Authors: Shin Jeong Jin
Abstract: Deep learning models have achieved unprecedented performance in the domain of object detection, resulting in breakthroughs in areas such as autonomous driving and security. However, deep learning models are vulnerable to backdoor attacks. These attacks prompt models to behave similarly to standard models without a trigger; however, they act maliciously upon detecting a predefined trigger. Despite extensive research on backdoor attacks in image classification, their application to object detection remains relatively underexplored. Given the widespread application of object detection in critical real-world scenarios, the sensitivity and potential impact of these vulnerabilities cannot be overstated. In this study, we propose an effective invisible backdoor attack on object detection utilizing a mask-based approach. Three distinct attack scenarios were explored for object detection: object disappearance, object misclassification, and object generation attack. Through extensive experiments, we comprehensively examined the effectiveness of these attacks and tested certain defense methods to determine effective countermeasures.
Authors: Zhuoying Li, Bohua Wan, Cong Mu, Ruzhang Zhao, Shushan Qiu, Chao Yan
Abstract: Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that combines adversarial training with source-target domain alignment to enhance generalization capabilities. By pretraining with Coral loss and standard loss, AD-Aligning aligns target domain statistics with those of the pretrained encoder, preserving robustness while accommodating domain shifts. Through extensive experiments on diverse datasets and domain shift scenarios, including noise-induced shifts and cognitive domain adaptation tasks, we demonstrate AD-Aligning's superior performance compared to existing methods such as Deep Coral and ADDA. Our findings highlight AD-Aligning's ability to emulate the nuanced cognitive processes inherent in human perception, making it a promising solution for real-world applications requiring adaptable and robust domain adaptation strategies.
Authors: Benjamin Camus (DGA.MI), Th\'eo Voillemin (DGA.MI), Corentin Le Barbu (DGA.MI), Jean-Christophe Louvign\'e (DGA.MI), Carole Belloni (DGA.MI), Emmanuel Vall\'ee (DGA.MI)
Abstract: In this work, we propose to tackle several challenges hindering the development of Automatic Target Detection (ATD) algorithms for ground targets in SAR images. To address the lack of representative training data, we propose a Deep Learning approach to train ATD models with synthetic target signatures produced with the MOCEM simulator. We define an incrustation pipeline to incorporate synthetic targets into real backgrounds. Using this hybrid dataset, we train ATD models specifically tailored to bridge the domain gap between synthetic and real data. Our approach notably relies on massive physics-based data augmentation techniques and Adversarial Training of two deep-learning detection architectures. We then test these models on several datasets, including (1) patchworks of real SAR images, (2) images with the incrustation of real targets in real backgrounds, and (3) images with the incrustation of synthetic background objects in real backgrounds. Results show that the produced hybrid datasets are exempt from image overlay bias. Our approach can reach up to 90% of Average Precision on real data while exclusively using synthetic targets for training.
Authors: Guo Yachan, Xiao Yi, Xue Danna, Jose Luis Gomez Zurita, Antonio M. L\'opez
Abstract: Unsupervised Domain Adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled target domain. While UDA methods for synthetic to real-world domains (synth-to-real) show remarkable performance in tasks such as semantic segmentation and object detection, very few were proposed for the instance segmentation task. In this paper, we introduce UDA4Inst, a model of synth-to-real UDA for instance segmentation in autonomous driving. We propose a novel cross-domain bidirectional data mixing method at the instance level to fully leverage the data from both source and target domains. Rare-class balancing and category module training are also employed to further improve the performance. It is worth noting that we are the first to demonstrate results on two new synth-to-real instance segmentation benchmarks, with 39.0 mAP on UrbanSyn->Cityscapes and 35.7 mAP on Synscapes->Cityscapes. UDA4Inst also achieves the state-of-the-art result on SYNTHIA->Cityscapes with 31.3 mAP, +15.6 higher than the latest approach. Our code will be released.
Authors: Jadie Adams, Krithika Iyer, Shireen Elhabian
Abstract: Anatomical shape analysis plays a pivotal role in clinical research and hypothesis testing, where the relationship between form and function is paramount. Correspondence-based statistical shape modeling (SSM) facilitates population-level morphometrics but requires a cumbersome, potentially bias-inducing construction pipeline. Recent advancements in deep learning have streamlined this process in inference by providing SSM prediction directly from unsegmented medical images. However, the proposed approaches are fully supervised and require utilizing a traditional SSM construction pipeline to create training data, thus inheriting the associated burdens and limitations. To address these challenges, we introduce a weakly supervised deep learning approach to predict SSM from images using point cloud supervision. Specifically, we propose reducing the supervision associated with the state-of-the-art fully Bayesian variational information bottleneck DeepSSM (BVIB-DeepSSM) model. BVIB-DeepSSM is an effective, principled framework for predicting probabilistic anatomical shapes from images with quantification of both aleatoric and epistemic uncertainties. Whereas the original BVIB-DeepSSM method requires strong supervision in the form of ground truth correspondence points, the proposed approach utilizes weak supervision via point cloud surface representations, which are more readily obtainable. Furthermore, the proposed approach learns correspondence in a completely data-driven manner without prior assumptions about the expected variability in shape cohort. Our experiments demonstrate that this approach yields similar accuracy and uncertainty estimation to the fully supervised scenario while substantially enhancing the feasibility of model training for SSM construction.
Authors: Jadie Adams, Shireen Elhabian
Abstract: Correspondence-based statistical shape modeling (SSM) stands as a powerful technology for morphometric analysis in clinical research. SSM facilitates population-level characterization and quantification of anatomical shapes such as bones and organs, aiding in pathology and disease diagnostics and treatment planning. Despite its potential, SSM remains under-utilized in medical research due to the significant overhead associated with automatic construction methods, which demand complete, aligned shape surface representations. Additionally, optimization-based techniques rely on bias-inducing assumptions or templates and have prolonged inference times as the entire cohort is simultaneously optimized. To overcome these challenges, we introduce Point2SSM++, a principled, self-supervised deep learning approach that directly learns correspondence points from point cloud representations of anatomical shapes. Point2SSM++ is robust to misaligned and inconsistent input, providing SSM that accurately samples individual shape surfaces while effectively capturing population-level statistics. Additionally, we present principled extensions of Point2SSM++ to adapt it for dynamic spatiotemporal and multi-anatomy use cases, demonstrating the broad versatility of the Point2SSM++ framework. Furthermore, we present extensions of Point2SSM++ tailored for dynamic spatiotemporal and multi-anatomy scenarios, showcasing the broad versatility of the framework. Through extensive validation across diverse anatomies, evaluation metrics, and clinically relevant downstream tasks, we demonstrate Point2SSM++'s superiority over existing state-of-the-art deep learning models and traditional approaches. Point2SSM++ substantially enhances the feasibility of SSM generation and significantly broadens its array of potential clinical applications.
Authors: Andong Wang, Bo Wu, Sunli Chen, Zhenfang Chen, Haotian Guan, Wei-Ning Lee, Li Erran Li, Joshua B Tenenbaum, Chuang Gan
Abstract: Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence. However, existing video reasoning benchmarks are still inadequate since they were mainly designed for factual or situated reasoning and rarely involve broader knowledge in the real world. Our work aims to delve deeper into reasoning evaluations, specifically within dynamic, open-world, and structured context knowledge. We propose a new benchmark (SOK-Bench), consisting of 44K questions and 10K situations with instance-level annotations depicted in the videos. The reasoning process is required to understand and apply situated knowledge and general knowledge for problem-solving. To create such a dataset, we propose an automatic and scalable generation method to generate question-answer pairs, knowledge graphs, and rationales by instructing the combinations of LLMs and MLLMs. Concretely, we first extract observable situated entities, relations, and processes from videos for situated knowledge and then extend to open-world knowledge beyond the visible content. The task generation is facilitated through multiple dialogues as iterations and subsequently corrected and refined by our designed self-promptings and demonstrations. With a corpus of both explicit situated facts and implicit commonsense, we generate associated question-answer pairs and reasoning processes, finally followed by manual reviews for quality assurance. We evaluated recent mainstream large vision-language models on the benchmark and found several insightful conclusions. For more information, please refer to our benchmark at www.bobbywu.com/SOKBench.
Authors: Siming He, Zach Osman, Pratik Chaudhari
Abstract: For robotics applications where there is a limited number of (typically ego-centric) views, parametric representations such as neural radiance fields (NeRFs) generalize better than non-parametric ones such as Gaussian splatting (GS) to views that are very different from those in the training data; GS however can render much faster than NeRFs. We develop a procedure to convert back and forth between the two. Our approach achieves the best of both NeRFs (superior PSNR, SSIM, and LPIPS on dissimilar views, and a compact representation) and GS (real-time rendering and ability for easily modifying the representation); the computational cost of these conversions is minor compared to training the two from scratch.
Authors: Vage Taamazyan, Alberto Dall'olio, Agastya Kalra
Abstract: 3D cameras have emerged as a critical source of information for applications in robotics and autonomous driving. These cameras provide robots with the ability to capture and utilize point clouds, enabling them to navigate their surroundings and avoid collisions with other objects. However, current standard camera evaluation metrics often fail to consider the specific application context. These metrics typically focus on measures like Chamfer distance (CD) or Earth Mover's Distance (EMD), which may not directly translate to performance in real-world scenarios. To address this limitation, we propose a novel metric for point cloud evaluation, specifically designed to assess the suitability of 3D cameras for the critical task of collision avoidance. This metric incorporates application-specific considerations and provides a more accurate measure of a camera's effectiveness in ensuring safe robot navigation.
Authors: Zhiqiang Shen, Peng Cao, Junming Su, Jinzhu Yang, Osmar R. Zaiane
Abstract: This paper investigates an extremely challenging problem, barely-supervised medical image segmentation (BSS), where the training dataset comprises limited labeled data with only single-slice annotations and numerous unlabeled images. Currently, state-of-the-art (SOTA) BSS methods utilize a registration-based paradigm, depending on image registration to propagate single-slice annotations into volumetric pseudo labels for constructing a complete labeled set. However, this paradigm has a critical limitation: the pseudo labels generated by image registration are unreliable and noisy. Motivated by this, we propose a new perspective: training a model using only single-annotated slices as the labeled set without relying on image registration. To this end, we formulate BSS as an unsupervised domain adaptation (UDA) problem. Specifically, we first design a novel noise-free labeled data construction algorithm (NFC) for slice-to-volume labeled data synthesis, which may result in a side effect: domain shifts between the synthesized images and the original images. Then, a frequency and spatial mix-up strategy (FSX) is further introduced to mitigate the domain shifts for UDA. Extensive experiments demonstrate that our method provides a promising alternative for BSS. Remarkably, the proposed method with only one labeled slice achieves an 80.77% dice score on left atrial segmentation, outperforming the SOTA by 61.28%. The code will be released upon the publication of this paper.
Authors: Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Runmin Cong, Xiaochun Cao, Qingming Huang
Abstract: This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://github.com/Ferry-Li/SI-SOD.
Authors: Wentao Jiang, Jing Zhang, Di Wang, Qiming Zhang, Zengmao Wang, Bo Du
Abstract: Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved in self-attention (SA) to reduce the overall token numbers within the calculation, avoiding the high computational cost issue in Vision Transformers. However, such methods usually obtain sparse tokens by hand-crafted or parallel-unfriendly designs, posing a challenge to reach a better balance between efficiency and performance. Different from them, this paper proposes to use learnable meta tokens to formulate sparse tokens, which effectively learn key information meanwhile improving the inference speed. Technically, the meta tokens are first initialized from image tokens via cross-attention. Then, we propose Dual Cross-Attention (DCA) to promote information exchange between image tokens and meta tokens, where they serve as query and key (value) tokens alternatively in a dual-branch structure, significantly reducing the computational complexity compared to self-attention. By employing DCA in the early stages with dense visual tokens, we obtain the hierarchical architecture LeMeViT with various sizes. Experimental results in classification and dense prediction tasks show that LeMeViT has a significant $1.7 \times$ speedup, fewer parameters, and competitive performance compared to the baseline models, and achieves a better trade-off between efficiency and performance.
Authors: Joseph Cho, Cyril Zakka, Rohan Shad, Ross Wightman, Akshay Chaudhari, William Hiesinger
Abstract: Diffusion models have recently gained significant traction due to their ability to generate high-fidelity and diverse images and videos conditioned on text prompts. In medicine, this application promises to address the critical challenge of data scarcity, a consequence of barriers in data sharing, stringent patient privacy regulations, and disparities in patient population and demographics. By generating realistic and varying medical 2D and 3D images, these models offer a rich, privacy-respecting resource for algorithmic training and research. To this end, we introduce MediSyn, a pair of instruction-tuned text-guided latent diffusion models with the ability to generate high-fidelity and diverse medical 2D and 3D images across specialties and modalities. Through established metrics, we show significant improvement in broad medical image and video synthesis guided by text prompts.
Authors: Alexander Lappe, Anna Bogn\'ar, Ghazaleh Ghamkhari Nejad, Albert Mukovskiy, Lucas Martini, Martin A. Giese, Rufin Vogels
Abstract: High-level visual brain regions contain subareas in which neurons appear to respond more strongly to examples of a particular semantic category, like faces or bodies, rather than objects. However, recent work has shown that while this finding holds on average, some out-of-category stimuli also activate neurons in these regions. This may be due to visual features common among the preferred class also being present in other images. Here, we propose a deep-learning-based approach for visualizing these features. For each neuron, we identify relevant visual features driving its selectivity by modelling responses to images based on latent activations of a deep neural network. Given an out-of-category image which strongly activates the neuron, our method first identifies a reference image from the preferred category yielding a similar feature activation pattern. We then backpropagate latent activations of both images to the pixel level, while enhancing the identified shared dimensions and attenuating non-shared features. The procedure highlights image regions containing shared features driving responses of the model neuron. We apply the algorithm to novel recordings from body-selective regions in macaque IT cortex in order to understand why some images of objects excite these neurons. Visualizations reveal object parts which resemble parts of a macaque body, shedding light on neural preference of these objects.
Authors: Xusheng Li, Chengliang Wang, Shumao Wang, Zhuo Zeng, Ji Liu
Abstract: Multi-line LiDAR is widely used in autonomous vehicles, so point cloud-based 3D detectors are essential for autonomous driving. Extracting rich multi-scale features is crucial for point cloud-based 3D detectors in autonomous driving due to significant differences in the size of different types of objects. However, due to the real-time requirements, large-size convolution kernels are rarely used to extract large-scale features in the backbone. Current 3D detectors commonly use feature pyramid networks to obtain large-scale features; however, some objects containing fewer point clouds are further lost during downsampling, resulting in degraded performance. Since pillar-based schemes require much less computation than voxel-based schemes, they are more suitable for constructing real-time 3D detectors. Hence, we propose PillarNeXt, a pillar-based scheme. We redesigned the feature encoding, the backbone, and the neck of the 3D detector. We propose Voxel2Pillar feature encoding, which uses a sparse convolution constructor to construct pillars with richer point cloud features, especially height features. Moreover, additional learnable parameters are added, which enables the initial pillar to achieve higher performance capabilities. We extract multi-scale and large-scale features in the proposed fully sparse backbone, which does not utilize large-size convolutional kernels; the backbone consists of the proposed multi-scale feature extraction module. The neck consists of the proposed sparse ConvNeXt, whose simple structure significantly improves the performance. The effectiveness of the proposed PillarNeXt is validated on the Waymo Open Dataset, and object detection accuracy for vehicles, pedestrians, and cyclists is improved; we also verify the effectiveness of each proposed module in detail.
Authors: Jihwan Kwak, Sungmin Cha, Taesup Moon
Abstract: This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with different pixel labels, which is far from practical incremental learning scenarios. Moreover, we identified that this flawed scenario may lead to biased results for two commonly used techniques in CISS, pseudo-labeling and exemplar memory, resulting in unintended advantages or disadvantages for certain techniques. To mitigate this, a practical scenario called partitioned is proposed, in which the dataset is first divided into distinct subsets representing each class, and then the subsets are assigned to each corresponding task. This efficiently addresses the issue above while meeting the requirement of CISS scenario, such as capturing the background shifts. Furthermore, we identify and address the code implementation issues related to retrieving data from the exemplar memory, which was ignored in previous works. Lastly, we introduce a simple yet competitive memory-based baseline, MiB-AugM, that handles background shifts of current tasks in the exemplar memory. This baseline achieves state-of-the-art results across multiple tasks involving learning numerous new classes.
Authors: Haonan An, Guang Hua, Zhiping Lin, Yuguang Fang
Abstract: Box-free model watermarking is an emerging technique to safeguard the intellectual property of deep learning models, particularly those for low-level image processing tasks. Existing works have verified and improved its effectiveness in several aspects. However, in this paper, we reveal that box-free model watermarking is prone to removal attacks, even under the real-world threat model such that the protected model and the watermark extractor are in black boxes. Under this setting, we carry out three studies. 1) We develop an extractor-gradient-guided (EGG) remover and show its effectiveness when the extractor uses ReLU activation only. 2) More generally, for an unknown extractor, we leverage adversarial attacks and design the EGG remover based on the estimated gradients. 3) Under the most stringent condition that the extractor is inaccessible, we design a transferable remover based on a set of private proxy models. In all cases, the proposed removers can successfully remove embedded watermarks while preserving the quality of the processed images, and we also demonstrate that the EGG remover can even replace the watermarks. Extensive experimental results verify the effectiveness and generalizability of the proposed attacks, revealing the vulnerabilities of the existing box-free methods and calling for further research.
Authors: Yongsong Huang, Tomo Miyazaki, Xiaofeng Liu, Shinichiro Omachi
Abstract: Infrared (IR) image super-resolution faces challenges from homogeneous background pixel distributions and sparse target regions, requiring models that effectively handle long-range dependencies and capture detailed local-global information. Recent advancements in Mamba-based (Selective Structured State Space Model) models, employing state space models, have shown significant potential in visual tasks, suggesting their applicability for IR enhancement. In this work, we introduce IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model, a novel Mamba-based model designed specifically for IR image super-resolution. This model enhances the restoration of context-sparse target details through its advanced dependency modeling capabilities. Additionally, a new wavelet transform feature modulation block improves multi-scale receptive field representation, capturing both global and local information efficiently. Comprehensive evaluations confirm that IRSRMamba outperforms existing models on multiple benchmarks. This research advances IR super-resolution and demonstrates the potential of Mamba-based models in IR image processing. Code are available at \url{https://github.com/yongsongH/IRSRMamba}.
Authors: Xinyang Li, Zhangyu Lai, Linning Xu, Jianfei Guo, Liujuan Cao, Shengchuan Zhang, Bo Dai, Rongrong Ji
Abstract: We present Dual3D, a novel text-to-3D generation framework that generates high-quality 3D assets from texts in only $1$ minute.The key component is a dual-mode multi-view latent diffusion model. Given the noisy multi-view latents, the 2D mode can efficiently denoise them with a single latent denoising network, while the 3D mode can generate a tri-plane neural surface for consistent rendering-based denoising. Most modules for both modes are tuned from a pre-trained text-to-image latent diffusion model to circumvent the expensive cost of training from scratch. To overcome the high rendering cost during inference, we propose the dual-mode toggling inference strategy to use only $1/10$ denoising steps with 3D mode, successfully generating a 3D asset in just $10$ seconds without sacrificing quality. The texture of the 3D asset can be further enhanced by our efficient texture refinement process in a short time. Extensive experiments demonstrate that our method delivers state-of-the-art performance while significantly reducing generation time. Our project page is available at https://dual3d.github.io
URLs: https://dual3d.github.io
Authors: Juwon Seo, Sung-Hoon Lee, Tae-Young Lee, Seungjun Moon, Gyeong-Moon Park
Abstract: Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only a reconstruction of real-world images but also the modification of attributes through various editing methods. However, in certain domains related to privacy issues, e.g., human faces, advanced generative models along with strong inversion methods can lead to potential misuses. In this paper, we propose an essential yet under-explored task called generative identity unlearning, which steers the model not to generate an image of a specific identity. In the generative identity unlearning, we target the following objectives: (i) preventing the generation of images with a certain identity, and (ii) preserving the overall quality of the generative model. To satisfy these goals, we propose a novel framework, Generative Unlearning for Any Identity (GUIDE), which prevents the reconstruction of a specific identity by unlearning the generator with only a single image. GUIDE consists of two parts: (i) finding a target point for optimization that un-identifies the source latent code and (ii) novel loss functions that facilitate the unlearning procedure while less affecting the learned distribution. Our extensive experiments demonstrate that our proposed method achieves state-of-the-art performance in the generative machine unlearning task. The code is available at https://github.com/KHU-AGI/GUIDE.
Authors: Yuchen Guo, Hanqun Cao, Lok Ming Lui
Abstract: 3D face registration is an important process in which a 3D face model is aligned and mapped to a template face. However, the task of 3D face registration becomes particularly challenging when dealing with partial face data, where only limited facial information is available. To address this challenge, this paper presents a novel deep learning-based approach that combines quasi-conformal geometry with deep neural networks for partial face registration. The proposed framework begins with a Landmark Detection Network that utilizes curvature information to detect the presence of facial features and estimate their corresponding coordinates. These facial landmark features serve as essential guidance for the registration process. To establish a dense correspondence between the partial face and the template surface, a registration network based on quasiconformal theories is employed. The registration network establishes a bijective quasiconformal surface mapping aligning corresponding partial faces based on detected landmarks and curvature values. It consists of the Coefficients Prediction Network, which outputs the optimal Beltrami coefficient representing the surface mapping. The Beltrami coefficient quantifies the local geometric distortion of the mapping. By controlling the magnitude of the Beltrami coefficient through a suitable activation function, the bijectivity and geometric distortion of the mapping can be controlled. The Beltrami coefficient is then fed into the Beltrami solver network to reconstruct the corresponding mapping. The surface registration enables the acquisition of corresponding regions and the establishment of point-wise correspondence between different partial faces, facilitating precise shape comparison through the evaluation of point-wise geometric differences at these corresponding regions. Experimental results demonstrate the effectiveness of the proposed method.
Authors: Yuhao Sun, Lingyun Yu, Hongtao Xie, Jiaming Li, Yongdong Zhang
Abstract: With the rapid development of face recognition (FR) systems, the privacy of face images on social media is facing severe challenges due to the abuse of unauthorized FR systems. Some studies utilize adversarial attack techniques to defend against malicious FR systems by generating adversarial examples. However, the generated adversarial examples, i.e., the protected face images, tend to suffer from subpar visual quality and low transferability. In this paper, we propose a novel face protection approach, dubbed DiffAM, which leverages the powerful generative ability of diffusion models to generate high-quality protected face images with adversarial makeup transferred from reference images. To be specific, we first introduce a makeup removal module to generate non-makeup images utilizing a fine-tuned diffusion model with guidance of textual prompts in CLIP space. As the inverse process of makeup transfer, makeup removal can make it easier to establish the deterministic relationship between makeup domain and non-makeup domain regardless of elaborate text prompts. Then, with this relationship, a CLIP-based makeup loss along with an ensemble attack strategy is introduced to jointly guide the direction of adversarial makeup domain, achieving the generation of protected face images with natural-looking makeup and high black-box transferability. Extensive experiments demonstrate that DiffAM achieves higher visual quality and attack success rates with a gain of 12.98% under black-box setting compared with the state of the arts. The code will be available at https://github.com/HansSunY/DiffAM.
Authors: Xiaosu Zhu, Hualian Sheng, Sijia Cai, Bing Deng, Shaopeng Yang, Qiao Liang, Ken Chen, Lianli Gao, Jingkuan Song, Jieping Ye
Abstract: We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more challenging traffic scenes. The highlights of RoScenes include significantly large perception area, full scene coverage and crowded traffic. More specifically, our dataset achieves surprising 21.13M 3D annotations within 64,000 $m^2$. To relieve the expensive costs of roadside 3D labeling, we present a novel BEV-to-3D joint annotation pipeline to efficiently collect such a large volume of data. After that, we organize a comprehensive study for current BEV methods on RoScenes in terms of effectiveness and efficiency. Tested methods suffer from the vast perception area and variation of sensor layout across scenes, resulting in performance levels falling below expectations. To this end, we propose RoBEV that incorporates feature-guided position embedding for effective 2D-3D feature assignment. With its help, our method outperforms state-of-the-art by a large margin without extra computational overhead on validation set. Our dataset and devkit will be made available at \url{https://github.com/xiaosu-zhu/RoScenes}.
Authors: Arwin Gansekoele, Tycho Bot, Rob van der Mei, Sandjai Bhulai, Mark Hoogendoorn
Abstract: Encryption on the internet with the shift to HTTPS has been an important step to improve the privacy of internet users. However, there is an increasing body of work about extracting information from encrypted internet traffic without having to decrypt it. Such attacks bypass security guarantees assumed to be given by HTTPS and thus need to be understood. Prior works showed that the variable bitrates of video streams are sufficient to identify which video someone is watching. These works generally have to make trade-offs in aspects such as accuracy, scalability, robustness, etc. These trade-offs complicate the practical use of these attacks. To that end, we propose a deep metric learning framework based on the triplet loss method. Through this framework, we achieve robust, generalisable, scalable and transferable encrypted video stream detection. First, the triplet loss is better able to deal with video streams not seen during training. Second, our approach can accurately classify videos not seen during training. Third, we show that our method scales well to a dataset of over 1000 videos. Finally, we show that a model trained on video streams over Chrome can also classify streams over Firefox. Our results suggest that this side-channel attack is more broadly applicable than originally thought. We provide our code alongside a diverse and up-to-date dataset for future research.
Authors: Valerio Marsocci (CEDRIC - VERTIGO, CNAM), Nicolas Audebert (CEDRIC - VERTIGO, CNAM, LaSTIG, IGN)
Abstract: Large-scale "foundation models" have gained traction as a way to leverage the vast amounts of unlabeled remote sensing data collected every day. However, due to the multiplicity of Earth Observation satellites, these models should learn "sensor agnostic" representations, that generalize across sensor characteristics with minimal fine-tuning. This is complicated by data availability, as low-resolution imagery, such as Sentinel-2 and Landsat-8 data, are available in large amounts, while very high-resolution aerial or satellite data is less common. To tackle these challenges, we introduce cross-sensor self-supervised training and alignment for remote sensing (X-STARS). We design a self-supervised training loss, the Multi-Sensor Alignment Dense loss (MSAD), to align representations across sensors, even with vastly different resolutions. Our X-STARS can be applied to train models from scratch, or to adapt large models pretrained on e.g low-resolution EO data to new high-resolution sensors, in a continual pretraining framework. We collect and release MSC-France, a new multi-sensor dataset, on which we train our X-STARS models, then evaluated on seven downstream classification and segmentation tasks. We demonstrate that X-STARS outperforms the state-of-the-art by a significant margin with less data across various conditions of data availability and resolutions.
Authors: Jie Liang, Radu Timofte, Qiaosi Yi, Shuaizheng Liu, Lingchen Sun, Rongyuan Wu, Xindong Zhang, Hui Zeng, Lei Zhang
Abstract: In this paper, we review the NTIRE 2024 challenge on Restore Any Image Model (RAIM) in the Wild. The RAIM challenge constructed a benchmark for image restoration in the wild, including real-world images with/without reference ground truth in various scenarios from real applications. The participants were required to restore the real-captured images from complex and unknown degradation, where generative perceptual quality and fidelity are desired in the restoration result. The challenge consisted of two tasks. Task one employed real referenced data pairs, where quantitative evaluation is available. Task two used unpaired images, and a comprehensive user study was conducted. The challenge attracted more than 200 registrations, where 39 of them submitted results with more than 400 submissions. Top-ranked methods improved the state-of-the-art restoration performance and obtained unanimous recognition from all 18 judges. The proposed datasets are available at https://drive.google.com/file/d/1DqbxUoiUqkAIkExu3jZAqoElr_nu1IXb/view?usp=sharing and the homepage of this challenge is at https://codalab.lisn.upsaclay.fr/competitions/17632.
URLs: https://drive.google.com/file/d/1DqbxUoiUqkAIkExu3jZAqoElr_nu1IXb/view?usp=sharing, https://codalab.lisn.upsaclay.fr/competitions/17632.
Authors: Xiaopei Zhu, Yuqiu Liu, Zhanhao Hu, Jianmin Li, Xiaolin Hu
Abstract: Infrared physical adversarial examples are of great significance for studying the security of infrared AI systems that are widely used in our lives such as autonomous driving. Previous infrared physical attacks mainly focused on 2D infrared pedestrian detection which may not fully manifest its destructiveness to AI systems. In this work, we propose a physical attack method against infrared detectors based on 3D modeling, which is applied to a real car. The goal is to design a set of infrared adversarial stickers to make cars invisible to infrared detectors at various viewing angles, distances, and scenes. We build a 3D infrared car model with real infrared characteristics and propose an infrared adversarial pattern generation method based on 3D mesh shadow. We propose a 3D control points-based mesh smoothing algorithm and use a set of smoothness loss functions to enhance the smoothness of adversarial meshes and facilitate the sticker implementation. Besides, We designed the aluminum stickers and conducted physical experiments on two real Mercedes-Benz A200L cars. Our adversarial stickers hid the cars from Faster RCNN, an object detector, at various viewing angles, distances, and scenes. The attack success rate (ASR) was 91.49% for real cars. In comparison, the ASRs of random stickers and no sticker were only 6.21% and 0.66%, respectively. In addition, the ASRs of the designed stickers against six unseen object detectors such as YOLOv3 and Deformable DETR were between 73.35%-95.80%, showing good transferability of the attack performance across detectors.
Authors: Yuchen Zhou, Linkai Liu, Chao Gou
Abstract: Most existing attention prediction research focuses on salient instances like humans and objects. However, the more complex interaction-oriented attention, arising from the comprehension of interactions between instances by human observers, remains largely unexplored. This is equally crucial for advancing human-machine interaction and human-centered artificial intelligence. To bridge this gap, we first collect a novel gaze fixation dataset named IG, comprising 530,000 fixation points across 740 diverse interaction categories, capturing visual attention during human observers cognitive processes of interactions. Subsequently, we introduce the zero-shot interaction-oriented attention prediction task ZeroIA, which challenges models to predict visual cues for interactions not encountered during training. Thirdly, we present the Interactive Attention model IA, designed to emulate human observers cognitive processes to tackle the ZeroIA problem. Extensive experiments demonstrate that the proposed IA outperforms other state-of-the-art approaches in both ZeroIA and fully supervised settings. Lastly, we endeavor to apply interaction-oriented attention to the interaction recognition task itself. Further experimental results demonstrate the promising potential to enhance the performance and interpretability of existing state-of-the-art HOI models by incorporating real human attention data from IG and attention labels generated by IA.
Authors: Fengjie Wang, Chengming Liu, Lei Shi, Pang Haibo
Abstract: Previous unsupervised anomaly detection (UAD) methods often struggle with significant intra-class diversity; i.e., a class in a dataset contains multiple subclasses, which we categorize as Feature-Rich Anomaly Detection Datasets (FRADs). This is evident in applications such as unified setting and unmanned supermarket scenarios. To address this challenge, we developed MiniMaxAD: a lightweight autoencoder designed to efficiently compress and memorize extensive information from normal images. Our model utilizes a large kernel convolutional network equipped with a Global Response Normalization (GRN) unit and employs a multi-scale feature reconstruction strategy. The GRN unit significantly increases the upper limit of the network's capacity, while the large kernel convolution facilitates the extraction of highly abstract patterns, leading to compact normal feature modeling. Additionally, we introduce an Adaptive Contraction Loss (ADCLoss), tailored to FRADs to overcome the limitations of global cosine distance loss. MiniMaxAD was comprehensively tested across six challenging UAD benchmarks, achieving state-of-the-art results in four and highly competitive outcomes in the remaining two. Notably, our model achieved a detection AUROC of up to 97.0\% in ViSA under the unified setting. Moreover, it not only achieved state-of-the-art performance in unmanned supermarket tasks but also exhibited an inference speed 37 times faster than the previous best method, demonstrating its effectiveness in complex UAD tasks.
Authors: Milda Pocevi\v{c}i\=ut\.e, Gabriel Eilertsen, Stina Garvin, Claes Lundstr\"om
Abstract: Multiple-instance learning (MIL) is an attractive approach for digital pathology applications as it reduces the costs related to data collection and labelling. However, it is not clear how sensitive MIL is to clinically realistic domain shifts, i.e., differences in data distribution that could negatively affect performance, and if already existing metrics for detecting domain shifts work well with these algorithms. We trained an attention-based MIL algorithm to classify whether a whole-slide image of a lymph node contains breast tumour metastases. The algorithm was evaluated on data from a hospital in a different country and various subsets of this data that correspond to different levels of domain shift. Our contributions include showing that MIL for digital pathology is affected by clinically realistic differences in data, evaluating which features from a MIL model are most suitable for detecting changes in performance, and proposing an unsupervised metric named Fr\'echet Domain Distance (FDD) for quantification of domain shifts. Shift measure performance was evaluated through the mean Pearson correlation to change in classification performance, where FDD achieved 0.70 on 10-fold cross-validation models. The baselines included Deep ensemble, Difference of Confidence, and Representation shift which resulted in 0.45, -0.29, and 0.56 mean Pearson correlation, respectively. FDD could be a valuable tool for care providers and vendors who need to verify if a MIL system is likely to perform reliably when implemented at a new site, without requiring any additional annotations from pathologists.
Authors: Siliang Ma, Yong Xu
Abstract: Bounding box regression is one of the important steps of object detection. However, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. Most of the existing loss functions for rotated object detection calculate the difference between two bounding boxes only focus on the deviation of area or each points distance (e.g., $\mathcal{L}_{Smooth-\ell 1}$, $\mathcal{L}_{RotatedIoU}$ and $\mathcal{L}_{PIoU}$). The calculation process of some loss functions is extremely complex (e.g. $\mathcal{L}_{KFIoU}$). In order to improve the efficiency and accuracy of bounding box regression for rotated object detection, we proposed a novel metric for arbitrary shapes comparison based on minimum points distance, which takes most of the factors from existing loss functions for rotated object detection into account, i.e., the overlap or nonoverlapping area, the central points distance and the rotation angle. We also proposed a loss function called $\mathcal{L}_{FPDIoU}$ based on four points distance for accurate bounding box regression focusing on faster and high quality anchor boxes. In the experiments, $FPDIoU$ loss has been applied to state-of-the-art rotated object detection (e.g., RTMDET, H2RBox) models training with three popular benchmarks of rotated object detection including DOTA, DIOR, HRSC2016 and two benchmarks of arbitrary orientation scene text detection including ICDAR 2017 RRC-MLT and ICDAR 2019 RRC-MLT, which achieves better performance than existing loss functions.
Authors: Usman A. Zahidi, Krystian {\L}ukasik, Grzegorz Cielniak
Abstract: The maturity classification of specialty crops such as strawberries and tomatoes is an essential agricultural downstream activity for selective harvesting and quality control (QC) at production and packaging sites. Recent advancements in Deep Learning (DL) have produced encouraging results in color images for maturity classification applications. However, hyperspectral imaging (HSI) outperforms methods based on color vision. Multivariate analysis methods and Convolutional Neural Networks (CNN) deliver promising results; however, a large amount of input data and the associated preprocessing requirements cause hindrances in practical application. Conventionally, the reflectance intensity in a given electromagnetic spectrum is employed in estimating fruit maturity. We present a feature extraction method to empirically demonstrate that the peak reflectance in subbands such as 500-670 nm (pigment band) and the wavelength of the peak position, and contrarily, the trough reflectance and its corresponding wavelength within 671-790 nm (chlorophyll band) are convenient to compute yet distinctive features for the maturity classification. The proposed feature selection method is beneficial because preprocessing, such as dimensionality reduction, is avoided before every prediction. The feature set is designed to capture these traits. The best SOTA methods, among 3D-CNN, 1D-CNN, and SVM, achieve at most 90.0 % accuracy for strawberries and 92.0 % for tomatoes on our dataset. Results show that the proposed method outperforms the SOTA as it yields an accuracy above 98.0 % in strawberry and 96.0 % in tomato classification. A comparative analysis of the time efficiency of these methods is also conducted, which shows the proposed method performs prediction at 13 Frames Per Second (FPS) compared to the maximum 1.16 FPS attained by the full-spectrum SVM classifier.
Authors: Zhengxu Shi
Abstract: With the development of deep neural network generative models in recent years, significant progress has been made in the research of depth estimation in lane scenes. However, current research achievements are mainly focused on clear daytime scenarios. In complex rainy environments, the influence of rain streaks and local fog effects often leads to erroneous increases in the overall depth estimation values in images. Moreover, these natural factors can introduce disturbances to the accurate prediction of depth boundaries in images. In this paper, we investigate lane depth estimation in complex rainy environments. Based on the concept of convolutional kernel prediction, we propose a dual-layer pixel-wise convolutional kernel prediction network trained on offline data. By predicting two sets of independent convolutional kernels for the target image, we restore the depth information loss caused by complex environmental factors and address the issue of rain streak artifacts generated by a single convolutional kernel set. Furthermore, considering the lack of real rainy lane data currently available, we introduce an image synthesis algorithm, RCFLane, which comprehensively considers the darkening of the environment due to rainfall and local fog effects. We create a synthetic dataset containing 820 experimental images, which we refer to as RainKITTI, on the commonly used depth estimation dataset KITTI. Extensive experiments demonstrate that our proposed depth estimation framework achieves favorable results in highly complex lane rainy environments.
Authors: Giordano Cicchetti, Eleonora Grassucci, Jihong Park, Jinho Choi, Sergio Barbarossa, Danilo Comminiello
Abstract: In the new paradigm of semantic communication (SC), the focus is on delivering meanings behind bits by extracting semantic information from raw data. Recent advances in data-to-text models facilitate language-oriented SC, particularly for text-transformed image communication via image-to-text (I2T) encoding and text-to-image (T2I) decoding. However, although semantically aligned, the text is too coarse to precisely capture sophisticated visual features such as spatial locations, color, and texture, incurring a significant perceptual difference between intended and reconstructed images. To address this limitation, in this paper, we propose a novel language-oriented SC framework that communicates both text and a compressed image embedding and combines them using a latent diffusion model to reconstruct the intended image. Experimental results validate the potential of our approach, which transmits only 2.09\% of the original image size while achieving higher perceptual similarities in noisy communication channels compared to a baseline SC method that communicates only through text.The code is available at https://github.com/ispamm/Img2Img-SC/ .
Authors: Kuofeng Gao, Yang Bai, Jiawang Bai, Yong Yang, Shu-Tao Xia
Abstract: Multi-modal Large Language Models (MLLMs) have recently achieved enhanced performance across various vision-language tasks including visual grounding capabilities. However, the adversarial robustness of visual grounding remains unexplored in MLLMs. To fill this gap, we use referring expression comprehension (REC) as an example task in visual grounding and propose three adversarial attack paradigms as follows. Firstly, untargeted adversarial attacks induce MLLMs to generate incorrect bounding boxes for each object. Besides, exclusive targeted adversarial attacks cause all generated outputs to the same target bounding box. In addition, permuted targeted adversarial attacks aim to permute all bounding boxes among different objects within a single image. Extensive experiments demonstrate that the proposed methods can successfully attack visual grounding capabilities of MLLMs. Our methods not only provide a new perspective for designing novel attacks but also serve as a strong baseline for improving the adversarial robustness for visual grounding of MLLMs.
Authors: Binghui Chen, Chongyang Zhong, Wangmeng Xiang, Yifeng Geng, Xuansong Xie
Abstract: Due to the significant advances in large-scale text-to-image generation by diffusion model (DM), controllable human image generation has been attracting much attention recently. Existing works, such as Controlnet [36], T2I-adapter [20] and HumanSD [10] have demonstrated good abilities in generating human images based on pose conditions, they still fail to meet the requirements of real e-commerce scenarios. These include (1) the interaction between the shown product and human should be considered, (2) human parts like face/hand/arm/foot and the interaction between human model and product should be hyper-realistic, and (3) the identity of the product shown in advertising should be exactly consistent with the product itself. To this end, in this paper, we first define a new human image generation task for e-commerce marketing, i.e., Object-ID-retentive Human-object Interaction image Generation (OHG), and then propose a VirtualModel framework to generate human images for product shown, which supports displays of any categories of products and any types of human-object interaction. As shown in Figure 1, VirtualModel not only outperforms other methods in terms of accurate pose control and image quality but also allows for the display of user-specified product objects by maintaining the product-ID consistency and enhancing the plausibility of human-object interaction. Codes and data will be released.
Authors: Junkai Fan, Jiangwei Weng, Kun Wang, Yijun Yang, Jianjun Qian, Jun Li, Jian Yang
Abstract: Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with unpredictable weather conditions. In this paper, we propose a pioneering approach that addresses this challenge through a nonaligned regularization strategy. Our core concept involves identifying clear frames that closely match hazy frames, serving as references to supervise a video dehazing network. Our approach comprises two key components: reference matching and video dehazing. Firstly, we introduce a non-aligned reference frame matching module, leveraging an adaptive sliding window to match high-quality reference frames from clear videos. Video dehazing incorporates flow-guided cosine attention sampler and deformable cosine attention fusion modules to enhance spatial multiframe alignment and fuse their improved information. To validate our approach, we collect a GoProHazy dataset captured effortlessly with GoPro cameras in diverse rural and urban road environments. Extensive experiments demonstrate the superiority of the proposed method over current state-of-the-art methods in the challenging task of real driving-video dehazing. Project page.
Authors: Michail Mamalakis, Antonios Mamalakis, Ingrid Agartz, Lynn Egeland M{\o}rch-Johnsen, Graham Murray, John Suckling, Pietro Lio
Abstract: The accelerated progress of artificial intelligence (AI) has popularized deep learning models across domains, yet their inherent opacity poses challenges, notably in critical fields like healthcare, medicine and the geosciences. Explainable AI (XAI) has emerged to shed light on these "black box" models, helping decipher their decision making process. Nevertheless, different XAI methods yield highly different explanations. This inter-method variability increases uncertainty and lowers trust in deep networks' predictions. In this study, for the first time, we propose a novel framework designed to enhance the explainability of deep networks, by maximizing both the accuracy and the comprehensibility of the explanations. Our framework integrates various explanations from established XAI methods and employs a non-linear "explanation optimizer" to construct a unique and optimal explanation. Through experiments on multi-class and binary classification tasks in 2D object and 3D neuroscience imaging, we validate the efficacy of our approach. Our explanation optimizer achieved superior faithfulness scores, averaging 155% and 63% higher than the best performing XAI method in the 3D and 2D applications, respectively. Additionally, our approach yielded lower complexity, increasing comprehensibility. Our results suggest that optimal explanations based on specific criteria are derivable and address the issue of inter-method variability in the current XAI literature.
Authors: Xingjian Wang, Li Chai, Jiming Chen
Abstract: The performance of single image super-resolution depends heavily on how to generate and complement high-frequency details to low-resolution images. Recently, diffusion-based models exhibit great potential in generating high-quality images for super-resolution tasks. However, existing models encounter difficulties in directly predicting high-frequency information of wide bandwidth by solely utilizing the high-resolution ground truth as the target for all sampling timesteps. To tackle this problem and achieve higher-quality super-resolution, we propose a novel Frequency Domain-guided multiscale Diffusion model (FDDiff), which decomposes the high-frequency information complementing process into finer-grained steps. In particular, a wavelet packet-based frequency complement chain is developed to provide multiscale intermediate targets with increasing bandwidth for reverse diffusion process. Then FDDiff guides reverse diffusion process to progressively complement the missing high-frequency details over timesteps. Moreover, we design a multiscale frequency refinement network to predict the required high-frequency components at multiple scales within one unified network. Comprehensive evaluations on popular benchmarks are conducted, and demonstrate that FDDiff outperforms prior generative methods with higher-fidelity super-resolution results.
Authors: Huiling Zhou, Xianhao Wu, Hongming Chen, Xiang Chen, Xin He
Abstract: Remote sensing image dehazing (RSID) aims to remove nonuniform and physically irregular haze factors for high-quality image restoration. The emergence of CNNs and Transformers has taken extraordinary strides in the RSID arena. However, these methods often struggle to demonstrate the balance of adequate long-range dependency modeling and maintaining computational efficiency. To this end, we propose the first lightweight network on the mamba-based model called RSDhamba in the field of RSID. Greatly inspired by the recent rise of Selective State Space Model (SSM) for its superior performance in modeling linear complexity and remote dependencies, our designed RSDehamba integrates the SSM framework into the U-Net architecture. Specifically, we propose the Vision Dehamba Block (VDB) as the core component of the overall network, which utilizes the linear complexity of SSM to achieve the capability of global context encoding. Simultaneously, the Direction-aware Scan Module (DSM) is designed to dynamically aggregate feature exchanges over different directional domains to effectively enhance the flexibility of sensing the spatially varying distribution of haze. In this way, our RSDhamba fully demonstrates the superiority of spatial distance capture dependencies and channel information exchange for better extraction of haze features. Extensive experimental results on widely used benchmarks validate the surpassing performance of our RSDehamba against existing state-of-the-art methods.
Authors: Zhilin Huang, Quanmin Liang, Yijie Yu, Chujun Qin, Xiawu Zheng, Kai Huang, Zikun Zhou, Wenming Yang
Abstract: Event Stream Super-Resolution (ESR) aims to address the challenge of insufficient spatial resolution in event streams, which holds great significance for the application of event cameras in complex scenarios. Previous works for ESR often process positive and negative events in a mixed paradigm. This paradigm limits their ability to effectively model the unique characteristics of each event and mutually refine each other by considering their correlations. In this paper, we propose a bilateral event mining and complementary network (BMCNet) to fully leverage the potential of each event and capture the shared information to complement each other simultaneously. Specifically, we resort to a two-stream network to accomplish comprehensive mining of each type of events individually. To facilitate the exchange of information between two streams, we propose a bilateral information exchange (BIE) module. This module is layer-wisely embedded between two streams, enabling the effective propagation of hierarchical global information while alleviating the impact of invalid information brought by inherent characteristics of events. The experimental results demonstrate that our approach outperforms the previous state-of-the-art methods in ESR, achieving performance improvements of over 11\% on both real and synthetic datasets. Moreover, our method significantly enhances the performance of event-based downstream tasks such as object recognition and video reconstruction. Our code is available at https://github.com/Lqm26/BMCNet-ESR.
Authors: Weizhen Liu, Ao Li, Ze Wu, Yue Li, Baobin Ge, Guangyu Lan, Shilin Chen, Minghe Li, Yunfei Liu, Xiaohui Yuan, Nanqing Dong
Abstract: Hierarchical leaf vein segmentation is a crucial but under-explored task in agricultural sciences, where analysis of the hierarchical structure of plant leaf venation can contribute to plant breeding. While current segmentation techniques rely on data-driven models, there is no publicly available dataset specifically designed for hierarchical leaf vein segmentation. To address this gap, we introduce the HierArchical Leaf Vein Segmentation (HALVS) dataset, the first public hierarchical leaf vein segmentation dataset. HALVS comprises 5,057 real-scanned high-resolution leaf images collected from three plant species: soybean, sweet cherry, and London planetree. It also includes human-annotated ground truth for three orders of leaf veins, with a total labeling effort of 83.8 person-days. Based on HALVS, we further develop a label-efficient learning paradigm that leverages partial label information, i.e. missing annotations for tertiary veins. Empirical studies are performed on HALVS, revealing new observations, challenges, and research directions on leaf vein segmentation.
Authors: Andrea Matteazzi, Pascal Colling, Michael Arnold, Dietmar Tutsch
Abstract: In recent years considerable research in LiDAR semantic segmentation was conducted, introducing several new state of the art models. However, most research focuses on single-scan point clouds, limiting performance especially in long distance outdoor scenarios, by omitting time-sequential information. Moreover, varying-density and occlusions constitute significant challenges in single-scan approaches. In this paper we propose a LiDAR point cloud preprocessing and postprocessing method. This multi-stage approach, in conjunction with state of the art models in a multi-scan setting, aims to solve those challenges. We demonstrate the benefits of our method through quantitative evaluation with the given models in single-scan settings. In particular, we achieve significant improvements in mIoU performance of over 5 percentage point in medium range and over 10 percentage point in far range. This is essential for 3D semantic scene understanding in long distance as well as for applications where offline processing is permissible.
Authors: Mingxuan Liu, Tyler L. Hayes, Elisa Ricci, Gabriela Csurka, Riccardo Volpi
Abstract: Open-vocabulary object detection (OvOD) has transformed detection into a language-guided task, empowering users to freely define their class vocabularies of interest during inference. However, our initial investigation indicates that existing OvOD detectors exhibit significant variability when dealing with vocabularies across various semantic granularities, posing a concern for real-world deployment. To this end, we introduce Semantic Hierarchy Nexus (SHiNe), a novel classifier that uses semantic knowledge from class hierarchies. It runs offline in three steps: i) it retrieves relevant super-/sub-categories from a hierarchy for each target class; ii) it integrates these categories into hierarchy-aware sentences; iii) it fuses these sentence embeddings to generate the nexus classifier vector. Our evaluation on various detection benchmarks demonstrates that SHiNe enhances robustness across diverse vocabulary granularities, achieving up to +31.9% mAP50 with ground truth hierarchies, while retaining improvements using hierarchies generated by large language models. Moreover, when applied to open-vocabulary classification on ImageNet-1k, SHiNe improves the CLIP zero-shot baseline by +2.8% accuracy. SHiNe is training-free and can be seamlessly integrated with any off-the-shelf OvOD detector, without incurring additional computational overhead during inference. The code is open source.
Authors: Kun Yuan, Vinkle Srivastav, Nassir Navab, Nicolas Padoy
Abstract: Natural language could play an important role in developing generalist surgical models by providing a broad source of supervision from raw texts. This flexible form of supervision can enable the model's transferability across datasets and tasks as natural language can be used to reference learned visual concepts or describe new ones. In this work, we present HecVL, a novel hierarchical video-language pretraining approach for building a generalist surgical model. Specifically, we construct a hierarchical video-text paired dataset by pairing the surgical lecture video with three hierarchical levels of texts: at clip-level, atomic actions using transcribed audio texts; at phase-level, conceptual text summaries; and at video-level, overall abstract text of the surgical procedure. Then, we propose a novel fine-to-coarse contrastive learning framework that learns separate embedding spaces for the three video-text hierarchies using a single model. By disentangling embedding spaces of different hierarchical levels, the learned multi-modal representations encode short-term and long-term surgical concepts in the same model. Thanks to the injected textual semantics, we demonstrate that the HecVL approach can enable zero-shot surgical phase recognition without any human annotation. Furthermore, we show that the same HecVL model for surgical phase recognition can be transferred across different surgical procedures and medical centers.
Authors: Konstantinos Tsigos, Evlampios Apostolidis, Vasileios Mezaris
Abstract: In this paper, we propose an integrated framework for multi-granular explanation of video summarization. This framework integrates methods for producing explanations both at the fragment level (indicating which video fragments influenced the most the decisions of the summarizer) and the more fine-grained visual object level (highlighting which visual objects were the most influential for the summarizer). To build this framework, we extend our previous work on this field, by investigating the use of a model-agnostic, perturbation-based approach for fragment-level explanation of the video summarization results, and introducing a new method that combines the results of video panoptic segmentation with an adaptation of a perturbation-based explanation approach to produce object-level explanations. The performance of the developed framework is evaluated using a state-of-the-art summarization method and two datasets for benchmarking video summarization. The findings of the conducted quantitative and qualitative evaluations demonstrate the ability of our framework to spot the most and least influential fragments and visual objects of the video for the summarizer, and to provide a comprehensive set of visual-based explanations about the output of the summarization process.
Authors: Jo\~ao Bordalo, Vasco Ramos, Rodrigo Val\'erio, Diogo Gl\'oria-Silva, Yonatan Bitton, Michal Yarom, Idan Szpektor, Joao Magalhaes
Abstract: Multistep instructions, such as recipes and how-to guides, greatly benefit from visual aids, such as a series of images that accompany the instruction steps. While Large Language Models (LLMs) have become adept at generating coherent textual steps, Large Vision/Language Models (LVLMs) are less capable of generating accompanying image sequences. The most challenging aspect is that each generated image needs to adhere to the relevant textual step instruction, as well as be visually consistent with earlier images in the sequence. To address this problem, we propose an approach for generating consistent image sequences, which integrates a Latent Diffusion Model (LDM) with an LLM to transform the sequence into a caption to maintain the semantic coherence of the sequence. In addition, to maintain the visual coherence of the image sequence, we introduce a copy mechanism to initialise reverse diffusion processes with a latent vector iteration from a previously generated image from a relevant step. Both strategies will condition the reverse diffusion process on the sequence of instruction steps and tie the contents of the current image to previous instruction steps and corresponding images. Experiments show that the proposed approach is preferred by humans in 46.6% of the cases against 26.6% for the second best method. In addition, automatic metrics showed that the proposed method maintains semantic coherence and visual consistency across steps in both domains.
Authors: Xinyu Zhang, Yijin Xiong, Qianxin Qu, Renjie Wang, Xin Gao, Jing Liu, Shichun Guo, Jun Li
Abstract: In the typical urban intersection scenario, both vehicles and infrastructures are equipped with visual and LiDAR sensors. By successfully integrating the data from vehicle-side and road monitoring devices, a more comprehensive and accurate environmental perception and information acquisition can be achieved. The Calibration of sensors, as an essential component of autonomous driving technology, has consistently drawn significant attention. Particularly in scenarios involving multiple sensors collaboratively perceiving and addressing localization challenges, the requirement for inter-sensor calibration becomes crucial. Recent years have witnessed the emergence of the concept of multi-end cooperation, where infrastructure captures and transmits surrounding environment information to vehicles, bolstering their perception capabilities while mitigating costs. However, this also poses technical complexities, underscoring the pressing need for diverse end calibration. Camera and LiDAR, the bedrock sensors in autonomous driving, exhibit expansive applicability. This paper comprehensively examines and analyzes the calibration of multi-end camera-LiDAR setups from vehicle, roadside, and vehicle-road cooperation perspectives, outlining their relevant applications and profound significance. Concluding with a summary, we present our future-oriented ideas and hypotheses.
Authors: Yifan Xu, Xiaoshan Yang, Yaguang Song, Changsheng Xu
Abstract: In this work, we introduce Libra, a prototype model with a decoupled vision system on a large language model (LLM). The decoupled vision system decouples inner-modal modeling and cross-modal interaction, yielding unique visual information modeling and effective cross-modal comprehension. Libra is trained through discrete auto-regressive modeling on both vision and language inputs. Specifically, we incorporate a routed visual expert with a cross-modal bridge module into a pretrained LLM to route the vision and language flows during attention computing to enable different attention patterns in inner-modal modeling and cross-modal interaction scenarios. Experimental results demonstrate that the dedicated design of Libra achieves a strong MLLM baseline that rivals existing works in the image-to-text scenario with merely 50 million training data, providing a new perspective for future multimodal foundation models. Code is available at https://github.com/YifanXu74/Libra.
Authors: Zhaoxu Li, Wei An, Gaowei Guo, Longguang Wang, Yingqian Wang, Zaiping Lin
Abstract: Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect point targets, some of which occupy a smaller than one-pixel area. However, existing HTD methods are developed based on per-pixel binary classification, which limits the feature representation capability for point targets. In this paper, we rethink the hyperspectral point target detection from the object detection perspective, and focus more on the object-level prediction capability rather than the pixel classification capability. Inspired by the token-based processing flow of Detection Transformer (DETR), we propose the first specialized network for hyperspectral multi-class point object detection, SpecDETR. Without the backbone part of the current object detection framework, SpecDETR treats the spectral features of each pixel in hyperspectral images as a token and utilizes a multi-layer Transformer encoder with local and global coordination attention modules to extract deep spatial-spectral joint features. SpecDETR regards point object detection as a one-to-many set prediction problem, thereby achieving a concise and efficient DETR decoder that surpasses the current state-of-the-art DETR decoder in terms of parameters and accuracy in point object detection. We develop a simulated hyperSpectral Point Object Detection benchmark termed SPOD, and for the first time, evaluate and compare the performance of current object detection networks and HTD methods on hyperspectral multi-class point object detection. SpecDETR demonstrates superior performance as compared to current object detection networks and HTD methods on the SPOD dataset. Additionally, we validate on a public HTD dataset that by using data simulation instead of manual annotation, SpecDETR can detect real-world single-spectral point objects directly.
Authors: Jiancheng Pan, Muyuan Ma, Qing Ma, Cong Bai, Shengyong Chen
Abstract: Remote sensing image-text retrieval constitutes a foundational aspect of remote sensing interpretation tasks, facilitating the alignment of vision and language representations. This paper introduces a prior instruction representation (PIR) learning paradigm that draws on prior knowledge to instruct adaptive learning of vision and text representations. Based on PIR, a domain-adapted remote sensing image-text retrieval framework PIR-ITR is designed to address semantic noise issues in vision-language understanding tasks. However, with massive additional data for pre-training the vision-language foundation model, remote sensing image-text retrieval is further developed into an open-domain retrieval task. Continuing with the above, we propose PIR-CLIP, a domain-specific CLIP-based framework for remote sensing image-text retrieval, to address semantic noise in remote sensing vision-language representations and further improve open-domain retrieval performance. In vision representation, Vision Instruction Representation (VIR) based on Spatial-PAE utilizes the prior-guided knowledge of the remote sensing scene recognition by building a belief matrix to select key features for reducing the impact of semantic noise. In text representation, Language Cycle Attention (LCA) based on Temporal-PAE uses the previous time step to cyclically activate the current time step to enhance text representation capability. A cluster-wise Affiliation Loss (AL) is proposed to constrain the inter-classes and to reduce the semantic confusion zones in the common subspace. Comprehensive experiments demonstrate that PIR could enhance vision and text representations and outperform the state-of-the-art methods of closed-domain and open-domain retrieval on two benchmark datasets, RSICD and RSITMD.
Authors: Bike Chen, Chen Gong, Juha R\"oning
Abstract: Point cloud segmentation (PCS) plays an essential role in robot perception and navigation tasks. To efficiently understand large-scale outdoor point clouds, their range image representation is commonly adopted. This image-like representation is compact and structured, making range image-based PCS models practical. However, undesirable missing values in the range images damage the shapes and patterns of objects. This problem creates difficulty for the models in learning coherent and complete geometric information from the objects. Consequently, the PCS models only achieve inferior performance. Delving deeply into this issue, we find that the use of unreasonable projection approaches and deskewing scans mainly leads to unwanted missing values in the range images. Besides, almost all previous works fail to consider filling in the unexpected missing values in the PCS task. To alleviate this problem, we first propose a new projection method, namely scan unfolding++ (SU++), to avoid massive missing values in the generated range images. Then, we introduce a simple yet effective approach, namely range-dependent $K$-nearest neighbor interpolation ($K$NNI), to further fill in missing values. Finally, we introduce the Filling Missing Values Network (FMVNet) and Fast FMVNet. Extensive experimental results on SemanticKITTI, SemanticPOSS, and nuScenes datasets demonstrate that by employing the proposed SU++ and $K$NNI, existing range image-based PCS models consistently achieve better performance than the baseline models. Besides, both FMVNet and Fast FMVNet achieve state-of-the-art performance in terms of the speed-accuracy trade-off. The proposed methods can be applied to other range image-based tasks and practical applications.
Authors: Chengxiang Fan, Muzhi Zhu, Hao Chen, Yang Liu, Weijia Wu, Huaqi Zhang, Chunhua Shen
Abstract: Instance segmentation is data-hungry, and as model capacity increases, data scale becomes crucial for improving the accuracy. Most instance segmentation datasets today require costly manual annotation, limiting their data scale. Models trained on such data are prone to overfitting on the training set, especially for those rare categories. While recent works have delved into exploiting generative models to create synthetic datasets for data augmentation, these approaches do not efficiently harness the full potential of generative models. To address these issues, we introduce a more efficient strategy to construct generative datasets for data augmentation, termed DiverGen. Firstly, we provide an explanation of the role of generative data from the perspective of distribution discrepancy. We investigate the impact of different data on the distribution learned by the model. We argue that generative data can expand the data distribution that the model can learn, thus mitigating overfitting. Additionally, we find that the diversity of generative data is crucial for improving model performance and enhance it through various strategies, including category diversity, prompt diversity, and generative model diversity. With these strategies, we can scale the data to millions while maintaining the trend of model performance improvement. On the LVIS dataset, DiverGen significantly outperforms the strong model X-Paste, achieving +1.1 box AP and +1.1 mask AP across all categories, and +1.9 box AP and +2.5 mask AP for rare categories.
Authors: Anderson de Andrade, Ivan Baji\'c
Abstract: We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount of information available in it. We interpret this issue using the predictive $\mathcal{V}$-information framework. In learnable scalable coding, previous work increased the utilization of side-information for input reconstruction by also rewarding input reconstruction when learning this shared representation. We evaluate the impact of this idea in the context of input reconstruction more rigorously and extended it to other computer vision tasks. We perform experiments using representations trained for object detection on COCO 2017 and depth estimation on the Cityscapes dataset, and use them to assist in image reconstruction and semantic segmentation tasks. The results show considerable improvements in the rate-distortion performance of the assisted tasks. Moreover, using the proposed representations, the performance of the base tasks are also improved. Results suggest that the proposed method induces simpler representations that are more compatible with downstream processes.
Authors: Xianzheng Ma, Yash Bhalgat, Brandon Smart, Shuai Chen, Xinghui Li, Jian Ding, Jindong Gu, Dave Zhenyu Chen, Songyou Peng, Jia-Wang Bian, Philip H Torr, Marc Pollefeys, Matthias Nie{\ss}ner, Ian D Reid, Angel X. Chang, Iro Laina, Victor Adrian Prisacariu
Abstract: As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.
Authors: Anshul Pundhir, Balasubramanian Raman, Pravendra Singh
Abstract: Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated exceptional performance in diagnosing skin diseases, often outperforming dermatologists. However, they have also unveiled biases linked to specific demographic traits, notably concerning diverse skin tones or gender, prompting concerns regarding fairness and limiting their widespread deployment. Researchers are actively working to ensure fairness in AI-based solutions, but existing methods incur an accuracy loss when striving for fairness. To solve this issue, we propose a `two-biased teachers' (i.e., biased on different sensitive attributes) based approach to transfer fair knowledge into the student network. Our approach mitigates biases present in the student network without harming its predictive accuracy. In fact, in most cases, our approach improves the accuracy of the baseline model. To achieve this goal, we developed a weighted loss function comprising biasing and debiasing loss terms. We surpassed available state-of-the-art approaches to attain fairness and also improved the accuracy at the same time. The proposed approach has been evaluated and validated on two dermatology datasets using standard accuracy and fairness evaluation measures. We will make source code publicly available to foster reproducibility and future research.
Authors: Charles Raude, K R Prajwal, Liliane Momeni, Hannah Bull, Samuel Albanie, Andrew Zisserman, G\"ul Varol
Abstract: In this work, our goals are two fold: large-vocabulary continuous sign language recognition (CSLR), and sign language retrieval. To this end, we introduce a multi-task Transformer model, CSLR2, that is able to ingest a signing sequence and output in a joint embedding space between signed language and spoken language text. To enable CSLR evaluation in the large-vocabulary setting, we introduce new dataset annotations that have been manually collected. These provide continuous sign-level annotations for six hours of test videos, and will be made publicly available. We demonstrate that by a careful choice of loss functions, training the model for both the CSLR and retrieval tasks is mutually beneficial in terms of performance -- retrieval improves CSLR performance by providing context, while CSLR improves retrieval with more fine-grained supervision. We further show the benefits of leveraging weak and noisy supervision from large-vocabulary datasets such as BOBSL, namely sign-level pseudo-labels, and English subtitles. Our model significantly outperforms the previous state of the art on both tasks.
Authors: Youngjoon Jang, Ji-Hoon Kim, Junseok Ahn, Doyeop Kwak, Hong-Sun Yang, Yoon-Cheol Ju, Il-Hwan Kim, Byeong-Yeol Kim, Joon Son Chung
Abstract: The goal of this work is to simultaneously generate natural talking faces and speech outputs from text. We achieve this by integrating Talking Face Generation (TFG) and Text-to-Speech (TTS) systems into a unified framework. We address the main challenges of each task: (1) generating a range of head poses representative of real-world scenarios, and (2) ensuring voice consistency despite variations in facial motion for the same identity. To tackle these issues, we introduce a motion sampler based on conditional flow matching, which is capable of high-quality motion code generation in an efficient way. Moreover, we introduce a novel conditioning method for the TTS system, which utilises motion-removed features from the TFG model to yield uniform speech outputs. Our extensive experiments demonstrate that our method effectively creates natural-looking talking faces and speech that accurately match the input text. To our knowledge, this is the first effort to build a multimodal synthesis system that can generalise to unseen identities.
Authors: Adrian Bulat, Yassine Ouali, Georgios Tzimiropoulos
Abstract: Despite noise and caption quality having been acknowledged as important factors impacting vision-language contrastive pre-training, in this paper, we show that the full potential of improving the training process by addressing such issues is yet to be realized. Specifically, we firstly study and analyze two issues affecting training: incorrect assignment of negative pairs, and low caption quality and diversity. Then, we devise effective solutions for addressing both problems, which essentially require training with multiple true positive pairs. Finally, we propose training with sigmoid loss to address such a requirement. We show very large gains over the current state-of-the-art for both image recognition ($\sim +6\%$ on average over 11 datasets) and image retrieval ($\sim +19\%$ on Flickr30k and $\sim +15\%$ on MSCOCO).
Authors: Tianhe Ren, Qing Jiang, Shilong Liu, Zhaoyang Zeng, Wenlong Liu, Han Gao, Hongjie Huang, Zhengyu Ma, Xiaoke Jiang, Yihao Chen, Yuda Xiong, Hao Zhang, Feng Li, Peijun Tang, Kent Yu, Lei Zhang
Abstract: This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detection. The suite encompasses two models: Grounding DINO 1.5 Pro, a high-performance model designed for stronger generalization capability across a wide range of scenarios, and Grounding DINO 1.5 Edge, an efficient model optimized for faster speed demanded in many applications requiring edge deployment. The Grounding DINO 1.5 Pro model advances its predecessor by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding. The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection capabilities by being trained on the same comprehensive dataset. Empirical results demonstrate the effectiveness of Grounding DINO 1.5, with the Grounding DINO 1.5 Pro model attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for open-set object detection. Furthermore, the Grounding DINO 1.5 Edge model, when optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark, making it more suitable for edge computing scenarios. Model examples and demos with API will be released at https://github.com/IDEA-Research/Grounding-DINO-1.5-API
URLs: https://github.com/IDEA-Research/Grounding-DINO-1.5-API
Authors: Jingkang Yang, Jun Cen, Wenxuan Peng, Shuai Liu, Fangzhou Hong, Xiangtai Li, Kaiyang Zhou, Qifeng Chen, Ziwei Liu
Abstract: We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such a 4D environment, we introduce 4D Panoptic Scene Graph (PSG-4D), a new representation that bridges the raw visual data perceived in a dynamic 4D world and high-level visual understanding. Specifically, PSG-4D abstracts rich 4D sensory data into nodes, which represent entities with precise location and status information, and edges, which capture the temporal relations. To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs. To solve PSG-4D, we propose PSG4DFormer, a Transformer-based model that can predict panoptic segmentation masks, track masks along the time axis, and generate the corresponding scene graphs via a relation component. Extensive experiments on the new dataset show that our method can serve as a strong baseline for future research on PSG-4D. In the end, we provide a real-world application example to demonstrate how we can achieve dynamic scene understanding by integrating a large language model into our PSG-4D system.
Authors: Ruiqi Gao, Aleksander Holynski, Philipp Henzler, Arthur Brussee, Ricardo Martin-Brualla, Pratul Srinivasan, Jonathan T. Barron, Ben Poole
Abstract: Advances in 3D reconstruction have enabled high-quality 3D capture, but require a user to collect hundreds to thousands of images to create a 3D scene. We present CAT3D, a method for creating anything in 3D by simulating this real-world capture process with a multi-view diffusion model. Given any number of input images and a set of target novel viewpoints, our model generates highly consistent novel views of a scene. These generated views can be used as input to robust 3D reconstruction techniques to produce 3D representations that can be rendered from any viewpoint in real-time. CAT3D can create entire 3D scenes in as little as one minute, and outperforms existing methods for single image and few-view 3D scene creation. See our project page for results and interactive demos at https://cat3d.github.io .
URLs: https://cat3d.github.io
Authors: Zheng Gu, Shiyuan Yang, Jing Liao, Jing Huo, Yang Gao
Abstract: Visual In-Context Learning (ICL) has emerged as a promising research area due to its capability to accomplish various tasks with limited example pairs through analogical reasoning. However, training-based visual ICL has limitations in its ability to generalize to unseen tasks and requires the collection of a diverse task dataset. On the other hand, existing methods in the inference-based visual ICL category solely rely on textual prompts, which fail to capture fine-grained contextual information from given examples and can be time-consuming when converting from images to text prompts. To address these challenges, we propose Analogist, a novel inference-based visual ICL approach that exploits both visual and textual prompting techniques using a text-to-image diffusion model pretrained for image inpainting. For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples. For textual prompting, we leverage GPT-4V's visual reasoning capability to efficiently generate text prompts and introduce a cross-attention masking (CAM) operation to enhance the accuracy of semantic-level analogy guided by text prompts. Our method is out-of-the-box and does not require fine-tuning or optimization. It is also generic and flexible, enabling a wide range of visual tasks to be performed in an in-context manner. Extensive experiments demonstrate the superiority of our method over existing approaches, both qualitatively and quantitatively.
Authors: Peiying Zhang, Nanxuan Zhao, Jing Liao
Abstract: Vector graphics are widely used in digital art and highly favored by designers due to their scalability and layer-wise properties. However, the process of creating and editing vector graphics requires creativity and design expertise, making it a time-consuming task. Recent advancements in text-to-vector (T2V) generation have aimed to make this process more accessible. However, existing T2V methods directly optimize control points of vector graphics paths, often resulting in intersecting or jagged paths due to the lack of geometry constraints. To overcome these limitations, we propose a novel neural path representation by designing a dual-branch Variational Autoencoder (VAE) that learns the path latent space from both sequence and image modalities. By optimizing the combination of neural paths, we can incorporate geometric constraints while preserving expressivity in generated SVGs. Furthermore, we introduce a two-stage path optimization method to improve the visual and topological quality of generated SVGs. In the first stage, a pre-trained text-to-image diffusion model guides the initial generation of complex vector graphics through the Variational Score Distillation (VSD) process. In the second stage, we refine the graphics using a layer-wise image vectorization strategy to achieve clearer elements and structure. We demonstrate the effectiveness of our method through extensive experiments and showcase various applications. The project page is https://intchous.github.io/T2V-NPR.
Authors: Ethan Weber, Riley Peterlinz, Rohan Mathur, Frederik Warburg, Alexei A. Efros, Angjoo Kanazawa
Abstract: In this work, we recover the underlying 3D structure of non-geometrically consistent scenes. We focus our analysis on hand-drawn images from cartoons and anime. Many cartoons are created by artists without a 3D rendering engine, which means that any new image of a scene is hand-drawn. The hand-drawn images are usually faithful representations of the world, but only in a qualitative sense, since it is difficult for humans to draw multiple perspectives of an object or scene 3D consistently. Nevertheless, people can easily perceive 3D scenes from inconsistent inputs! In this work, we correct for 2D drawing inconsistencies to recover a plausible 3D structure such that the newly warped drawings are consistent with each other. Our pipeline consists of a user-friendly annotation tool, camera pose estimation, and image deformation to recover a dense structure. Our method warps images to obey a perspective camera model, enabling our aligned results to be plugged into novel-view synthesis reconstruction methods to experience cartoons from viewpoints never drawn before. Our project page is https://toon3d.studio/.
URLs: https://toon3d.studio/.
Authors: Jiayi Wang, Yi-An Mao, Xiaoyu Ma, Sicen Guo, Yuting Shao, Xiao Lv, Wenting Han, Mark Christopher, Linda M. Zangwill, Yanlong Bi, Rui Fan
Abstract: Optic nerve head (ONH) detection has been an important topic in the medical community for many years. Previous approaches in this domain primarily center on the analysis, localization, and detection of fundus images. However, the non-negligible discrepancy between fundus image datasets, all exclusively generated using a single type of fundus camera, challenges the generalizability of ONH detection approaches. Furthermore, despite the numerous recent semantic segmentation methods employing convolutional neural networks (CNNs) and Transformers, there is currently a lack of benchmarks for these state-of-the-art (SoTA) networks trained specifically for ONH detection. Therefore, in this article, we first introduce ODFormer, a network based on the Swin Transformer architecture. ODFormer is designed to enhance the extraction of correlation information between features, leading to improved generalizability. In our experimental evaluations, we compare our top-performing implementation with 13 SoTA CNNs and Transformers. The results indicate that our proposed ODFormer outperforms all other approaches in ONH detection. Subsequently, we release TongjiU-DCOD dataset, the first multi-resolution mixed fundus image dataset with corresponding ONH ground-truth annotations. This dataset comprises 400 fundus images captured using two different types of fundus cameras with varying resolutions. This diversity enhances the availability of data regularity information, contributing to the improved generalizability of the model. Moreover, we establish a benchmark to thoroughly evaluate the performance for ONH detection of SoTA networks designed for semantic segmentation with extensive experiments.
Authors: Vittorio Rampa, Federica Fieramosca, Stefano Savazzi, Michele D'Amico
Abstract: Device-Free Localization (DFL) employs passive radio techniques capable to detect and locate people without imposing them to wear any electronic device. By exploiting the Integrated Sensing and Communication paradigm, DFL networks employ Radio Frequency (RF) nodes to measure the excess attenuation introduced by the subjects (i.e., human bodies) moving inside the monitored area, and to estimate their positions and movements. Physical, statistical, and ElectroMagnetic (EM) models have been proposed in the literature to estimate the body positions according to the RF signals collected by the nodes. These body models usually employ a single-antenna processing for localization purposes. However, the availability of low-cost multi-antenna devices such as those used for WLAN (Wireless Local Area Network) applications and the timely development of array-based body models, allow us to employ array-based processing techniques in DFL networks. By exploiting a suitable array-capable EM body model, this paper proposes an array-based framework to improve people sensing and localization. In particular, some simulations are proposed and discussed to compare the model results in both single- and multi-antenna scenarios. The proposed framework paves the way for a wider use of multi-antenna devices (e.g., those employed in current IEEE 802.11ac/ax/be and forthcoming IEEE 802.11be networks) and novel beamforming algorithms for DFL scenarios.
Authors: Kang Liu, Zhuoqi Ma, Mengmeng Liu, Zhicheng Jiao, Xiaolu Kang, Qiguang Miao, Kun Xie
Abstract: The automation of writing imaging reports is a valuable tool for alleviating the workload of radiologists. Crucial steps in this process involve the cross-modal alignment between medical images and reports, as well as the retrieval of similar historical cases. However, the presence of presentation-style vocabulary (e.g., sentence structure and grammar) in reports poses challenges for cross-modal alignment. Additionally, existing methods for similar historical cases retrieval face suboptimal performance owing to the modal gap issue. In response, this paper introduces a novel method, named Factual Serialization Enhancement (FSE), for chest X-ray report generation. FSE begins with the structural entities approach to eliminate presentation-style vocabulary in reports, providing specific input for our model. Then, uni-modal features are learned through cross-modal alignment between images and factual serialization in reports. Subsequently, we present a novel approach to retrieve similar historical cases from the training set, leveraging aligned image features. These features implicitly preserve semantic similarity with their corresponding reference reports, enabling us to calculate similarity solely among aligned features. This effectively eliminates the modal gap issue for knowledge retrieval without the requirement for disease labels. Finally, the cross-modal fusion network is employed to query valuable information from these cases, enriching image features and aiding the text decoder in generating high-quality reports. Experiments on MIMIC-CXR and IU X-ray datasets from both specific and general scenarios demonstrate the superiority of FSE over state-of-the-art approaches in both natural language generation and clinical efficacy metrics.
Authors: Pranab Sahoo, Prabhash Meharia, Akash Ghosh, Sriparna Saha, Vinija Jain, Aman Chadha
Abstract: The rapid advancement of foundation models (FMs) across language, image, audio, and video domains has shown remarkable capabilities in diverse tasks. However, the proliferation of FMs brings forth a critical challenge: the potential to generate hallucinated outputs, particularly in high-stakes applications. The tendency of foundation models to produce hallucinated content arguably represents the biggest hindrance to their widespread adoption in real-world scenarios, especially in domains where reliability and accuracy are paramount. This survey paper presents a comprehensive overview of recent developments that aim to identify and mitigate the problem of hallucination in FMs, spanning text, image, video, and audio modalities. By synthesizing recent advancements in detecting and mitigating hallucination across various modalities, the paper aims to provide valuable insights for researchers, developers, and practitioners. Essentially, it establishes a clear framework encompassing definition, taxonomy, and detection strategies for addressing hallucination in multimodal foundation models, laying the foundation for future research in this pivotal area.
Authors: Sameer Khanna, Daniel Michael, Marinka Zitnik, Pranav Rajpurkar
Abstract: Medical image interpretation using deep learning has shown promise but often requires extensive expert-annotated datasets. To reduce this annotation burden, we develop an Image-Graph Contrastive Learning framework that pairs chest X-rays with structured report knowledge graphs automatically extracted from radiology notes. Our approach uniquely encodes the disconnected graph components via a relational graph convolution network and transformer attention. In experiments on the CheXpert dataset, this novel graph encoding strategy enabled the framework to outperform existing methods that use image-text contrastive learning in 1% linear evaluation and few-shot settings, while achieving comparable performance to radiologists. By exploiting unlabeled paired images and text, our framework demonstrates the potential of structured clinical insights to enhance contrastive learning for medical images. This work points toward reducing demands on medical experts for annotations, improving diagnostic precision, and advancing patient care through robust medical image understanding.
Authors: Vishwesh Sangarya, Richard Bradford, Jung-Eun Kim
Abstract: In this paper, we propose a predictive quantifier to estimate the retraining cost of a trained model in distribution shifts. The proposed Aggregated Representation Measure (ARM) quantifies the change in the model's representation from the old to new data distribution. It provides, before actually retraining the model, a single concise index of resources - epochs, energy, and carbon emissions - required for the retraining. This enables reuse of a model with a much lower cost than training a new model from scratch. The experimental results indicate that ARM reasonably predicts retraining costs for varying noise intensities and enables comparisons among multiple model architectures to determine the most cost-effective and sustainable option.
Authors: Shaohua Pi, Razieh Ganjee, Lingyun Wang, Riley K. Arbuckle, Chengcheng Zhao, Jose A Sahel, Bingjie Wang, Yuanyuan Chen
Abstract: This study introduces a groundbreaking optical coherence tomography (OCT) imaging system dedicated for high-throughput screening applications using ex vivo tissue culture. Leveraging OCT's non-invasive, high-resolution capabilities, the system is equipped with a custom-designed motorized platform and tissue detection ability for automated, successive imaging across samples. Transformer-based deep learning segmentation algorithms further ensure robust, consistent, and efficient readouts meeting the standards for screening assays. Validated using retinal explant cultures from a mouse model of retinal degeneration, the system provides robust, rapid, reliable, unbiased, and comprehensive readouts of tissue response to treatments. This fully automated OCT-based system marks a significant advancement in tissue screening, promising to transform drug discovery, as well as other relevant research fields.
Authors: Zekun Wu, Anna Maria Feit
Abstract: This study examines the role of visual highlights in guiding user attention in drone monitoring tasks, employing a simulated interface for observation. The experiment results show that such highlights can significantly expedite the visual attention on the corresponding area. Based on this observation, we leverage both the temporal and spatial information in the highlight to develop a new saliency model: the highlight-informed saliency model (HISM), to infer the visual attention change in the highlight condition. Our findings show the effectiveness of visual highlights in enhancing user attention and demonstrate the potential of incorporating these cues into saliency prediction models.
Authors: Bo Wu, Shoubin Yu, Zhenfang Chen, Joshua B Tenenbaum, Chuang Gan
Abstract: Reasoning in the real world is not divorced from situations. How to capture the present knowledge from surrounding situations and perform reasoning accordingly is crucial and challenging for machine intelligence. This paper introduces a new benchmark that evaluates the situated reasoning ability via situation abstraction and logic-grounded question answering for real-world videos, called Situated Reasoning in Real-World Videos (STAR Benchmark). This benchmark is built upon the real-world videos associated with human actions or interactions, which are naturally dynamic, compositional, and logical. The dataset includes four types of questions, including interaction, sequence, prediction, and feasibility. We represent the situations in real-world videos by hyper-graphs connecting extracted atomic entities and relations (e.g., actions, persons, objects, and relationships). Besides visual perception, situated reasoning also requires structured situation comprehension and logical reasoning. Questions and answers are procedurally generated. The answering logic of each question is represented by a functional program based on a situation hyper-graph. We compare various existing video reasoning models and find that they all struggle on this challenging situated reasoning task. We further propose a diagnostic neuro-symbolic model that can disentangle visual perception, situation abstraction, language understanding, and functional reasoning to understand the challenges of this benchmark.
Authors: Long Chen, Mobarakol Islam, Matt Clarkson, Thomas Dowrick
Abstract: The advances in deep generative models have greatly accelerate the process of video procession such as video enhancement and synthesis. Learning spatio-temporal video models requires to capture the temporal dynamics of a scene, in addition to the visual appearance of individual frames. Illumination consistency, which reflects the variations of illumination in the dynamic video sequences, play a vital role in video processing. Unfortunately, to date, no well-accepted quantitative metric has been proposed for video illumination consistency evaluation. In this paper, we propose a illumination histogram consistency (IHC) metric to quantitatively and automatically evaluate the illumination consistency of the video sequences. IHC measures the illumination variation of any video sequence based on the illumination histogram discrepancies across all the frames in the video sequence. Specifically, given a video sequence, we first estimate the illumination map of each individual frame using the Retinex model; Then, using the illumination maps, the mean illumination histogram of the video sequence is computed by the mean operation across all the frames; Next, we compute the illumination histogram discrepancy between each individual frame and the mean illumination histogram and sum up all the illumination histogram discrepancies to represent the illumination variations of the video sequence. Finally, we obtain the IHC score from the illumination histogram discrepancies via normalization and subtraction operations. Experiments are conducted to illustrate the performance of the proposed IHC metric and its capability to measure the illumination variations in video sequences. The source code is available on \url{https://github.com/LongChenCV/IHC-Metric}.
Authors: Dominic LaBella, Ujjwal Baid, Omaditya Khanna, Shan McBurney-Lin, Ryan McLean, Pierre Nedelec, Arif Rashid, Nourel Hoda Tahon, Talissa Altes, Radhika Bhalerao, Yaseen Dhemesh, Devon Godfrey, Fathi Hilal, Scott Floyd, Anastasia Janas, Anahita Fathi Kazerooni, John Kirkpatrick, Collin Kent, Florian Kofler, Kevin Leu, Nazanin Maleki, Bjoern Menze, Maxence Pajot, Zachary J. Reitman, Jeffrey D. Rudie, Rachit Saluja, Yury Velichko, Chunhao Wang, Pranav Warman, Maruf Adewole, Jake Albrecht, Udunna Anazodo, Syed Muhammad Anwar, Timothy Bergquist, Sully Francis Chen, Verena Chung, Gian-Marco Conte, Farouk Dako, James Eddy, Ivan Ezhov, Nastaran Khalili, Juan Eugenio Iglesias, Zhifan Jiang, Elaine Johanson, Koen Van Leemput, Hongwei Bran Li, Marius George Linguraru, Xinyang Liu, Aria Mahtabfar, Zeke Meier, Ahmed W. Moawad, John Mongan, Marie Piraud, Russell Takeshi Shinohara, Walter F. Wiggins, Aly H. Abayazeed, Rachel Akinola, Andr\'as Jakab, Michel Bilello, Maria Correia de Verdier, Priscila Crivellaro, Christos Davatzikos, Keyvan Farahani, John Freymann, Christopher Hess, Raymond Huang, Philipp Lohmann, Mana Moassefi, Matthew W. Pease, Phillipp Vollmuth, Nico Sollmann, David Diffley, Khanak K. Nandolia, Daniel I. Warren, Ali Hussain, Pascal Fehringer, Yulia Bronstein, Lisa Deptula, Evan G. Stein, Mahsa Taherzadeh, Eduardo Portela de Oliveira, Aoife Haughey, Marinos Kontzialis, Luca Saba, Benjamin Turner, Melanie M. T. Br\"u{\ss}eler, Shehbaz Ansari, Athanasios Gkampenis, David Maximilian Weiss, Aya Mansour, Islam H. Shawali, Nikolay Yordanov, Joel M. Stein, Roula Hourani, Mohammed Yahya Moshebah, Ahmed Magdy Abouelatta, Tanvir Rizvi, Klara Willms, Dann C. Martin, Abdullah Okar, Gennaro D'Anna, Ahmed Taha, Yasaman Sharifi, Shahriar Faghani, Dominic Kite, Marco Pinho, Muhammad Ammar Haider, Alejandro Aristizabal, Alexandros Karargyris, Hasan Kassem, Sarthak Pati, Micah Sheller, Michelle Alonso-Basanta, Javier Villanueva-Meyer, Andreas M. Rauschecker, Ayman Nada, Mariam Aboian, Adam E. Flanders, Benedikt Wiestler, Spyridon Bakas, Evan Calabrese
Abstract: We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, T2/FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing T2/FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.
Authors: Yixing Jiang, Jeremy Irvin, Ji Hun Wang, Muhammad Ahmed Chaudhry, Jonathan H. Chen, Andrew Y. Ng
Abstract: Large language models are well-known to be effective at few-shot in-context learning (ICL). Recent advancements in multimodal foundation models have enabled unprecedentedly long context windows, presenting an opportunity to explore their capability to perform ICL with many more demonstrating examples. In this work, we evaluate the performance of multimodal foundation models scaling from few-shot to many-shot ICL. We benchmark GPT-4o and Gemini 1.5 Pro across 10 datasets spanning multiple domains (natural imagery, medical imagery, remote sensing, and molecular imagery) and tasks (multi-class, multi-label, and fine-grained classification). We observe that many-shot ICL, including up to almost 2,000 multimodal demonstrating examples, leads to substantial improvements compared to few-shot (<100 examples) ICL across all of the datasets. Further, Gemini 1.5 Pro performance continues to improve log-linearly up to the maximum number of tested examples on many datasets. Given the high inference costs associated with the long prompts required for many-shot ICL, we also explore the impact of batching multiple queries in a single API call. We show that batching up to 50 queries can lead to performance improvements under zero-shot and many-shot ICL, with substantial gains in the zero-shot setting on multiple datasets, while drastically reducing per-query cost and latency. Finally, we measure ICL data efficiency of the models, or the rate at which the models learn from more demonstrating examples. We find that while GPT-4o and Gemini 1.5 Pro achieve similar zero-shot performance across the datasets, Gemini 1.5 Pro exhibits higher ICL data efficiency than GPT-4o on most datasets. Our results suggest that many-shot ICL could enable users to efficiently adapt multimodal foundation models to new applications and domains. Our codebase is publicly available at https://github.com/stanfordmlgroup/ManyICL .
Authors: Zeyi Zhang, Tenglong Ao, Yuyao Zhang, Qingzhe Gao, Chuan Lin, Baoquan Chen, Libin Liu
Abstract: In this work, we present Semantic Gesticulator, a novel framework designed to synthesize realistic gestures accompanying speech with strong semantic correspondence. Semantically meaningful gestures are crucial for effective non-verbal communication, but such gestures often fall within the long tail of the distribution of natural human motion. The sparsity of these movements makes it challenging for deep learning-based systems, trained on moderately sized datasets, to capture the relationship between the movements and the corresponding speech semantics. To address this challenge, we develop a generative retrieval framework based on a large language model. This framework efficiently retrieves suitable semantic gesture candidates from a motion library in response to the input speech. To construct this motion library, we summarize a comprehensive list of commonly used semantic gestures based on findings in linguistics, and we collect a high-quality motion dataset encompassing both body and hand movements. We also design a novel GPT-based model with strong generalization capabilities to audio, capable of generating high-quality gestures that match the rhythm of speech. Furthermore, we propose a semantic alignment mechanism to efficiently align the retrieved semantic gestures with the GPT's output, ensuring the naturalness of the final animation. Our system demonstrates robustness in generating gestures that are rhythmically coherent and semantically explicit, as evidenced by a comprehensive collection of examples. User studies confirm the quality and human-likeness of our results, and show that our system outperforms state-of-the-art systems in terms of semantic appropriateness by a clear margin.
Authors: Zenglin Shi, Pei Liu, Tong Su, Yunpeng Wu, Kuien Liu, Yu Song, Meng Wang
Abstract: Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their ability to distill the cumulative knowledge of all the previous tasks. To remedy this, we propose Dense Knowledge Distillation (DKD). DKD uses a task pool to track the model's capabilities. It partitions the output logits of the model into dense groups, each corresponding to a task in the task pool. It then distills all tasks' knowledge using all groups. However, using all the groups can be computationally expensive, we also suggest random group selection in each optimization step. Moreover, we propose an adaptive weighting scheme, which balances the learning of new classes and the retention of old classes, based on the count and similarity of the classes. Our DKD outperforms recent state-of-the-art baselines across diverse benchmarks and scenarios. Empirical analysis underscores DKD's ability to enhance model stability, promote flatter minima for improved generalization, and remains robust across various memory budgets and task orders. Moreover, it seamlessly integrates with other CL methods to boost performance and proves versatile in offline scenarios like model compression.
Authors: Yi Cui, Yao Li, Jayson R. Miedema, Sharon N. Edmiston, Sherif Farag, J. S. Marron, Nancy E. Thomas
Abstract: Automated region of interest detection in histopathological image analysis is a challenging and important topic with tremendous potential impact on clinical practice. The deep-learning methods used in computational pathology may help us to reduce costs and increase the speed and accuracy of cancer diagnosis. We started with the UNC Melanocytic Tumor Dataset cohort that contains 160 hematoxylin and eosin whole-slide images of primary melanomas (86) and nevi (74). We randomly assigned 80% (134) as a training set and built an in-house deep-learning method to allow for classification, at the slide level, of nevi and melanomas. The proposed method performed well on the other 20% (26) test dataset; the accuracy of the slide classification task was 92.3% and our model also performed well in terms of predicting the region of interest annotated by the pathologists, showing excellent performance of our model on melanocytic skin tumors. Even though we tested the experiments on the skin tumor dataset, our work could also be extended to other medical image detection problems to benefit the clinical evaluation and diagnosis of different tumors.
Authors: A. Asensio Ramos (IAC+ULL)
Abstract: The study of astronomical phenomena through ground-based observations is always challenged by the distorting effects of Earth's atmosphere. Traditional methods of post-facto image correction, essential for correcting these distortions, often rely on simplifying assumptions that limit their effectiveness, particularly in the presence of spatially variant atmospheric turbulence. Such cases are often solved by partitioning the field-of-view into small patches, deconvolving each patch independently, and merging all patches together. This approach is often inefficient and can produce artifacts. Recent advancements in computational techniques and the advent of deep learning offer new pathways to address these limitations. This paper introduces a novel framework leveraging a deep neural network to emulate spatially variant convolutions, offering a breakthrough in the efficiency and accuracy of astronomical image deconvolution. By training on a dataset of images convolved with spatially invariant point spread functions and validating its generalizability to spatially variant conditions, this approach presents a significant advancement over traditional methods. The convolution emulator is used as a forward model in a multi-object multi-frame blind deconvolution algorithm for solar images. The emulator enables the deconvolution of solar observations across large fields of view without resorting to patch-wise mosaicking, thus avoiding artifacts associated with such techniques. This method represents a significant computational advantage, reducing processing times by orders of magnitude.
Authors: Reuben Dorent, Erickson Torio, Nazim Haouchine, Colin Galvin, Sarah Frisken, Alexandra Golby, Tina Kapur, William Wells
Abstract: Intraoperative ultrasound (iUS) imaging has the potential to improve surgical outcomes in brain surgery. However, its interpretation is challenging, even for expert neurosurgeons. In this work, we designed the first patient-specific framework that performs brain tumor segmentation in trackerless iUS. To disambiguate ultrasound imaging and adapt to the neurosurgeon's surgical objective, a patient-specific real-time network is trained using synthetic ultrasound data generated by simulating virtual iUS sweep acquisitions in pre-operative MR data. Extensive experiments performed in real ultrasound data demonstrate the effectiveness of the proposed approach, allowing for adapting to the surgeon's definition of surgical targets and outperforming non-patient-specific models, neurosurgeon experts, and high-end tracking systems. Our code is available at: \url{https://github.com/ReubenDo/MHVAE-Seg}.
Authors: Jack Breen, Katie Allen, Kieran Zucker, Lucy Godson, Nicolas M. Orsi, Nishant Ravikumar
Abstract: Large pretrained transformers are increasingly being developed as generalised foundation models which can underpin powerful task-specific artificial intelligence models. Histopathology foundation models show promise across many tasks, but analyses have been limited by arbitrary hyperparameters that were not tuned to the specific task/dataset. We report the most rigorous single-task validation conducted to date of a histopathology foundation model, and the first performed in ovarian cancer subtyping. Attention-based multiple instance learning classifiers were compared using vision transformer and ResNet features generated through varied preprocessing and pretraining procedures. The training set consisted of 1864 whole slide images from 434 ovarian carcinoma cases at Leeds Hospitals. Five-class classification performance was evaluated through five-fold cross-validation, and these cross-validation models were ensembled for evaluation on a hold-out test set and an external set from the Transcanadian study. Reporting followed the TRIPOD+AI checklist. The vision transformer-based histopathology foundation model, UNI, performed best in every evaluation, with five-class balanced accuracies of 88% and 93% in hold-out internal and external testing, compared to the best ResNet model scores of 68% and 81%, respectively. Normalisations and augmentations aided the generalisability of ResNet-based models, but these still did not match the performance of UNI, which gave the best external performance in any ovarian cancer subtyping study to date. Histopathology foundation models offer a clear benefit to subtyping, improving classification performance to a degree where clinical utility is tangible, albeit with an increased computational burden. Such models could provide a second opinion in challenging cases and may improve the accuracy, objectivity, and efficiency of pathological diagnoses overall.
Authors: Johannes R\"uckert, Louise Bloch, Raphael Br\"ungel, Ahmad Idrissi-Yaghir, Henning Sch\"afer, Cynthia S. Schmidt, Sven Koitka, Obioma Pelka, Asma Ben Abacha, Alba G. Seco de Herrera, Henning M\"uller, Peter A. Horn, Felix Nensa, Christoph M. Friedrich
Abstract: Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions extracted from the PMC Open Access subset. It is an updated version of the ROCO dataset published in 2018, and adds 35,705 new images added to PMC since 2018. It further provides manually curated concepts for imaging modalities with additional anatomical and directional concepts for X-rays. The dataset consists of 79,789 images and has been used, with minor modifications, in the concept detection and caption prediction tasks of ImageCLEFmedical Caption 2023. The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image. In addition, it can serve for pre-training of medical domain models, and evaluation of deep learning models for multi-task learning.
Authors: Albert Yu, Adeline Foote, Raymond Mooney, Roberto Mart\'in-Mart\'in
Abstract: The main challenge in learning image-conditioned robotic policies is acquiring a visual representation conducive to low-level control. Due to the high dimensionality of the image space, learning a good visual representation requires a considerable amount of visual data. However, when learning in the real world, data is expensive. Sim2Real is a promising paradigm for overcoming data scarcity in the real-world target domain by using a simulator to collect large amounts of cheap data closely related to the target task. However, it is difficult to transfer an image-conditioned policy from sim to real when the domains are very visually dissimilar. To bridge the sim2real visual gap, we propose using natural language descriptions of images as a unifying signal across domains that captures the underlying task-relevant semantics. Our key insight is that if two image observations from different domains are labeled with similar language, the policy should predict similar action distributions for both images. We demonstrate that training the image encoder to predict the language description or the distance between descriptions of a sim or real image serves as a useful, data-efficient pretraining step that helps learn a domain-invariant image representation. We can then use this image encoder as the backbone of an IL policy trained simultaneously on a large amount of simulated and a handful of real demonstrations. Our approach outperforms widely used prior sim2real methods and strong vision-language pretraining baselines like CLIP and R3M by 25 to 40%.
Authors: Ruizhe Li, Grazziela Figueredo, Dorothee Auer, Christian Wagner, Xin Chen
Abstract: Deformable image registration (alignment) is highly sought after in numerous clinical applications, such as computer aided diagnosis and disease progression analysis. Deep Convolutional Neural Network (DCNN)-based image registration methods have demonstrated advantages in terms of registration accuracy and computational speed. However, while most methods excel at global alignment, they often perform worse in aligning local regions. To address this challenge, this paper proposes a mask-guided encoder-decoder DCNN-based image registration method, named as MrRegNet. This approach employs a multi-resolution encoder for feature extraction and subsequently estimates multi-resolution displacement fields in the decoder to handle the substantial deformation of images. Furthermore, segmentation masks are employed to direct the model's attention toward aligning local regions. The results show that the proposed method outperforms traditional methods like Demons and a well-known deep learning method, VoxelMorph, on a public 3D brain MRI dataset (OASIS) and a local 2D brain MRI dataset with large deformations. Importantly, the image alignment accuracies are significantly improved at local regions guided by segmentation masks. Github link:https://github.com/ruizhe-l/MrRegNet.
Authors: Xinru Zhang, Ni Ou, Berke Doga Basaran, Marco Visentin, Mengyun Qiao, Renyang Gu, Cheng Ouyang, Yaou Liu, Paul M. Matthew, Chuyang Ye, Wenjia Bai
Abstract: Brain lesion segmentation plays an essential role in neurological research and diagnosis. As brain lesions can be caused by various pathological alterations, different types of brain lesions tend to manifest with different characteristics on different imaging modalities. Due to this complexity, brain lesion segmentation methods are often developed in a task-specific manner. A specific segmentation model is developed for a particular lesion type and imaging modality. However, the use of task-specific models requires predetermination of the lesion type and imaging modality, which complicates their deployment in real-world scenarios. In this work, we propose a universal foundation model for 3D brain lesion segmentation, which can automatically segment different types of brain lesions for input data of various imaging modalities. We formulate a novel Mixture of Modality Experts (MoME) framework with multiple expert networks attending to different imaging modalities. A hierarchical gating network combines the expert predictions and fosters expertise collaboration. Furthermore, we introduce a curriculum learning strategy during training to avoid the degeneration of each expert network and preserve their specialization. We evaluated the proposed method on nine brain lesion datasets, encompassing five imaging modalities and eight lesion types. The results show that our model outperforms state-of-the-art universal models and provides promising generalization to unseen datasets.
Authors: George Shaikovski, Adam Casson, Kristen Severson, Eric Zimmermann, Yi Kan Wang, Jeremy D. Kunz, Juan A. Retamero, Gerard Oakley, David Klimstra, Christopher Kanan, Matthew Hanna, Michal Zelechowski, Julian Viret, Neil Tenenholtz, James Hall, Nicolo Fusi, Razik Yousfi, Peter Hamilton, William A. Moye, Eugene Vorontsov, Siqi Liu, Thomas J. Fuchs
Abstract: Foundation models in computational pathology promise to unlock the development of new clinical decision support systems and models for precision medicine. However, there is a mismatch between most clinical analysis, which is defined at the level of one or more whole slide images, and foundation models to date, which process the thousands of image tiles contained in a whole slide image separately. The requirement to train a network to aggregate information across a large number of tiles in multiple whole slide images limits these models' impact. In this work, we present a slide-level foundation model for H&E-stained histopathology, PRISM, that builds on Virchow tile embeddings and leverages clinical report text for pre-training. Using the tile embeddings, PRISM produces slide-level embeddings with the ability to generate clinical reports, resulting in several modes of use. Using text prompts, PRISM achieves zero-shot cancer detection and sub-typing performance approaching and surpassing that of a supervised aggregator model. Using the slide embeddings with linear classifiers, PRISM surpasses supervised aggregator models. Furthermore, we demonstrate that fine-tuning of the PRISM slide encoder yields label-efficient training for biomarker prediction, a task that typically suffers from low availability of training data; an aggregator initialized with PRISM and trained on as little as 10% of the training data can outperform a supervised baseline that uses all of the data.
Authors: Junpeng Zhang, Qing Li, Liang Lin, Quanshi Zhang
Abstract: This paper investigates the dynamics of a deep neural network (DNN) learning interactions. Previous studies have discovered and mathematically proven that given each input sample, a well-trained DNN usually only encodes a small number of interactions (non-linear relationships) between input variables in the sample. A series of theorems have been derived to prove that we can consider the DNN's inference equivalent to using these interactions as primitive patterns for inference. In this paper, we discover the DNN learns interactions in two phases. The first phase mainly penalizes interactions of medium and high orders, and the second phase mainly learns interactions of gradually increasing orders. We can consider the two-phase phenomenon as the starting point of a DNN learning over-fitted features. Such a phenomenon has been widely shared by DNNs with various architectures trained for different tasks. Therefore, the discovery of the two-phase dynamics provides a detailed mechanism for how a DNN gradually learns different inference patterns (interactions). In particular, we have also verified the claim that high-order interactions have weaker generalization power than low-order interactions. Thus, the discovered two-phase dynamics also explains how the generalization power of a DNN changes during the training process.
Authors: Yuexiang Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Shengbang Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, Sergey Levine
Abstract: Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to efficiently learn optimal decision-making agents in multi-step goal-directed tasks from interactive environments. To address this challenge, we propose an algorithmic framework that fine-tunes VLMs with reinforcement learning (RL). Specifically, our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning, enabling the VLM to efficiently explore intermediate reasoning steps that lead to the final text-based action. Next, the open-ended text output is parsed into an executable action to interact with the environment to obtain goal-directed task rewards. Finally, our framework uses these task rewards to fine-tune the entire VLM with RL. Empirically, we demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks, enabling 7b models to outperform commercial models such as GPT4-V or Gemini. Furthermore, we find that CoT reasoning is a crucial component for performance improvement, as removing the CoT reasoning results in a significant decrease in the overall performance of our method.
Authors: Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, Yu Su
Abstract: Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop. However, existing methods are either zero-shot or trained on an automatically synthesized dataset, which contains a high volume of noise. Thus, they still require lots of manual tuning to produce desirable outcomes in practice. To address this issue, we introduce MagicBrush (https://osu-nlp-group.github.io/MagicBrush/), the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing. MagicBrush comprises over 10K manually annotated triplets (source image, instruction, target image), which supports trainining large-scale text-guided image editing models. We fine-tune InstructPix2Pix on MagicBrush and show that the new model can produce much better images according to human evaluation. We further conduct extensive experiments to evaluate current image editing baselines from multiple dimensions including quantitative, qualitative, and human evaluations. The results reveal the challenging nature of our dataset and the gap between current baselines and real-world editing needs.
Authors: Kalyani Marathe, Mahtab Bigverdi, Nishat Khan, Tuhin Kundu, Patrick Howe, Sharan Ranjit S, Anand Bhattad, Aniruddha Kembhavi, Linda G. Shapiro, Ranjay Krishna
Abstract: Dense pixel-specific representation learning at scale has been bottlenecked due to the unavailability of large-scale multi-view datasets. Current methods for building effective pretraining datasets heavily rely on annotated 3D meshes, point clouds, and camera parameters from simulated environments, preventing them from building datasets from real-world data sources where such metadata is lacking. We propose a pretraining dataset-curation approach that does not require any additional annotations. Our method allows us to generate multi-view datasets from both real-world videos and simulated environments at scale. Specifically, we experiment with two scales: MIMIC-1M with 1.3M and MIMIC-3M with 3.1M multi-view image pairs. We train multiple models with different masked image modeling objectives to showcase the following findings: Representations trained on our automatically generated MIMIC-3M outperform those learned from expensive crowdsourced datasets (ImageNet-1K) and those learned from synthetic environments (MULTIVIEW-HABITAT) on two dense geometric tasks: depth estimation on NYUv2 (1.7%), and surface normals estimation on Taskonomy (2.05%). For dense tasks which also require object understanding, we outperform MULTIVIEW-HABITAT, on semantic segmentation on ADE20K (3.89%), pose estimation on MSCOCO (9.4%), and reduce the gap with models pre-trained on the object-centric expensive ImageNet-1K. We outperform even when the representations are frozen, and when downstream training data is limited to few-shot. Larger dataset (MIMIC-3M) significantly improves performance, which is promising since our curation method can arbitrarily scale to produce even larger datasets. MIMIC code, dataset, and pretrained models are open-sourced at https://github.com/RAIVNLab/MIMIC.
Authors: Jisong Kim, Minjae Seong, Geonho Bang, Dongsuk Kum, Jun Won Choi
Abstract: While LiDAR sensors have been successfully applied to 3D object detection, the affordability of radar and camera sensors has led to a growing interest in fusing radars and cameras for 3D object detection. However, previous radar-camera fusion models were unable to fully utilize the potential of radar information. In this paper, we propose Radar-Camera Multi-level fusion (RCM-Fusion), which attempts to fuse both modalities at both feature and instance levels. For feature-level fusion, we propose a Radar Guided BEV Encoder which transforms camera features into precise BEV representations using the guidance of radar Bird's-Eye-View (BEV) features and combines the radar and camera BEV features. For instance-level fusion, we propose a Radar Grid Point Refinement module that reduces localization error by accounting for the characteristics of the radar point clouds. The experiments conducted on the public nuScenes dataset demonstrate that our proposed RCM-Fusion achieves state-of-the-art performances among single frame-based radar-camera fusion methods in the nuScenes 3D object detection benchmark. Code will be made publicly available.
Authors: Peiyan Zhang, Haoyang Liu, Chaozhuo Li, Xing Xie, Sunghun Kim, Haohan Wang
Abstract: Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal robust model will probably behave similarly to the oracle (e.g., the human users), thus a good evaluation protocol is probably to evaluate the models' behaviors in comparison to the oracle. In this paper, we introduce a new robustness measurement that directly measures the image classification model's performance compared with a surrogate oracle (i.e., a foundation model). Besides, we design a simple method that can accomplish the evaluation beyond the scope of the benchmarks. Our method extends the image datasets with new samples that are sufficiently perturbed to be distinct from the ones in the original sets, but are still bounded within the same image-label structure the original test image represents, constrained by a foundation model pretrained with a large amount of samples. As a result, our new method will offer us a new way to evaluate the models' robustness performance, free of limitations of fixed benchmarks or constrained perturbations, although scoped by the power of the oracle. In addition to the evaluation results, we also leverage our generated data to understand the behaviors of the model and our new evaluation strategies.
Authors: Daniel Ajisafe, James Tang, Shih-Yang Su, Bastian Wandt, Helge Rhodin
Abstract: Human motion capture either requires multi-camera systems or is unreliable when using single-view input due to depth ambiguities. Meanwhile, mirrors are readily available in urban environments and form an affordable alternative by recording two views with only a single camera. However, the mirror setting poses the additional challenge of handling occlusions of real and mirror image. Going beyond existing mirror approaches for 3D human pose estimation, we utilize mirrors for learning a complete body model, including shape and dense appearance. Our main contributions are extending articulated neural radiance fields to include a notion of a mirror, making it sample-efficient over potential occlusion regions. Together, our contributions realize a consumer-level 3D motion capture system that starts from off-the-shelf 2D poses by automatically calibrating the camera, estimating mirror orientation, and subsequently lifting 2D keypoint detections to 3D skeleton pose that is used to condition the mirror-aware NeRF. We empirically demonstrate the benefit of learning a body model and accounting for occlusion in challenging mirror scenes.
Authors: Haotian Liu, Chunyuan Li, Yuheng Li, Yong Jae Lee
Abstract: Large multimodal models (LMM) have recently shown encouraging progress with visual instruction tuning. In this note, we show that the fully-connected vision-language cross-modal connector in LLaVA is surprisingly powerful and data-efficient. With simple modifications to LLaVA, namely, using CLIP-ViT-L-336px with an MLP projection and adding academic-task-oriented VQA data with simple response formatting prompts, we establish stronger baselines that achieve state-of-the-art across 11 benchmarks. Our final 13B checkpoint uses merely 1.2M publicly available data, and finishes full training in ~1 day on a single 8-A100 node. We hope this can make state-of-the-art LMM research more accessible. Code and model will be publicly available.
Authors: Ehsan Pajouheshgar, Yitao Xu, Alexander Mordvintsev, Eyvind Niklasson, Tong Zhang, Sabine S\"usstrunk
Abstract: Texture modeling and synthesis are essential for enhancing the realism of virtual environments. Methods that directly synthesize textures in 3D offer distinct advantages to the UV-mapping-based methods as they can create seamless textures and align more closely with the ways textures form in nature. We propose Mesh Neural Cellular Automata (MeshNCA), a method that directly synthesizes dynamic textures on 3D meshes without requiring any UV maps. MeshNCA is a generalized type of cellular automata that can operate on a set of cells arranged on non-grid structures such as the vertices of a 3D mesh. MeshNCA accommodates multi-modal supervision and can be trained using different targets such as images, text prompts, and motion vector fields. Only trained on an Icosphere mesh, MeshNCA shows remarkable test-time generalization and can synthesize textures on unseen meshes in real time. We conduct qualitative and quantitative comparisons to demonstrate that MeshNCA outperforms other 3D texture synthesis methods in terms of generalization and producing high-quality textures. Moreover, we introduce a way of grafting trained MeshNCA instances, enabling interpolation between textures. MeshNCA allows several user interactions including texture density/orientation controls, grafting/regenerate brushes, and motion speed/direction controls. Finally, we implement the forward pass of our MeshNCA model using the WebGL shading language and showcase our trained models in an online interactive demo, which is accessible on personal computers and smartphones and is available at https://meshnca.github.io.
Authors: Miguel \'Angel Mu\~noz-Ba\~n\'on, Alejandro Olivas, Edison Velasco-S\'anchez, Francisco A. Candelas, Fernando Torres
Abstract: Feature-based geo-localization relies on associating features extracted from aerial imagery with those detected by the vehicle's sensors. This requires that the type of landmarks must be observable from both sources. This lack of variety of feature types generates poor representations that lead to outliers and deviations produced by ambiguities and lack of detections, respectively. To mitigate these drawbacks, in this paper, we present a dynamically weighted factor graph model for the vehicle's trajectory estimation. The weight adjustment in this implementation depends on information quantification in the detections performed using a LiDAR sensor. Also, a prior (GNSS-based) error estimation is included in the model. Then, when the representation becomes ambiguous or sparse, the weights are dynamically adjusted to rely on the corrected prior trajectory, mitigating outliers and deviations in this way. We compare our method against state-of-the-art geo-localization ones in a challenging and ambiguous environment, where we also cause detection losses. We demonstrate mitigation of the mentioned drawbacks where the other methods fail.
Authors: Junyu Gao, Xuan Yao, Changsheng Xu
Abstract: The ability to accurately comprehend natural language instructions and navigate to the target location is essential for an embodied agent. Such agents are typically required to execute user instructions in an online manner, leading us to explore the use of unlabeled test samples for effective online model adaptation. However, for online Vision-and-Language Navigation (VLN), due to the intrinsic nature of inter-sample online instruction execution and intra-sample multi-step action decision, frequent updates can result in drastic changes in model parameters, while occasional updates can make the model ill-equipped to handle dynamically changing environments. Therefore, we propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for online VLN by performing joint decomposition-accumulation analysis for both gradients and parameters in a unified framework. Extensive experiments show that our method obtains impressive performance gains on four popular benchmarks. Code is available at https://github.com/Feliciaxyao/ICML2024-FSTTA.
Authors: Li Ma, Vasu Agrawal, Haithem Turki, Changil Kim, Chen Gao, Pedro Sander, Michael Zollh\"ofer, Christian Richardt
Abstract: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.
Authors: Jilan Xu, Yifei Huang, Junlin Hou, Guo Chen, Yuejie Zhang, Rui Feng, Weidi Xie
Abstract: Understanding human actions from videos of first-person view poses significant challenges. Most prior approaches explore representation learning on egocentric videos only, while overlooking the potential benefit of exploiting existing large-scale third-person videos. In this paper, (1) we develop EgoInstructor, a retrieval-augmented multimodal captioning model that automatically retrieves semantically relevant third-person instructional videos to enhance the video captioning of egocentric videos. (2) For training the cross-view retrieval module, we devise an automatic pipeline to discover ego-exo video pairs from distinct large-scale egocentric and exocentric datasets. (3) We train the cross-view retrieval module with a novel EgoExoNCE loss that pulls egocentric and exocentric video features closer by aligning them to shared text features that describe similar actions. (4) Through extensive experiments, our cross-view retrieval module demonstrates superior performance across seven benchmarks. Regarding egocentric video captioning, EgoInstructor exhibits significant improvements by leveraging third-person videos as references.
Authors: Xiang Xu, Joseph G. Lambourne, Pradeep Kumar Jayaraman, Zhengqing Wang, Karl D. D. Willis, Yasutaka Furukawa
Abstract: This paper presents BrepGen, a diffusion-based generative approach that directly outputs a Boundary representation (B-rep) Computer-Aided Design (CAD) model. BrepGen represents a B-rep model as a novel structured latent geometry in a hierarchical tree. With the root node representing a whole CAD solid, each element of a B-rep model (i.e., a face, an edge, or a vertex) progressively turns into a child-node from top to bottom. B-rep geometry information goes into the nodes as the global bounding box of each primitive along with a latent code describing the local geometric shape. The B-rep topology information is implicitly represented by node duplication. When two faces share an edge, the edge curve will appear twice in the tree, and a T-junction vertex with three incident edges appears six times in the tree with identical node features. Starting from the root and progressing to the leaf, BrepGen employs Transformer-based diffusion models to sequentially denoise node features while duplicated nodes are detected and merged, recovering the B-Rep topology information. Extensive experiments show that BrepGen advances the task of CAD B-rep generation, surpassing existing methods on various benchmarks. Results on our newly collected furniture dataset further showcase its exceptional capability in generating complicated geometry. While previous methods were limited to generating simple prismatic shapes, BrepGen incorporates free-form and doubly-curved surfaces for the first time. Additional applications of BrepGen include CAD autocomplete and design interpolation. The code, pretrained models, and dataset are available at https://github.com/samxuxiang/BrepGen.
Authors: Bo Yang, Chen Wang, Xiaoshuang Ma, Beiping Song, Zhuang Liu, Fangde Sun
Abstract: Effectively and efficiently retrieving images from remote sensing databases is a critical challenge in the realm of remote sensing big data. Utilizing hand-drawn sketches as retrieval inputs offers intuitive and user-friendly advantages, yet the potential of multi-level feature integration from sketches remains underexplored, leading to suboptimal retrieval performance. To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update. This approach employs only vision information and does not require semantic knowledge concerning the sketch and image. It starts by employing multi-level self-attention guided feature extraction to tokenize the query sketches, as well as self-attention feature extraction to tokenize the candidate images. It then employs cross-attention mechanisms to establish token correspondence between these two modalities, facilitating the computation of sketch-to-image similarity. Our method significantly outperforms existing sketch-based remote sensing image retrieval techniques, as evidenced by tests on multiple datasets. Notably, it also exhibits robust zero-shot learning capabilities and strong generalizability in handling unseen categories and novel remote sensing data. The method's scalability can be further enhanced by the pre-calculation of retrieval tokens for all candidate images in a database. This research underscores the significant potential of multi-level, attention-guided tokenization in cross-modal remote sensing image retrieval. For broader accessibility and research facilitation, we have made the code and dataset used in this study publicly available online. Code and dataset are available at https://github.com/Snowstormfly/Cross-modal-retrieval-MLAGT.
URLs: https://github.com/Snowstormfly/Cross-modal-retrieval-MLAGT.
Authors: Yoad Tewel, Omri Kaduri, Rinon Gal, Yoni Kasten, Lior Wolf, Gal Chechik, Yuval Atzmon
Abstract: Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to consistently portray the same subject across diverse prompts remains challenging. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects or add image conditioning to the model. These methods require lengthy per-subject optimization or large-scale pre-training. Moreover, they struggle to align generated images with text prompts and face difficulties in portraying multiple subjects. Here, we present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model. We introduce a subject-driven shared attention block and correspondence-based feature injection to promote subject consistency between images. Additionally, we develop strategies to encourage layout diversity while maintaining subject consistency. We compare ConsiStory to a range of baselines, and demonstrate state-of-the-art performance on subject consistency and text alignment, without requiring a single optimization step. Finally, ConsiStory can naturally extend to multi-subject scenarios, and even enable training-free personalization for common objects.
Authors: Jian Chen, Ruiyi Zhang, Yufan Zhou, Rajiv Jain, Zhiqiang Xu, Ryan Rossi, Changyou Chen
Abstract: Controllable layout generation refers to the process of creating a plausible visual arrangement of elements within a graphic design (e.g., document and web designs) with constraints representing design intentions. Although recent diffusion-based models have achieved state-of-the-art FID scores, they tend to exhibit more pronounced misalignment compared to earlier transformer-based models. In this work, we propose the $\textbf{LA}$yout $\textbf{C}$onstraint diffusion mod$\textbf{E}$l (LACE), a unified model to handle a broad range of layout generation tasks, such as arranging elements with specified attributes and refining or completing a coarse layout design. The model is based on continuous diffusion models. Compared with existing methods that use discrete diffusion models, continuous state-space design can enable the incorporation of differentiable aesthetic constraint functions in training. For conditional generation, we introduce conditions via masked input. Extensive experiment results show that LACE produces high-quality layouts and outperforms existing state-of-the-art baselines.
Authors: Yunwei Bai, Ying Kiat Tan, Tsuhan Chen
Abstract: Few-shot-learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labelled samples of the new classes (support set) as reference. As the test classes are novel, FSL is challenging with high generalization error with respect to the novel classes, where outliers query or support image during inference exacerbate the error further. So far, plenty of algorithms involve training data augmentation to improve the generalization capability of FSL models. In contrast, inspired by the fact that test samples are more relevant to the target domain, we believe that test-time augmentation may be more useful than training augmentation for FSL. In this work, to reduce the bias caused by unconventional test samples, we generate new test samples through combining them with similar train-class samples. Averaged representations of the test-time augmentation are then considered for few-shot classification. According to our experiments, by augmenting the support set and query with a few additional generated sample, we can achieve improvement for trained FSL models. Importantly, our method is universally compatible with different off-the-shelf FSL models, whose performance can be improved without extra dataset nor further training of the models themselves. Codes are available at https://github.com/WendyBaiYunwei/FSL-Rectifier.
Authors: Lu Jiang, Qi Wang, Yuhang Chang, Jianing Song, Haoyue Fu, Xiaochun Yang
Abstract: Category imbalance is one of the most popular and important issues in the domain of classification. Emotion classification model trained on imbalanced datasets easily leads to unreliable prediction. The traditional machine learning method tends to favor the majority class, which leads to the lack of minority class information in the model. Moreover, most existing models will produce abnormal sensitivity issues or performance degradation. We propose a robust learning algorithm based on adaptive cost-sensitiveity and recursive denoising, which is a generalized framework and can be incorporated into most stochastic optimization algorithms. The proposed method uses the dynamic kernel distance optimization model between the sample and the decision boundary, which makes full use of the sample's prior information. In addition, we also put forward an effective method to filter noise, the main idea of which is to judge the noise by finding the nearest neighbors of the minority class. In order to evaluate the strength of the proposed method, we not only carry out experiments on standard datasets but also apply it to emotional classification problems with different imbalance rates (IR). Experimental results show that the proposed general framework is superior to traditional methods in accuracy, recall and G-means.
Authors: Bowen Huang, Yanwei Zheng, Chuanlin Lan, Xinpeng Zhao, Yifei Zou, Dongxiao yu
Abstract: Vision-and-Language Navigation (VLN) is a challenging task where an agent is required to navigate to a natural language described location via vision observations. The navigation abilities of the agent can be enhanced by the relations between objects, which are usually learned using internal objects or external datasets. The relationships between internal objects are modeled employing graph convolutional network (GCN) in traditional studies. However, GCN tends to be shallow, limiting its modeling ability. To address this issue, we utilize a cross attention mechanism to learn the connections between objects over a trajectory, which takes temporal continuity into account, termed as Temporal Object Relations (TOR). The external datasets have a gap with the navigation environment, leading to inaccurate modeling of relations. To avoid this problem, we construct object connections based on observations from all viewpoints in the navigational environment, which ensures complete spatial coverage and eliminates the gap, called Spatial Object Relations (SOR). Additionally, we observe that agents may repeatedly visit the same location during navigation, significantly hindering their performance. For resolving this matter, we introduce the Turning Back Penalty (TBP) loss function, which penalizes the agent's repetitive visiting behavior, substantially reducing the navigational distance. Experimental results on the REVERIE, SOON, and R2R datasets demonstrate the effectiveness of the proposed method.
Authors: Gan Pei, Jiangning Zhang, Menghan Hu, Zhenyu Zhang, Chengjie Wang, Yunsheng Wu, Guangtao Zhai, Jian Yang, Chunhua Shen, Dacheng Tao
Abstract: Deepfake is a technology dedicated to creating highly realistic facial images and videos under specific conditions, which has significant application potential in fields such as entertainment, movie production, digital human creation, to name a few. With the advancements in deep learning, techniques primarily represented by Variational Autoencoders and Generative Adversarial Networks have achieved impressive generation results. More recently, the emergence of diffusion models with powerful generation capabilities has sparked a renewed wave of research. In addition to deepfake generation, corresponding detection technologies continuously evolve to regulate the potential misuse of deepfakes, such as for privacy invasion and phishing attacks. This survey comprehensively reviews the latest developments in deepfake generation and detection, summarizing and analyzing current state-of-the-arts in this rapidly evolving field. We first unify task definitions, comprehensively introduce datasets and metrics, and discuss developing technologies. Then, we discuss the development of several related sub-fields and focus on researching four representative deepfake fields: face swapping, face reenactment, talking face generation, and facial attribute editing, as well as forgery detection. Subsequently, we comprehensively benchmark representative methods on popular datasets for each field, fully evaluating the latest and influential published works. Finally, we analyze challenges and future research directions of the discussed fields.
Authors: David Hagens, Jan M. Knaup, Elke Hergenr\"other, Andreas Weinmann
Abstract: The automation of games using Deep Reinforcement Learning Strategies (DRL) is a well-known challenge in AI research. While for feature extraction in a video game typically the whole image is used, this is hardly practical for many real world games. Instead, using a smaller game state reducing the dimension of the parameter space to include essential parameters only seems to be a promising approach. In the game of Foosball, a compact and comprehensive game state description consists of the positional shifts and rotations of the figures and the position of the ball over time. In particular, velocities and accelerations can be derived from consecutive time samples of the game state. In this paper, a figure detection system to determine the game state in Foosball is presented. We capture a dataset containing the rotations of the rods which were measured using accelerometers and the positional shifts were derived using traditional Computer Vision techniques (in a laboratory setting). This dataset is utilized to train Convolutional Neural Network (CNN) based end-to-end regression models to predict the rotations and shifts of each rod. We present an evaluation of our system using different state-of-the-art CNNs as base architectures for the regression model. We show that our system is able to predict the game state with high accuracy. By providing data for both black and white teams, the presented system is intended to provide the required data for future developments of Imitation Learning techniques w.r.t. to observing human players.
Authors: Sanggeon Yun, Ryozo Masukawa, SungHeon Jeong, Mohsen Imani
Abstract: In the face of burgeoning image data, efficiently retrieving similar images poses a formidable challenge. Past research has focused on refining hash functions to distill images into compact indicators of resemblance. Initial attempts used shallow models, evolving to attention mechanism-based architectures from Convolutional Neural Networks (CNNs) to advanced models. Recognizing limitations in gradient-based models for spatial information embedding, we propose an innovative image hashing method, NeuroHash leveraging Hyperdimensional Computing (HDC). HDC symbolically encodes spatial information into high-dimensional vectors, reshaping image representation. Our approach combines pre-trained large vision models with HDC operations, enabling spatially encoded feature representations. Hashing with locality-sensitive hashing (LSH) ensures swift and efficient image retrieval. Notably, our framework allows dynamic hash manipulation for conditional image retrieval. Our work introduces a transformative image hashing framework enabling spatial-aware conditional retrieval. By seamlessly combining DNN-based neural and HDC-based symbolic models, our methodology breaks from traditional training, offering flexible and conditional image retrieval. Performance evaluations signify a paradigm shift in image-hashing methodologies, demonstrating enhanced retrieval accuracy.
Authors: Zeyu Li, Ruitong Gan, Chuanchen Luo, Yuxi Wang, Jiaheng Liu, Ziwei Zhu Man Zhang, Qing Li, Xucheng Yin, Zhaoxiang Zhang, Junran Peng
Abstract: Driven by powerful image diffusion models, recent research has achieved the automatic creation of 3D objects from textual or visual guidance. By performing score distillation sampling (SDS) iteratively across different views, these methods succeed in lifting 2D generative prior to the 3D space. However, such a 2D generative image prior bakes the effect of illumination and shadow into the texture. As a result, material maps optimized by SDS inevitably involve spurious correlated components. The absence of precise material definition makes it infeasible to relight the generated assets reasonably in novel scenes, which limits their application in downstream scenarios. In contrast, humans can effortlessly circumvent this ambiguity by deducing the material of the object from its appearance and semantics. Motivated by this insight, we propose MaterialSeg3D, a 3D asset material generation framework to infer underlying material from the 2D semantic prior. Based on such a prior model, we devise a mechanism to parse material in 3D space. We maintain a UV stack, each map of which is unprojected from a specific viewpoint. After traversing all viewpoints, we fuse the stack through a weighted voting scheme and then employ region unification to ensure the coherence of the object parts. To fuel the learning of semantics prior, we collect a material dataset, named Materialized Individual Objects (MIO), which features abundant images, diverse categories, and accurate annotations. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method.
Authors: Xuanyu Zhang, Youmin Xu, Runyi Li, Jiwen Yu, Weiqi Li, Zhipei Xu, Jian Zhang
Abstract: AI-generated video has revolutionized short video production, filmmaking, and personalized media, making video local editing an essential tool. However, this progress also blurs the line between reality and fiction, posing challenges in multimedia forensics. To solve this urgent issue, V2A-Mark is proposed to address the limitations of current video tampering forensics, such as poor generalizability, singular function, and single modality focus. Combining the fragility of video-into-video steganography with deep robust watermarking, our method can embed invisible visual-audio localization watermarks and copyright watermarks into the original video frames and audio, enabling precise manipulation localization and copyright protection. We also design a temporal alignment and fusion module and degradation prompt learning to enhance the localization accuracy and decoding robustness. Meanwhile, we introduce a sample-level audio localization method and a cross-modal copyright extraction mechanism to couple the information of audio and video frames. The effectiveness of V2A-Mark has been verified on a visual-audio tampering dataset, emphasizing its superiority in localization precision and copyright accuracy, crucial for the sustainable development of video editing in the AIGC video era.
Authors: Peihao Xiang, Chaohao Lin, Kaida Wu, Ou Bai
Abstract: This paper presents a novel approach to processing multimodal data for dynamic emotion recognition, named as the Multimodal Masked Autoencoder for Dynamic Emotion Recognition (MultiMAE-DER). The MultiMAE-DER leverages the closely correlated representation information within spatiotemporal sequences across visual and audio modalities. By utilizing a pre-trained masked autoencoder model, the MultiMAEDER is accomplished through simple, straightforward finetuning. The performance of the MultiMAE-DER is enhanced by optimizing six fusion strategies for multimodal input sequences. These strategies address dynamic feature correlations within cross-domain data across spatial, temporal, and spatiotemporal sequences. In comparison to state-of-the-art multimodal supervised learning models for dynamic emotion recognition, MultiMAE-DER enhances the weighted average recall (WAR) by 4.41% on the RAVDESS dataset and by 2.06% on the CREMAD. Furthermore, when compared with the state-of-the-art model of multimodal self-supervised learning, MultiMAE-DER achieves a 1.86% higher WAR on the IEMOCAP dataset.
Authors: Yian Zhao, Kehan Li, Zesen Cheng, Pengchong Qiao, Xiawu Zheng, Rongrong Ji, Chang Liu, Li Yuan, Jie Chen
Abstract: Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity output and multi-granularity output. The latter aims to alleviate the spatial ambiguity present in the former. However, the multi-granularity output pipeline suffers from limited interaction flexibility and produces redundant results. In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing additional parameters to input. This enhances the customization of the interactive system and eliminates redundancy while resolving ambiguity. Nevertheless, the exorbitant cost of annotating multi-granularity masks and the lack of available datasets with granularity annotations make it difficult for models to acquire the necessary guidance to control output granularity. To address this problem, we design an any-granularity mask generator that exploits the semantic property of the pre-trained IS model to automatically generate abundant mask-granularity pairs without requiring additional manual annotation. Based on these pairs, we propose a granularity-controllable learning strategy that efficiently imparts the granularity controllability to the IS model. Extensive experiments on intricate scenarios at object and part levels demonstrate that our GraCo has significant advantages over previous methods. This highlights the potential of GraCo to be a flexible annotation tool, capable of adapting to diverse segmentation scenarios. The project page: https://zhao-yian.github.io/GraCo.
Authors: Hritik Bansal, Yonatan Bitton, Michal Yarom, Idan Szpektor, Aditya Grover, Kai-Wei Chang
Abstract: Recent advances in diffusion-based generative modeling have led to the development of text-to-video (T2V) models that can generate high-quality videos conditioned on a text prompt. Most of these T2V models often produce single-scene video clips that depict an entity performing a particular action (e.g., `a red panda climbing a tree'). However, it is pertinent to generate multi-scene videos since they are ubiquitous in the real-world (e.g., `a red panda climbing a tree' followed by `the red panda sleeps on the top of the tree'). To generate multi-scene videos from the pretrained T2V model, we introduce Time-Aligned Captions (TALC) framework. Specifically, we enhance the text-conditioning mechanism in the T2V architecture to recognize the temporal alignment between the video scenes and scene descriptions. For instance, we condition the visual features of the earlier and later scenes of the generated video with the representations of the first scene description (e.g., `a red panda climbing a tree') and second scene description (e.g., `the red panda sleeps on the top of the tree'), respectively. As a result, we show that the T2V model can generate multi-scene videos that adhere to the multi-scene text descriptions and be visually consistent (e.g., entity and background). Further, we finetune the pretrained T2V model with multi-scene video-text data using the TALC framework. We show that the TALC-finetuned model outperforms the baseline methods by 15.5 points in the overall score, which averages visual consistency and text adherence using human evaluation. The project website is https://talc-mst2v.github.io/.
Authors: Yu Lei, Haolun Luo, Lituan Wang, Zhenwei Zhang, Lei Zhang
Abstract: In weakly supervised medical image segmentation, the absence of structural priors and the discreteness of class feature distribution present a challenge, i.e., how to accurately propagate supervision signals from local to global regions without excessively spreading them to other irrelevant regions? To address this, we propose a novel weakly supervised medical image segmentation framework named PCLMix, comprising dynamic mix augmentation, pixel-level contrastive learning, and consistency regularization strategies. Specifically, PCLMix is built upon a heterogeneous dual-decoder backbone, addressing the absence of structural priors through a strategy of dynamic mix augmentation during training. To handle the discrete distribution of class features, PCLMix incorporates pixel-level contrastive learning based on prediction uncertainty, effectively enhancing the model's ability to differentiate inter-class pixel differences and intra-class consistency. Furthermore, to reinforce segmentation consistency and robustness, PCLMix employs an auxiliary decoder for dual consistency regularization. In the inference phase, the auxiliary decoder will be dropped and no computation complexity is increased. Extensive experiments on the ACDC dataset demonstrate that PCLMix appropriately propagates local supervision signals to the global scale, further narrowing the gap between weakly supervised and fully supervised segmentation methods. Our code is available at https://github.com/Torpedo2648/PCLMix.
Authors: Vasileios Karampinis, Anastasios Arsenos, Orfeas Filippopoulos, Evangelos Petrongonas, Christos Skliros, Dimitrios Kollias, Stefanos Kollias, Athanasios Voulodimos
Abstract: In the last twenty years, unmanned aerial vehicles (UAVs) have garnered growing interest due to their expanding applications in both military and civilian domains. Detecting non-cooperative aerial vehicles with efficiency and estimating collisions accurately are pivotal for achieving fully autonomous aircraft and facilitating Advanced Air Mobility (AAM). This paper presents a deep-learning framework that utilizes optical sensors for the detection, tracking, and distance estimation of non-cooperative aerial vehicles. In implementing this comprehensive sensing framework, the availability of depth information is essential for enabling autonomous aerial vehicles to perceive and navigate around obstacles. In this work, we propose a method for estimating the distance information of a detected aerial object in real time using only the input of a monocular camera. In order to train our deep learning components for the object detection, tracking and depth estimation tasks we utilize the Amazon Airborne Object Tracking (AOT) Dataset. In contrast to previous approaches that integrate the depth estimation module into the object detector, our method formulates the problem as image-to-image translation. We employ a separate lightweight encoder-decoder network for efficient and robust depth estimation. In a nutshell, the object detection module identifies and localizes obstacles, conveying this information to both the tracking module for monitoring obstacle movement and the depth estimation module for calculating distances. Our approach is evaluated on the Airborne Object Tracking (AOT) dataset which is the largest (to the best of our knowledge) air-to-air airborne object dataset.
Authors: Anastasios Arsenos, Vasileios Karampinis, Evangelos Petrongonas, Christos Skliros, Dimitrios Kollias, Stefanos Kollias, Athanasios Voulodimos
Abstract: The main barrier to achieving fully autonomous flights lies in autonomous aircraft navigation. Managing non-cooperative traffic presents the most important challenge in this problem. The most efficient strategy for handling non-cooperative traffic is based on monocular video processing through deep learning models. This study contributes to the vision-based deep learning aircraft detection and tracking literature by investigating the impact of data corruption arising from environmental and hardware conditions on the effectiveness of these methods. More specifically, we designed $7$ types of common corruptions for camera inputs taking into account real-world flight conditions. By applying these corruptions to the Airborne Object Tracking (AOT) dataset we constructed the first robustness benchmark dataset named AOT-C for air-to-air aerial object detection. The corruptions included in this dataset cover a wide range of challenging conditions such as adverse weather and sensor noise. The second main contribution of this letter is to present an extensive experimental evaluation involving $8$ diverse object detectors to explore the degradation in the performance under escalating levels of corruptions (domain shifts). Based on the evaluation results, the key observations that emerge are the following: 1) One-stage detectors of the YOLO family demonstrate better robustness, 2) Transformer-based and multi-stage detectors like Faster R-CNN are extremely vulnerable to corruptions, 3) Robustness against corruptions is related to the generalization ability of models. The third main contribution is to present that finetuning on our augmented synthetic data results in improvements in the generalisation ability of the object detector in real-world flight experiments.
Authors: Guanyu Hu, Eleni Papadopoulou, Dimitrios Kollias, Paraskevi Tzouveli, Jie Wei, Xinyu Yang
Abstract: The increasing integration of machine learning algorithms in daily life underscores the critical need for fairness and equity in their deployment. As these technologies play a pivotal role in decision-making, addressing biases across diverse subpopulation groups, including age, gender, and race, becomes paramount. Automatic affect analysis, at the intersection of physiology, psychology, and machine learning, has seen significant development. However, existing databases and methodologies lack uniformity, leading to biased evaluations. This work addresses these issues by analyzing six affective databases, annotating demographic attributes, and proposing a common protocol for database partitioning. Emphasis is placed on fairness in evaluations. Extensive experiments with baseline and state-of-the-art methods demonstrate the impact of these changes, revealing the inadequacy of prior assessments. The findings underscore the importance of considering demographic attributes in affect analysis research and provide a foundation for more equitable methodologies. Our annotations, code and pre-trained models are available at: https://github.com/dkollias/Fair-Consistent-Affect-Analysis
URLs: https://github.com/dkollias/Fair-Consistent-Affect-Analysis
Authors: Zhiwei Wang, Jun Huang, Longhua Ma, Chengyu Wu, Hongyu Ma
Abstract: In visual tasks, large teacher models capture essential features and deep information, enhancing performance. However, distilling this information into smaller student models often leads to performance loss due to structural differences and capacity limitations. To tackle this, we propose a distillation framework based on graph knowledge, including a multi-level feature alignment strategy and an attention-guided mechanism to provide a targeted learning trajectory for the student model. We emphasize spectral embedding (SE) as a key technique in our distillation process, which merges the student's feature space with the relational knowledge and structural complexities similar to the teacher network. This method captures the teacher's understanding in a graph-based representation, enabling the student model to more accurately mimic the complex structural dependencies present in the teacher model. Compared to methods that focus only on specific distillation areas, our strategy not only considers key features within the teacher model but also endeavors to capture the relationships and interactions among feature sets, encoding these complex pieces of information into a graph structure to understand and utilize the dynamic relationships among these pieces of information from a global perspective. Experiments show that our method outperforms previous feature distillation methods on the CIFAR-100, MS-COCO, and Pascal VOC datasets, proving its efficiency and applicability.
Authors: Memoona Aziz, Umair Rehman, Muhammad Umair Danish, Katarina Grolinger
Abstract: This paper introduces the Global-Local Image Perceptual Score (GLIPS), an image metric designed to assess the photorealistic image quality of AI-generated images with a high degree of alignment to human visual perception. Traditional metrics such as FID and KID scores do not align closely with human evaluations. The proposed metric incorporates advanced transformer-based attention mechanisms to assess local similarity and Maximum Mean Discrepancy (MMD) to evaluate global distributional similarity. To evaluate the performance of GLIPS, we conducted a human study on photorealistic image quality. Comprehensive tests across various generative models demonstrate that GLIPS consistently outperforms existing metrics like FID, SSIM, and MS-SSIM in terms of correlation with human scores. Additionally, we introduce the Interpolative Binning Scale (IBS), a refined scaling method that enhances the interpretability of metric scores by aligning them more closely with human evaluative standards. The proposed metric and scaling approach not only provides more reliable assessments of AI-generated images but also suggest pathways for future enhancements in image generation technologies.
Authors: Vivian Lin, Kuk Jin Jang, Souradeep Dutta, Michele Caprio, Oleg Sokolsky, Insup Lee
Abstract: Deep neural networks have repeatedly been shown to be non-robust to the uncertainties of the real world, even to naturally occurring ones. A vast majority of current approaches have focused on data-augmentation methods to expand the range of perturbations that the classifier is exposed to while training. A relatively unexplored avenue that is equally promising involves sanitizing an image as a preprocessing step, depending on the nature of perturbation. In this paper, we propose to use control for learned models to recover from distribution shifts online. Specifically, our method applies a sequence of semantic-preserving transformations to bring the shifted data closer in distribution to the training set, as measured by the Wasserstein distance. Our approach is to 1) formulate the problem of distribution shift recovery as a Markov decision process, which we solve using reinforcement learning, 2) identify a minimum condition on the data for our method to be applied, which we check online using a binary classifier, and 3) employ dimensionality reduction through orthonormal projection to aid in our estimates of the Wasserstein distance. We provide theoretical evidence that orthonormal projection preserves characteristics of the data at the distributional level. We apply our distribution shift recovery approach to the ImageNet-C benchmark for distribution shifts, demonstrating an improvement in average accuracy of up to 14.21% across a variety of state-of-the-art ImageNet classifiers. We further show that our method generalizes to composites of shifts from the ImageNet-C benchmark, achieving improvements in average accuracy of up to 9.81%. Finally, we test our method on CIFAR-100-C and report improvements of up to 8.25%.
Authors: Arwa Al-Rubaian, Gozde N. Gunesli, Wajd A. Althakfi, Ayesha Azam, Nasir Rajpoot, Shan E Ahmed Raza
Abstract: Lung adenocarcinoma is a morphologically heterogeneous disease, characterized by five primary histologic growth patterns. The quantity of these patterns can be related to tumor behavior and has a significant impact on patient prognosis. In this work, we propose a novel machine learning pipeline capable of classifying tissue tiles into one of the five patterns or as non-tumor, with an Area Under the Receiver Operating Characteristic Curve (AUCROC) score of 0.97. Our model's strength lies in its comprehensive consideration of cellular spatial patterns, where it first generates cell maps from Hematoxylin and Eosin (H&E) whole slide images (WSIs), which are then fed into a convolutional neural network classification model. Exploiting these cell maps provides the model with robust generalizability to new data, achieving approximately 30% higher accuracy on unseen test-sets compared to current state of the art approaches. The insights derived from our model can be used to predict prognosis, enhancing patient outcomes.
Authors: Jos\'e Guilherme de Almeida, Nuno M. Rodrigues, Sara Silva, Nickolas Papanikolaou
Abstract: Deep learning models trained with large amounts of data have become a recent and effective approach to predictive problem solving -- these have become known as "foundation models" as they can be used as fundamental tools for other applications. While the paramount examples of image classification (earlier) and large language models (more recently) led the way, the Segment Anything Model (SAM) was recently proposed and stands as the first foundation model for image segmentation, trained on over 10 million images and with recourse to over 1 billion masks. However, the question remains -- what are the limits of this foundation? Given that magnetic resonance imaging (MRI) stands as an important method of diagnosis, we sought to understand whether SAM could be used for a few tasks of zero-shot segmentation using MRI data. Particularly, we wanted to know if selecting masks from the pool of SAM predictions could lead to good segmentations. Here, we provide a critical assessment of the performance of SAM on magnetic resonance imaging data. We show that, while acceptable in a very limited set of cases, the overall trend implies that these models are insufficient for MRI segmentation across the whole volume, but can provide good segmentations in a few, specific slices. More importantly, we note that while foundation models trained on natural images are set to become key aspects of predictive modelling, they may prove ineffective when used on other imaging modalities.
Authors: Yuwei Sun, Ippei Fujisawa, Arthur Juliani, Jun Sakuma, Ryota Kanai
Abstract: Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task identity information during inference and cannot eliminate interference among different tasks, while soft parameter sharing approaches encounter the problem of an increasing model parameter size. To tackle these challenges, we propose the Remembering Transformer, inspired by the brain's Complementary Learning Systems (CLS). Remembering Transformer employs a mixture-of-adapters architecture and a generative model-based novelty detection mechanism in a pretrained Transformer to alleviate CF. Remembering Transformer dynamically routes task data to the most relevant adapter with enhanced parameter efficiency based on knowledge distillation. We conducted extensive experiments, including ablation studies on the novelty detection mechanism and model capacity of the mixture-of-adapters, in a broad range of class-incremental split tasks and permutation tasks. Our approach demonstrated SOTA performance surpassing the second-best method by 15.90% in the split tasks, reducing the memory footprint from 11.18M to 0.22M in the five splits CIFAR10 task.
Authors: Shihao Zhang, kenji kawaguchi, Angela Yao
Abstract: Most works studying representation learning focus only on classification and neglect regression. Yet, the learning objectives and, therefore, the representation topologies of the two tasks are fundamentally different: classification targets class separation, leading to disconnected representations, whereas regression requires ordinality with respect to the target, leading to continuous representations. We thus wonder how the effectiveness of a regression representation is influenced by its topology, with evaluation based on the Information Bottleneck (IB) principle. The IB principle is an important framework that provides principles for learning effective representations. We establish two connections between it and the topology of regression representations. The first connection reveals that a lower intrinsic dimension of the feature space implies a reduced complexity of the representation Z. This complexity can be quantified as the conditional entropy of Z on the target Y, and serves as an upper bound on the generalization error. The second connection suggests a feature space that is topologically similar to the target space will better align with the IB principle. Based on these two connections, we introduce PH-Reg, a regularizer specific to regression that matches the intrinsic dimension and topology of the feature space with the target space. Experiments on synthetic and real-world regression tasks demonstrate the benefits of PH-Reg. Code: https://github.com/needylove/PH-Reg.
Authors: Kristina P. Sinaga
Abstract: In this paper, we show two new variants of multi-view k-means (MVKM) algorithms to address multi-view data. The general idea is to outline the distance between $h$-th view data points $x_i^h$ and $h$-th view cluster centers $a_k^h$ in a different manner of centroid-based approach. Unlike other methods, our proposed methods learn the multi-view data by calculating the similarity using Euclidean norm in the space of Gaussian-kernel, namely as multi-view k-means with exponent distance (MVKM-ED). By simultaneously aligning the stabilizer parameter $p$ and kernel coefficients $\beta^h$, the compression of Gaussian-kernel based weighted distance in Euclidean norm reduce the sensitivity of MVKM-ED. To this end, this paper designated as Gaussian-kernel multi-view k-means (GKMVKM) clustering algorithm. Numerical evaluation of five real-world multi-view data demonstrates the robustness and efficiency of our proposed MVKM-ED and GKMVKM approaches.
Authors: Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang
Abstract: A recent study by De et al. (2022) has reported that large-scale representation learning through pre-training on a public dataset significantly enhances differentially private (DP) learning in downstream tasks, despite the high dimensionality of the feature space. To theoretically explain this phenomenon, we consider the setting of a layer-peeled model in representation learning, which results in interesting phenomena related to learned features in deep learning and transfer learning, known as Neural Collapse (NC). Within the framework of NC, we establish an error bound indicating that the misclassification error is independent of dimension when the distance between actual features and the ideal ones is smaller than a threshold. Additionally, the quality of the features in the last layer is empirically evaluated under different pre-trained models within the framework of NC, showing that a more powerful transformer leads to a better feature representation. Furthermore, we reveal that DP fine-tuning is less robust compared to fine-tuning without DP, particularly in the presence of perturbations. These observations are supported by both theoretical analyses and experimental evaluation. Moreover, to enhance the robustness of DP fine-tuning, we suggest several strategies, such as feature normalization or employing dimension reduction methods like Principal Component Analysis (PCA). Empirically, we demonstrate a significant improvement in testing accuracy by conducting PCA on the last-layer features.
Authors: Chengyu Wu, Chengkai Wang, Yaqi Wang, Huiyu Zhou, Yatao Zhang, Qifeng Wang, Shuai Wang
Abstract: Esophageal cancer is one of the most common types of cancer worldwide and ranks sixth in cancer-related mortality. Accurate computer-assisted diagnosis of cancer progression can help physicians effectively customize personalized treatment plans. Currently, CT-based cancer diagnosis methods have received much attention for their comprehensive ability to examine patients' conditions. However, multi-modal based methods may likely introduce information redundancy, leading to underperformance. In addition, efficient and effective interactions between multi-modal representations need to be further explored, lacking insightful exploration of prognostic correlation in multi-modality features. In this work, we introduce a multi-modal heterogeneous graph-based conditional feature-guided diffusion model for lymph node metastasis diagnosis based on CT images as well as clinical measurements and radiomics data. To explore the intricate relationships between multi-modal features, we construct a heterogeneous graph. Following this, a conditional feature-guided diffusion approach is applied to eliminate information redundancy. Moreover, we propose a masked relational representation learning strategy, aiming to uncover the latent prognostic correlations and priorities of primary tumor and lymph node image representations. Various experimental results validate the effectiveness of our proposed method. The code is available at https://github.com/wuchengyu123/MMFusion.