongyang Jiang, Ahmed Elazab, Wangting Li, Xiang Wan, Shaochong Zhang, Changmiao Wang
Abstract: Fundus photography, in combination with the ultra-wide-angle fundus (UWF) techniques, becomes an indispensable diagnostic tool in clinical settings by offering a more comprehensive view of the retina. Nonetheless, UWF fluorescein angiography (UWF-FA) necessitates the administration of a fluorescent dye via injection into the patient's hand or elbow unlike UWF scanning laser ophthalmoscopy (UWF-SLO). To mitigate potential adverse effects associated with injections, researchers have proposed the development of cross-modality medical image generation algorithms capable of converting UWF-SLO images into their UWF-FA counterparts. Current image generation techniques applied to fundus photography encounter difficulties in producing high-resolution retinal images, particularly in capturing minute vascular lesions. To address these issues, we introduce a novel conditional generative adversarial network (UWAFA-GAN) to synthesize UWF-FA from UWF-SLO. This approach employs multi-scale generators and an attention transmit module to efficiently extract both global structures and local lesions. Additionally, to counteract the image blurriness issue that arises from training with misaligned data, a registration module is integrated within this framework. Our method performs non-trivially on inception scores and details generation. Clinical user studies further indicate that the UWF-FA images generated by UWAFA-GAN are clinically comparable to authentic images in terms of diagnostic reliability. Empirical evaluations on our proprietary UWF image datasets elucidate that UWAFA-GAN outperforms extant methodologies. The code is accessible at https://github.com/Tinysqua/UWAFA-GAN.
Authors: Catarina G Bel\'em, Preethi Seshadri, Yasaman Razeghi, Sameer Singh
Abstract: Gender bias research has been pivotal in revealing undesirable behaviors in large language models, exposing serious gender stereotypes associated with occupations, and emotions. A key observation in prior work is that models reinforce stereotypes as a consequence of the gendered correlations that are present in the training data. In this paper, we focus on bias where the effect from training data is unclear, and instead address the question: Do language models still exhibit gender bias in non-stereotypical settings? To do so, we introduce UnStereoEval (USE), a novel framework tailored for investigating gender bias in stereotype-free scenarios. USE defines a sentence-level score based on pretraining data statistics to determine if the sentence contain minimal word-gender associations. To systematically benchmark the fairness of popular language models in stereotype-free scenarios, we utilize USE to automatically generate benchmarks without any gender-related language. By leveraging USE's sentence-level score, we also repurpose prior gender bias benchmarks (Winobias and Winogender) for non-stereotypical evaluation. Surprisingly, we find low fairness across all 28 tested models. Concretely, models demonstrate fair behavior in only 9%-41% of stereotype-free sentences, suggesting that bias does not solely stem from the presence of gender-related words. These results raise important questions about where underlying model biases come from and highlight the need for more systematic and comprehensive bias evaluation. We release the full dataset and code at https://ucinlp.github.io/unstereo-eval.
Authors: Theodor Westny, Bj\"orn Olofsson, Erik Frisk
Abstract: The availability of high-quality datasets is crucial for the development of behavior prediction algorithms in autonomous vehicles. This paper highlights the need for standardizing the use of certain datasets for motion forecasting research to simplify comparative analysis and proposes a set of tools and practices to achieve this. Drawing on extensive experience and a comprehensive review of current literature, we summarize our proposals for preprocessing, visualizing, and evaluation in the form of an open-sourced toolbox designed for researchers working on trajectory prediction problems. The clear specification of necessary preprocessing steps and evaluation metrics is intended to alleviate development efforts and facilitate the comparison of results across different studies. The toolbox is available at: https://github.com/westny/dronalize.
Authors: Julia Guerrero-Viu, Milos Hasan, Arthur Roullier, Midhun Harikumar, Yiwei Hu, Paul Guerrero, Diego Gutierrez, Belen Masia, Valentin Deschaintre
Abstract: Generative models have enabled intuitive image creation and manipulation using natural language. In particular, diffusion models have recently shown remarkable results for natural image editing. In this work, we propose to apply diffusion techniques to edit textures, a specific class of images that are an essential part of 3D content creation pipelines. We analyze existing editing methods and show that they are not directly applicable to textures, since their common underlying approach, manipulating attention maps, is unsuitable for the texture domain. To address this, we propose a novel approach that instead manipulates CLIP image embeddings to condition the diffusion generation. We define editing directions using simple text prompts (e.g., "aged wood" to "new wood") and map these to CLIP image embedding space using a texture prior, with a sampling-based approach that gives us identity-preserving directions in CLIP space. To further improve identity preservation, we project these directions to a CLIP subspace that minimizes identity variations resulting from entangled texture attributes. Our editing pipeline facilitates the creation of arbitrary sliders using natural language prompts only, with no ground-truth annotated data necessary.
Authors: Julieta Martinez, Sasha Doubov, Jack Fan, Ioan Andrei B\^arsan, Shenlong Wang, Gell\'ert M\'attyus, Raquel Urtasun
Abstract: We are interested in understanding whether retrieval-based localization approaches are good enough in the context of self-driving vehicles. Towards this goal, we introduce Pit30M, a new image and LiDAR dataset with over 30 million frames, which is 10 to 100 times larger than those used in previous work. Pit30M is captured under diverse conditions (i.e., season, weather, time of the day, traffic), and provides accurate localization ground truth. We also automatically annotate our dataset with historical weather and astronomical data, as well as with image and LiDAR semantic segmentation as a proxy measure for occlusion. We benchmark multiple existing methods for image and LiDAR retrieval and, in the process, introduce a simple, yet effective convolutional network-based LiDAR retrieval method that is competitive with the state of the art. Our work provides, for the first time, a benchmark for sub-metre retrieval-based localization at city scale. The dataset, its Python SDK, as well as more information about the sensors, calibration, and metadata, are available on the project website: https://pit30m.github.io/
Authors: Luk\'a\v{s} Adam, Vojt\v{e}ch \v{C}erm\'ak, Kostas Papafitsoros, Luk\'a\v{s} Picek
Abstract: This paper introduces the first public large-scale, long-span dataset with sea turtle photographs captured in the wild -- \href{https://www.kaggle.com/datasets/wildlifedatasets/seaturtleid2022}{SeaTurtleID2022}. The dataset contains 8729 photographs of 438 unique individuals collected within 13 years, making it the longest-spanned dataset for animal re-identification. All photographs include various annotations, e.g., identity, encounter timestamp, and body parts segmentation masks. Instead of standard "random" splits, the dataset allows for two realistic and ecologically motivated splits: (i) a \textit{time-aware closed-set} with training, validation, and test data from different days/years, and (ii) a \textit{time-aware open-set} with new unknown individuals in test and validation sets. We show that time-aware splits are essential for benchmarking re-identification methods, as random splits lead to performance overestimation. Furthermore, a baseline instance segmentation and re-identification performance over various body parts is provided. Finally, an end-to-end system for sea turtle re-identification is proposed and evaluated. The proposed system based on Hybrid Task Cascade for head instance segmentation and ArcFace-trained feature-extractor achieved an accuracy of 86.8\%.
URLs: https://www.kaggle.com/datasets/wildlifedatasets/seaturtleid2022
Authors: Yidong Zhao, Changchun Yang, Artur Schweidtmann, Qian Tao
Abstract: The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely considered as the model of choice and a strong baseline for medical image segmentation. However, despite its extraordinary performance, nnU-Net does not supply a measure of uncertainty to indicate its possible failure. This can be problematic for large-scale image segmentation applications, where data are heterogeneous and nnU-Net may fail without notice. In this work, we introduce a novel method to estimate nnU-Net uncertainty for medical image segmentation. We propose a highly effective scheme for posterior sampling of weight space for Bayesian uncertainty estimation. Different from previous baseline methods such as Monte Carlo Dropout and mean-field Bayesian Neural Networks, our proposed method does not require a variational architecture and keeps the original nnU-Net architecture intact, thereby preserving its excellent performance and ease of use. Additionally, we boost the segmentation performance over the original nnU-Net via marginalizing multi-modal posterior models. We applied our method on the public ACDC and M&M datasets of cardiac MRI and demonstrated improved uncertainty estimation over a range of baseline methods. The proposed method further strengthens nnU-Net for medical image segmentation in terms of both segmentation accuracy and quality control.
Authors: Baran Ozaydin, Tong Zhang, Sabine S\"usstrunk, Mathieu Salzmann
Abstract: Unpaired exemplar-based image-to-image (UEI2I) translation aims to translate a source image to a target image domain with the style of a target image exemplar, without ground-truth input-translation pairs. Existing UEI2I methods represent style using one vector per image or rely on semantic supervision to define one style vector per object. Here, in contrast, we propose to represent style as a dense feature map, allowing for a finer-grained transfer to the source image without requiring any external semantic information. We then rely on perceptual and adversarial losses to disentangle our dense style and content representations. To stylize the source content with the exemplar style, we extract unsupervised cross-domain semantic correspondences and warp the exemplar style to the source content. We demonstrate the effectiveness of our method on four datasets using standard metrics together with a localized style metric we propose, which measures style similarity in a class-wise manner. Our results show that the translations produced by our approach are more diverse, preserve the source content better, and are closer to the exemplars when compared to the state-of-the-art methods. Project page: https://github.com/IVRL/dsi2i
Authors: Yiyang Shen, Mingqiang Wei, Yongzhen Wang, Xueyang Fu, Jing Qin
Abstract: Recent diffusion models have exhibited great potential in generative modeling tasks. Part of their success can be attributed to the ability of training stable on huge sets of paired synthetic data. However, adapting these models to real-world image deraining remains difficult for two aspects. First, collecting a large-scale paired real-world clean/rainy dataset is unavailable while regular conditional diffusion models heavily rely on paired data for training. Second, real-world rain usually reflects real-world scenarios with a variety of unknown rain degradation types, which poses a significant challenge for the generative modeling process. To meet these challenges, we propose RainDiff, the first real-world image deraining paradigm based on diffusion models, serving as a new standard bar for real-world image deraining. We address the first challenge by introducing a stable and non-adversarial unpaired cycle-consistent architecture that can be trained, end-to-end, with only unpaired data for supervision; and the second challenge by proposing a degradation-conditioned diffusion model that refines the desired output via a diffusive generative process conditioned by learned priors of multiple rain degradations. Extensive experiments confirm the superiority of our RainDiff over existing unpaired/semi-supervised methods and show its competitive advantages over several fully-supervised ones.
Authors: Sanket Thakur, Cigdem Beyan, Pietro Morerio, Vittorio Murino, Alessio Del Bue
Abstract: This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place. The problem is considerably hard, as we aim at estimating the position of such objects in a scenario where the observed clip and the action segment are separated by the so-called ``time to contact'' (TTC) segment. Many methods have been proposed to anticipate the action of a person based on previous hand movements and interactions with the surroundings. However, there have been no attempts to investigate the next possible interactable object, and its future location with respect to the first-person's motion and the field-of-view drift during the TTC window. We define this as the task of Anticipating the Next ACTive Object (ANACTO). To this end, we propose a transformer-based self-attention framework to identify and locate the next-active-object in an egocentric clip. We benchmark our method on three datasets: EpicKitchens-100, EGTEA+ and Ego4D. We also provide annotations for the first two datasets. Our approach performs best compared to relevant baseline methods. We also conduct ablation studies to understand the effectiveness of the proposed and baseline methods on varying conditions. Code and ANACTO task annotations will be made available upon paper acceptance.
Authors: Chuanxin Song, Hanbo Wu, Xin Ma
Abstract: Exploring the semantic context in scene images is essential for indoor scene recognition. However, due to the diverse intra-class spatial layouts and the coexisting inter-class objects, modeling contextual relationships to adapt various image characteristics is a great challenge. Existing contextual modeling methods for scene recognition exhibit two limitations: 1) They typically model only one kind of spatial relationship among objects within scenes in an artificially predefined manner, with limited exploration of diverse spatial layouts. 2) They often overlook the differences in coexisting objects across different scenes, suppressing scene recognition performance. To overcome these limitations, we propose SpaCoNet, which simultaneously models Spatial relation and Co-occurrence of objects guided by semantic segmentation. Firstly, the Semantic Spatial Relation Module (SSRM) is constructed to model scene spatial features. With the help of semantic segmentation, this module decouples the spatial information from the scene image and thoroughly explores all spatial relationships among objects in an end-to-end manner. Secondly, both spatial features from the SSRM and deep features from the Image Feature Extraction Module are allocated to each object, so as to distinguish the coexisting object across different scenes. Finally, utilizing the discriminative features above, we design a Global-Local Dependency Module to explore the long-range co-occurrence among objects, and further generate a semantic-guided feature representation for indoor scene recognition. Experimental results on three widely used scene datasets demonstrate the effectiveness and generality of the proposed method.
Authors: Aditya Aditya, Bharat Lohani, Jagannath Aryal, Stephan Winter
Abstract: Vegetation is crucial for sustainable and resilient cities providing various ecosystem services and well-being of humans. However, vegetation is under critical stress with rapid urbanization and expanding infrastructure footprints. Consequently, mapping of this vegetation is essential in the urban environment. Recently, deep learning for point cloud semantic segmentation has shown significant progress. Advanced models attempt to obtain state-of-the-art performance on benchmark datasets, comprising multiple classes and representing real world scenarios. However, class specific segmentation with respect to vegetation points has not been explored. Therefore, selection of a deep learning model for vegetation points segmentation is ambiguous. To address this problem, we provide a comprehensive assessment of point-based deep learning models for semantic segmentation of vegetation class. We have selected seven representative point-based models, namely PointCNN, KPConv (omni-supervised), RandLANet, SCFNet, PointNeXt, SPoTr and PointMetaBase. These models are investigated on three different datasets, specifically Chandigarh, Toronto3D and Kerala, which are characterized by diverse nature of vegetation and varying scene complexity combined with changing per-point features and class-wise composition. PointMetaBase and KPConv (omni-supervised) achieve the highest mIoU on the Chandigarh (95.24%) and Toronto3D datasets (91.26%), respectively while PointCNN provides the highest mIoU on the Kerala dataset (85.68%). The paper develops a deeper insight, hitherto not reported, into the working of these models for vegetation segmentation and outlines the ingredients that should be included in a model specifically for vegetation segmentation. This paper is a step towards the development of a novel architecture for vegetation points segmentation.
Authors: Xin Lai, Zhuotao Tian, Yukang Chen, Yanwei Li, Yuhui Yuan, Shu Liu, Jiaya Jia
Abstract: Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems cannot actively reason and comprehend implicit user intention. In this work, we propose a new segmentation task -- reasoning segmentation. The task is designed to output a segmentation mask given a complex and implicit query text. Furthermore, we establish a benchmark comprising over one thousand image-instruction-mask data samples, incorporating intricate reasoning and world knowledge for evaluation purposes. Finally, we present LISA: large Language Instructed Segmentation Assistant, which inherits the language generation capabilities of multimodal Large Language Models (LLMs) while also possessing the ability to produce segmentation masks. We expand the original vocabulary with a
Authors: Jordan Dotzel, Gang Wu, Andrew Li, Muhammad Umar, Yun Ni, Mohamed S. Abdelfattah, Zhiru Zhang, Liqun Cheng, Martin G. Dixon, Norman P. Jouppi, Quoc V. Le, Sheng Li
Abstract: Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent hardware, including multiple variants of integer and floating point, mixed-precision quantization has become necessary to achieve high-quality results with low model cost. Prior mixed-precision methods have performed either a post-training quantization search, which compromises on accuracy, or a differentiable quantization search, which leads to high memory usage from branching. Therefore, we propose the first one-shot mixed-precision quantization search that eliminates the need for retraining in both integer and low-precision floating point models. We evaluate our search (FLIQS) on multiple convolutional and vision transformer networks to discover Pareto-optimal models. Our approach improves upon uniform precision, manual mixed-precision, and recent integer quantization search methods. With integer models, we increase the accuracy of ResNet-18 on ImageNet by 1.31% and ResNet-50 by 0.90% with equivalent model cost over previous methods. Additionally, for the first time, we explore a novel mixed-precision floating-point search and improve MobileNetV2 by up to 0.98% compared to prior state-of-the-art FP8 models. Finally, we extend FLIQS to simultaneously search a joint quantization and neural architecture space and improve the ImageNet accuracy by 2.69% with similar model cost on a MobileNetV2 search space.
Authors: Che Liu, Sibo Cheng, Miaojing Shi, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: In the field of medical Vision-Language Pre-training (VLP), significant efforts have been devoted to deriving text and image features from both clinical reports and associated medical images. However, most existing methods may have overlooked the opportunity in leveraging the inherent hierarchical structure of clinical reports, which are generally split into `findings' for descriptive content and `impressions' for conclusive observation. Instead of utilizing this rich, structured format, current medical VLP approaches often simplify the report into either a unified entity or fragmented tokens. In this work, we propose a novel clinical prior guided VLP framework named IMITATE to learn the structure information from medical reports with hierarchical vision-language alignment. The framework derives multi-level visual features from the chest X-ray (CXR) images and separately aligns these features with the descriptive and the conclusive text encoded in the hierarchical medical report. Furthermore, a new clinical-informed contrastive loss is introduced for cross-modal learning, which accounts for clinical prior knowledge in formulating sample correlations in contrastive learning. The proposed model, IMITATE, outperforms baseline VLP methods across six different datasets, spanning five medical imaging downstream tasks. Comprehensive experimental results highlight the advantages of integrating the hierarchical structure of medical reports for vision-language alignment.
Authors: Yu Tian, Min Shi, Yan Luo, Ava Kouhana, Tobias Elze, Mengyu Wang
Abstract: Fairness in artificial intelligence models has gained significantly more attention in recent years, especially in the area of medicine, as fairness in medical models is critical to people's well-being and lives. High-quality medical fairness datasets are needed to promote fairness learning research. Existing medical fairness datasets are all for classification tasks, and no fairness datasets are available for medical segmentation, while medical segmentation is an equally important clinical task as classifications, which can provide detailed spatial information on organ abnormalities ready to be assessed by clinicians. In this paper, we propose the first fairness dataset for medical segmentation named Harvard-FairSeg with 10,000 subject samples. In addition, we propose a fair error-bound scaling approach to reweight the loss function with the upper error-bound in each identity group, using the segment anything model (SAM). We anticipate that the segmentation performance equity can be improved by explicitly tackling the hard cases with high training errors in each identity group. To facilitate fair comparisons, we utilize a novel equity-scaled segmentation performance metric to compare segmentation metrics in the context of fairness, such as the equity-scaled Dice coefficient. Through comprehensive experiments, we demonstrate that our fair error-bound scaling approach either has superior or comparable fairness performance to the state-of-the-art fairness learning models. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/datasets/harvard-fairseg10k.
URLs: https://ophai.hms.harvard.edu/datasets/harvard-fairseg10k.
Authors: Dan Song, Xuanpu Zhang, Juan Zhou, Weizhi Nie, Ruofeng Tong, Mohan Kankanhalli, An-An Liu
Abstract: Image-based virtual try-on aims to synthesize a naturally dressed person image with a clothing image, which revolutionizes online shopping and inspires related topics within image generation, showing both research significance and commercial potential. However, there is a gap between current research progress and commercial applications and an absence of comprehensive overview of this field to accelerate the development. In this survey, we provide a comprehensive analysis of the state-of-the-art techniques and methodologies in aspects of pipeline architecture, person representation and key modules such as try-on indication, clothing warping and try-on stage. We propose a new semantic criteria with CLIP, and evaluate representative methods with uniformly implemented evaluation metrics on the same dataset. In addition to quantitative and qualitative evaluation of current open-source methods, unresolved issues are highlighted and future research directions are prospected to identify key trends and inspire further exploration. The uniformly implemented evaluation metrics, dataset and collected methods will be made public available at https://github.com/little-misfit/Survey-Of-Virtual-Try-On.
URLs: https://github.com/little-misfit/Survey-Of-Virtual-Try-On.
Authors: Lei Wang, Bo Liu, Yinchi Ma, Fangfang Liang, Nawei Guo
Abstract: Gait recognition has achieved promising advances in controlled settings, yet it significantly struggles in unconstrained environments due to challenges such as view changes, occlusions, and varying walking speeds. Additionally, efforts to fuse multiple modalities often face limited improvements because of cross-modality incompatibility, particularly in outdoor scenarios. To address these issues, we present a multi-modal Hierarchy in Hierarchy network (HiH) that integrates silhouette and pose sequences for robust gait recognition. HiH features a main branch that utilizes Hierarchical Gait Decomposer (HGD) modules for depth-wise and intra-module hierarchical examination of general gait patterns from silhouette data. This approach captures motion hierarchies from overall body dynamics to detailed limb movements, facilitating the representation of gait attributes across multiple spatial resolutions. Complementing this, an auxiliary branch, based on 2D joint sequences, enriches the spatial and temporal aspects of gait analysis. It employs a Deformable Spatial Enhancement (DSE) module for pose-guided spatial attention and a Deformable Temporal Alignment (DTA) module for aligning motion dynamics through learned temporal offsets. Extensive evaluations across diverse indoor and outdoor datasets demonstrate HiH's state-of-the-art performance, affirming a well-balanced trade-off between accuracy and efficiency.
Authors: Zheng Zhang, Cuong Nguyen, Kevin Wells, Thanh-Toan Do, Gustavo Carneiro
Abstract: Real-world image classification tasks tend to be complex, where expert labellers are sometimes unsure about the classes present in the images, leading to the issue of learning with noisy labels (LNL). The ill-posedness of the LNL task requires the adoption of strong assumptions or the use of multiple noisy labels per training image, resulting in accurate models that work well in isolation but fail to optimise human-AI collaborative classification (HAI-CC). Unlike such LNL methods, HAI-CC aims to leverage the synergies between human expertise and AI capabilities but requires clean training labels, limiting its real-world applicability. This paper addresses this gap by introducing the innovative Learning to Complement with Multiple Humans (LECOMH) approach. LECOMH is designed to learn from noisy labels without depending on clean labels, simultaneously maximising collaborative accuracy while minimising the cost of human collaboration, measured by the number of human expert annotations required per image. Additionally, new benchmarks featuring multiple noisy labels for both training and testing are proposed to evaluate HAI-CC methods. Through quantitative comparisons on these benchmarks, LECOMH consistently outperforms competitive HAI-CC approaches, human labellers, multi-rater learning, and noisy-label learning methods across various datasets, offering a promising solution for addressing real-world image classification challenges.
Authors: Mike Ranzinger, Greg Heinrich, Jan Kautz, Pavlo Molchanov
Abstract: A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks. VFMs like CLIP, DINOv2, SAM are trained with distinct objectives, exhibiting unique characteristics for various downstream tasks. We find that despite their conceptual differences, these models can be effectively merged into a unified model through multi-teacher distillation. We name this approach AM-RADIO (Agglomerative Model -- Reduce All Domains Into One). This integrative approach not only surpasses the performance of individual teacher models but also amalgamates their distinctive features, such as zero-shot vision-language comprehension, detailed pixel-level understanding, and open vocabulary segmentation capabilities. In pursuit of the most hardware-efficient backbone, we evaluated numerous architectures in our multi-teacher distillation pipeline using the same training recipe. This led to the development of a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 7x faster than the teacher models. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, ADE20k semantic segmentation, COCO object detection and LLaVa-1.5 framework. Code: https://github.com/NVlabs/RADIO
Authors: Nathan Vance, Patrick Flynn
Abstract: Model architecture refinement is a challenging task in deep learning research fields such as remote photoplethysmography (rPPG). One architectural consideration, the depth of the model, can have significant consequences on the resulting performance. In rPPG models that are overprovisioned with more layers than necessary, redundancies exist, the removal of which can result in faster training and reduced computational load at inference time. With too few layers the models may exhibit sub-optimal error rates. We apply Centered Kernel Alignment (CKA) to an array of rPPG architectures of differing depths, demonstrating that shallower models do not learn the same representations as deeper models, and that after a certain depth, redundant layers are added without significantly increased functionality. An empirical study confirms how the architectural deficiencies discovered using CKA impact performance, and we show how CKA as a diagnostic can be used to refine rPPG architectures.
Authors: Kai He, Kaixin Yao, Qixuan Zhang, Lingjie Liu, Jingyi Yu, Lan Xu
Abstract: Apparel's significant role in human appearance underscores the importance of garment digitalization for digital human creation. Recent advances in 3D content creation are pivotal for digital human creation. Nonetheless, garment generation from text guidance is still nascent. We introduce a text-driven 3D garment generation framework, DressCode, which aims to democratize design for novices and offer immense potential in fashion design, virtual try-on, and digital human creation. We first introduce SewingGPT, a GPT-based architecture integrating cross-attention with text-conditioned embedding to generate sewing patterns with text guidance. We then tailor a pre-trained Stable Diffusion to generate tile-based Physically-based Rendering (PBR) textures for the garments. By leveraging a large language model, our framework generates CG-friendly garments through natural language interaction. It also facilitates pattern completion and texture editing, streamlining the design process through user-friendly interaction. This framework fosters innovation by allowing creators to freely experiment with designs and incorporate unique elements into their work. With comprehensive evaluations and comparisons with other state-of-the-art methods, our method showcases superior quality and alignment with input prompts. User studies further validate our high-quality rendering results, highlighting its practical utility and potential in production settings. Our project page is https://IHe-KaiI.github.io/DressCode/.
Authors: Jan Valosek, Theo Mathieu, Raphaelle Schlienger, Olivia S. Kowalczyk, Julien Cohen-Adad
Abstract: Precise identification of spinal nerve rootlets is relevant to delineate spinal levels for the study of functional activity in the spinal cord. The goal of this study was to develop an automatic method for the semantic segmentation of spinal nerve rootlets from T2-weighted magnetic resonance imaging (MRI) scans. Images from two open-access MRI datasets were used to train a 3D multi-class convolutional neural network using an active learning approach to segment C2-C8 dorsal nerve rootlets. Each output class corresponds to a spinal level. The method was tested on 3T T2-weighted images from datasets unseen during training to assess inter-site, inter-session, and inter-resolution variability. The test Dice score was 0.67 +- 0.16 (mean +- standard deviation across testing images and rootlets levels), suggesting a good performance. The method also demonstrated low inter-vendor and inter-site variability (coefficient of variation <= 1.41 %), as well as low inter-session variability (coefficient of variation <= 1.30 %) indicating stable predictions across different MRI vendors, sites, and sessions. The proposed methodology is open-source and readily available in the Spinal Cord Toolbox (SCT) v6.2 and higher.
Authors: Jingwang Ling, Ruihan Yu, Feng Xu, Chun Du, Shuang Zhao
Abstract: Physics-based inverse rendering enables joint optimization of shape, material, and lighting based on captured 2D images. To ensure accurate reconstruction, using a light model that closely resembles the captured environment is essential. Although the widely adopted distant environmental lighting model is adequate in many cases, we demonstrate that its inability to capture spatially varying illumination can lead to inaccurate reconstructions in many real-world inverse rendering scenarios. To address this limitation, we incorporate NeRF as a non-distant environment emitter into the inverse rendering pipeline. Additionally, we introduce an emitter importance sampling technique for NeRF to reduce the rendering variance. Through comparisons on both real and synthetic datasets, our results demonstrate that our NeRF-based emitter offers a more precise representation of scene lighting, thereby improving the accuracy of inverse rendering.
Authors: Binyan Hu, A. K. Qin
Abstract: Medical image segmentation (MIS) plays an instrumental role in medical image analysis, where considerable effort has been devoted to automating the process. Currently, mainstream MIS approaches are based on deep neural networks (DNNs), which are typically trained on a dataset with annotations produced by certain medical experts. In the medical domain, the annotations generated by different experts can be inherently distinct due to complexity of medical images and variations in expertise and post-segmentation missions. Consequently, the DNN model trained on the data annotated by some experts may hardly adapt to a new expert. In this work, we evaluate a customised expert-adaptive method, characterised by multi-expert annotation, multi-task DNN-based model training, and lightweight model fine-tuning, to investigate model's adaptivity to a new expert in the situation where the amount and mobility of training images are limited. Experiments conducted on brain MRI segmentation tasks with limited training data demonstrate its effectiveness and the impact of its key parameters.
Authors: Safouane El Ghazouali, Youssef Mhirit, Ali Oukhrid, Umberto Michelucci, Hichem Nouira
Abstract: In the realm of computer vision, the integration of advanced techniques into the processing of RGB-D camera inputs poses a significant challenge, given the inherent complexities arising from diverse environmental conditions and varying object appearances. Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for the robust 3D segmentation of objects in RGB-D imagery. Traditional computer vision systems face limitations in simultaneously capturing precise object boundaries and achieving high-precision object detection on depth map as they are mainly proposed for RGB cameras. To address this challenge, FusionVision adopts an integrated approach by merging state-of-the-art object detection techniques, with advanced instance segmentation methods. The integration of these components enables a holistic (unified analysis of information obtained from both color \textit{RGB} and depth \textit{D} channels) interpretation of RGB-D data, facilitating the extraction of comprehensive and accurate object information. The proposed FusionVision pipeline employs YOLO for identifying objects within the RGB image domain. Subsequently, FastSAM, an innovative semantic segmentation model, is applied to delineate object boundaries, yielding refined segmentation masks. The synergy between these components and their integration into 3D scene understanding ensures a cohesive fusion of object detection and segmentation, enhancing overall precision in 3D object segmentation. The code and pre-trained models are publicly available at https://github.com/safouaneelg/FusionVision/.
Authors: Pengyu Yan, Mahesh Bhosale, Jay Lal, Bikhyat Adhikari, David Doermann
Abstract: Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and supplementary information, making it difficult to alter their appearance for different application scenarios. To eliminate the need for original underlying data and information to perform chart editing, we propose ChartReformer, a natural language-driven chart image editing solution that directly edits the charts from the input images with the given instruction prompts. The key in this method is that we allow the model to comprehend the chart and reason over the prompt to generate the corresponding underlying data table and visual attributes for new charts, enabling precise edits. Additionally, to generalize ChartReformer, we define and standardize various types of chart editing, covering style, layout, format, and data-centric edits. The experiments show promising results for the natural language-driven chart image editing.
Authors: Yew Ken Chia, Vernon Toh Yan Han, Deepanway Ghosal, Lidong Bing, Soujanya Poria
Abstract: Large multimodal models extend the impressive capabilities of large language models by integrating multimodal understanding abilities. However, it is not clear how they can emulate the general intelligence and reasoning ability of humans. As recognizing patterns and abstracting concepts are key to general intelligence, we introduce PuzzleVQA, a collection of puzzles based on abstract patterns. With this dataset, we evaluate large multimodal models with abstract patterns based on fundamental concepts, including colors, numbers, sizes, and shapes. Through our experiments on state-of-the-art large multimodal models, we find that they are not able to generalize well to simple abstract patterns. Notably, even GPT-4V cannot solve more than half of the puzzles. To diagnose the reasoning challenges in large multimodal models, we progressively guide the models with our ground truth reasoning explanations for visual perception, inductive reasoning, and deductive reasoning. Our systematic analysis finds that the main bottlenecks of GPT-4V are weaker visual perception and inductive reasoning abilities. Through this work, we hope to shed light on the limitations of large multimodal models and how they can better emulate human cognitive processes in the future (Our data and code will be released publicly at https://github.com/declare-lab/LLM-PuzzleTest).
Authors: Linchen Qian, Jiasong Chen, Linhai Ma, Timur Urakov, Weiyong Gu, Liang Liang
Abstract: Lumbar disc degeneration, a progressive structural wear and tear of lumbar intervertebral disc, is regarded as an essential role on low back pain, a significant global health concern. Automated lumbar spine geometry reconstruction from MR images will enable fast measurement of medical parameters to evaluate the lumbar status, in order to determine a suitable treatment. Existing image segmentation-based techniques often generate erroneous segments or unstructured point clouds, unsuitable for medical parameter measurement. In this work, we present $\textit{UNet-DeformSA}$ and $\textit{TransDeformer}$: novel attention-based deep neural networks that reconstruct the geometry of the lumbar spine with high spatial accuracy and mesh correspondence across patients, and we also present a variant of $\textit{TransDeformer}$ for error estimation. Specially, we devise new attention modules with a new attention formula, which integrate image features and tokenized contour features to predict the displacements of the points on a shape template without the need for image segmentation. The deformed template reveals the lumbar spine geometry in an image. Experiment results show that our networks generate artifact-free geometry outputs, and the variant of $\textit{TransDeformer}$ can predict the errors of a reconstructed geometry. Our code is available at https://github.com/linchenq/TransDeformer-Mesh.
Authors: Maxim Nikolaev, Mikhail Kuznetsov, Dmitry Vetrov, Aibek Alanov
Abstract: Our paper addresses the complex task of transferring a hairstyle from a reference image to an input photo for virtual hair try-on. This task is challenging due to the need to adapt to various photo poses, the sensitivity of hairstyles, and the lack of objective metrics. The current state of the art hairstyle transfer methods use an optimization process for different parts of the approach, making them inexcusably slow. At the same time, faster encoder-based models are of very low quality because they either operate in StyleGAN's W+ space or use other low-dimensional image generators. Additionally, both approaches have a problem with hairstyle transfer when the source pose is very different from the target pose, because they either don't consider the pose at all or deal with it inefficiently. In our paper, we present the HairFast model, which uniquely solves these problems and achieves high resolution, near real-time performance, and superior reconstruction compared to optimization problem-based methods. Our solution includes a new architecture operating in the FS latent space of StyleGAN, an enhanced inpainting approach, and improved encoders for better alignment, color transfer, and a new encoder for post-processing. The effectiveness of our approach is demonstrated on realism metrics after random hairstyle transfer and reconstruction when the original hairstyle is transferred. In the most difficult scenario of transferring both shape and color of a hairstyle from different images, our method performs in less than a second on the Nvidia V100. Our code is available at https://github.com/AIRI-Institute/HairFastGAN.
Authors: Safouane El Ghazouali, Arnaud Gucciardi, Nicola Venturi, Michael Rueegsegger, Umberto Michelucci
Abstract: Object detection in remotely sensed satellite pictures is fundamental in many fields such as biophysical, and environmental monitoring. While deep learning algorithms are constantly evolving, they have been mostly implemented and tested on popular ground-based taken photos. This paper critically evaluates and compares a suite of advanced object detection algorithms customized for the task of identifying aircraft within satellite imagery. Using the large HRPlanesV2 dataset, together with a rigorous validation with the GDIT dataset, this research encompasses an array of methodologies including YOLO versions 5 and 8, Faster RCNN, CenterNet, RetinaNet, RTMDet, and DETR, all trained from scratch. This exhaustive training and validation study reveal YOLOv5 as the preeminent model for the specific case of identifying airplanes from remote sensing data, showcasing high precision and adaptability across diverse imaging conditions. This research highlight the nuanced performance landscapes of these algorithms, with YOLOv5 emerging as a robust solution for aerial object detection, underlining its importance through superior mean average precision, Recall, and Intersection over Union scores. The findings described here underscore the fundamental role of algorithm selection aligned with the specific demands of satellite imagery analysis and extend a comprehensive framework to evaluate model efficacy. The benchmark toolkit and codes, available via https://github.com/toelt-llc/FlightScope_Bench, aims to further exploration and innovation in the realm of remote sensing object detection, paving the way for improved analytical methodologies in satellite imagery applications.
Authors: Zhihao Chen, Yiyuan Ge
Abstract: The goal of occluded person re-identification (ReID) is to retrieve specific pedestrians in occluded situations. However, occluded person ReID still suffers from background clutter and low-quality local feature representations, which limits model performance. In our research, we introduce a new framework called PAB-ReID, which is a novel ReID model incorporating part-attention mechanisms to tackle the aforementioned issues effectively. Firstly, we introduce the human parsing label to guide the generation of more accurate human part attention maps. In addition, we propose a fine-grained feature focuser for generating fine-grained human local feature representations while suppressing background interference. Moreover, We also design a part triplet loss to supervise the learning of human local features, which optimizes intra/inter-class distance. We conducted extensive experiments on specialized occlusion and regular ReID datasets, showcasing that our approach outperforms the existing state-of-the-art methods.
Authors: Sam Cantrill, David Ahmedt-Aristizabal, Lars Petersson, Hanna Suominen, Mohammad Ali Armin
Abstract: Camera-based remote photoplethysmography (rPPG) enables contactless measurement of important physiological signals such as pulse rate (PR). However, dynamic and unconstrained subject motion introduces significant variability into the facial appearance in video, confounding the ability of video-based methods to accurately extract the rPPG signal. In this study, we leverage the 3D facial surface to construct a novel orientation-conditioned facial texture video representation which improves the motion robustness of existing video-based facial rPPG estimation methods. Our proposed method achieves a significant 18.2% performance improvement in cross-dataset testing on MMPD over our baseline using the PhysNet model trained on PURE, highlighting the efficacy and generalization benefits of our designed video representation. We demonstrate significant performance improvements of up to 29.6% in all tested motion scenarios in cross-dataset testing on MMPD, even in the presence of dynamic and unconstrained subject motion, emphasizing the benefits of disentangling motion through modeling the 3D facial surface for motion robust facial rPPG estimation. We validate the efficacy of our design decisions and the impact of different video processing steps through an ablation study. Our findings illustrate the potential strengths of exploiting the 3D facial surface as a general strategy for addressing dynamic and unconstrained subject motion in videos. The code is available at https://samcantrill.github.io/orientation-uv-rppg/.
Authors: Khai Nguyen, Nhat Ho
Abstract: Sliced Wasserstein (SW) and Generalized Sliced Wasserstein (GSW) have been widely used in applications due to their computational and statistical scalability. However, the SW and the GSW are only defined between distributions supported on a homogeneous domain. This limitation prevents their usage in applications with heterogeneous joint distributions with marginal distributions supported on multiple different domains. Using SW and GSW directly on the joint domains cannot make a meaningful comparison since their homogeneous slicing operator i.e., Radon Transform (RT) and Generalized Radon Transform (GRT) are not expressive enough to capture the structure of the joint supports set. To address the issue, we propose two new slicing operators i.e., Partial Generalized Radon Transform (PGRT) and Hierarchical Hybrid Radon Transform (HHRT). In greater detail, PGRT is the generalization of Partial Radon Transform (PRT), which transforms a subset of function arguments non-linearly while HHRT is the composition of PRT and multiple domain-specific PGRT on marginal domain arguments. By using HHRT, we extend the SW into Hierarchical Hybrid Sliced Wasserstein (H2SW) distance which is designed specifically for comparing heterogeneous joint distributions. We then discuss the topological, statistical, and computational properties of H2SW. Finally, we demonstrate the favorable performance of H2SW in 3D mesh deformation, deep 3D mesh autoencoders, and datasets comparison.
Authors: Teng Hu, Jiangning Zhang, Ran Yi, Yating Wang, Hongrui Huang, Jieyu Weng, Yabiao Wang, Lizhuang Ma
Abstract: The emergence of diffusion models has greatly propelled the progress in image and video generation. Recently, some efforts have been made in controllable video generation, including text-to-video generation and video motion control, among which camera motion control is an important topic. However, existing camera motion control methods rely on training a temporal camera module, and necessitate substantial computation resources due to the large amount of parameters in video generation models. Moreover, existing methods pre-define camera motion types during training, which limits their flexibility in camera control. Therefore, to reduce training costs and achieve flexible camera control, we propose COMD, a novel training-free video motion transfer model, which disentangles camera motions and object motions in source videos and transfers the extracted camera motions to new videos. We first propose a one-shot camera motion disentanglement method to extract camera motion from a single source video, which separates the moving objects from the background and estimates the camera motion in the moving objects region based on the motion in the background by solving a Poisson equation. Furthermore, we propose a few-shot camera motion disentanglement method to extract the common camera motion from multiple videos with similar camera motions, which employs a window-based clustering technique to extract the common features in temporal attention maps of multiple videos. Finally, we propose a motion combination method to combine different types of camera motions together, enabling our model a more controllable and flexible camera control. Extensive experiments demonstrate that our training-free approach can effectively decouple camera-object motion and apply the decoupled camera motion to a wide range of controllable video generation tasks, achieving flexible and diverse camera motion control.
Authors: Xin Zhang, Liangxiu Han, Tam Sobeih, Lianghao Han, Darren Dancey
Abstract: Depth estimation is crucial for interpreting complex environments, especially in areas such as autonomous vehicle navigation and robotics. Nonetheless, obtaining accurate depth readings from event camera data remains a formidable challenge. Event cameras operate differently from traditional digital cameras, continuously capturing data and generating asynchronous binary spikes that encode time, location, and light intensity. Yet, the unique sampling mechanisms of event cameras render standard image based algorithms inadequate for processing spike data. This necessitates the development of innovative, spike-aware algorithms tailored for event cameras, a task compounded by the irregularity, continuity, noise, and spatial and temporal characteristics inherent in spiking data.Harnessing the strong generalization capabilities of transformer neural networks for spatiotemporal data, we propose a purely spike-driven spike transformer network for depth estimation from spiking camera data. To address performance limitations with Spiking Neural Networks (SNN), we introduce a novel single-stage cross-modality knowledge transfer framework leveraging knowledge from a large vision foundational model of artificial neural networks (ANN) (DINOv2) to enhance the performance of SNNs with limited data. Our experimental results on both synthetic and real datasets show substantial improvements over existing models, with notable gains in Absolute Relative and Square Relative errors (49% and 39.77% improvements over the benchmark model Spike-T, respectively). Besides accuracy, the proposed model also demonstrates reduced power consumptions, a critical factor for practical applications.
Authors: Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
Abstract: Document layout analysis involves understanding the arrangement of elements within a document. This paper navigates the complexities of understanding various elements within document images, such as text, images, tables, and headings. The approach employs an advanced Transformer-based object detection network as an innovative graphical page object detector for identifying tables, figures, and displayed elements. We introduce a query encoding mechanism to provide high-quality object queries for contrastive learning, enhancing efficiency in the decoder phase. We also present a hybrid matching scheme that integrates the decoder's original one-to-one matching strategy with the one-to-many matching strategy during the training phase. This approach aims to improve the model's accuracy and versatility in detecting various graphical elements on a page. Our experiments on PubLayNet, DocLayNet, and PubTables benchmarks show that our approach outperforms current state-of-the-art methods. It achieves an average precision of 97.3% on PubLayNet, 81.6% on DocLayNet, and 98.6 on PubTables, demonstrating its superior performance in layout analysis. These advancements not only enhance the conversion of document images into editable and accessible formats but also streamline information retrieval and data extraction processes.
Authors: Tengjun Huang
Abstract: With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal downstream tasks, its implementation in the remote sensing domain encounters some obstacles. Specifically, the tendency for same-modality embeddings to cluster together impedes efficient transfer learning. To tackle this issue, we review the aim of multimodal transfer learning for downstream tasks from a unified perspective, and rethink the optimization process based on three distinct objectives. We propose "Harmonized Transfer Learning and Modality Alignment (HarMA)", a method that simultaneously satisfies task constraints, modality alignment, and single-modality uniform alignment, while minimizing training overhead through parameter-efficient fine-tuning. Remarkably, without the need for external data for training, HarMA achieves state-of-the-art performance in two popular multimodal retrieval tasks in the field of remote sensing. Our experiments reveal that HarMA achieves competitive and even superior performance to fully fine-tuned models with only minimal adjustable parameters. Due to its simplicity, HarMA can be integrated into almost all existing multimodal pretraining models. We hope this method can facilitate the efficient application of large models to a wide range of downstream tasks while significantly reducing the resource consumption. Code is available at https://github.com/seekerhuang/HarMA.
Authors: Jinwon Ko, Dongkwon Jin, Chang-Su Kim
Abstract: A novel algorithm, called semantic line combination detector (SLCD), to find an optimal combination of semantic lines is proposed in this paper. It processes all lines in each line combination at once to assess the overall harmony of the lines. First, we generate various line combinations from reliable lines. Second, we estimate the score of each line combination and determine the best one. Experimental results demonstrate that the proposed SLCD outperforms existing semantic line detectors on various datasets. Moreover, it is shown that SLCD can be applied effectively to three vision tasks of vanishing point detection, symmetry axis detection, and composition-based image retrieval. Our codes are available at https://github.com/Jinwon-Ko/SLCD.
Authors: Xin Ma, Puchen Zhu, Xiao Li, Xiaoyin Zheng, Jianshu Zhou, Xuchen Wang, Kwok Wai Samuel Au
Abstract: Depth position highly affects lens distortion, especially in close-range photography, which limits the measurement accuracy of existing stereo vision systems. Moreover, traditional depth-dependent distortion models and their calibration methods have remained complicated. In this work, we propose a minimal set of parameters based depth-dependent distortion model (MDM), which considers the radial and decentering distortions of the lens to improve the accuracy of stereo vision systems and simplify their calibration process. In addition, we present an easy and flexible calibration method for the MDM of stereo vision systems with a commonly used planar pattern, which requires cameras to observe the planar pattern in different orientations. The proposed technique is easy to use and flexible compared with classical calibration techniques for depth-dependent distortion models in which the lens must be perpendicular to the planar pattern. The experimental validation of the MDM and its calibration method showed that the MDM improved the calibration accuracy by 56.55% and 74.15% compared with the Li's distortion model and traditional Brown's distortion model. Besides, an iteration-based reconstruction method is proposed to iteratively estimate the depth information in the MDM during three-dimensional reconstruction. The results showed that the accuracy of the iteration-based reconstruction method was improved by 9.08% compared with that of the non-iteration reconstruction method.
Authors: Zhenglin Li, Bo Guan, Yuanzhou Wei, Yiming Zhou, Jingyu Zhang, Jinxin Xu
Abstract: Generative Adversarial Networks (GANs) have significantly advanced image processing, with Pix2Pix being a notable framework for image-to-image translation. This paper explores a novel application of Pix2Pix to transform abstract map images into realistic ground truth images, addressing the scarcity of such images crucial for domains like urban planning and autonomous vehicle training. We detail the Pix2Pix model's utilization for generating high-fidelity datasets, supported by a dataset of paired map and aerial images, and enhanced by a tailored training regimen. The results demonstrate the model's capability to accurately render complex urban features, establishing its efficacy and potential for broad real-world applications.
Authors: Lingyi Hong, Zhongying Liu, Wenchao Chen, Chenzhi Tan, Yuang Feng, Xinyu Zhou, Pinxue Guo, Jinglun Li, Zhaoyu Chen, Shuyong Gao, Wei Zhang, Wenqiang Zhang
Abstract: Video object segmentation (VOS) aims to distinguish and track target objects in a video. Despite the excellent performance achieved by off-the-shell VOS models, existing VOS benchmarks mainly focus on short-term videos lasting about 5 seconds, where objects remain visible most of the time. However, these benchmarks poorly represent practical applications, and the absence of long-term datasets restricts further investigation of VOS in realistic scenarios. Thus, we propose a novel benchmark named LVOS, comprising 720 videos with 296,401 frames and 407,945 high-quality annotations. Videos in LVOS last 1.14 minutes on average, approximately 5 times longer than videos in existing datasets. Each video includes various attributes, especially challenges deriving from the wild, such as long-term reappearing and cross-temporal similar objects. Compared to previous benchmarks, our LVOS better reflects VOS models' performance in real scenarios. Based on LVOS, we evaluate 20 existing VOS models under 4 different settings and conduct a comprehensive analysis. On LVOS, these models suffer a large performance drop, highlighting the challenge of achieving precise tracking and segmentation in real-world scenarios. Attribute-based analysis indicates that key factor to accuracy decline is the increased video length, emphasizing LVOS's crucial role. We hope our LVOS can advance development of VOS in real scenes. Data and code are available at https://lingyihongfd.github.io/lvos.github.io/.
Authors: Zhexi Peng, Tianjia Shao, Yong Liu, Jingke Zhou, Yin Yang, Jingdong Wang, Kun Zhou
Abstract: We present Real-time Gaussian SLAM (RTG-SLAM), a real-time 3D reconstruction system with an RGBD camera for large-scale environments using Gaussian splatting. The system features a compact Gaussian representation and a highly efficient on-the-fly Gaussian optimization scheme. We force each Gaussian to be either opaque or nearly transparent, with the opaque ones fitting the surface and dominant colors, and transparent ones fitting residual colors. By rendering depth in a different way from color rendering, we let a single opaque Gaussian well fit a local surface region without the need of multiple overlapping Gaussians, hence largely reducing the memory and computation cost. For on-the-fly Gaussian optimization, we explicitly add Gaussians for three types of pixels per frame: newly observed, with large color errors, and with large depth errors. We also categorize all Gaussians into stable and unstable ones, where the stable Gaussians are expected to well fit previously observed RGBD images and otherwise unstable. We only optimize the unstable Gaussians and only render the pixels occupied by unstable Gaussians. In this way, both the number of Gaussians to be optimized and pixels to be rendered are largely reduced, and the optimization can be done in real time. We show real-time reconstructions of a variety of large scenes. Compared with the state-of-the-art NeRF-based RGBD SLAM, our system achieves comparable high-quality reconstruction but with around twice the speed and half the memory cost, and shows superior performance in the realism of novel view synthesis and camera tracking accuracy.
Authors: Emiel Hoogeboom, Tim Salimans
Abstract: Recently, Rissanen et al., (2022) have presented a new type of diffusion process for generative modeling based on heat dissipation, or blurring, as an alternative to isotropic Gaussian diffusion. Here, we show that blurring can equivalently be defined through a Gaussian diffusion process with non-isotropic noise. In making this connection, we bridge the gap between inverse heat dissipation and denoising diffusion, and we shed light on the inductive bias that results from this modeling choice. Finally, we propose a generalized class of diffusion models that offers the best of both standard Gaussian denoising diffusion and inverse heat dissipation, which we call Blurring Diffusion Models.
Authors: Samuel Goree, Gabriel Appleby, David Crandall, Norman Su
Abstract: Research papers, in addition to textual documents, are a designed interface through which researchers communicate. Recently, rapid growth has transformed that interface in many fields of computing. In this work, we examine the effects of this growth from a media archaeology perspective, through the changes to figures and tables in research papers. Specifically, we study these changes in computer vision over the past decade, as the deep learning revolution has driven unprecedented growth in the discipline. We ground our investigation through interviews with veteran researchers spanning computer vision, graphics and visualization. Our analysis focuses on the research attention economy: how research paper elements contribute towards advertising, measuring and disseminating an increasingly commodified ``contribution.'' Through this work, we seek to motivate future discussion surrounding the design of both the research paper itself as well as the larger sociotechnical research publishing system, including tools for finding, reading and writing research papers.
Authors: Sixing Yu, J. Pablo Mu\~noz, Ali Jannesari
Abstract: Federated Learning (FL) is extensively used to train AI/ML models in distributed and privacy-preserving settings. Participant edge devices in FL systems typically contain non-independent and identically distributed (Non-IID) private data and unevenly distributed computational resources. Preserving user data privacy while optimizing AI/ML models in a heterogeneous federated network requires us to address data and system/resource heterogeneity. To address these challenges, we propose Resource-aware Federated Learning (RaFL). RaFL allocates resource-aware specialized models to edge devices using Neural Architecture Search (NAS) and allows heterogeneous model architecture deployment by knowledge extraction and fusion. Combining NAS and FL enables on-demand customized model deployment for resource-diverse edge devices. Furthermore, we propose a multi-model architecture fusion scheme allowing the aggregation of the distributed learning results. Results demonstrate RaFL's superior resource efficiency compared to SoTA.
Authors: Pedro C. Neto, Diana Montezuma, Sara P. Oliveira, Domingos Oliveira, Jo\~ao Fraga, Ana Monteiro, Jo\~ao Monteiro, Liliana Ribeiro, Sofia Gon\c{c}alves, Stefan Reinhard, Inti Zlobec, Isabel M. Pinto, Jaime S. Cardoso
Abstract: Considering the profound transformation affecting pathology practice, we aimed to develop a scalable artificial intelligence (AI) system to diagnose colorectal cancer from whole-slide images (WSI). For this, we propose a deep learning (DL) system that learns from weak labels, a sampling strategy that reduces the number of training samples by a factor of six without compromising performance, an approach to leverage a small subset of fully annotated samples, and a prototype with explainable predictions, active learning features and parallelisation. Noting some problems in the literature, this study is conducted with one of the largest WSI colorectal samples dataset with approximately 10,500 WSIs. Of these samples, 900 are testing samples. Furthermore, the robustness of the proposed method is assessed with two additional external datasets (TCGA and PAIP) and a dataset of samples collected directly from the proposed prototype. Our proposed method predicts, for the patch-based tiles, a class based on the severity of the dysplasia and uses that information to classify the whole slide. It is trained with an interpretable mixed-supervision scheme to leverage the domain knowledge introduced by pathologists through spatial annotations. The mixed-supervision scheme allowed for an intelligent sampling strategy effectively evaluated in several different scenarios without compromising the performance. On the internal dataset, the method shows an accuracy of 93.44% and a sensitivity between positive (low-grade and high-grade dysplasia) and non-neoplastic samples of 0.996. On the external test samples varied with TCGA being the most challenging dataset with an overall accuracy of 84.91% and a sensitivity of 0.996.
Authors: Debesh Jha, Nikhil Kumar Tomar, Debayan Bhattacharya, Ulas Bagci
Abstract: Colorectal cancer is among the most common cause of cancer worldwide. Removal of precancerous polyps through early detection is essential to prevent them from progressing to colon cancer. We develop an advanced deep learning-based architecture, Transformer based Residual Upsampling Network (TransRUPNet) for automatic and real-time polyp segmentation. The proposed architecture, TransRUPNet, is an encoder-decoder network consisting of three encoder and decoder blocks with additional upsampling blocks at the end of the network. With the image size of $256\times256$, the proposed method achieves an excellent real-time operation speed of 47.07 frames per second with an average mean dice coefficient score of 0.7786 and mean Intersection over Union of 0.7210 on the out-of-distribution polyp datasets. The results on the publicly available PolypGen dataset suggest that TransRUPNet can give real-time feedback while retaining high accuracy for in-distribution datasets. Furthermore, we demonstrate the generalizability of the proposed method by showing that it significantly improves performance on out-of-distribution datasets compared to the existing methods. The source code of our network is available at https://github.com/DebeshJha/TransRUPNet.
Authors: Zeyu Tang, Xiaodan Xing, Guang Yang
Abstract: Deep learning-based Generative Models have the potential to convert low-resolution CT images into high-resolution counterparts without long acquisition times and increased radiation exposure in thin-slice CT imaging. However, procuring appropriate training data for these Super-Resolution (SR) models is challenging. Previous SR research has simulated thick-slice CT images from thin-slice CT images to create training pairs. However, these methods either rely on simplistic interpolation techniques that lack realism or sinogram reconstruction, which require the release of raw data and complex reconstruction algorithms. Thus, we introduce a simple yet realistic method to generate thick CT images from thin-slice CT images, facilitating the creation of training pairs for SR algorithms. The training pairs produced by our method closely resemble real data distributions (PSNR=49.74 vs. 40.66, p$<$0.05). A multivariate Cox regression analysis involving thick slice CT images with lung fibrosis revealed that only the radiomics features extracted using our method demonstrated a significant correlation with mortality (HR=1.19 and HR=1.14, p$<$0.005). This paper represents the first to identify and address the challenge of generating appropriate paired training data for Deep Learning-based CT SR models, which enhances the efficacy and applicability of SR models in real-world scenarios.
Authors: Junyu Chen, Yihao Liu, Shuwen Wei, Zhangxing Bian, Shalini Subramanian, Aaron Carass, Jerry L. Prince, Yong Du
Abstract: Deep learning technologies have dramatically reshaped the field of medical image registration over the past decade. The initial developments, such as regression-based and U-Net-based networks, established the foundation for deep learning in image registration. Subsequent progress has been made in various aspects of deep learning-based registration, including similarity measures, deformation regularizations, network architectures, and uncertainty estimation. These advancements have not only enriched the field of image registration but have also facilitated its application in a wide range of tasks, including atlas construction, multi-atlas segmentation, motion estimation, and 2D-3D registration. In this paper, we present a comprehensive overview of the most recent advancements in deep learning-based image registration. We begin with a concise introduction to the core concepts of deep learning-based image registration. Then, we delve into innovative network architectures, loss functions specific to registration, and methods for estimating registration uncertainty. Additionally, this paper explores appropriate evaluation metrics for assessing the performance of deep learning models in registration tasks. Finally, we highlight the practical applications of these novel techniques in medical imaging and discuss the future prospects of deep learning-based image registration.
Authors: Md Yousuf Harun, Jhair Gallardo, Junyu Chen, Christopher Kanan
Abstract: Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of previously learned abilities. A popular solution is rehearsal: storing past observations in a buffer and then sampling the buffer to update the DNN. Uniform sampling in a class-balanced manner is highly effective, and better sample selection policies have been elusive. Here, we propose a new sample selection policy called GRASP that selects the most prototypical (easy) samples first and then gradually selects less prototypical (harder) examples. GRASP has little additional compute or memory overhead compared to uniform selection, enabling it to scale to large datasets. Compared to 17 other rehearsal policies, GRASP achieves higher accuracy in CL experiments on ImageNet. Compared to uniform balanced sampling, GRASP achieves the same performance with 40% fewer updates. We also show that GRASP is effective for CL on five text classification datasets.
Authors: Jan-Nico Zaech, Martin Danelljan, Tolga Birdal, Luc Van Gool
Abstract: Adiabatic quantum computing (AQC) is a promising approach for discrete and often NP-hard optimization problems. Current AQCs allow to implement problems of research interest, which has sparked the development of quantum representations for many computer vision tasks. Despite requiring multiple measurements from the noisy AQC, current approaches only utilize the best measurement, discarding information contained in the remaining ones. In this work, we explore the potential of using this information for probabilistic balanced k-means clustering. Instead of discarding non-optimal solutions, we propose to use them to compute calibrated posterior probabilities with little additional compute cost. This allows us to identify ambiguous solutions and data points, which we demonstrate on a D-Wave AQC on synthetic tasks and real visual data.
Authors: Yidong Zhao, Yi Zhang, Qian Tao
Abstract: Deep learning-based methods have achieved prestigious performance for magnetic resonance imaging (MRI) reconstruction, enabling fast imaging for many clinical applications. Previous methods employ convolutional networks to learn the image prior as the regularization term. In quantitative MRI, the physical model of nuclear magnetic resonance relaxometry is known, providing additional prior knowledge for image reconstruction. However, traditional reconstruction networks are limited to learning the spatial domain prior knowledge, ignoring the relaxometry prior. Therefore, we propose a relaxometry-guided quantitative MRI reconstruction framework to learn the spatial prior from data and the relaxometry prior from MRI physics. Additionally, we also evaluated the performance of two popular reconstruction backbones, namely, recurrent variational networks (RVN) and variational networks (VN) with U- Net. Experiments demonstrate that the proposed method achieves highly promising results in quantitative MRI reconstruction.
Authors: Amir Aghabiglou, Chung San Chu, Arwa Dabbech, Yves Wiaux
Abstract: Radio-interferometric (RI) imaging entails solving high-resolution high-dynamic range inverse problems from large data volumes. Recent image reconstruction techniques grounded in optimization theory have demonstrated remarkable capability for imaging precision, well beyond CLEAN's capability. These range from advanced proximal algorithms propelled by handcrafted regularization operators, such as the SARA family, to hybrid plug-and-play (PnP) algorithms propelled by learned regularization denoisers, such as AIRI. Optimization and PnP structures are however highly iterative, which hinders their ability to handle the extreme data sizes expected from future instruments. To address this scalability challenge, we introduce a novel deep learning approach, dubbed "Residual-to-Residual DNN series for high-Dynamic range imaging". R2D2's reconstruction is formed as a series of residual images, iteratively estimated as outputs of Deep Neural Networks (DNNs) taking the previous iteration's image estimate and associated data residual as inputs. It thus takes a hybrid structure between a PnP algorithm and a learned version of the matching pursuit algorithm that underpins CLEAN. We present a comprehensive study of our approach, featuring its multiple incarnations distinguished by their DNN architectures. We provide a detailed description of its training process, targeting a telescope-specific approach. R2D2's capability to deliver high precision is demonstrated in simulation, across a variety of image and observation settings using the Very Large Array (VLA). Its reconstruction speed is also demonstrated: with only few iterations required to clean data residuals at dynamic ranges up to 100000, R2D2 opens the door to fast precision imaging. R2D2 codes are available in the BASPLib library on GitHub.
Authors: Richard Osuala, Daniel Lang, Preeti Verma, Smriti Joshi, Apostolia Tsirikoglou, Grzegorz Skorupko, Kaisar Kushibar, Lidia Garrucho, Walter H. L. Pinaya, Oliver Diaz, Julia Schnabel, Karim Lekadir
Abstract: Contrast agents in dynamic contrast enhanced magnetic resonance imaging allow to localize tumors and observe their contrast kinetics, which is essential for cancer characterization and respective treatment decision-making. However, contrast agent administration is not only associated with adverse health risks, but also restricted for patients during pregnancy, and for those with kidney malfunction, or other adverse reactions. With contrast uptake as key biomarker for lesion malignancy, cancer recurrence risk, and treatment response, it becomes pivotal to reduce the dependency on intravenous contrast agent administration. To this end, we propose a multi-conditional latent diffusion model capable of acquisition time-conditioned image synthesis of DCE-MRI temporal sequences. To evaluate medical image synthesis, we additionally propose and validate the Fr\'echet radiomics distance as an image quality measure based on biomarker variability between synthetic and real imaging data. Our results demonstrate our method's ability to generate realistic multi-sequence fat-saturated breast DCE-MRI and uncover the emerging potential of deep learning based contrast kinetics simulation. We publicly share our accessible codebase at https://github.com/RichardObi/ccnet and provide a user-friendly library for Fr\'echet radiomics distance calculation at https://pypi.org/project/frd-score.
URLs: https://github.com/RichardObi/ccnet, https://pypi.org/project/frd-score.
Authors: Daniel Platnick, Sourena Khanzadeh, Alireza Sadeghian, Richard Anthony Valenzano
Abstract: Microplastic particle ingestion or inhalation by humans is a problem of growing concern. Unfortunately, current research methods that use machine learning to understand their potential harms are obstructed by a lack of available data. Deep learning techniques in particular are challenged by such domains where only small or imbalanced data sets are available. Overcoming this challenge often involves oversampling underrepresented classes or augmenting the existing data to improve model performance. This paper proposes GANsemble: a two-module framework connecting data augmentation with conditional generative adversarial networks (cGANs) to generate class-conditioned synthetic data. First, the data chooser module automates augmentation strategy selection by searching for the best data augmentation strategy. Next, the cGAN module uses this strategy to train a cGAN for generating enhanced synthetic data. We experiment with the GANsemble framework on a small and imbalanced microplastics data set. A Microplastic-cGAN (MPcGAN) algorithm is introduced, and baselines for synthetic microplastics (SYMP) data are established in terms of Frechet Inception Distance (FID) and Inception Scores (IS). We also provide a synthetic microplastics filter (SYMP-Filter) algorithm to increase the quality of generated SYMP. Additionally, we show the best amount of oversampling with augmentation to fix class imbalance in small microplastics data sets. To our knowledge, this study is the first application of generative AI to synthetically create microplastics data.
Authors: Khaled Saab, Tao Tu, Wei-Hung Weng, Ryutaro Tanno, David Stutz, Ellery Wulczyn, Fan Zhang, Tim Strother, Chunjong Park, Elahe Vedadi, Juanma Zambrano Chaves, Szu-Yeu Hu, Mike Schaekermann, Aishwarya Kamath, Yong Cheng, David G. T. Barrett, Cathy Cheung, Basil Mustafa, Anil Palepu, Daniel McDuff, Le Hou, Tomer Golany, Luyang Liu, Jean-baptiste Alayrac, Neil Houlsby, Nenad Tomasev, Jan Freyberg, Charles Lau, Jonas Kemp, Jeremy Lai, Shekoofeh Azizi, Kimberly Kanada, SiWai Man, Kavita Kulkarni, Ruoxi Sun, Siamak Shakeri, Luheng He, Ben Caine, Albert Webson, Natasha Latysheva, Melvin Johnson, Philip Mansfield, Jian Lu, Ehud Rivlin, Jesper Anderson, Bradley Green, Renee Wong, Jonathan Krause, Jonathon Shlens, Ewa Dominowska, S. M. Ali Eslami, Katherine Chou, Claire Cui, Oriol Vinyals, Koray Kavukcuoglu, James Manyika, Jeff Dean, Demis Hassabis, Yossi Matias, Dale Webster, Joelle Barral, Greg Corrado, Christopher Semturs, S. Sara Mahdavi, Juraj Gottweis, Alan Karthikesalingam, Vivek Natarajan
Abstract: Excellence in a wide variety of medical applications poses considerable challenges for AI, requiring advanced reasoning, access to up-to-date medical knowledge and understanding of complex multimodal data. Gemini models, with strong general capabilities in multimodal and long-context reasoning, offer exciting possibilities in medicine. Building on these core strengths of Gemini, we introduce Med-Gemini, a family of highly capable multimodal models that are specialized in medicine with the ability to seamlessly use web search, and that can be efficiently tailored to novel modalities using custom encoders. We evaluate Med-Gemini on 14 medical benchmarks, establishing new state-of-the-art (SoTA) performance on 10 of them, and surpass the GPT-4 model family on every benchmark where a direct comparison is viable, often by a wide margin. On the popular MedQA (USMLE) benchmark, our best-performing Med-Gemini model achieves SoTA performance of 91.1% accuracy, using a novel uncertainty-guided search strategy. On 7 multimodal benchmarks including NEJM Image Challenges and MMMU (health & medicine), Med-Gemini improves over GPT-4V by an average relative margin of 44.5%. We demonstrate the effectiveness of Med-Gemini's long-context capabilities through SoTA performance on a needle-in-a-haystack retrieval task from long de-identified health records and medical video question answering, surpassing prior bespoke methods using only in-context learning. Finally, Med-Gemini's performance suggests real-world utility by surpassing human experts on tasks such as medical text summarization, alongside demonstrations of promising potential for multimodal medical dialogue, medical research and education. Taken together, our results offer compelling evidence for Med-Gemini's potential, although further rigorous evaluation will be crucial before real-world deployment in this safety-critical domain.