Authors: Muhammad Aurangzeb Ahmad, Ilker Yaramis, Taposh Dutta Roy
Large language models have proliferated across multiple domains in as short period of time. There is however hesitation in the medical and healthcare domain towards their adoption because of issues like factuality, coherence, and hallucinations. Give the high stakes nature of healthcare, many researchers have even cautioned against its usage until these issues are resolved. The key to the implementation and deployment of LLMs in healthcare is to make these models trustworthy, transparent (as much possible) and explainable. In this paper we describe the key elements in creating reliable, trustworthy, and unbiased models as a necessary condition for their adoption in healthcare. Specifically we focus on the quantification, validation, and mitigation of hallucinations in the context in healthcare. Lastly, we discuss how the future of LLMs in healthcare may look like.
Authors: Jiakai Wang, Donghua Wang, Jin Hu, Siyang Wu, Tingsong Jiang, Wen Yao, Aishan Liu, Xianglong Liu
Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples. Besides the attacks in the digital world, the practical implications of adversarial examples in the physical world present significant challenges and safety concerns. However, current research on physical adversarial examples (PAEs) lacks a comprehensive understanding of their unique characteristics, leading to limited significance and understanding. In this paper, we address this gap by thoroughly examining the characteristics of PAEs within a practical workflow encompassing training, manufacturing, and re-sampling processes. By analyzing the links between physical adversarial attacks, we identify manufacturing and re-sampling as the primary sources of distinct attributes and particularities in PAEs. Leveraging this knowledge, we develop a comprehensive analysis and classification framework for PAEs based on their specific characteristics, covering over 100 studies on physical-world adversarial examples. Furthermore, we investigate defense strategies against PAEs and identify open challenges and opportunities for future research. We aim to provide a fresh, thorough, and systematic understanding of PAEs, thereby promoting the development of robust adversarial learning and its application in open-world scenarios.
Authors: Isaac Wasserman, Jeova Farias Sales Rocha Neto
Unsupervised image segmentation aims at grouping different semantic patterns in an image without the use of human annotation. Similarly, image clustering searches for groupings of images based on their semantic content without supervision. Classically, both problems have captivated researchers as they drew from sound mathematical concepts to produce concrete applications. With the emergence of deep learning, the scientific community turned its attention to complex neural network-based solvers that achieved impressive results in those domains but rarely leveraged the advances made by classical methods. In this work, we propose a patch-based unsupervised image segmentation strategy that bridges advances in unsupervised feature extraction from deep clustering methods with the algorithmic help of classical graph-based methods. We show that a simple convolutional neural network, trained to classify image patches and iteratively regularized using graph cuts, naturally leads to a state-of-the-art fully-convolutional unsupervised pixel-level segmenter. Furthermore, we demonstrate that this is the ideal setting for leveraging the patch-level pairwise features generated by vision transformer models. Our results on real image data demonstrate the effectiveness of our proposed methodology.
Authors: Liqiang Jing, Ruosen Li, Yunmo Chen, Mengzhao Jia, Xinya Du
We introduce FAITHSCORE (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs). The FAITHSCORE evaluation first identifies sub-sentences containing descriptive statements that need to be verified, then extracts a comprehensive list of atomic facts from these sub-sentences, and finally conducts consistency verification between fine-grained atomic facts and the input image. Meta-evaluation demonstrates that our metric highly correlates with human judgments of faithfulness. We collect two benchmark datasets (i.e. LLaVA-1k and MSCOCO-Cap) for evaluating LVLMs instruction-following hallucinations. We measure hallucinations in state-of-the-art LVLMs with FAITHSCORE on the datasets. Results reveal that current systems are prone to generate hallucinated content unfaithful to the image, which leaves room for future improvements. Further, we find that current LVLMs despite doing well on color and counting, still struggle with long answers, relations, and multiple objects.
Authors: Aakriti Shah
Physical adversarial attacks on road signs are continuously exploiting vulnerabilities in modern day autonomous vehicles (AVs) and impeding their ability to correctly classify what type of road sign they encounter. Current models cannot generalize input data well, resulting in overfitting or underfitting. In overfitting, the model memorizes the input data but cannot generalize to new scenarios. In underfitting, the model does not learn enough of the input data to accurately classify these road signs. This paper explores the resilience of autonomous driving systems against three main physical adversarial attacks (tape, graffiti, illumination), specifically targeting object classifiers. Several machine learning models were developed and evaluated on two distinct datasets: road signs (stop signs, speed limit signs, traffic lights, and pedestrian crosswalk signs) and geometric shapes (octagons, circles, squares, and triangles). The study compared algorithm performance under different conditions, including clean and adversarial training and testing on these datasets. To build robustness against attacks, defense techniques like adversarial training and transfer learning were implemented. Results demonstrated transfer learning models played a crucial role in performance by allowing knowledge gained from shape training to improve generalizability of road sign classification, despite the datasets being completely different. The paper suggests future research directions, including human-in-the-loop validation, security analysis, real-world testing, and explainable AI for transparency. This study aims to contribute to improving security and robustness of object classifiers in autonomous vehicles and mitigating adversarial example impacts on driving systems.
Authors: Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen
Visual instruction tuning is an essential approach to improving the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs). A surge of visual instruction datasets with various focuses and characteristics have been proposed recently, enabling MLLMs to achieve surprising results on evaluation benchmarks. To develop more capable MLLMs, in this paper, we aim to investigate a more fundamental question: ``what makes for good visual instructions?''. By conducting a comprehensive empirical study, we find that instructions focused on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs on evaluation benchmarks. Building upon this finding, we design a systematic approach to automatically creating high-quality complex visual reasoning instructions. Our approach employs a synthesis-complication-reformulation paradigm, leveraging multiple stages to gradually increase the complexity of the instructions while guaranteeing quality. Based on this approach, we create the synthetic visual reasoning instruction dataset consisting of 32K examples, namely ComVint, and fine-tune four MLLMs on it. Experimental results demonstrate that our dataset consistently enhances the performance of all the compared MLLMs, e.g., improving the performance of MiniGPT-4 and BLIP-2 on MME-Cognition by 32.6% and 28.8%, respectively. Our code and data are publicly available at the link: https://github.com/RUCAIBox/ComVint.
Authors: Ali Athar, Enxu Li, Sergio Casas, Raquel Urtasun
4D panoptic segmentation is a challenging but practically useful task that requires every point in a LiDAR point-cloud sequence to be assigned a semantic class label, and individual objects to be segmented and tracked over time. Existing approaches utilize only LiDAR inputs which convey limited information in regions with point sparsity. This problem can, however, be mitigated by utilizing RGB camera images which offer appearance-based information that can reinforce the geometry-based LiDAR features. Motivated by this, we propose 4D-Former: a novel method for 4D panoptic segmentation which leverages both LiDAR and image modalities, and predicts semantic masks as well as temporally consistent object masks for the input point-cloud sequence. We encode semantic classes and objects using a set of concise queries which absorb feature information from both data modalities. Additionally, we propose a learned mechanism to associate object tracks over time which reasons over both appearance and spatial location. We apply 4D-Former to the nuScenes and SemanticKITTI datasets where it achieves state-of-the-art results.
Authors: Enxu Li, Sergio Casas, Raquel Urtasun
Semantic segmentation of LiDAR point clouds has been widely studied in recent years, with most existing methods focusing on tackling this task using a single scan of the environment. However, leveraging the temporal stream of observations can provide very rich contextual information on regions of the scene with poor visibility (e.g., occlusions) or sparse observations (e.g., at long range), and can help reduce redundant computation frame after frame. In this paper, we tackle the challenge of exploiting the information from the past frames to improve the predictions of the current frame in an online fashion. To address this challenge, we propose a novel framework for semantic segmentation of a temporal sequence of LiDAR point clouds that utilizes a memory network to store, update and retrieve past information. Our framework also includes a regularizer that penalizes prediction variations in the neighborhood of the point cloud. Prior works have attempted to incorporate memory in range view representations for semantic segmentation, but these methods fail to handle occlusions and the range view representation of the scene changes drastically as agents nearby move. Our proposed framework overcomes these limitations by building a sparse 3D latent representation of the surroundings. We evaluate our method on SemanticKITTI, nuScenes, and PandaSet. Our experiments demonstrate the effectiveness of the proposed framework compared to the state-of-the-art.
Authors: Abhijith Sharma, Phil Munz, Apurva Narayan
Adversarial patches threaten visual AI models in the real world. The number of patches in a patch attack is variable and determines the attack's potency in a specific environment. Most existing defenses assume a single patch in the scene, and the multiple patch scenarios are shown to overcome them. This paper presents a model-agnostic defense against patch attacks based on total variation for image resurfacing (TVR). The TVR is an image-cleansing method that processes images to remove probable adversarial regions. TVR can be utilized solely or augmented with a defended model, providing multi-level security for robust prediction. TVR nullifies the influence of patches in a single image scan with no prior assumption on the number of patches in the scene. We validate TVR on the ImageNet-Patch benchmark dataset and with real-world physical objects, demonstrating its ability to mitigate patch attack.
Authors: Hadrien Reynaud, Bernhard Kainz
This work presents an extensive hyperparameter search on Image Diffusion Models for Echocardiogram generation. The objective is to establish foundational benchmarks and provide guidelines within the realm of ultrasound image and video generation. This study builds over the latest advancements, including cutting-edge model architectures and training methodologies. We also examine the distribution shift between real and generated samples and consider potential solutions, crucial to train efficient models on generated data. We determine an Optimal FID score of $0.88$ for our research problem and achieve an FID of $2.60$. This work is aimed at contributing valuable insights and serving as a reference for further developments in the specialized field of ultrasound image and video generation.
Authors: Jiawei Du, Qin Shi, Joey Tianyi Zhou
Dataset distillation is a newly emerging task that synthesizes a small-size dataset used in training deep neural networks (DNNs) for reducing data storage and model training costs. The synthetic datasets are expected to capture the essence of the knowledge contained in real-world datasets such that the former yields a similar performance as the latter. Recent advancements in distillation methods have produced notable improvements in generating synthetic datasets. However, current state-of-the-art methods treat the entire synthetic dataset as a unified entity and optimize each synthetic instance equally. This static optimization approach may lead to performance degradation in dataset distillation. Specifically, we argue that static optimization can give rise to a coupling issue within the synthetic data, particularly when a larger amount of synthetic data is being optimized. This coupling issue, in turn, leads to the failure of the distilled dataset to extract the high-level features learned by the deep neural network (DNN) in the latter epochs.
In this study, we propose a new dataset distillation strategy called Sequential Subset Matching (SeqMatch), which tackles this problem by adaptively optimizing the synthetic data to encourage sequential acquisition of knowledge during dataset distillation. Our analysis indicates that SeqMatch effectively addresses the coupling issue by sequentially generating the synthetic instances, thereby enhancing its performance significantly. Our proposed SeqMatch outperforms state-of-the-art methods in various datasets, including SVNH, CIFAR-10, CIFAR-100, and Tiny ImageNet. Our code is available at https://github.com/shqii1j/seqmatch.
Authors: Moreno D'Incà, Christos Tzelepis, Ioannis Patras, Nicu Sebe
Fairness is crucial when training a deep-learning discriminative model, especially in the facial domain. Models tend to correlate specific characteristics (such as age and skin color) with unrelated attributes (downstream tasks), resulting in biases which do not correspond to reality. It is common knowledge that these correlations are present in the data and are then transferred to the models during training. This paper proposes a method to mitigate these correlations to improve fairness. To do so, we learn interpretable and meaningful paths lying in the semantic space of a pre-trained diffusion model (DiffAE) -- such paths being supervised by contrastive text dipoles. That is, we learn to edit protected characteristics (age and skin color). These paths are then applied to augment images to improve the fairness of a given dataset. We test the proposed method on CelebA-HQ and UTKFace on several downstream tasks with age and skin color as protected characteristics. As a proxy for fairness, we compute the difference in accuracy with respect to the protected characteristics. Quantitative results show how the augmented images help the model improve the overall accuracy, the aforementioned metric, and the disparity of equal opportunity. Code is available at: https://github.com/Moreno98/Vision-Language-Bias-Control.
Authors: Gowtham Krishnan Murugesan, Diana McCrumb, Eric Brunner, Jithendra Kumar, Rahul Soni, Vasily Grigorash, Stephen Moore, Jeff Van Oss
Automatic segmentation of lesions in FDG-18 Whole Body (WB) PET/CT scans using deep learning models is instrumental for determining treatment response, optimizing dosimetry, and advancing theranostic applications in oncology. However, the presence of organs with elevated radiotracer uptake, such as the liver, spleen, brain, and bladder, often leads to challenges, as these regions are often misidentified as lesions by deep learning models. To address this issue, we propose a novel approach of segmenting both organs and lesions, aiming to enhance the performance of automatic lesion segmentation methods. In this study, we assessed the effectiveness of our proposed method using the AutoPET II challenge dataset, which comprises 1014 subjects. We evaluated the impact of inclusion of additional labels and data in the segmentation performance of the model. In addition to the expert-annotated lesion labels, we introduced eight additional labels for organs, including the liver, kidneys, urinary bladder, spleen, lung, brain, heart, and stomach. These labels were integrated into the dataset, and a 3D UNET model was trained within the nnUNet framework. Our results demonstrate that our method achieved the top ranking in the held-out test dataset, underscoring the potential of this approach to significantly improve lesion segmentation accuracy in FDG-18 Whole-Body PET/CT scans, ultimately benefiting cancer patients and advancing clinical practice.
Authors: Rouzbeh Meshkinnejad, Jie Mei, Daniel Lizotte, Yalda Mohsenzadeh
Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in continual learning has addressed forgetting by using previous task data and trained models. Inspired by event models created and updated in the brain, we propose a new mechanism that takes place during task boundaries, i.e., when one task finishes and another starts. By observing the redundancy-inducing ability of contrastive loss on the output of a neural network, our method leverages the first few samples of the new task to identify and retain parameters contributing most to the transfer ability of the neural network, freeing up the remaining parts of the network to learn new features. We evaluate the proposed methods on benchmark computer vision datasets including CIFAR10 and TinyImagenet and demonstrate state-of-the-art performance in the task-incremental, class-incremental, and domain-incremental continual learning scenarios.
Authors: André Luiz Buarque Vieira e Silva, Heitor de Castro Felix, Franscisco Paulo Magalhães Simões, Veronica Teichrieb, Michel Mozinho dos Santos, Hemir Santiago, Virginia Sgotti, Henrique Lott Neto
Power line maintenance and inspection are essential to avoid power supply interruptions, reducing its high social and financial impacts yearly. Automating power line visual inspections remains a relevant open problem for the industry due to the lack of public real-world datasets of power line components and their various defects to foster new research. This paper introduces InsPLAD, a Power Line Asset Inspection Dataset and Benchmark containing 10,607 high-resolution Unmanned Aerial Vehicles colour images. The dataset contains seventeen unique power line assets captured from real-world operating power lines. Additionally, five of those assets present six defects: four of which are corrosion, one is a broken component, and one is a bird's nest presence. All assets were labelled according to their condition, whether normal or the defect name found on an image level. We thoroughly evaluate state-of-the-art and popular methods for three image-level computer vision tasks covered by InsPLAD: object detection, through the AP metric; defect classification, through Balanced Accuracy; and anomaly detection, through the AUROC metric. InsPLAD offers various vision challenges from uncontrolled environments, such as multi-scale objects, multi-size class instances, multiple objects per image, intra-class variation, cluttered background, distinct point-of-views, perspective distortion, occlusion, and varied lighting conditions. To the best of our knowledge, InsPLAD is the first large real-world dataset and benchmark for power line asset inspection with multiple components and defects for various computer vision tasks, with a potential impact to improve state-of-the-art methods in the field. It will be publicly available in its integrity on a repository with a thorough description. It can be found at https://github.com/andreluizbvs/InsPLAD.
Authors: Te-Lin Wu, Zi-Yi Dou, Qingyuan Hu, Yu Hou, Nischal Reddy Chandra, Marjorie Freedman, Ralph M. Weischedel, Nanyun Peng
Multimodal counterfactual reasoning is a vital yet challenging ability for AI systems. It involves predicting the outcomes of hypothetical circumstances based on vision and language inputs, which enables AI models to learn from failures and explore hypothetical scenarios. Despite its importance, there are only a few datasets targeting the counterfactual reasoning abilities of multimodal models. Among them, they only cover reasoning over synthetic environments or specific types of events (e.g. traffic collisions), making them hard to reliably benchmark the model generalization ability in diverse real-world scenarios and reasoning dimensions. To overcome these limitations, we develop a video question answering dataset, ACQUIRED: it consists of 3.9K annotated videos, encompassing a wide range of event types and incorporating both first and third-person viewpoints, which ensures a focus on real-world diversity. In addition, each video is annotated with questions that span three distinct dimensions of reasoning, including physical, social, and temporal, which can comprehensively evaluate the model counterfactual abilities along multiple aspects. We benchmark our dataset against several state-of-the-art language-only and multimodal models and experimental results demonstrate a significant performance gap (>13%) between models and humans. The findings suggest that multimodal counterfactual reasoning remains an open challenge and ACQUIRED is a comprehensive and reliable benchmark for inspiring future research in this direction.
Authors: Shan Yu, Zhenting Zhu, Yu Chen, Hanchen Xu, Pengzhan Zhao, Yang Wang, Arthi Padmanabhan, Hugo Latapie, Harry Xu
Video analytics is widely used in contemporary systems and services. At the forefront of video analytics are video queries that users develop to find objects of particular interest. Building upon the insight that video objects (e.g., human, animals, cars, etc.), the center of video analytics, are similar in spirit to objects modeled by traditional object-oriented languages, we propose to develop an object-oriented approach to video analytics. This approach, named VQPy, consists of a frontend$\unicode{x2015}$a Python variant with constructs that make it easy for users to express video objects and their interactions$\unicode{x2015}$as well as an extensible backend that can automatically construct and optimize pipelines based on video objects. We have implemented and open-sourced VQPy, which has been productized in Cisco as part of its DeepVision framework.
Authors: Mohammed Q. Alkhatib, Mina Al-Saad, Nour Aburaed, M. Sami Zitouni, Hussain Al Ahmad
This research work presents a novel dual-branch model for hyperspectral image classification that combines two streams: one for processing standard hyperspectral patches using Real-Valued Neural Network (RVNN) and the other for processing their corresponding Fourier transforms using Complex-Valued Neural Network (CVNN). The proposed model is evaluated on the Pavia University and Salinas datasets. Results show that the proposed model outperforms state-of-the-art methods in terms of overall accuracy, average accuracy, and Kappa. Through the incorporation of Fourier transforms in the second stream, the model is able to extract frequency information, which complements the spatial information extracted by the first stream. The combination of these two streams improves the overall performance of the model. Furthermore, to enhance the model performance, the Squeeze and Excitation (SE) mechanism has been utilized. Experimental evidence show that SE block improves the models overall accuracy by almost 1\%.
Authors: Abdelhak Lemkhenter, Manchen Wang, Luca Zancato, Gurumurthy Swaminathan, Paolo Favaro, Davide Modolo
In this paper we introduce SemiGPC, a distribution-aware label refinement strategy based on Gaussian Processes where the predictions of the model are derived from the labels posterior distribution. Differently from other buffer-based semi-supervised methods such as CoMatch and SimMatch, our SemiGPC includes a normalization term that addresses imbalances in the global data distribution while maintaining local sensitivity. This explicit control allows SemiGPC to be more robust to confirmation bias especially under class imbalance. We show that SemiGPC improves performance when paired with different Semi-Supervised methods such as FixMatch, ReMixMatch, SimMatch and FreeMatch and different pre-training strategies including MSN and Dino. We also show that SemiGPC achieves state of the art results under different degrees of class imbalance on standard CIFAR10-LT/CIFAR100-LT especially in the low data-regime. Using SemiGPC also results in about 2% avg.accuracy increase compared to a new competitive baseline on the more challenging benchmarks SemiAves, SemiCUB, SemiFungi and Semi-iNat.
Authors: Anna Mikaelyan, Fernando Alonso-Fernandez, Josef Bigun
We present a model-based feature extractor to describe neighborhoods around keypoints by finite expansion, estimating the spatially varying orientation by harmonic functions. The iso-curves of such functions are highly symmetric w.r.t. the origin (a keypoint) and the estimated parameters have well defined geometric interpretations. The origin is also a unique singularity of all harmonic functions, helping to determine the location of a keypoint precisely, whereas the functions describe the object shape of the neighborhood. This is novel and complementary to traditional texture features which describe texture-shape properties i.e. they are purposively invariant to translation (within a texture). We report on experiments of verification and identification of keypoints in forensic fingerprints by using publicly available data (NIST SD27) and discuss the results in comparison to other studies. These support our conclusions that the novel features can equip single cores or single minutia with a significant verification power at 19% EER, and an identification power of 24-78% for ranks of 1-20. Additionally, we report verification results of periocular biometrics using near-infrared images, reaching an EER performance of 13%, which is comparable to the state of the art. More importantly, fusion of two systems, our and texture features (Gabor), result in a measurable performance improvement. We report reduction of the EER to 9%, supporting the view that the novel features capture relevant visual information, which traditional texture features do not.
Authors: Bo Xiong, Changqing Su, Zihan Lin, You Zhou, Zhaofei Yu
Computed Tomography (CT) with its remarkable capability for three-dimensional imaging from multiple projections, enjoys a broad range of applications in clinical diagnosis, scientific observation, and industrial detection. Neural Adaptive Tomography (NeAT) is a recently proposed 3D rendering method based on neural radiance field for CT, and it demonstrates superior performance compared to traditional methods. However, it still faces challenges when dealing with the substantial perturbations and pose shifts encountered in CT scanning processes. Here, we propose a neural rendering method for CT reconstruction, named Iterative Neural Adaptive Tomography (INeAT), which incorporates iterative posture optimization to effectively counteract the influence of posture perturbations in data, particularly in cases involving significant posture variations. Through the implementation of a posture feedback optimization strategy, INeAT iteratively refines the posture corresponding to the input images based on the reconstructed 3D volume. We demonstrate that INeAT achieves artifact-suppressed and resolution-enhanced reconstruction in scenarios with significant pose disturbances. Furthermore, we show that our INeAT maintains comparable reconstruction performance to stable-state acquisitions even using data from unstable-state acquisitions, which significantly reduces the time required for CT scanning and relaxes the stringent requirements on imaging hardware systems, underscoring its immense potential for applications in short-time and low-cost CT technology.
Authors: Preetam Prabhu Srikar Dammu, Chirag Shah
Often machine learning models tend to automatically learn associations present in the training data without questioning their validity or appropriateness. This undesirable property is the root cause of the manifestation of spurious correlations, which render models unreliable and prone to failure in the presence of distribution shifts. Research shows that most methods attempting to remedy spurious correlations are only effective for a model's known spurious associations. Current spurious correlation detection algorithms either rely on extensive human annotations or are too restrictive in their formulation. Moreover, they rely on strict definitions of visual artifacts that may not apply to data produced by generative models, as they are known to hallucinate contents that do not conform to standard specifications. In this work, we introduce a general-purpose method that efficiently detects potential spurious correlations, and requires significantly less human interference in comparison to the prior art. Additionally, the proposed method provides intuitive explanations while eliminating the need for pixel-level annotations. We demonstrate the proposed method's tolerance to the peculiarity of AI-generated images, which is a considerably challenging task, one where most of the existing methods fall short. Consequently, our method is also suitable for detecting spurious correlations that may propagate to downstream applications originating from generative models.
Authors: Derek Jacoby, Donglin Xu, Weder Ribas, Minyi Xu, Ting Liu, Vishwanath Jayaraman, Mengdi Wei, Emma De Blois, Yvonne Coady
Since their introduction in 2020, Neural Radiance Fields (NeRFs) have taken the computer vision community by storm. They provide a multi-view representation of a scene or object that is ideal for eXtended Reality (XR) applications and for creative endeavors such as virtual production, as well as change detection operations in geospatial analytics. The computational cost of these generative AI models is quite high, however, and the construction of cloud pipelines to generate NeRFs is neccesary to realize their potential in client applications. In this paper, we present pipelines on a high performance academic computing cluster and compare it with a pipeline implemented on Microsoft Azure. Along the way, we describe some uses of NeRFs in enabling novel user interaction scenarios.
We explore how to capture the significance of a sub-text block in an article and how it may be used for text mining tasks. A sub-text block is a sub-sequence of sentences in the article. We formulate the notion of content significance distribution (CSD) of sub-text blocks, referred to as CSD of the first kind and denoted by CSD-1. In particular, we leverage Hugging Face's SentenceTransformer to generate contextual sentence embeddings, and use MoverScore over text embeddings to measure how similar a sub-text block is to the entire text. To overcome the exponential blowup on the number of sub-text blocks, we present an approximation algorithm and show that the approximated CSD-1 is almost identical to the exact CSD-1. Under this approximation, we show that the average and median CSD-1's for news, scholarly research, argument, and narrative articles share the same pattern. We also show that under a certain linear transformation, the complement of the cumulative distribution function of the beta distribution with certain values of $\alpha$ and $\beta$ resembles a CSD-1 curve. We then use CSD-1's to extract linguistic features to train an SVC classifier for assessing how well an article is organized. Through experiments, we show that this method achieves high accuracy for assessing student essays. Moreover, we study CSD of sentence locations, referred to as CSD of the second kind and denoted by CSD-2, and show that average CSD-2's for different types of articles possess distinctive patterns, which either conform common perceptions of article structures or provide rectification with minor deviation.
Authors: Ezra MacDonald, Derek Jacoby, Yvonne Coady
Assessing the environmental impact of the mineral extraction industry plays a critical role in understanding and mitigating the ecological consequences of extractive activities. This paper presents MineSegSAT, a model that presents a novel approach to predicting environmentally impacted areas of mineral extraction sites using the SegFormer deep learning segmentation architecture trained on Sentinel-2 data. The data was collected from non-overlapping regions over Western Canada in 2021 containing areas of land that have been environmentally impacted by mining activities that were identified from high-resolution satellite imagery in 2021. The SegFormer architecture, a state-of-the-art semantic segmentation framework, is employed to leverage its advanced spatial understanding capabilities for accurate land cover classification. We investigate the efficacy of loss functions including Dice, Tversky, and Lovasz loss respectively. The trained model was utilized for inference over the test region in the ensuing year to identify potential areas of expansion or contraction over these same periods. The Sentinel-2 data is made available on Amazon Web Services through a collaboration with Earth Daily Analytics which provides corrected and tiled analytics-ready data on the AWS platform. The model and ongoing API to access the data on AWS allow the creation of an automated tool to monitor the extent of disturbed areas surrounding known mining sites to ensure compliance with their environmental impact goals.
Authors: Haibao Yu, Yingjuan Tang, Enze Xie, Jilei Mao, Ping Luo, Zaiqing Nie
Cooperatively utilizing both ego-vehicle and infrastructure sensor data can significantly enhance autonomous driving perception abilities. However, the uncertain temporal asynchrony and limited communication conditions can lead to fusion misalignment and constrain the exploitation of infrastructure data. To address these issues in vehicle-infrastructure cooperative 3D (VIC3D) object detection, we propose the Feature Flow Net (FFNet), a novel cooperative detection framework. FFNet is a flow-based feature fusion framework that uses a feature flow prediction module to predict future features and compensate for asynchrony. Instead of transmitting feature maps extracted from still-images, FFNet transmits feature flow, leveraging the temporal coherence of sequential infrastructure frames. Furthermore, we introduce a self-supervised training approach that enables FFNet to generate feature flow with feature prediction ability from raw infrastructure sequences. Experimental results demonstrate that our proposed method outperforms existing cooperative detection methods while only requiring about 1/100 of the transmission cost of raw data and covers all latency in one model on the DAIR-V2X dataset. The code is available at \href{https://github.com/haibao-yu/FFNet-VIC3D}{https://github.com/haibao-yu/FFNet-VIC3D}.
Authors: Zhuohang Dang, Minnan Luo, Chengyou Jia, Guang Dai, Jihong Wang, Xiaojun Chang, Jingdong Wang, Qinghua Zheng
Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop; 2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose \textbf{DisTIB} (\textbf{T}ransmitted \textbf{I}nformation \textbf{B}ottleneck for \textbf{Dis}entangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses.
Authors: Donghua Wang, Wen Yao, Tingsong Jiang, Xiaoqian Chen
Deep neural networks (DNNs) are demonstrated to be vulnerable to universal perturbation, a single quasi-perceptible perturbation that can deceive the DNN on most images. However, the previous works are focused on using universal perturbation to perform adversarial attacks, while the potential usability of universal perturbation as data carriers in data hiding is less explored, especially for the key-controlled data hiding method. In this paper, we propose a novel universal perturbation-based secret key-controlled data-hiding method, realizing data hiding with a single universal perturbation and data decoding with the secret key-controlled decoder. Specifically, we optimize a single universal perturbation, which serves as a data carrier that can hide multiple secret images and be added to most cover images. Then, we devise a secret key-controlled decoder to extract different secret images from the single container image constructed by the universal perturbation by using different secret keys. Moreover, a suppress loss function is proposed to prevent the secret image from leakage. Furthermore, we adopt a robust module to boost the decoder's capability against corruption. Finally, A co-joint optimization strategy is proposed to find the optimal universal perturbation and decoder. Extensive experiments are conducted on different datasets to demonstrate the effectiveness of the proposed method. Additionally, the physical test performed on platforms (e.g., WeChat and Twitter) verifies the usability of the proposed method in practice.
Authors: Yuemeng Li, Yong Fan
Deep learning (DL) has shown remarkable success in various medical imaging data analysis applications. However, it remains challenging for DL models to achieve good generalization, especially when the training and testing datasets are collected at sites with different scanners, due to domain shift caused by differences in data distributions. Domain adaptation has emerged as an effective means to address this challenge by mitigating domain gaps in medical imaging applications. In this review, we specifically focus on domain adaptation approaches for DL-based medical image segmentation. We first present the motivation and background knowledge underlying domain adaptations, then provide a comprehensive review of domain adaptation applications in medical image segmentations, and finally discuss the challenges, limitations, and future research trends in the field to promote the methodology development of domain adaptation in the context of medical image segmentation. Our goal was to provide researchers with up-to-date references on the applications of domain adaptation in medical image segmentation studies.
Authors: Mackenzie J. Meni, Trupti Mahendrakar, Olivia D. M. Raney, Ryan T. White, Michael L. Mayo, Kevin Pilkiewicz
The escalating risk of collisions and the accumulation of space debris in Low Earth Orbit (LEO) has reached critical concern due to the ever increasing number of spacecraft. Addressing this crisis, especially in dealing with non-cooperative and unidentified space debris, is of paramount importance. This paper contributes to efforts in enabling autonomous swarms of small chaser satellites for target geometry determination and safe flight trajectory planning for proximity operations in LEO. Our research explores on-orbit use of the You Only Look Once v5 (YOLOv5) object detection model trained to detect satellite components. While this model has shown promise, its inherent lack of interpretability hinders human understanding, a critical aspect of validating algorithms for use in safety-critical missions. To analyze the decision processes, we introduce Probabilistic Explanations for Entropic Knowledge extraction (PEEK), a method that utilizes information theoretic analysis of the latent representations within the hidden layers of the model. Through both synthetic in hardware-in-the-loop experiments, PEEK illuminates the decision-making processes of the model, helping identify its strengths, limitations and biases.
Authors: Zhengzhe Liu, Jingyu Hu, Ka-Hei Hui, Xiaojuan Qi, Daniel Cohen-Or, Chi-Wing Fu
This paper presents a new text-guided technique for generating 3D shapes. The technique leverages a hybrid 3D shape representation, namely EXIM, combining the strengths of explicit and implicit representations. Specifically, the explicit stage controls the topology of the generated 3D shapes and enables local modifications, whereas the implicit stage refines the shape and paints it with plausible colors. Also, the hybrid approach separates the shape and color and generates color conditioned on shape to ensure shape-color consistency. Unlike the existing state-of-the-art methods, we achieve high-fidelity shape generation from natural-language descriptions without the need for time-consuming per-shape optimization or reliance on human-annotated texts during training or test-time optimization. Further, we demonstrate the applicability of our approach to generate indoor scenes with consistent styles using text-induced 3D shapes. Through extensive experiments, we demonstrate the compelling quality of our results and the high coherency of our generated shapes with the input texts, surpassing the performance of existing methods by a significant margin. Codes and models are released at https://github.com/liuzhengzhe/EXIM.
Authors: Changdae Oh, Mijoo Kim, Hyesu Lim, Junhyeok Park, Euiseog Jeong, Zhi-Qi Cheng, Kyungwoo Song
While fine-tuning unleashes the potential of a pre-trained model to a specific task, it trades off the model's generalization capability on out-of-distribution (OOD) datasets. To mitigate this, robust fine-tuning aims to ensure performance on OOD datasets as well as an in-distribution (ID) dataset for which the model is being tuned. However, another criterion for reliable machine learning (ML), confidence calibration, has been overlooked despite its increasing demand for real-world high-stakes ML applications (e.g., autonomous driving and medical diagnosis). For the first time, we raise concerns about the calibration of fine-tuned vision-language models (VLMs) under distribution shift by showing that naive fine-tuning and even state-of-the-art robust fine-tuning methods hurt the calibration of pre-trained VLMs, especially on OOD datasets. To address this, we provide a simple approach, called a calibrated robust fine-tuning (CaRot) that incentivizes the calibration and robustness on both ID and OOD datasets. Empirical results on ImageNet-1K distribution shift evaluation verify the effectiveness of our method.
Authors: Javad Mirzapour Kaleybar, Hooman Saadat, Hooman Khaloo
This paper introduces a groundbreaking classification model called the Controllable Ensemble Transformer and CNN (CETC) for the analysis of medical images. The CETC model combines the powerful capabilities of convolutional neural networks (CNNs) and transformers to effectively capture both local and global features present in medical images. The model architecture comprises three main components: a convolutional encoder block (CEB), a transposed-convolutional decoder block (TDB), and a transformer classification block (TCB). The CEB is responsible for capturing multi-local features at different scales and draws upon components from VGGNet, ResNet, and MobileNet as backbones. By leveraging this combination, the CEB is able to effectively detect and encode local features. The TDB, on the other hand, consists of sub-decoders that decode and sum the captured features using ensemble coefficients. This enables the model to efficiently integrate the information from multiple scales. Finally, the TCB utilizes the SwT backbone and a specially designed prediction head to capture global features, ensuring a comprehensive understanding of the entire image. The paper provides detailed information on the experimental setup and implementation, including the use of transfer learning, data preprocessing techniques, and training settings. The CETC model is trained and evaluated using two publicly available COVID-19 datasets. Remarkably, the model outperforms existing state-of-the-art models across various evaluation metrics. The experimental results clearly demonstrate the superiority of the CETC model, emphasizing its potential for accurately and efficiently analyzing medical images.
Authors: Yipeng Gao, Zeyu Wang, Wei-Shi Zheng, Cihang Xie, Yuyin Zhou
Contrastive learning has emerged as a promising paradigm for 3D open-world understanding, jointly with text, image, and point cloud. In this paper, we introduce MixCon3D, which combines the complementary information between 2D images and 3D point clouds to enhance contrastive learning. With the further integration of multi-view 2D images, MixCon3D enhances the traditional tri-modal representation by offering a more accurate and comprehensive depiction of real-world 3D objects and bolstering text alignment. Additionally, we pioneer the first thorough investigation of various training recipes for the 3D contrastive learning paradigm, building a solid baseline with improved performance. Extensive experiments conducted on three representative benchmarks reveal that our method renders significant improvement over the baseline, surpassing the previous state-of-the-art performance on the challenging 1,156-category Objaverse-LVIS dataset by 5.7%. We further showcase the effectiveness of our approach in more applications, including text-to-3D retrieval and point cloud captioning. The code is available at https://github.com/UCSC-VLAA/MixCon3D.
Authors: Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Puhua Chen
In the context of the long-tail scenario, models exhibit a strong demand for high-quality data. Data-centric approaches aim to enhance both the quantity and quality of data to improve model performance. Among these approaches, information augmentation has been progressively introduced as a crucial category. It achieves a balance in model performance by augmenting the richness and quantity of samples in the tail classes. However, there is currently a lack of research into the underlying mechanisms explaining the effectiveness of information augmentation methods. Consequently, the utilization of information augmentation in long-tail recognition tasks relies heavily on empirical and intricate fine-tuning. This work makes two primary contributions. Firstly, we approach the problem from the perspectives of feature diversity and distribution shift, introducing the concept of Feature Diversity Gain (FDG) to elucidate why information augmentation is effective. We find that the performance of information augmentation can be explained by FDG, and its performance peaks when FDG achieves an appropriate balance. Experimental results demonstrate that by using FDG to select augmented data, we can further enhance model performance without the need for any modifications to the model's architecture. Thus, data-centric approaches hold significant potential in the field of long-tail recognition, beyond the development of new model structures. Furthermore, we systematically introduce the core components and fundamental tasks of a data-centric long-tail learning framework for the first time. These core components guide the implementation and deployment of the system, while the corresponding fundamental tasks refine and expand the research area.
Authors: Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li
Scene graph generation (SGG) and human-object interaction (HOI) detection are two important visual tasks aiming at localising and recognising relationships between objects, and interactions between humans and objects, respectively.
Prevailing works treat these tasks as distinct tasks, leading to the development of task-specific models tailored to individual datasets. However, we posit that the presence of visual relationships can furnish crucial contextual and intricate relational cues that significantly augment the inference of human-object interactions. This motivates us to think if there is a natural intrinsic relationship between the two tasks, where scene graphs can serve as a source for inferring human-object interactions. In light of this, we introduce SG2HOI+, a unified one-step model based on the Transformer architecture. Our approach employs two interactive hierarchical Transformers to seamlessly unify the tasks of SGG and HOI detection. Concretely, we initiate a relation Transformer tasked with generating relation triples from a suite of visual features. Subsequently, we employ another transformer-based decoder to predict human-object interactions based on the generated relation triples. A comprehensive series of experiments conducted across established benchmark datasets including Visual Genome, V-COCO, and HICO-DET demonstrates the compelling performance of our SG2HOI+ model in comparison to prevalent one-stage SGG models. Remarkably, our approach achieves competitive performance when compared to state-of-the-art HOI methods. Additionally, we observe that our SG2HOI+ jointly trained on both SGG and HOI tasks in an end-to-end manner yields substantial improvements for both tasks compared to individualized training paradigms.
Authors: Xin Yuan, Jie Guo, Weidong Qiu, Zheng Huang, Shujun Li
Mis- and disinformation online have become a major societal problem as major sources of online harms of different kinds. One common form of mis- and disinformation is out-of-context (OOC) information, where different pieces of information are falsely associated, e.g., a real image combined with a false textual caption or a misleading textual description. Although some past studies have attempted to defend against OOC mis- and disinformation through external evidence, they tend to disregard the role of different pieces of evidence with different stances. Motivated by the intuition that the stance of evidence represents a bias towards different detection results, we propose a stance extraction network (SEN) that can extract the stances of different pieces of multi-modal evidence in a unified framework. Moreover, we introduce a support-refutation score calculated based on the co-occurrence relations of named entities into the textual SEN. Extensive experiments on a public large-scale dataset demonstrated that our proposed method outperformed the state-of-the-art baselines, with the best model achieving a performance gain of 3.2% in accuracy.
Authors: Jiaqi Wu, Junbiao Pang, Qingming Huang
Semi-supervised pose estimation is a practically challenging task for computer vision. Although numerous excellent semi-supervised classification methods have emerged, these methods typically use confidence to evaluate the quality of pseudo-labels, which is difficult to achieve in pose estimation tasks. For example, in pose estimation, confidence represents only the possibility that a position of the heatmap is a keypoint, not the quality of that prediction. In this paper, we propose a simple yet efficient framework to estimate the quality of pseudo-labels in semi-supervised pose estimation tasks from the perspective of modeling the uncertainty of the pseudo-labels. Concretely, under the dual mean-teacher framework, we construct the two maximum discrepant students (MDSs) to effectively push two teachers to generate different decision boundaries for the same sample. Moreover, we create multiple uncertainties to assess the quality of the pseudo-labels. Experimental results demonstrate that our method improves the performance of semi-supervised pose estimation on three datasets.
Authors: Yuhan Ding, Fukun Yin, Jiayuan Fan, Hui Li, Xin Chen, Wen Liu, Chongshan Lu, Gang YU, Tao Chen
Recent advances in implicit neural representations have achieved impressive results by sampling and fusing individual points along sampling rays in the sampling space. However, due to the explosively growing sampling space, finely representing and synthesizing detailed textures remains a challenge for unbounded large-scale outdoor scenes. To alleviate the dilemma of using individual points to perceive the entire colossal space, we explore learning the surface distribution of the scene to provide structural priors and reduce the samplable space and propose a Point Diffusion implicit Function, PDF, for large-scale scene neural representation. The core of our method is a large-scale point cloud super-resolution diffusion module that enhances the sparse point cloud reconstructed from several training images into a dense point cloud as an explicit prior. Then in the rendering stage, only sampling points with prior points within the sampling radius are retained. That is, the sampling space is reduced from the unbounded space to the scene surface. Meanwhile, to fill in the background of the scene that cannot be provided by point clouds, the region sampling based on Mip-NeRF 360 is employed to model the background representation. Expensive experiments have demonstrated the effectiveness of our method for large-scale scene novel view synthesis, which outperforms relevant state-of-the-art baselines.
Authors: Sanskriti Singh
The global challenge in chest radiograph X-ray (CXR) abnormalities often being misdiagnosed is primarily associated with perceptual errors, where healthcare providers struggle to accurately identify the location of abnormalities, rather than misclassification errors. We currently address this problem through disease-specific segmentation models. Unfortunately, these models cannot be released in the field due to their lack of generalizability across all thoracic diseases. A binary model tends to perform poorly when it encounters a disease that isn't represented in the dataset. We present CheX-nomaly: a binary localization U-net model that leverages transfer learning techniques with the incorporation of an innovative contrastive learning approach. Trained on the VinDr-CXR dataset, which encompasses 14 distinct diseases in addition to 'no finding' cases, my model achieves generalizability across these 14 diseases and others it has not seen before. We show that we can significantly improve the generalizability of an abnormality localization model by incorporating a contrastive learning method and dissociating the bounding boxes with its disease class. We also introduce a new loss technique to apply to enhance the U-nets performance on bounding box segmentation. By introducing CheX-nomaly, we offer a promising solution to enhance the precision of chest disease diagnosis, with a specific focus on reducing the significant number of perceptual errors in healthcare.
Authors: Jiaqi Wu, Junbiao Pang, Qingming Huang
Both semi-supervised classification and regression are practically challenging tasks for computer vision. However, semi-supervised classification methods are barely applied to regression tasks. Because the threshold-to-pseudo label process (T2L) in classification uses confidence to determine the quality of label. It is successful for classification tasks but inefficient for regression tasks. In nature, regression also requires unbiased methods to generate high-quality labels. On the other hand, T2L for classification often fails if the confidence is generated by a biased method. To address this issue, in this paper, we propose a theoretically guaranteed constraint for generating unbiased labels based on Chebyshev's inequality, combining multiple predictions to generate superior quality labels from several inferior ones. In terms of high-quality labels, the unbiased method naturally avoids the drawback of T2L. Specially, we propose an Unbiased Pseudo-labels network (UBPL network) with multiple branches to combine multiple predictions as pseudo-labels, where a Feature Decorrelation loss (FD loss) is proposed based on Chebyshev constraint. In principle, our method can be used for both classification and regression and can be easily extended to any semi-supervised framework, e.g. Mean Teacher, FixMatch, DualPose. Our approach achieves superior performance over SOTAs on the pose estimation datasets Mouse, FLIC and LSP, as well as the classification datasets CIFAR10/100 and SVHN.
Authors: Tawin Jiramahapokee
Manga, a form of Japanese comics and distinct visual storytelling, has captivated readers worldwide. Traditionally presented in black and white, manga's appeal lies in its ability to convey complex narratives and emotions through intricate line art and shading. Yet, the desire to experience manga in vibrant colors has sparked the pursuit of manga colorization, a task of paramount significance for artists. However, existing methods, originally designed for line art and sketches, face challenges when applied to manga. These methods often fall short in achieving the desired results, leading to the need for specialized manga-specific solutions. Existing approaches frequently rely on a single training step or extensive manual artist intervention, which can yield less satisfactory outcomes. To address these challenges, we propose a specialized framework for manga colorization. Leveraging established models for shading and vibrant coloring, our approach aligns both using a multi-encoder VAE. This structured workflow ensures clear and colorful results, with the option to incorporate reference images and manual hints.
Authors: Tao Liu, Chenpeng Du, Shuai Fan, Feilong Chen, Kai Yu
Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough landmarks or are confined to a single speaker, thus limiting their performance. In this paper, we propose DiffDub: Diffusion-based dubbing. We first craft the Diffusion auto-encoder by an inpainting renderer incorporating a mask to delineate editable zones and unaltered regions. This allows for seamless filling of the lower-face region while preserving the remaining parts. Throughout our experiments, we encountered several challenges. Primarily, the semantic encoder lacks robustness, constricting its ability to capture high-level features. Besides, the modeling ignored facial positioning, causing mouth or nose jitters across frames. To tackle these issues, we employ versatile strategies, including data augmentation and supplementary eye guidance. Moreover, we encapsulated a conformer-based reference encoder and motion generator fortified by a cross-attention mechanism. This enables our model to learn person-specific textures with varying references and reduces reliance on paired audio-visual data. Our rigorous experiments comprehensively highlight that our ground-breaking approach outpaces existing methods with considerable margins and delivers seamless, intelligible videos in person-generic and multilingual scenarios.
Authors: Yuanxin Liu, Lei Li, Shuhuai Ren, Rundong Gao, Shicheng Li, Sishuo Chen, Xu Sun, Lu Hou
Recently, open-domain text-to-video (T2V) generation models have made remarkable progress. However, the promising results are mainly shown by the qualitative cases of generated videos, while the quantitative evaluation of T2V models still faces two critical problems. Firstly, existing studies lack fine-grained evaluation of T2V models on different categories of text prompts. Although some benchmarks have categorized the prompts, their categorization either only focuses on a single aspect or fails to consider the temporal information in video generation. Secondly, it is unclear whether the automatic evaluation metrics are consistent with human standards. To address these problems, we propose FETV, a benchmark for Fine-grained Evaluation of Text-to-Video generation. FETV is multi-aspect, categorizing the prompts based on three orthogonal aspects: the major content, the attributes to control and the prompt complexity. FETV is also temporal-aware, which introduces several temporal categories tailored for video generation. Based on FETV, we conduct comprehensive manual evaluations of four representative T2V models, revealing their pros and cons on different categories of prompts from different aspects. We also extend FETV as a testbed to evaluate the reliability of automatic T2V metrics. The multi-aspect categorization of FETV enables fine-grained analysis of the metrics' reliability in different scenarios. We find that existing automatic metrics (e.g., CLIPScore and FVD) correlate poorly with human evaluation. To address this problem, we explore several solutions to improve CLIPScore and FVD, and develop two automatic metrics that exhibit significant higher correlation with humans than existing metrics. Benchmark page: https://github.com/llyx97/FETV.
Authors: Jianxiong Shen, Ruijie Ren, Adria Ruiz, Francesc Moreno-Noguer
Current methods based on Neural Radiance Fields (NeRF) significantly lack the capacity to quantify uncertainty in their predictions, particularly on the unseen space including the occluded and outside scene content. This limitation hinders their extensive applications in robotics, where the reliability of model predictions has to be considered for tasks such as robotic exploration and planning in unknown environments. To address this, we propose a novel approach to estimate a 3D Uncertainty Field based on the learned incomplete scene geometry, which explicitly identifies these unseen regions. By considering the accumulated transmittance along each camera ray, our Uncertainty Field infers 2D pixel-wise uncertainty, exhibiting high values for rays directly casting towards occluded or outside the scene content. To quantify the uncertainty on the learned surface, we model a stochastic radiance field. Our experiments demonstrate that our approach is the only one that can explicitly reason about high uncertainty both on 3D unseen regions and its involved 2D rendered pixels, compared with recent methods. Furthermore, we illustrate that our designed uncertainty field is ideally suited for real-world robotics tasks, such as next-best-view selection.
Authors: Florian Sauerbeck, Dominik Kulmer, Markus Pielmeier, Maximilian Leitenstern, Christoph Weiß, Johannes Betz
Autonomous vehicles require accurate and robust localization and mapping algorithms to navigate safely and reliably in urban environments. We present a novel sensor fusion-based pipeline for offline mapping and online localization based on LiDAR sensors. The proposed approach leverages four LiDAR sensors. Mapping and localization algorithms are based on the KISS-ICP, enabling real-time performance and high accuracy. We introduce an approach to generate semantic maps for driving tasks such as path planning. The presented pipeline is integrated into the ROS 2 based Autoware software stack, providing a robust and flexible environment for autonomous driving applications. We show that our pipeline outperforms state-of-the-art approaches for a given research vehicle and real-world autonomous driving application.
Authors: Alexandros Stergiou, Brent De Weerdt, Nikos Deligiannis
Video anomaly detection deals with the recognition of abnormal events in videos. Apart from the visual signal, video anomaly detection has also been addressed with the use of skeleton sequences. We propose a holistic representation of skeleton trajectories to learn expected motions across segments at different times. Our approach uses multitask learning to reconstruct any continuous unobserved temporal segment of the trajectory allowing the extrapolation of past or future segments and the interpolation of in-between segments. We use an end-to-end attention-based encoder-decoder. We encode temporally occluded trajectories, jointly learn latent representations of the occluded segments, and reconstruct trajectories based on expected motions across different temporal segments. Extensive experiments on three trajectory-based video anomaly detection datasets show the advantages and effectiveness of our approach with state-of-the-art results on anomaly detection in skeleton trajectories.
Authors: Behzad Moayedi, Abdalsamad Keramatfar, Mohammad Hadi Goldani, Mohammad Javad Fallahi, Alborz Jahangirisisakht, Mohammad Saboori, Leyla badiei
The rapid spread of COVID-19 and the emergence of new variants underscore the importance of effective screening measures. Rapid diagnosis and subsequent quarantine of infected individuals can prevent further spread of the virus in society. While PCR tests are the gold standard for COVID-19 diagnosis, they are costly and time-consuming. In contrast, urine test strips are an inexpensive, non-invasive, and rapidly obtainable screening method that can provide important information about a patient's health status. In this study, we collected a new dataset and used the RGB (Red Green Blue) color space of urine test strips parameters to detect the health status of individuals. To improve the accuracy of our model, we converted the RGB space to 10 additional color spaces. After evaluating four different machine learning models, we proposed a new ensemble model based on a multi-layer perceptron neural network. Although the initial results were not strong, we were able to improve the model's screening performance for COVID-19 by removing uncertain regions of the model space. Ultimately, our model achieved a screening accuracy of 80% based on urine parameters. Our results suggest that urine test strips can be a useful tool for COVID-19 screening, particularly in resource-constrained settings where PCR testing may not be feasible. Further research is needed to validate our findings and explore the potential role of urine test strips in COVID-19 diagnosis and management.
Authors: Xilai Li, Xiaosong Li, Tao Ye, Xiaoqi Cheng, Wuyang Liu, Haishu Tan
Multi-modal image fusion (MMIF) integrates valuable information from different modality images into a fused one. However, the fusion of multiple visible images with different focal regions and infrared images is a unprecedented challenge in real MMIF applications. This is because of the limited depth of the focus of visible optical lenses, which impedes the simultaneous capture of the focal information within the same scene. To address this issue, in this paper, we propose a MMIF framework for joint focused integration and modalities information extraction. Specifically, a semi-sparsity-based smoothing filter is introduced to decompose the images into structure and texture components. Subsequently, a novel multi-scale operator is proposed to fuse the texture components, capable of detecting significant information by considering the pixel focus attributes and relevant data from various modal images. Additionally, to achieve an effective capture of scene luminance and reasonable contrast maintenance, we consider the distribution of energy information in the structural components in terms of multi-directional frequency variance and information entropy. Extensive experiments on existing MMIF datasets, as well as the object detection and depth estimation tasks, consistently demonstrate that the proposed algorithm can surpass the state-of-the-art methods in visual perception and quantitative evaluation. The code is available at https://github.com/ixilai/MFIF-MMIF.
Authors: Christiane Posselt (1), Mehmet Yigit Avci (2), Mehmet Yigitsoy (2), Patrick Schünke (3), Christoph Kolbitsch (3), Tobias Schäffter (3 and 4), Stefanie Remmele (1) ((1) University of Applied Sciences, Faculty of Electrical and Industrial Engineering, Am Lurzenhof 1, Landshut, Germany, (2) deepc GmbH, Blumenstrasse 28, 80331 Munich, Germany, (3) Physikalisch Technische Bundesanstalt, Abbestrasse 2-12, 10587 Berlin, Germany, (4) Technical University of Berlin, Department of Medical Engineering, Dovestrasse 6, Berlin, Germany)
Purpose: To provide a simulation framework for routine neuroimaging test data, which allows for "stress testing" of deep segmentation networks against acquisition shifts that commonly occur in clinical practice for T2 weighted (T2w) fluid attenuated inversion recovery (FLAIR) Magnetic Resonance Imaging (MRI) protocols.
Approach: The approach simulates "acquisition shift derivatives" of MR images based on MR signal equations. Experiments comprise the validation of the simulated images by real MR scans and example stress tests on state-of-the-art MS lesion segmentation networks to explore a generic model function to describe the F1 score in dependence of the contrast-affecting sequence parameters echo time (TE) and inversion time (TI).
Results: The differences between real and simulated images range up to 19 % in gray and white matter for extreme parameter settings. For the segmentation networks under test the F1 score dependency on TE and TI can be well described by quadratic model functions (R^2 > 0.9). The coefficients of the model functions indicate that changes of TE have more influence on the model performance than TI.
Conclusions: We show that these deviations are in the range of values as may be caused by erroneous or individual differences of relaxation times as described by literature. The coefficients of the F1 model function allow for quantitative comparison of the influences of TE and TI. Limitations arise mainly from tissues with the low baseline signal (like CSF) and when the protocol contains contrast-affecting measures that cannot be modelled due to missing information in the DICOM header.
Authors: Jack Borer, Jeremy Tschirner, Florian Ölsner, Stefan Milz
Sensor fusion is vital for the safe and robust operation of autonomous vehicles. Accurate extrinsic sensor to sensor calibration is necessary to accurately fuse multiple sensor's data in a common spatial reference frame. In this paper, we propose a target free extrinsic calibration algorithm that requires no ground truth training data, artificially constrained motion trajectories, hand engineered features or offline optimization and that is accurate, precise and extremely robust to initialization error.
Most current research on online camera-LiDAR extrinsic calibration requires ground truth training data which is impossible to capture at scale. We revisit analytical mutual information based methods first proposed in 2012 and demonstrate that geometric features provide a robust information metric for camera-LiDAR extrinsic calibration. We demonstrate our proposed improvement using the KITTI and KITTI-360 fisheye data set.
Authors: Yujin Oh, Sangjoon Park, Hwa Kyung Byun, Jin Sung Kim, Jong Chul Ye
Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present a novel LLM-driven multi-modal AI that utilizes the clinical text information and is applicable to the challenging task of target volume contouring for radiation therapy, and validate it within the context of breast cancer radiation therapy target volume contouring. Using external validation and data-insufficient environments, which attributes highly conducive to real-world applications, we demonstrate that the proposed model exhibits markedly improved performance compared to conventional vision-only AI models, particularly exhibiting robust generalization performance and data-efficiency. To our best knowledge, this is the first LLM-driven multimodal AI model that integrates the clinical text information into target volume delineation for radiation oncology.
Authors: Mahdi Bagheri, Farhad Piri, Hadi Digale, Saem Sattarzadeh, Mohammad Reza Mohammadi
Augmented Reality (AR) has emerged as a significant advancement in surgical procedures, offering a solution to the challenges posed by traditional neuronavigation methods. These conventional techniques often necessitate surgeons to split their focus between the surgical site and a separate monitor that displays guiding images. Over the years, many systems have been developed to register and track the hologram at the targeted locations, each employed its own evaluation technique. On the other hand, hologram displacement measurement is not a straightforward task because of various factors such as occlusion, Vengence-Accomodation Conflict, and unstable holograms in space. In this study, we explore and classify different techniques for assessing an AR-assisted neurosurgery system and propose a new technique to systematize the assessment procedure. Moreover, we conduct a deeper investigation to assess surgeon error in the pre- and intra-operative phases of the surgery based on the respective feedback given. We found that although the system can undergo registration and tracking errors, physical feedback can significantly reduce the error caused by hologram displacement. However, the lack of visual feedback on the hologram does not have a significant effect on the user 3D perception.
Authors: Xinqi Li, Yi Zhang, Yidong Zhao, Jan van Gemert, Qian Tao
Quantitative cardiac magnetic resonance imaging (MRI) is an increasingly important diagnostic tool for cardiovascular diseases. Yet, co-registration of all baseline images within the quantitative MRI sequence is essential for the accuracy and precision of quantitative maps. However, co-registering all baseline images from a quantitative cardiac MRI sequence remains a nontrivial task because of the simultaneous changes in intensity and contrast, in combination with cardiac and respiratory motion. To address the challenge, we propose a novel motion correction framework based on robust principle component analysis (rPCA) that decomposes quantitative cardiac MRI into low-rank and sparse components, and we integrate the groupwise CNN-based registration backbone within the rPCA framework. The low-rank component of rPCA corresponds to the quantitative mapping (i.e. limited degree of freedom in variation), while the sparse component corresponds to the residual motion, making it easier to formulate and solve the groupwise registration problem. We evaluated our proposed method on cardiac T1 mapping by the modified Look-Locker inversion recovery (MOLLI) sequence, both before and after the Gadolinium contrast agent administration. Our experiments showed that our method effectively improved registration performance over baseline methods without introducing rPCA, and reduced quantitative mapping error in both in-domain (pre-contrast MOLLI) and out-of-domain (post-contrast MOLLI) inference. The proposed rPCA framework is generic and can be integrated with other registration backbones.
Authors: Xing Di, Yiyu Zheng, Xiaoming Liu, Yu Cheng
This paper presents a novel approach, called Prototype-based Self-Distillation (ProS), for unsupervised face representation learning. The existing supervised methods heavily rely on a large amount of annotated training facial data, which poses challenges in terms of data collection and privacy concerns. To address these issues, we propose ProS, which leverages a vast collection of unlabeled face images to learn a comprehensive facial omni-representation. In particular, ProS consists of two vision-transformers (teacher and student models) that are trained with different augmented images (cropping, blurring, coloring, etc.). Besides, we build a face-aware retrieval system along with augmentations to obtain the curated images comprising predominantly facial areas. To enhance the discrimination of learned features, we introduce a prototype-based matching loss that aligns the similarity distributions between features (teacher or student) and a set of learnable prototypes. After pre-training, the teacher vision transformer serves as a backbone for downstream tasks, including attribute estimation, expression recognition, and landmark alignment, achieved through simple fine-tuning with additional layers. Extensive experiments demonstrate that our method achieves state-of-the-art performance on various tasks, both in full and few-shot settings. Furthermore, we investigate pre-training with synthetic face images, and ProS exhibits promising performance in this scenario as well.
Authors: M. Miró-Nicolau, A. Jaume-i-Capó, G. Moyà-Alcover
The evaluation of the fidelity of eXplainable Artificial Intelligence (XAI) methods to their underlying models is a challenging task, primarily due to the absence of a ground truth for explanations. However, assessing fidelity is a necessary step for ensuring a correct XAI methodology. In this study, we conduct a fair and objective comparison of the current state-of-the-art XAI methods by introducing three novel image datasets with reliable ground truth for explanations. The primary objective of this comparison is to identify methods with low fidelity and eliminate them from further research, thereby promoting the development of more trustworthy and effective XAI techniques. Our results demonstrate that XAI methods based on the backpropagation of output information to input yield higher accuracy and reliability compared to methods relying on sensitivity analysis or Class Activation Maps (CAM). However, the backpropagation method tends to generate more noisy saliency maps. These findings have significant implications for the advancement of XAI methods, enabling the elimination of erroneous explanations and fostering the development of more robust and reliable XAI.
Authors: Christos Sevastopoulos, Joey Hussain, Stasinos Konstantopoulos, Vangelis Karkaletsis, Fillia Makedon
Accurate indoor free-space segmentation is a challenging task due to the complexity and the dynamic nature that indoor environments exhibit. We propose an indoors free-space segmentation method that associates large depth values with navigable regions. Our method leverages an unsupervised masking technique that, using positive instances, generates segmentation labels based on textural homogeneity and depth uniformity. Moreover, we generate superpixels corresponding to areas of higher depth and align them with features extracted from a Dense Prediction Transformer (DPT). Using the estimated free-space masks and the DPT feature representation, a SegFormer model is fine-tuned on our custom-collected indoor dataset. Our experiments demonstrate sufficient performance in intricate scenarios characterized by cluttered obstacles and challenging identification of free space.
Authors: Junqing Huang, Haihui Wang, Andreas Weiermann, Michael Ruzhansky
In this paper, we derive a novel optimal image transport algorithm over sparse dictionaries by taking advantage of Sparse Representation (SR) and Optimal Transport (OT). Concisely, we design a unified optimization framework in which the individual image features (color, textures, styles, etc.) are encoded using sparse representation compactly, and an optimal transport plan is then inferred between two learned dictionaries in accordance with the encoding process. This paradigm gives rise to a simple but effective way for simultaneous image representation and transformation, which is also empirically solvable because of the moderate size of sparse coding and optimal transport sub-problems. We demonstrate its versatility and many benefits to different image-to-image translation tasks, in particular image color transform and artistic style transfer, and show the plausible results for photo-realistic transferred effects.
Authors: Shichao Dong, Fayao Liu, Guosheng Lin
Recently, large-scale pre-trained models such as Segment-Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP) have demonstrated remarkable success and revolutionized the field of computer vision. These foundation vision models effectively capture knowledge from a large-scale broad data with their vast model parameters, enabling them to perform zero-shot segmentation on previously unseen data without additional training. While they showcase competence in 2D tasks, their potential for enhancing 3D scene understanding remains relatively unexplored. To this end, we present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. We then project these mask predictions from various frames of RGB-D video sequences into 3D space. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting. We examine diverse scenarios, like zero-shot learning and limited guidance from sparse 2D point labels, to assess the pros and cons of different vision foundation models. Our approach is experimented on ScanNet dataset for 3D indoor scenes, and the results demonstrate the effectiveness of adopting general 2D foundation models on solving 3D point cloud segmentation tasks.
Authors: AKM Enzam-Ul Haque, Golam Rabbany, Md. Siam
One of the most serious corneal disorders, keratoconus is difficult to diagnose in its early stages and can result in blindness. This illness, which often appears in the second decade of life, affects people of all sexes and races. Convolutional neural networks (CNNs), one of the deep learning approaches, have recently come to light as particularly promising tools for the accurate and timely diagnosis of keratoconus. The purpose of this study was to evaluate how well different D-CNN models identified keratoconus-related diseases. To be more precise, we compared five different CNN-based deep learning architectures (DenseNet201, InceptionV3, MobileNetV2, VGG19, Xception). In our comprehensive experimental analysis, the DenseNet201-based model performed very well in keratoconus disease identification in our extensive experimental research. This model outperformed its D-CNN equivalents, with an astounding accuracy rate of 89.14% in three crucial classes: Keratoconus, Normal, and Suspect. The results demonstrate not only the stability and robustness of the model but also its practical usefulness in real-world applications for accurate and dependable keratoconus identification. In addition, D-CNN DenseNet201 performs extraordinarily well in terms of precision, recall rates, and F1 scores in addition to accuracy. These measures validate the model's usefulness as an effective diagnostic tool by highlighting its capacity to reliably detect instances of keratoconus and to reduce false positives and negatives.
Authors: Chicago Park, Weijie Gan, Zihao Zou, Yuyang Hu, Zhixin Sun, Ulugbek S. Kamilov
There is a growing interest in model-based deep learning (MBDL) for solving imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and a learned image prior specified using a convolutional neural net (CNNs). The iterative nature of MBDL networks increases the test-time computational complexity, which limits their applicability in certain large-scale applications. We address this issue by presenting structured pruning algorithm for model-based deep learning (SPADE) as the first structured pruning algorithm for MBDL networks. SPADE reduces the computational complexity of CNNs used within MBDL networks by pruning its non-essential weights. We propose three distinct strategies to fine-tune the pruned MBDL networks to minimize the performance loss. Each fine-tuning strategy has a unique benefit that depends on the presence of a pre-trained model and a high-quality ground truth. We validate SPADE on two distinct inverse problems, namely compressed sensing MRI and image super-resolution. Our results highlight that MBDL models pruned by SPADE can achieve substantial speed up in testing time while maintaining competitive performance.
Authors: Lunjun Zhang, Anqi Joyce Yang, Yuwen Xiong, Sergio Casas, Bin Yang, Mengye Ren, Raquel Urtasun
In this paper, we study the problem of unsupervised object detection from 3D point clouds in self-driving scenes. We present a simple yet effective method that exploits (i) point clustering in near-range areas where the point clouds are dense, (ii) temporal consistency to filter out noisy unsupervised detections, (iii) translation equivariance of CNNs to extend the auto-labels to long range, and (iv) self-supervision for improving on its own. Our approach, OYSTER (Object Discovery via Spatio-Temporal Refinement), does not impose constraints on data collection (such as repeated traversals of the same location), is able to detect objects in a zero-shot manner without supervised finetuning (even in sparse, distant regions), and continues to self-improve given more rounds of iterative self-training. To better measure model performance in self-driving scenarios, we propose a new planning-centric perception metric based on distance-to-collision. We demonstrate that our unsupervised object detector significantly outperforms unsupervised baselines on PandaSet and Argoverse 2 Sensor dataset, showing promise that self-supervision combined with object priors can enable object discovery in the wild. For more information, visit the project website: https://waabi.ai/research/oyster
Authors: Manjie Xu, Guangyuan Jiang, Wei Liang, Chi Zhang, Yixin Zhu
Recent advances in vision-language learning have achieved notable success on complete-information question-answering datasets through the integration of extensive world knowledge. Yet, most models operate passively, responding to questions based on pre-stored knowledge. In stark contrast, humans possess the ability to actively explore, accumulate, and reason using both newfound and existing information to tackle incomplete-information questions. In response to this gap, we introduce $Conan$, an interactive open-world environment devised for the assessment of active reasoning. $Conan$ facilitates active exploration and promotes multi-round abductive inference, reminiscent of rich, open-world settings like Minecraft. Diverging from previous works that lean primarily on single-round deduction via instruction following, $Conan$ compels agents to actively interact with their surroundings, amalgamating new evidence with prior knowledge to elucidate events from incomplete observations. Our analysis on $Conan$ underscores the shortcomings of contemporary state-of-the-art models in active exploration and understanding complex scenarios. Additionally, we explore Abduction from Deduction, where agents harness Bayesian rules to recast the challenge of abduction as a deductive process. Through $Conan$, we aim to galvanize advancements in active reasoning and set the stage for the next generation of artificial intelligence agents adept at dynamically engaging in environments.
Authors: David Paz, Narayanan E. Ranganatha, Srinidhi K. Srinivas, Yunchao Yao, Henrik I. Christensen
This research work seeks to explore and identify strategies that can determine road topology information in 2D and 3D under highly dynamic urban driving scenarios. To facilitate this exploration, we introduce a substantial dataset comprising nearly one million automatically labeled data frames. A key contribution of our research lies in developing an automatic label-generation process and an occlusion handling strategy. This strategy is designed to model a wide range of occlusion scenarios, from mild disruptions to severe blockages. Furthermore, we present a comprehensive ablation study wherein multiple centerline detection methods are developed and evaluated. This analysis not only benchmarks the performance of various approaches but also provides valuable insights into the interpretability of these methods. Finally, we demonstrate the practicality of our methods and assess their adaptability across different sensor configurations, highlighting their versatility and relevance in real-world scenarios. Our dataset and experimental models are publicly available.
Authors: Weikang Wan, Yifeng Zhu, Rutav Shah, Yuke Zhu
We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is constructing an ever-growing skill library from a sequence of new tasks with a small number of human demonstrations. LOTUS starts with a continual skill discovery process using an open-vocabulary vision model, which extracts skills as recurring patterns presented in unsegmented demonstrations. Continual skill discovery updates existing skills to avoid catastrophic forgetting of previous tasks and adds new skills to solve novel tasks. LOTUS trains a meta-controller that flexibly composes various skills to tackle vision-based manipulation tasks in the lifelong learning process. Our comprehensive experiments show that LOTUS outperforms state-of-the-art baselines by over 11% in success rate, showing its superior knowledge transfer ability compared to prior methods. More results and videos can be found on the project website: https://ut-austin-rpl.github.io/Lotus/.
Authors: Wenrui Cai, Qingjie Liu, Yunhong Wang
Most trackers perform template and search region similarity matching to find the most similar object to the template during tracking. However, they struggle to make prediction when the target appearance changes due to the limited historical information introduced by roughly cropping the current search region based on the predicted result of previous frame. In this paper, we identify that the central impediment to improving the performance of existing trackers is the incapacity to integrate abundant and effective historical information. To address this issue, we propose a Historical Information Prompter (HIP) to enhance the provision of historical information. We also build HIPTrack upon HIP module. HIP is a plug-and-play module that make full use of search region features to introduce historical appearance information. It also incorporates historical position information by constructing refined mask of the target. HIP is a lightweight module to generate historical information prompts. By integrating historical information prompts, HIPTrack significantly enhances the tracking performance without the need to retrain the backbone. Experimental results demonstrate that our method outperforms all state-of-the-art approaches on LaSOT, LaSOT ext, GOT10k and NfS. Futhermore, HIP module exhibits strong generality and can be seamlessly integrated into trackers to improve tracking performance. The source code and models will be released for further research.
Authors: Jiawei Yang, Boris Ivanovic, Or Litany, Xinshuo Weng, Seung Wook Kim, Boyi Li, Tong Che, Danfei Xu, Sanja Fidler, Marco Pavone, Yue Wang
We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. EmerNeRF hinges upon two core components: First, it stratifies scenes into static and dynamic fields. This decomposition emerges purely from self-supervision, enabling our model to learn from general, in-the-wild data sources. Second, EmerNeRF parameterizes an induced flow field from the dynamic field and uses this flow field to further aggregate multi-frame features, amplifying the rendering precision of dynamic objects. Coupling these three fields (static, dynamic, and flow) enables EmerNeRF to represent highly-dynamic scenes self-sufficiently, without relying on ground truth object annotations or pre-trained models for dynamic object segmentation or optical flow estimation. Our method achieves state-of-the-art performance in sensor simulation, significantly outperforming previous methods when reconstructing static (+2.93 PSNR) and dynamic (+3.70 PSNR) scenes. In addition, to bolster EmerNeRF's semantic generalization, we lift 2D visual foundation model features into 4D space-time and address a general positional bias in modern Transformers, significantly boosting 3D perception performance (e.g., 37.50% relative improvement in occupancy prediction accuracy on average). Finally, we construct a diverse and challenging 120-sequence dataset to benchmark neural fields under extreme and highly-dynamic settings.
Authors: Jiasong Wu, Xuan Li, Taotao Li, Fanman Meng, Youyong Kong, Guanyu Yang, Lotfi Senhadji, Huazhong Shu
Previous audio-visual speech separation methods use the synchronization of the speaker's facial movement and speech in the video to supervise the speech separation in a self-supervised way. In this paper, we propose a model to solve the speech separation problem assisted by both face and sign language, which we call the extended speech separation problem. We design a general deep learning network for learning the combination of three modalities, audio, face, and sign language information, for better solving the speech separation problem. To train the model, we introduce a large-scale dataset named the Chinese Sign Language News Speech (CSLNSpeech) dataset, in which three modalities of audio, face, and sign language coexist. Experiment results show that the proposed model has better performance and robustness than the usual audio-visual system. Besides, sign language modality can also be used alone to supervise speech separation tasks, and the introduction of sign language is helpful for hearing-impaired people to learn and communicate. Last, our model is a general speech separation framework and can achieve very competitive separation performance on two open-source audio-visual datasets. The code is available at https://github.com/iveveive/SLNSpeech
Authors: Andrés C. Rodríguez, Stefano D'Aronco, Rodrigo Caye Daudt, Jan D. Wegner, Konrad Schindler
We exploit field guides to learn bird species recognition, in particular zero-shot recognition of unseen species. Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side information to transfer knowledge from seen to unseen bird species. We study two approaches: (1) a contrastive encoding of illustrations, which can be fed into standard zero-shot learning schemes; and (2) a novel method that leverages the fact that illustrations are also images and as such structurally more similar to photographs than other kinds of side information. Our results show that illustrations from field guides, which are readily available for a wide range of species, are indeed a competitive source of side information for zero-shot learning. On a subset of the iNaturalist2021 dataset with 749 seen and 739 unseen species, we obtain a classification accuracy of unseen bird species of $12\%$ @top-1 and $38\%$ @top-10, which shows the potential of field guides for challenging real-world scenarios with many species. Our code is available at https://github.com/ac-rodriguez/zsl_billow
Authors: Rezvan Sherkati, James J. Clark
We present a new method for image salience prediction, Clustered Saliency Prediction. This method divides subjects into clusters based on their personal features and their known saliency maps, and generates an image salience model conditioned on the cluster label. We test our approach on a public dataset of personalized saliency maps and cluster the subjects using selected importance weights for personal feature factors. We propose the Multi-Domain Saliency Translation model which uses image stimuli and universal saliency maps to predict saliency maps for each cluster. For obtaining universal saliency maps, we applied various state-of-the-art methods, DeepGaze IIE, ML-Net and SalGAN, and compared their effectiveness in our system. We show that our Clustered Saliency Prediction technique outperforms the universal saliency prediction models. Also, we demonstrate the effectiveness of our clustering method by comparing the results of Clustered Saliency Prediction using clusters obtained by our algorithm with some baseline methods. Finally, we propose an approach to assign new people to their most appropriate cluster and prove its usefulness in the experiments.
Authors: Xinzhe Ni, Yong Liu, Hao Wen, Yatai Ji, Jing Xiao, Yujiu Yang
Current methods for few-shot action recognition mainly fall into the metric learning framework following ProtoNet, which demonstrates the importance of prototypes. Although they achieve relatively good performance, the effect of multimodal information is ignored, e.g. label texts. In this work, we propose a novel MultimOdal PRototype-ENhanced Network (MORN), which uses the semantic information of label texts as multimodal information to enhance prototypes. A CLIP visual encoder and a frozen CLIP text encoder are introduced to obtain features with good multimodal initialization. Then in the visual flow, visual prototypes are computed by a Temporal-Relational CrossTransformer (TRX) module for example. In the text flow, a semantic-enhanced (SE) module and an inflating operation are used to obtain text prototypes. The final multimodal prototypes are then computed by a multimodal prototype-enhanced (MPE) module. Besides, we define a PRototype SImilarity DiffErence (PRIDE) to evaluate the quality of prototypes, which is used to verify our improvement on the prototype level and effectiveness of MORN. We conduct extensive experiments on four popular datasets, and MORN achieves state-of-the-art results on HMDB51, UCF101, Kinetics and SSv2. When plugging PRIDE into the training stage, the performance can be further improved.
Authors: Qingyi Pan, Ning Guo, Letu Qingge, Jingyi Zhang, Pei Yang
Blind image quality assessment (BIQA) remains challenging due to the diversity of distortion and image content variation, which complicate the distortion patterns crossing different scales and aggravate the difficulty of the regression problem for BIQA. However, existing BIQA methods often fail to consider multi-scale distortion patterns and image content, and little research has been done on learning strategies to make the regression model produce better performance. In this paper, we propose a simple yet effective Progressive Multi-Task Image Quality Assessment (PMT-IQA) model, which contains a multi-scale feature extraction module (MS) and a progressive multi-task learning module (PMT), to help the model learn complex distortion patterns and better optimize the regression issue to align with the law of human learning process from easy to hard. To verify the effectiveness of the proposed PMT-IQA model, we conduct experiments on four widely used public datasets, and the experimental results indicate that the performance of PMT-IQA is superior to the comparison approaches, and both MS and PMT modules improve the model's performance.
Authors: Zinuo Li, Xuhang Chen, Shuqiang Wang, Chi-Man Pun
Film, a classic image style, is culturally significant to the whole photographic industry since it marks the birth of photography. However, film photography is time-consuming and expensive, necessitating a more efficient method for collecting film-style photographs. Numerous datasets that have emerged in the field of image enhancement so far are not film-specific. In order to facilitate film-based image stylization research, we construct FilmSet, a large-scale and high-quality film style dataset. Our dataset includes three different film types and more than 5000 in-the-wild high resolution images. Inspired by the features of FilmSet images, we propose a novel framework called FilmNet based on Laplacian Pyramid for stylizing images across frequency bands and achieving film style outcomes. Experiments reveal that the performance of our model is superior than state-of-the-art techniques. The link of code and data is \url{https://github.com/CXH-Research/FilmNet}.
Authors: Carsten T. Lüth, Till J. Bungert, Lukas Klein, Paul F. Jaeger
Active Learning (AL) aims to reduce the labeling burden by interactively selecting the most informative samples from a pool of unlabeled data. While there has been extensive research on improving AL query methods in recent years, some studies have questioned the effectiveness of AL compared to emerging paradigms such as semi-supervised (Semi-SL) and self-supervised learning (Self-SL), or a simple optimization of classifier configurations. Thus, today's AL literature presents an inconsistent and contradictory landscape, leaving practitioners uncertain about whether and how to use AL in their tasks. In this work, we make the case that this inconsistency arises from a lack of systematic and realistic evaluation of AL methods. Specifically, we identify five key pitfalls in the current literature that reflect the delicate considerations required for AL evaluation. Further, we present an evaluation framework that overcomes these pitfalls and thus enables meaningful statements about the performance of AL methods. To demonstrate the relevance of our protocol, we present a large-scale empirical study and benchmark for image classification spanning various data sets, query methods, AL settings, and training paradigms. Our findings clarify the inconsistent picture in the literature and enable us to give hands-on recommendations for practitioners. The benchmark is hosted at https://github.com/IML-DKFZ/realistic-al .
Authors: Manuel Brack, Felix Friedrich, Dominik Hintersdorf, Lukas Struppek, Patrick Schramowski, Kristian Kersting
Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly impossible, yet small changes to the input prompt often result in very different images. This leaves the user with little semantic control. To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions. This semantic guidance (SEGA) generalizes to any generative architecture using classifier-free guidance. More importantly, it allows for subtle and extensive edits, changes in composition and style, as well as optimizing the overall artistic conception. We demonstrate SEGA's effectiveness on both latent and pixel-based diffusion models such as Stable Diffusion, Paella, and DeepFloyd-IF using a variety of tasks, thus providing strong evidence for its versatility, flexibility, and improvements over existing methods.
Authors: Jindong Jiang, Fei Deng, Gautam Singh, Sungjin Ahn
The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in image generation, their integration into object-centric learning remains largely unexplored in this domain. In this paper, we explore the feasibility and potential of integrating diffusion models into object-centric learning and investigate the pros and cons of this approach. We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes: it is the first object-centric learning model to replace conventional slot decoders with a latent diffusion model conditioned on object slots, and it is also the first unsupervised compositional conditional diffusion model that operates without the need for supervised annotations like text. Through experiments on various object-centric tasks, including the first application of the FFHQ dataset in this field, we demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders, particularly in more complex scenes, and exhibits superior unsupervised compositional generation quality. In addition, we conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD and demonstrate its effectiveness in real-world image segmentation and generation. Project page is available at https://latentslotdiffusion.github.io
Authors: Arijit Ray, Filip Radenovic, Abhimanyu Dubey, Bryan A. Plummer, Ranjay Krishna, Kate Saenko
Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of compositional capability, we design Cola, a text-to-image retrieval benchmark to Compose Objects Localized with Attributes. To solve Cola, a model must retrieve images with the correct configuration of attributes and objects and avoid choosing a distractor image with the same objects and attributes but in the wrong configuration. Cola contains about 1.2k composed queries of 168 objects and 197 attributes on around 30K images. Our human evaluation finds that Cola is 83.33% accurate, similar to contemporary compositionality benchmarks. Using Cola as a testbed, we explore empirical modeling designs to adapt pre-trained vision-language models to reason compositionally. We explore 6 adaptation strategies on 2 seminal vision-language models, using compositionality-centric test benchmarks - Cola and CREPE. We find the optimal adaptation strategy is to train a multi-modal attention layer that jointly attends over the frozen pre-trained image and language features. Surprisingly, training multimodal layers on CLIP performs better than tuning a larger FLAVA model with already pre-trained multimodal layers. Furthermore, our adaptation strategy improves CLIP and FLAVA to comparable levels, suggesting that training multimodal layers using contrastive attribute-object data is key, as opposed to using them pre-trained. Lastly, we show that Cola is harder than a closely related contemporary benchmark, CREPE, since simpler fine-tuning strategies without multimodal layers suffice on CREPE but not on Cola. However, we still see a significant gap between our best adaptation and human accuracy, suggesting considerable room for further research.
Authors: Fabio Bellavia
This paper presents Slime, a novel non-deep image matching framework which models the scene as rough local overlapping planes. This intermediate representation sits in-between the local affine approximation of the keypoint patches and the global matching based on both spatial and similarity constraints, providing a progressive pruning of the correspondences, as planes are easier to handle with respect to general scenes.
Slime decomposes the images into overlapping regions at different scales and computes loose planar homographies. Planes are mutually extended by compatible matches and the images are split into fixed tiles, with only the best homographies retained for each pair of tiles. Stable matches are identified according to the consensus of the admissible stereo configurations provided by pairwise homographies. Within tiles, the rough planes are then merged according to their overlap in terms of matches and further consistent correspondences are extracted.
The whole process only involves homography constraints. As a result, both the coverage and the stability of correct matches over the scene are amplified, together with the ability to spot matches in challenging scenes, allowing traditional hybrid matching pipelines to make up lost ground against recent end-to-end deep matching methods.
In addition, the paper gives a thorough comparative analysis of recent state-of-the-art in image matching represented by end-to-end deep networks and hybrid pipelines. The evaluation considers both planar and non-planar scenes, taking into account critical and challenging scenarios including abrupt temporal image changes and strong variations in relative image rotations. According to this analysis, although the impressive progress done in this field, there is still a wide room for improvements to be investigated in future research.
Foundation models (e.g., CLIP or DINOv2) have shown their impressive learning and transfer capabilities in a wide range of visual tasks, by training on a large corpus of data and adapting to specific downstream tasks. It is, however, interesting that foundation models have not been fully explored for universal domain adaptation (UniDA), which is to learn models using labeled data in a source domain and unlabeled data in a target one, such that the learned models can successfully adapt to the target data. In this paper, we make comprehensive empirical studies of state-of-the-art UniDA methods using foundation models. We first observe that, unlike fine-tuning from ImageNet pre-trained models, as previous methods do, fine-tuning from foundation models yields significantly poorer results, sometimes even worse than training from scratch. While freezing the backbones, we demonstrate that although the foundation models greatly improve the performance of the baseline method that trains the models on the source data alone, existing UniDA methods generally fail to improve over the baseline. This suggests that new research efforts are very necessary for UniDA using foundation models. Based on these findings, we introduce \textit{CLIP distillation}, a parameter-free method specifically designed to distill target knowledge from CLIP models. The core of our \textit{CLIP distillation} lies in a self-calibration technique for automatic temperature scaling, a feature that significantly enhances the baseline's out-class detection capability. Although simple, our method outperforms previous approaches in most benchmark tasks, excelling in evaluation metrics including H-score/H$^3$-score and the newly proposed universal classification rate (UCR) metric. We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.
Authors: Jinghan Yao, Nawras Alnaasan, Tian Chen, Aamir Shafi, Hari Subramoni, Dhabaleswar K. (DK) Panda
Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on these models, by design, harnesses a temporal dependency, where the current token's probability distribution is conditioned on preceding tokens. This inherent characteristic severely impedes computational efficiency during inference as a typical inference request can require more than thousands of tokens, where generating each token requires a load of entire model weights, making the inference more memory-bound. The large overhead becomes profound in real deployment where requests arrive randomly, necessitating various generation lengths. Existing solutions, such as dynamic batching and concurrent instances, introduce significant response delays and bandwidth contention, falling short of achieving optimal latency and throughput. To address these shortcomings, we propose Flover -- a temporal fusion framework for efficiently inferring multiple requests in parallel. We deconstruct the general generation pipeline into pre-processing and token generation, and equip the framework with a dedicated work scheduler for fusing the generation process temporally across all requests. By orchestrating the token-level parallelism, Flover exhibits optimal hardware efficiency and significantly spares the system resources. By further employing a fast buffer reordering algorithm that allows memory eviction of finished tasks, it brings over 11x inference speedup on GPT and 16x on LLAMA compared to the cutting-edge solutions provided by NVIDIA FasterTransformer. Crucially, by leveraging the advanced tensor parallel technique, Flover proves efficacious across diverse computational landscapes, from single-GPU setups to distributed scenarios, thereby offering robust performance optimization that adapts to variable use cases.
Authors: Qi Wu, Mingyan Han, Ting Jiang, Haoqiang Fan, Bing Zeng, Shuaicheng Liu
Deep image denoising models often rely on large amount of training data for the high quality performance. However, it is challenging to obtain sufficient amount of data under real-world scenarios for the supervised training. As such, synthesizing realistic noise becomes an important solution. However, existing techniques have limitations in modeling complex noise distributions, resulting in residual noise and edge artifacts in denoising methods relying on synthetic data. To overcome these challenges, we propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD). In particular, the proposed time-aware controlling module can simulate various environmental conditions under given camera settings. RNSD can incorporate guided multiscale content, such that more realistic noise with spatial correlations can be generated at multiple frequencies. In addition, we construct an inversion mechanism to predict the unknown camera setting, which enables the extension of RNSD to datasets without setting information. Extensive experiments demonstrate that our RNSD method significantly outperforms the existing methods not only in the synthesized noise under multiple realism metrics, but also in the single image denoising performances.
Authors: Davit Soselia, Khalid Saifullah, Tianyi Zhou
Automated reverse engineering of HTML/CSS code from UI screenshots is an important yet challenging problem with broad applications in website development and design. In this paper, we propose a novel vision-code transformer (ViCT) composed of a vision encoder processing the screenshots and a language decoder to generate the code. They are initialized by pre-trained models such as ViT/DiT and GPT-2/LLaMA but aligning the two modalities requires end-to-end finetuning, which aims to minimize the visual discrepancy between the code-rendered webpage and the original screenshot. However, the rendering is non-differentiable and causes costly overhead. We address this problem by actor-critic fine-tuning where a visual critic without rendering (ViCR) is developed to predict visual discrepancy given the original and generated code. To train and evaluate our models, we created two synthetic datasets of varying complexity, with over 75,000 unique (code, screenshot) pairs. We evaluate the UI-to-Code performance using a combination of automated metrics such as MSE, BLEU, IoU, and a novel htmlBLEU score. ViCT outperforms a strong baseline model DiT-GPT2, improving IoU from 0.64 to 0.79 and lowering MSE from 12.25 to 9.02. With much lower computational cost, it can achieve comparable performance as when using a larger decoder such as LLaMA.
Authors: Benno Krojer, Elinor Poole-Dayan, Vikram Voleti, Christopher Pal, Siva Reddy
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like like CLEVR and Winoground. We further boost its compositional performance with a transfer setup by fine-tuning on MS-COCO while retaining generative capabilities. We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2.1 is, for the most part, less biased than Stable Diffusion 1.5. Overall, our results point in an exciting direction bringing discriminative and generative model evaluation closer. We will release code and benchmark setup soon.
Authors: Yue Xu, Yong-Lu Li, Kaitong Cui, Ziyu Wang, Cewu Lu, Yu-Wing Tai, Chi-Keung Tang
Data-efficient learning has drawn significant attention, especially given the current trend of large multi-modal models, where dataset distillation can be an effective solution. However, the dataset distillation process itself is still very inefficient. In this work, we model the distillation problem with reference to information transport. Observing that severe data redundancy exists in dataset distillation, we argue to put more emphasis on the utility of the training samples. We propose a family of methods to exploit the most valuable samples, which is validated by our comprehensive analysis of the optimal data selection. The new strategy significantly reduces the training cost and extends a variety of existing distillation algorithms to larger and more diversified datasets, e.g., in some cases only 0.04% training data is sufficient for comparable distillation performance. Moreover, our strategy consistently enhances the performance, which may open up new analyses on the dynamics of distillation and networks. Our method is able to extend the distillation algorithms to much larger-scale datasets and more heterogeneous datasets, e.g., ImageNet-1K and Kinetics-400. Our code is available on https://github.com/silicx/GoldFromOres.
Authors: Banghua Zhu, Mingyu Ding, Philip Jacobson, Ming Wu, Wei Zhan, Michael Jordan, Jiantao Jiao
Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels. In this paper, we introduce doubly robust self-training, a novel semi-supervised algorithm that provably balances between two extremes. When the pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data. Conversely, when the pseudo-labels are completely accurate, our method transforms into a training process utilizing all pseudo-labeled data and labeled data, thus increasing the effective sample size. Through empirical evaluations on both the ImageNet dataset for image classification and the nuScenes autonomous driving dataset for 3D object detection, we demonstrate the superiority of the doubly robust loss over the standard self-training baseline.
Authors: Zizheng Yan, Yushuang Wu, Yipeng Qin, Xiaoguang Han, Shuguang Cui, Guanbin Li
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different label sets, i.e., they share a common label set and hold their own private label set, and iii) requires only a few labeled samples in each class of the target domain. To address USMA, we propose a collaborative consistency training framework that regularizes the prediction consistency between two models, i.e., a pre-trained source model and its variant pre-trained with target data only, and combines their complementary strengths to learn a more powerful model. The rationale of our framework stems from the observation that the source model performs better on common categories than the target-only model, while on target-private categories, the target-only model performs better. We also propose a two-perspective, i.e., sample-wise and class-wise, consistency regularization to improve the training. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
Authors: Guangyuan Zhao, Xin Shu
Optical computing systems can provide high-speed and low-energy data processing but face deficiencies in computationally demanding training and simulation-to-reality gap. We propose a model-free solution for lightweight in situ optimization of optical computing systems based on the score gradient estimation algorithm. This approach treats the system as a black box and back-propagates loss directly to the optical weights' probabilistic distributions, hence circumventing the need for computation-heavy and biased system simulation. We demonstrate a superior classification accuracy on the MNIST and FMNIST datasets through experiments on a single-layer diffractive optical computing system. Furthermore, we show its potential for image-free and high-speed cell analysis. The inherent simplicity of our proposed method, combined with its low demand for computational resources, expedites the transition of optical computing from laboratory demonstrations to real-world applications.
Authors: Mengjie Zhou, Liu Liu, Yiran Zhong, Andrew Calway
We study the image-based geolocalization problem, aiming to localize ground-view query images on cartographic maps. Current methods often utilize cross-view localization techniques to match ground-view query images with 2D maps. However, the performance of these methods is unsatisfactory due to significant cross-view appearance differences. In this paper, we lift cross-view matching to a 2.5D space, where heights of structures (e.g., trees and buildings) provide geometric information to guide the cross-view matching. We propose a new approach to learning representative embeddings from multi-modal data. Specifically, we establish a projection relationship between 2.5D space and 2D aerial-view space. The projection is further used to combine multi-modal features from the 2.5D and 2D maps using an effective pixel-to-point fusion method. By encoding crucial geometric cues, our method learns discriminative location embeddings for matching panoramic images and maps. Additionally, we construct the first large-scale ground-to-2.5D map geolocalization dataset to validate our method and facilitate future research. Both single-image based and route based localization experiments are conducted to test our method. Extensive experiments demonstrate that the proposed method achieves significantly higher localization accuracy and faster convergence than previous 2D map-based approaches.
Authors: Chenqiu Zhao, Guanfang Dong, Anup Basu
Recently, images are considered samples from a high-dimensional distribution, and deep learning has become almost synonymous with image generation. However, is a deep learning network truly necessary for image generation? In this paper, we investigate the possibility of image generation without using a deep learning network, motivated by validating the assumption that images follow a high-dimensional distribution. Since images are assumed to be samples from such a distribution, we utilize the Gaussian Mixture Model (GMM) to describe it. In particular, we employ a recent distribution learning technique named as Monte-Carlo Marginalization to capture the parameters of the GMM based on image samples. Moreover, we also use the Singular Value Decomposition (SVD) for dimensionality reduction to decrease computational complexity. During our evaluation experiment, we first attempt to model the distribution of image samples directly to verify the assumption that images truly follow a distribution. We then use the SVD for dimensionality reduction. The principal components, rather than raw image data, are used for distribution learning. Compared to methods relying on deep learning networks, our approach is more explainable, and its performance is promising. Experiments show that our images have a lower FID value compared to those generated by variational auto-encoders, demonstrating the feasibility of image generation without deep learning networks.
Authors: Ziyun Liang, Harry Anthony, Felix Wagner, Konstantinos Kamnitsas
Unsupervised anomaly segmentation aims to detect patterns that are distinct from any patterns processed during training, commonly called abnormal or out-of-distribution patterns, without providing any associated manual segmentations. Since anomalies during deployment can lead to model failure, detecting the anomaly can enhance the reliability of models, which is valuable in high-risk domains like medical imaging. This paper introduces Masked Modality Cycles with Conditional Diffusion (MMCCD), a method that enables segmentation of anomalies across diverse patterns in multimodal MRI. The method is based on two fundamental ideas. First, we propose the use of cyclic modality translation as a mechanism for enabling abnormality detection. Image-translation models learn tissue-specific modality mappings, which are characteristic of tissue physiology. Thus, these learned mappings fail to translate tissues or image patterns that have never been encountered during training, and the error enables their segmentation. Furthermore, we combine image translation with a masked conditional diffusion model, which attempts to `imagine' what tissue exists under a masked area, further exposing unknown patterns as the generative model fails to recreate them. We evaluate our method on a proxy task by training on healthy-looking slices of BraTS2021 multi-modality MRIs and testing on slices with tumors. We show that our method compares favorably to previous unsupervised approaches based on image reconstruction and denoising with autoencoders and diffusion models.
Authors: Xueyi Wang
Falls are significant and often fatal for vulnerable populations such as the elderly. Previous works have addressed the detection of falls by relying on data capture by a single sensor, images or accelerometers. In this work, we rely on multimodal descriptors extracted from videos captured by egocentric cameras. Our proposed method includes a late decision fusion layer that builds on top of the extracted descriptors. Furthermore, we collect a new dataset on which we assess our proposed approach. We believe this is the first public dataset of its kind. The dataset comprises 10,948 video samples by 14 subjects. We conducted ablation experiments to assess the performance of individual feature extractors, fusion of visual information, and fusion of both visual and audio information. Moreover, we experimented with internal and external cross-validation. Our results demonstrate that the fusion of audio and visual information through late decision fusion improves detection performance, making it a promising tool for fall prevention and mitigation.
Authors: Devang Mehta, Noah Klarmann
Manufacturing industries require efficient and voluminous production of high-quality finished goods. In the context of Industry 4.0, visual anomaly detection poses an optimistic solution for automatically controlled product quality with high precision. In general, automation based on computer vision is a promising solution to prevent bottlenecks at the product quality checkpoint. We considered recent advancements in machine learning to improve visual defect localization, but challenges persist in obtaining a balanced feature set and database of the wide variety of defects occurring in the production line. Hence, this paper proposes a defect localizing autoencoder with unsupervised class selection by clustering with k-means the features extracted from a pre-trained VGG16 network. Moreover, the selected classes of defects are augmented with natural wild textures to simulate artificial defects. The study demonstrates the effectiveness of the defect localizing autoencoder with unsupervised class selection for improving defect detection in manufacturing industries. The proposed methodology shows promising results with precise and accurate localization of quality defects on melamine-faced boards for the furniture industry. Incorporating artificial defects into the training data shows significant potential for practical implementation in real-world quality control scenarios.
Authors: Helbert Paat, Qing Lian, Weilong Yao, Tong Zhang
Advancements in deep learning-based 3D object detection necessitate the availability of large-scale datasets. However, this requirement introduces the challenge of manual annotation, which is often both burdensome and time-consuming. To tackle this issue, the literature has seen the emergence of several weakly supervised frameworks for 3D object detection which can automatically generate pseudo labels for unlabeled data. Nevertheless, these generated pseudo labels contain noise and are not as accurate as those labeled by humans. In this paper, we present the first approach that addresses the inherent ambiguities present in pseudo labels by introducing an Evidential Deep Learning (EDL) based uncertainty estimation framework. Specifically, we propose MEDL-U, an EDL framework based on MTrans, which not only generates pseudo labels but also quantifies the associated uncertainties. However, applying EDL to 3D object detection presents three primary challenges: (1) relatively lower pseudolabel quality in comparison to other autolabelers; (2) excessively high evidential uncertainty estimates; and (3) lack of clear interpretability and effective utilization of uncertainties for downstream tasks. We tackle these issues through the introduction of an uncertainty-aware IoU-based loss, an evidence-aware multi-task loss function, and the implementation of a post-processing stage for uncertainty refinement. Our experimental results demonstrate that probabilistic detectors trained using the outputs of MEDL-U surpass deterministic detectors trained using outputs from previous 3D annotators on the KITTI val set for all difficulty levels. Moreover, MEDL-U achieves state-of-the-art results on the KITTI official test set compared to existing 3D automatic annotators.
Authors: Uyoung Jeong, Seungryul Baek, Hyung Jin Chang, Kwang In Kim
Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances under crowded scenes. In this paper, we propose a bounding box-level instance representation learning called BoIR, which simultaneously solves instance detection, instance disentanglement, and instance-keypoint association problems. Our new instance embedding loss provides a learning signal on the entire area of the image with bounding box annotations, achieving globally consistent and disentangled instance representation. Our method exploits multi-task learning of bottom-up keypoint estimation, bounding box regression, and contrastive instance embedding learning, without additional computational cost during inference. BoIR is effective for crowded scenes, outperforming state-of-the-art on COCO val (0.8 AP), COCO test-dev (0.5 AP), CrowdPose (4.9 AP), and OCHuman (3.5 AP). Code will be available at https://github.com/uyoung-jeong/BoIR
Authors: Peng Zhang, Xin Li, Liang He, Xin Lin
3D multi-object tracking (3D MOT) stands as a pivotal domain within autonomous driving, experiencing a surge in scholarly interest and commercial promise over recent years. Despite its paramount significance, 3D MOT confronts a myriad of formidable challenges, encompassing abrupt alterations in object appearances, pervasive occlusion, the presence of diminutive targets, data sparsity, missed detections, and the unpredictable initiation and termination of object motion trajectories. Countless methodologies have emerged to grapple with these issues, yet 3D MOT endures as a formidable problem that warrants further exploration. This paper undertakes a comprehensive examination, assessment, and synthesis of the research landscape in this domain, remaining attuned to the latest developments in 3D MOT while suggesting prospective avenues for future investigation. Our exploration commences with a systematic exposition of key facets of 3D MOT and its associated domains, including problem delineation, classification, methodological approaches, fundamental principles, and empirical investigations. Subsequently, we categorize these methodologies into distinct groups, dissecting each group meticulously with regard to its challenges, underlying rationale, progress, merits, and demerits. Furthermore, we present a concise recapitulation of experimental metrics and offer an overview of prevalent datasets, facilitating a quantitative comparison for a more intuitive assessment. Lastly, our deliberations culminate in a discussion of the prevailing research landscape, highlighting extant challenges and charting possible directions for 3D MOT research. We present a structured and lucid road-map to guide forthcoming endeavors in this field.
Authors: Fabio Ferreira, Ivo Rapant, Frank Hutter
Many Contrastive Learning (CL) methods train their models to be invariant to different "views" of an image input for which a good data augmentation pipeline is crucial. While considerable efforts were directed towards improving pre-text tasks, architectures, or robustness (e.g., Siamese networks or teacher-softmax centering), the majority of these methods remain strongly reliant on the random sampling of operations within the image augmentation pipeline, such as the random resized crop or color distortion operation. In this paper, we argue that the role of the view generation and its effect on performance has so far received insufficient attention. To address this, we propose an easy, learning-free, yet powerful Hard View Selection (HVS) strategy designed to extend the random view generation to expose the pretrained model to harder samples during CL training. It encompasses the following iterative steps: 1) randomly sample multiple views and create pairs of two views, 2) run forward passes for each view pair on the currently trained model, 3) adversarially select the pair yielding the worst loss, and 4) run the backward pass with the selected pair. In our empirical analysis we show that under the hood, HVS increases task difficulty by controlling the Intersection over Union of views during pretraining. With only 300-epoch pretraining, HVS is able to closely rival the 800-epoch DINO baseline which remains very favorable even when factoring in the slowdown induced by the additional forwards of HVS. Additionally, HVS consistently achieves accuracy improvements on ImageNet between 0.4% and 1.9% on linear evaluation and similar improvements on transfer tasks across multiple CL methods, such as DINO, SimSiam, and SimCLR.
Authors: Songtao Luo, Shuang Yang, Shiguang Shan, Xilin Chen
In this paper, we propose a novel method for speaker adaptation in lip reading, motivated by two observations. Firstly, a speaker's own characteristics can always be portrayed well by his/her few facial images or even a single image with shallow networks, while the fine-grained dynamic features associated with speech content expressed by the talking face always need deep sequential networks to represent accurately. Therefore, we treat the shallow and deep layers differently for speaker adaptive lip reading. Secondly, we observe that a speaker's unique characteristics ( e.g. prominent oral cavity and mandible) have varied effects on lip reading performance for different words and pronunciations, necessitating adaptive enhancement or suppression of the features for robust lip reading. Based on these two observations, we propose to take advantage of the speaker's own characteristics to automatically learn separable hidden unit contributions with different targets for shallow layers and deep layers respectively. For shallow layers where features related to the speaker's characteristics are stronger than the speech content related features, we introduce speaker-adaptive features to learn for enhancing the speech content features. For deep layers where both the speaker's features and the speech content features are all expressed well, we introduce the speaker-adaptive features to learn for suppressing the speech content irrelevant noise for robust lip reading. Our approach consistently outperforms existing methods, as confirmed by comprehensive analysis and comparison across different settings. Besides the evaluation on the popular LRW-ID and GRID datasets, we also release a new dataset for evaluation, CAS-VSR-S68h, to further assess the performance in an extreme setting where just a few speakers are available but the speech content covers a large and diversified range.
Authors: Zakhar Shumaylov, Jeremy Budd, Subhadip Mukherjee, Carola-Bibiane Schönlieb
An emerging new paradigm for solving inverse problems is via the use of deep learning to learn a regularizer from data. This leads to high-quality results, but often at the cost of provable guarantees. In this work, we show how well-posedness and convergent regularization arises within the convex-nonconvex (CNC) framework for inverse problems. We introduce a novel input weakly convex neural network (IWCNN) construction to adapt the method of learned adversarial regularization to the CNC framework. Empirically we show that our method overcomes numerical issues of previous adversarial methods.
Authors: José Rodríguez-Ortega (1 and 2), Rohaifa Khaldi (2), Domingo Alcaraz-Segura (3), Siham Tabik (1) ((1) Department of Computer Science and Artificial Intelligence, DaSCI, University of Granada, Granada, Spain, (2) LifeWatch-ERIC ICT Core, Seville, Spain, (3) Department of Botany, Faculty of Science, University of Granada, Granada, Spain)
Remotely sensed data are dominated by mixed Land Use and Land Cover (LULC) types. Spectral unmixing is a technique to extract information from mixed pixels into their constituent LULC types and corresponding abundance fractions. Traditionally, solving this task has relied on either classical methods that require prior knowledge of endmembers or machine learning methods that avoid explicit endmembers calculation, also known as blind spectral unmixing (BSU). Most BSU studies based on Deep Learning (DL) focus on one time-step hyperspectral or multispectral data. To our knowledge, here we provide the first study on BSU of LULC classes using MODIS multispectral time series, in presence of missing data, with end-to-end DL models. We further boost the performance of a Long-Short Term Memory (LSTM)-based model by incorporating geographic plus topographic (geo-topographic) and climatic ancillary information. Our experiments show that combining spectral-temporal input data together with geo-topographic and climatic information substantially improves the abundance estimation of LULC classes in mixed pixels. To carry out this study, we built a new labeled dataset of the region of Andalusia (Spain) with monthly multispectral time series of pixels for the year 2013 from MODIS at 460m resolution, for two hierarchical levels of LULC classes, named Andalusia MultiSpectral MultiTemporal Unmixing (Andalusia-MSMTU). This dataset provides, at the pixel level, a multispectral time series plus ancillary information annotated with the abundance of each LULC class inside each pixel. The dataset (https://zenodo.org/record/7752348##.ZBmkkezMLdo) and code (https://github.com/jrodriguezortega/MSMTU) are available to the public.
Authors: Yifan Pu, Weicong Liang, Yiduo Hao, Yuhui Yuan, Yukang Yang, Chao Zhang, Han Hu, Gao Huang
Modern detection transformers (DETRs) use a set of object queries to predict a list of bounding boxes, sort them by their classification confidence scores, and select the top-ranked predictions as the final detection results for the given input image. A highly performant object detector requires accurate ranking for the bounding box predictions. For DETR-based detectors, the top-ranked bounding boxes suffer from less accurate localization quality due to the misalignment between classification scores and localization accuracy, thus impeding the construction of high-quality detectors. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs, combinedly called Rank-DETR. Our key contributions include: (i) a rank-oriented architecture design that can prompt positive predictions and suppress the negative ones to ensure lower false positive rates, as well as (ii) a rank-oriented loss function and matching cost design that prioritizes predictions of more accurate localization accuracy during ranking to boost the AP under high IoU thresholds. We apply our method to improve the recent SOTA methods (e.g., H-DETR and DINO-DETR) and report strong COCO object detection results when using different backbones such as ResNet-$50$, Swin-T, and Swin-L, demonstrating the effectiveness of our approach. Code is available at \url{https://github.com/LeapLabTHU/Rank-DETR}.
Authors: Kai Li, Yupeng Deng, Yunlong Kong, Diyou Liu, Jingbo Chen, Yu Meng, Junxian Ma
Accurate measurement of the offset from roof-to-footprint in very-high-resolution remote sensing imagery is crucial for urban information extraction tasks. With the help of deep learning, existing methods typically rely on two-stage CNN models to extract regions of interest on building feature maps. At the first stage, a Region Proposal Network (RPN) is applied to extract thousands of ROIs (Region of Interests) which will post-imported into a Region-based Convolutional Neural Networks (RCNN) to extract wanted information. However, because of inflexible RPN, these methods often lack effective user interaction, encounter difficulties in instance correspondence, and struggle to keep up with the advancements in general artificial intelligence. This paper introduces an interactive Transformer model combined with a prompt encoder to precisely extract building segmentation as well as the offset vectors from roofs to footprints. In our model, a powerful module, namely ROAM, was tailored for common problems in predicting roof-to-footprint offsets. We tested our model's feasibility on the publicly available BONAI dataset, achieving a significant reduction in Prompt-Instance-Level offset errors ranging from 14.6% to 16.3%. Additionally, we developed a Distance-NMS algorithm tailored for large-scale building offsets, significantly enhancing the accuracy of predicted building offset angles and lengths in a straightforward and efficient manner. To further validate the model's robustness, we created a new test set using 0.5m remote sensing imagery from Huizhou, China, for inference testing. Our code, training methods, and the updated dataset will be accessable at https://github.com/likaiucas.
Authors: You-Ming Chang, Chen Yeh, Wei-Chen Chiu, Ning Yu
Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically train classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel approach using VLMs (e.g. InstructBLIP) and prompt tuning techniques to improve the deepfake detection accuracy over unseen data. We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to distinguish a query image is real or fake. We conduct full-spectrum experiments on datasets from 3 held-in and 13 held-out generative models, covering modern text-to-image generation, image editing and image attacks. Results demonstrate that (1) the deepfake detection accuracy can be significantly and consistently improved (from 54.6% to 91.31%, in average accuracy over unseen data) using pretrained vision-language models with prompt tuning; (2) our superior performance is at less cost of trainable parameters, resulting in an effective and efficient solution for deepfake detection. Code and models can be found at https://github.com/nctu-eva-lab/AntifakePrompt.
Authors: Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, Jiming Chen
Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due to various concerns, \eg, data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/organs, can vary significantly. Recently large pre-trained vision-language models (VLMs), such as CLIP, have demonstrated strong zero-shot recognition ability in various vision tasks, including anomaly detection. However, their ZSAD performance is weak since the VLMs focus more on modeling the class semantics of the foreground objects rather than the abnormality/normality in the images. In this paper we introduce a novel approach, namely AnomalyCLIP, to adapt CLIP for accurate ZSAD across different domains. The key insight of AnomalyCLIP is to learn object-agnostic text prompts that capture generic normality and abnormality in an image regardless of its foreground objects. This allows our model to focus on the abnormal image regions rather than the object semantics, enabling generalized normality and abnormality recognition on diverse types of objects. Large-scale experiments on 17 real-world anomaly detection datasets show that AnomalyCLIP achieves superior zero-shot performance of detecting and segmenting anomalies in datasets of highly diverse class semantics from various defect inspection and medical imaging domains. Code will be made available at https://github.com/zqhang/AnomalyCLIP.
Authors: Yao Yao, Peike Li, Boyu Chen, Alex Wang
With rapid advances in generative artificial intelligence, the text-to-music synthesis task has emerged as a promising direction for music generation from scratch. However, finer-grained control over multi-track generation remains an open challenge. Existing models exhibit strong raw generation capability but lack the flexibility to compose separate tracks and combine them in a controllable manner, differing from typical workflows of human composers. To address this issue, we propose JEN-1 Composer, a unified framework to efficiently model marginal, conditional, and joint distributions over multi-track music via a single model. JEN-1 Composer framework exhibits the capacity to seamlessly incorporate any diffusion-based music generation system, \textit{e.g.} Jen-1, enhancing its capacity for versatile multi-track music generation. We introduce a curriculum training strategy aimed at incrementally instructing the model in the transition from single-track generation to the flexible generation of multi-track combinations. During the inference, users have the ability to iteratively produce and choose music tracks that meet their preferences, subsequently creating an entire musical composition incrementally following the proposed Human-AI co-composition workflow. Quantitative and qualitative assessments demonstrate state-of-the-art performance in controllable and high-fidelity multi-track music synthesis. The proposed JEN-1 Composer represents a significant advance toward interactive AI-facilitated music creation and composition. Demos will be available at https://www.jenmusic.ai/audio-demos.
Authors: Maria R. Kodenko, Yuriy A. Vasilev, Nicholas S. Kulberg, Andrey V. Samorodov, Anton V. Vladzimirskyy, Olga V. Omelyanskaya, Roman V. Reshetnikov
Background and objective: CTA is a gold standard of preoperative diagnosis of abdominal aorta and typically used for geometric-only characteristic extraction. We assume that a model describing the dynamic behavior of the contrast agent in the vessel can be developed from the data of routine CTA studies, allowing the procedure to be investigated and optimized without the need for additional perfusion CT studies. Obtained spatial distribution of CA can be valuable for both increasing the diagnostic value of a particular study and improving the CT data processing tools. Methods: In accordance with the Beer-Lambert law and the absence of chemical interaction between blood and CA, we postulated the existence of a deterministic CA-induced component in the CT signal density. The proposed model, having a double-sigmoid structure, contains six coefficients relevant to the properties of hemodynamics. To validate the model, expert segmentation was performed using the 3D Slicer application for the CTA data obtained from publicly available source. The model was fitted to the data using the non-linear least square method with Levenberg-Marquardt optimization. Results: We analyzed 594 CTA images (4 studies with median size of 144 slices, IQR [134; 158.5]; 1:1 normal:pathology balance). Goodness-of-fit was proved by Wilcox test (p-value > 0.05 for all cases). The proposed model correctly simulated normal blood flow and hemodynamics disturbances caused by local abnormalities (aneurysm, thrombus and arterial branching). Conclusions: Proposed approach can be useful for personalized CA modeling of vessels, improvement of CTA image processing and preparation of synthetic CT training data for artificial intelligence.
Authors: Ruxue Wen, Hangjie Yuan, Dong Ni, Wenbo Xiao, Yaoyao Wu
In medical image segmentation, domain generalization poses a significant challenge due to domain shifts caused by variations in data acquisition devices and other factors. These shifts are particularly pronounced in the most common scenario, which involves only single-source domain data due to privacy concerns. To address this, we draw inspiration from the self-supervised learning paradigm that effectively discourages overfitting to the source domain. We propose the Denoising Y-Net (DeY-Net), a novel approach incorporating an auxiliary denoising decoder into the basic U-Net architecture. The auxiliary decoder aims to perform denoising training, augmenting the domain-invariant representation that facilitates domain generalization. Furthermore, this paradigm provides the potential to utilize unlabeled data. Building upon denoising training, we propose Denoising Test Time Adaptation (DeTTA) that further: (i) adapts the model to the target domain in a sample-wise manner, and (ii) adapts to the noise-corrupted input. Extensive experiments conducted on widely-adopted liver segmentation benchmarks demonstrate significant domain generalization improvements over our baseline and state-of-the-art results compared to other methods. Code is available at https://github.com/WenRuxue/DeTTA.
Authors: Yingshu Li, Yunyi Liu, Zhanyu Wang, Xinyu Liang, Lingqiao Liu, Lei Wang, Leyang Cui, Zhaopeng Tu, Longyue Wang, Luping Zhou
This paper presents a comprehensive evaluation of GPT-4V's capabilities across diverse medical imaging tasks, including Radiology Report Generation, Medical Visual Question Answering (VQA), and Visual Grounding. While prior efforts have explored GPT-4V's performance in medical image anaylsis, to the best of our knowledge, our study represents the first quantitative evaluation on publicly available benchmarks. Our findings highlight GPT-4V's potential in generating descriptive reports for chest X-ray images, particularly when guided by well-structured prompts. Meanwhile, its performance on the MIMIC-CXR dataset benchmark reveals areas for improvement in certain evaluation metrics, such as CIDEr. In the domain of Medical VQA, GPT-4V demonstrates proficiency in distinguishing between question types but falls short of the VQA-RAD benchmark in terms of accuracy. Furthermore, our analysis finds the limitations of conventional evaluation metrics like the BLEU score, advocating for the development of more semantically robust assessment methods. In the field of Visual Grounding, GPT-4V exhibits preliminary promise in recognizing bounding boxes, but its precision is lacking, especially in identifying specific medical organs and signs. Our evaluation underscores the significant potential of GPT-4V in the medical imaging domain, while also emphasizing the need for targeted refinements to fully unlock its capabilities.
Authors: Qiying Yu, Quan Sun, Xiaosong Zhang, Yufeng Cui, Fan Zhang, Yue Cao, Xinlong Wang, Jingjing Liu
Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However, our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions, which have been largely obscured by their initial benchmark success. Upon closer examination, we identify the root cause as the overly-simplified language structure and lack of knowledge details in existing synthetic captions. To provide higher-quality and more scalable multimodal pretraining data, we propose CapsFusion, an advanced framework that leverages large language models to consolidate and refine information from both web-based image-text pairs and synthetic captions. Extensive experiments show that CapsFusion captions exhibit remarkable all-round superiority over existing captions in terms of model performance (e.g., 18.8 and 18.3 improvements in CIDEr score on COCO and NoCaps), sample efficiency (requiring 11-16 times less computation than baselines), world knowledge depth, and scalability. These effectiveness, efficiency and scalability advantages position CapsFusion as a promising candidate for future scaling of LMM training.
Authors: Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, Michele Magno
Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.
Authors: Yiangos Georgiou, Marios Loizou, Tom Kelly, Melinos Averkiou
We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints. Our method employs a conditional GAN, taking a single view of a facade along with the desired viewpoint information and generates an image of the facade from the distinct viewpoint. To precisely modify view-dependent elements like windows and doors while preserving the structure of view-independent components such as walls, we introduce a selective editing module. This module leverages image embeddings extracted from a pre-trained vision transformer. Our experiments demonstrated state-of-the-art performance on building facade generation, surpassing alternative methods.