Authors: Mehdi Maboudi, Jan Backhaus, Yahya Ghassoun, Yogesh Khedar, Dirk Lowke, Inka Mai, Bjoern Riedel, Ulf Bestmann, Markus Gerke
Abstract: Accurate and efficient structural health monitoring of infrastructure objects such as bridges is a vital task, as many existing constructions have already reached or are approaching their planned service life. In this contribution, we address the question of the suitability of UAV-based monitoring for SHM, in particular focusing on the geometric deformation under load. Such an advanced technology is becoming increasingly popular due to its ability to decrease the cost and risk of tedious traditional inspection methods. To this end, we performed extensive tests employing a research reinforced concrete bridge that can be exposed to a predefined load via ground anchors. Very high-resolution image blocks have been captured before, during, and after the application of controlled loads. From those images, the motion of distinct points on the bridge has been monitored, and in addition, dense image point clouds were computed to evaluate the performance of surface-based data acquisition. Moreover, a geodetic control network in stable regions is used as control information for bundle adjustment. We applied different sensing technologies in order to be able to judge the image-based deformation results: displacement transducers, tachymetry, and laser profiling. As a platform for the photogrammetric measurements, a multi-rotor UAV DJI Matrice 600 Pro was employed, equipped with two RTK-GNSS receivers. The mounted camera was a PhaseOne iXM-100 (100MP) with an 80 mm lens. With a flying height of 30 m above the terrain, this resulted in a GSD of 1.3 mm while a forward and sideward overlap of 80% was maintained. The comparison with reference data (displacement transducers) reveals a difference of less than 1 mm. We show that by employing the introduced UAV-based monitoring approach, a full area-wide quantification of deformation is possible in contrast to classical point or profile measurements.
Authors: Hayata Morita, Kohei Shintani, Chenyang Yuan, Frank Permenter
Abstract: A main challenge in mechanical design is to efficiently explore the design space while satisfying engineering constraints. This work explores the use of 3D generative models to explore the design space in the context of vehicle development, while estimating and enforcing engineering constraints. Specifically, we generate diverse 3D models of cars that meet a given set of geometric specifications, while also obtaining quick estimates of performance parameters such as aerodynamic drag. For this, we employ a data-driven approach (using the ShapeNet dataset) to train VehicleSDF, a DeepSDF based model that represents potential designs in a latent space witch can be decoded into a 3D model. We then train surrogate models to estimate engineering parameters from this latent space representation, enabling us to efficiently optimize latent vectors to match specifications. Our experiments show that we can generate diverse 3D models while matching the specified geometric parameters. Finally, we demonstrate that other performance parameters such as aerodynamic drag can be estimated in a differentiable pipeline.
Authors: Ernst R\"oell, Bastian Rieck
Abstract: The Euler Characteristic Transform (ECT) is a powerful invariant for assessing geometrical and topological characteristics of a large variety of objects, including graphs and embedded simplicial complexes. Although the ECT is invertible in theory, no explicit algorithm for general data sets exists. In this paper, we address this lack and demonstrate that it is possible to learn the inversion, permitting us to develop a novel framework for shape generation tasks on point clouds. Our model exhibits high quality in reconstruction and generation tasks, affords efficient latent-space interpolation, and is orders of magnitude faster than existing methods.
Authors: Lingxiao Li, Kaixiong Gong, Weihong Li, Xili Dai, Tao Chen, Xiaojun Yuan, Xiangyu Yue
Abstract: This paper introduces Bifr\"ost, a novel 3D-aware framework that is built upon diffusion models to perform instruction-based image composition. Previous methods concentrate on image compositing at the 2D level, which fall short in handling complex spatial relationships ($\textit{e.g.}$, occlusion). Bifr\"ost addresses these issues by training MLLM as a 2.5D location predictor and integrating depth maps as an extra condition during the generation process to bridge the gap between 2D and 3D, which enhances spatial comprehension and supports sophisticated spatial interactions. Our method begins by fine-tuning MLLM with a custom counterfactual dataset to predict 2.5D object locations in complex backgrounds from language instructions. Then, the image-compositing model is uniquely designed to process multiple types of input features, enabling it to perform high-fidelity image compositions that consider occlusion, depth blur, and image harmonization. Extensive qualitative and quantitative evaluations demonstrate that Bifr\"ost significantly outperforms existing methods, providing a robust solution for generating realistically composed images in scenarios demanding intricate spatial understanding. This work not only pushes the boundaries of generative image compositing but also reduces reliance on expensive annotated datasets by effectively utilizing existing resources in innovative ways.
Authors: Serap A. Savari
Abstract: Sampling and quantization are standard practices in signal and image processing, but a theoretical understanding of their impact is incomplete. We consider discrete image registration when the underlying function is a one-dimensional spatially-limited piecewise constant function. For ideal noiseless sampling the number of samples from each region of the support of the function generally depends on the placement of the sampling grid. Therefore, if the samples of the function are noisy, then image registration requires alignment and segmentation of the data sequences. One popular strategy for aligning images is selecting the maximum from cross-correlation template matching. To motivate more robust and accurate approaches which also address segmentation, we provide an example of a one-dimensional spatially-limited piecewise constant function for which the cross-correlation technique can perform poorly on noisy samples. While earlier approaches to improve the method involve normalization, our example suggests a novel strategy in our setting. Difference sequences, thresholding, and dynamic programming are well-known techniques in image processing. We prove that they are tools to correctly align and segment noisy data sequences under some conditions on the noise. We also address some of the potential difficulties that could arise in a more general case.
Authors: Lawrence Jang, Yinheng Li, Charles Ding, Justin Lin, Paul Pu Liang, Dan Zhao, Rogerio Bonatti, Kazuhito Koishida
Abstract: Videos are often used to learn or extract the necessary information to complete tasks in ways different than what text and static imagery alone can provide. However, many existing agent benchmarks neglect long-context video understanding, instead focusing on text or static image inputs. To bridge this gap, we introduce VideoWebArena (VideoWA), a benchmark for evaluating the capabilities of long-context multimodal agents for video understanding. VideoWA consists of 2,021 web agent tasks based on manually crafted video tutorials, which total almost four hours of content. For our benchmark, we define a taxonomy of long-context video-based agent tasks with two main areas of focus: skill retention and factual retention. While skill retention tasks evaluate whether an agent can use a given human demonstration to complete a task efficiently, the factual retention task evaluates whether an agent can retrieve instruction-relevant information from a video to complete a task. We find that the best model achieves 13.3% success on factual retention tasks and 45.8% on factual retention QA pairs, far below human performance at 73.9% and 79.3%, respectively. On skill retention tasks, long-context models perform worse with tutorials than without, exhibiting a 5% performance decrease in WebArena tasks and a 10.3% decrease in VisualWebArena tasks. Our work highlights the need to improve the agentic abilities of long-context multimodal models and provides a testbed for future development with long-context video agents.
Authors: Ruicheng Wang, Sicheng Xu, Cassie Dai, Jianfeng Xiang, Yu Deng, Xin Tong, Jiaolong Yang
Abstract: We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is agnostic to true global scale and shift. This new representation precludes ambiguous supervision in training and facilitate effective geometry learning. Furthermore, we propose a set of novel global and local geometry supervisions that empower the model to learn high-quality geometry. These include a robust, optimal, and efficient point cloud alignment solver for accurate global shape learning, and a multi-scale local geometry loss promoting precise local geometry supervision. We train our model on a large, mixed dataset and demonstrate its strong generalizability and high accuracy. In our comprehensive evaluation on diverse unseen datasets, our model significantly outperforms state-of-the-art methods across all tasks, including monocular estimation of 3D point map, depth map, and camera field of view. Code and models will be released on our project page.
Authors: Abhirama Subramanyam Penamakuri, Anand Mishra
Abstract: We revisit knowledge-aware text-based visual question answering, also known as Text-KVQA, in the light of modern advancements in large multimodal models (LMMs), and make the following contributions: (i) We propose VisTEL - a principled approach to perform visual text entity linking. The proposed VisTEL module harnesses a state-of-the-art visual text recognition engine and the power of a large multimodal model to jointly reason using textual and visual context obtained using surrounding cues in the image to link the visual text entity to the correct knowledge base entity. (ii) We present KaLMA - a knowledge-aware large multimodal assistant that augments an LMM with knowledge associated with visual text entity in the image to arrive at an accurate answer. Further, we provide a comprehensive experimental analysis and comparison of our approach with traditional visual question answering, pre-large multimodal models, and large multimodal models, as well as prior top-performing approaches. Averaging over three splits of Text-KVQA, our proposed approach surpasses the previous best approach by a substantial 23.3% on an absolute scale and establishes a new state of the art. We make our implementation publicly available.
Authors: Burak Ercan, Onur Eker, Aykut Erdem, Erkut Erdem
Abstract: Low-light environments pose significant challenges for image enhancement methods. To address these challenges, in this work, we introduce the HUE dataset, a comprehensive collection of high-resolution event and frame sequences captured in diverse and challenging low-light conditions. Our dataset includes 106 sequences, encompassing indoor, cityscape, twilight, night, driving, and controlled scenarios, each carefully recorded to address various illumination levels and dynamic ranges. Utilizing a hybrid RGB and event camera setup. we collect a dataset that combines high-resolution event data with complementary frame data. We employ both qualitative and quantitative evaluations using no-reference metrics to assess state-of-the-art low-light enhancement and event-based image reconstruction methods. Additionally, we evaluate these methods on a downstream object detection task. Our findings reveal that while event-based methods perform well in specific metrics, they may produce false positives in practical applications. This dataset and our comprehensive analysis provide valuable insights for future research in low-light vision and hybrid camera systems.
Authors: Mahtab Ranjbar (Department of Mathematical and Computer Sciences, Kharazmi University), Mehdi Mohebbi (Department of Mathematical and Computer Sciences, Kharazmi University), Mahdi Cherakhloo (Department of Medical Engineering, Electrical Engineering Department, Sharif University of Technology), Bijan Vosoughi. Vahdat (Department of Medical Engineering, Electrical Engineering Department, Sharif University of Technology)
Abstract: In recent years, the integration of advanced imaging techniques and deep learning methods has significantly advanced computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Transformers, which have shown great promise in computer vision, are now being applied to medical image analysis. However, their application to histopathological images presents challenges due to the need for extensive manual annotations of whole-slide images (WSIs), as these models require large amounts of data to work effectively, which is costly and time-consuming. Furthermore, the quadratic computational cost of Vision Transformers (ViTs) is particularly prohibitive for large, high-resolution histopathological images, especially on edge devices with limited computational resources. In this study, we introduce a novel lightweight breast cancer classification approach using transformers that operates effectively without large datasets. By incorporating parallel processing pathways for Discrete Cosine Transform (DCT) Attention and MobileConv, we convert image data from the spatial domain to the frequency domain to utilize the benefits such as filtering out high frequencies in the image, which reduces computational cost. This demonstrates the potential of our approach to improve breast cancer classification in histopathological images, offering a more efficient solution with reduced reliance on extensive annotated datasets. Our proposed model achieves an accuracy of 96.00% $\pm$ 0.48% for binary classification and 87.85% $\pm$ 0.93% for multiclass classification, which is comparable to state-of-the-art models while significantly reducing computational costs. This demonstrates the potential of our approach to improve breast cancer classification in histopathological images, offering a more efficient solution with reduced reliance on extensive annotated datasets.
Authors: Xiaxia Wang, XueSong Leng, Guoping Xu
Abstract: The escalating significance of information security has underscored the per-vasive role of encryption technology in safeguarding communication con-tent. Morse code, a well-established and effective encryption method, has found widespread application in telegraph communication and various do-mains. However, the transmission of Morse code images faces challenges due to diverse noises and distortions, thereby hindering comprehensive clas-sification outcomes. Existing methodologies predominantly concentrate on categorizing Morse code images affected by a single type of noise, neglecting the multitude of scenarios that noise pollution can generate. To overcome this limitation, we propose a novel two-stage approach, termed the Noise Adaptation Network (NANet), for Morse code image classification. Our method involves exclusive training on pristine images while adapting to noisy ones through the extraction of critical information unaffected by noise. In the initial stage, we introduce a U-shaped network structure designed to learn representative features and denoise images. Subsequently, the second stage employs a deep convolutional neural network for classification. By leveraging the denoising module from the first stage, our approach achieves enhanced accuracy and robustness in the subsequent classification phase. We conducted an evaluation of our approach on a diverse dataset, encom-passing Gaussian, salt-and-pepper, and uniform noise variations. The results convincingly demonstrate the superiority of our methodology over existing approaches. The datasets are available on https://github.com/apple1986/MorseCodeImageClassify
Authors: Yuan Huang, Valentin De Bortoli, Fugen Zhou, Jerome Gilles
Abstract: Wavelet-based segmentation approaches are widely used for texture segmentation purposes because of their ability to characterize different textures. In this paper, we assess the influence of the chosen wavelet and propose to use the recently introduced empirical wavelets. We show that the adaptability of the empirical wavelet permits to reach better results than classic wavelets. In order to focus only on the textural information, we also propose to perform a cartoon + texture decomposition step before applying the segmentation algorithm. The proposed method is tested on six classic benchmarks, based on several popular texture images.
Authors: Kal Backman, Ben Beck, Dana Kuli\'c
Abstract: While cycling offers an attractive option for sustainable transportation, many potential cyclists are discouraged from taking up cycling due to the lack of suitable and safe infrastructure. Efficiently mapping cycling infrastructure across entire cities is necessary to advance our understanding of how to provide connected networks of high-quality infrastructure. Therefore we propose a system capable of classifying available cycling infrastructure from on-bike smartphone camera data. The system receives an image sequence as input, temporally analyzing the sequence to account for sparsity of signage. The model outputs cycling infrastructure class labels defined by a hierarchical classification system. Data is collected via participant cyclists covering 7,006Km across the Greater Melbourne region that is automatically labeled via a GPS and OpenStreetMap database matching algorithm. The proposed model achieved an accuracy of 95.38%, an increase in performance of 7.55% compared to the non-temporal model. The model demonstrated robustness to extreme absence of image features where the model lost only 6.6% in accuracy after 90% of images being replaced with blank images. This work is the first to classify cycling infrastructure using only street-level imagery collected from bike-mounted mobile phone cameras, while demonstrating robustness to feature sparsity via long temporal sequence analysis.
Authors: Haiyang Zheng, Nan Pu, Wenjing Li, Nicu Sebe, Zhun Zhong
Abstract: In this paper, we study a practical yet challenging task, On-the-fly Category Discovery (OCD), aiming to online discover the newly-coming stream data that belong to both known and unknown classes, by leveraging only known category knowledge contained in labeled data. Previous OCD methods employ the hash-based technique to represent old/new categories by hash codes for instance-wise inference. However, directly mapping features into low-dimensional hash space not only inevitably damages the ability to distinguish classes and but also causes "high sensitivity" issue, especially for fine-grained classes, leading to inferior performance. To address these issues, we propose a novel Prototypical Hash Encoding (PHE) framework consisting of Category-aware Prototype Generation (CPG) and Discriminative Category Encoding (DCE) to mitigate the sensitivity of hash code while preserving rich discriminative information contained in high-dimension feature space, in a two-stage projection fashion. CPG enables the model to fully capture the intra-category diversity by representing each category with multiple prototypes. DCE boosts the discrimination ability of hash code with the guidance of the generated category prototypes and the constraint of minimum separation distance. By jointly optimizing CPG and DCE, we demonstrate that these two components are mutually beneficial towards an effective OCD. Extensive experiments show the significant superiority of our PHE over previous methods, e.g., obtaining an improvement of +5.3% in ALL ACC averaged on all datasets. Moreover, due to the nature of the interpretable prototypes, we visually analyze the underlying mechanism of how PHE helps group certain samples into either known or unknown categories. Code is available at https://github.com/HaiyangZheng/PHE.
Authors: Pengcheng Zhang, Xiaohan Yu, Xiao Bai, Jin Zheng, Xin Ning
Abstract: The development of person search techniques has been greatly promoted in recent years for its superior practicality and challenging goals. Despite their significant progress, existing person search models still lack the ability to continually learn from increaseing real-world data and adaptively process input from different domains. To this end, this work introduces the continual person search task that sequentially learns on multiple domains and then performs person search on all seen domains. This requires balancing the stability and plasticity of the model to continually learn new knowledge without catastrophic forgetting. For this, we propose a Prompt-based Continual Person Search (PoPS) model in this paper. First, we design a compositional person search transformer to construct an effective pre-trained transformer without exhaustive pre-training from scratch on large-scale person search data. This serves as the fundamental for prompt-based continual learning. On top of that, we design a domain incremental prompt pool with a diverse attribute matching module. For each domain, we independently learn a set of prompts to encode the domain-oriented knowledge. Meanwhile, we jointly learn a group of diverse attribute projections and prototype embeddings to capture discriminative domain attributes. By matching an input image with the learned attributes across domains, the learned prompts can be properly selected for model inference. Extensive experiments are conducted to validate the proposed method for continual person search. The source code is available at https://github.com/PatrickZad/PoPS.
Authors: Xingyu Zhu, Beier Zhu, Yi Tan, Shuo Wang, Yanbin Hao, Hanwang Zhang
Abstract: Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data has proven effective in improving performance, these methods entail labor costs for annotations and are limited by their quality. Additionally, since CLIP is pre-trained on highly imbalanced Web-scale data, it suffers from inherent label bias that leads to suboptimal performance. To tackle the above challenges, we propose a label-Free prompt distribution learning and bias correction framework, dubbed as **Frolic**, which boosts zero-shot performance without the need for labeled data. Specifically, our Frolic learns distributions over prompt prototypes to capture diverse visual representations and adaptively fuses these with the original CLIP through confidence matching. This fused model is further enhanced by correcting label bias via a label-free logit adjustment. Notably, our method is not only training-free but also circumvents the necessity for hyper-parameter tuning. Extensive experimental results across 16 datasets demonstrate the efficacy of our approach, particularly outperforming the state-of-the-art by an average of $2.6\%$ on 10 datasets with CLIP ViT-B/16 and achieving an average margin of $1.5\%$ on ImageNet and its five distribution shifts with CLIP ViT-B/16. Codes are available in https://github.com/zhuhsingyuu/Frolic.
Authors: Zhengyang Lu, Tianhao Guo, Feng Wang
Abstract: Classical Chinese poetry and painting represent the epitome of artistic expression, but the abstract and symbolic nature of their relationship poses a significant challenge for computational translation. Most existing methods rely on large-scale paired datasets, which are scarce in this domain. In this work, we propose a semi-supervised approach using cycle-consistent adversarial networks to leverage the limited paired data and large unpaired corpus of poems and paintings. The key insight is to learn bidirectional mappings that enforce semantic alignment between the visual and textual modalities. We introduce novel evaluation metrics to assess the quality, diversity, and consistency of the generated poems and paintings. Extensive experiments are conducted on a new Chinese Painting Description Dataset (CPDD). The proposed model outperforms previous methods, showing promise in capturing the symbolic essence of artistic expression. Codes are available online \url{https://github.com/Mnster00/poemtopainting}.
Authors: Zemin Huang, Zhengyang Geng, Weijian Luo, Guo-jun Qi
Abstract: In the realm of Artificial Intelligence Generated Content (AIGC), flow-matching models have emerged as a powerhouse, achieving success due to their robust theoretical underpinnings and solid ability for large-scale generative modeling. These models have demonstrated state-of-the-art performance, but their brilliance comes at a cost. The process of sampling from these models is notoriously demanding on computational resources, as it necessitates the use of multi-step numerical ordinary differential equations (ODEs). Against this backdrop, this paper presents a novel solution with theoretical guarantees in the form of Flow Generator Matching (FGM), an innovative approach designed to accelerate the sampling of flow-matching models into a one-step generation, while maintaining the original performance. On the CIFAR10 unconditional generation benchmark, our one-step FGM model achieves a new record Fr\'echet Inception Distance (FID) score of 3.08 among few-step flow-matching-based models, outperforming original 50-step flow-matching models. Furthermore, we use the FGM to distill the Stable Diffusion 3, a leading text-to-image flow-matching model based on the MM-DiT architecture. The resulting MM-DiT-FGM one-step text-to-image model demonstrates outstanding industry-level performance. When evaluated on the GenEval benchmark, MM-DiT-FGM has delivered remarkable generating qualities, rivaling other multi-step models in light of the efficiency of a single generation step.
Authors: Emiel Hoogeboom, Thomas Mensink, Jonathan Heek, Kay Lamerigts, Ruiqi Gao, Tim Salimans
Abstract: Latent diffusion models have become the popular choice for scaling up diffusion models for high resolution image synthesis. Compared to pixel-space models that are trained end-to-end, latent models are perceived to be more efficient and to produce higher image quality at high resolution. Here we challenge these notions, and show that pixel-space models can in fact be very competitive to latent approaches both in quality and efficiency, achieving 1.5 FID on ImageNet512 and new SOTA results on ImageNet128 and ImageNet256. We present a simple recipe for scaling end-to-end pixel-space diffusion models to high resolutions. 1: Use the sigmoid loss (Kingma & Gao, 2023) with our prescribed hyper-parameters. 2: Use our simplified memory-efficient architecture with fewer skip-connections. 3: Scale the model to favor processing the image at high resolution with fewer parameters, rather than using more parameters but at a lower resolution. When combining these three steps with recently proposed tricks like guidance intervals, we obtain a family of pixel-space diffusion models we call Simple Diffusion v2 (SiD2).
Authors: Muhammad Zaeem Shahzad, Muhammad Abdullah Hanif, Muhammad Shafique
Abstract: The proliferation of smartphones and other mobile devices provides a unique opportunity to make Advanced Driver Assistance Systems (ADAS) accessible to everyone in the form of an application empowered by low-cost Machine/Deep Learning (ML/DL) models to enhance road safety. For the critical feature of Collision Avoidance in Mobile ADAS, lightweight Deep Neural Networks (DNN) for object detection exist, but conventional pixel-wise depth/distance estimation DNNs are vastly more computationally expensive making them unsuitable for a real-time application on resource-constrained devices. In this paper, we present a distance estimation model, DECADE, that processes each detector output instead of constructing pixel-wise depth/disparity maps. In it, we propose a pose estimation DNN to estimate allocentric orientation of detections to supplement the distance estimation DNN in its prediction of distance using bounding box features. We demonstrate that these modules can be attached to any detector to extend object detection with fast distance estimation. Evaluation of the proposed modules with attachment to and fine-tuning on the outputs of the YOLO object detector on the KITTI 3D Object Detection dataset achieves state-of-the-art performance with 1.38 meters in Mean Absolute Error and 7.3% in Mean Relative Error in the distance range of 0-150 meters. Our extensive evaluation scheme not only evaluates class-wise performance, but also evaluates range-wise accuracy especially in the critical range of 0-70m.
Authors: Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao, Ziwei Liu, Kwan-Yee K. Wong
Abstract: In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that \textit{directly reusing adjacent-step features degrades video quality due to the loss of subtle variations}. We further perform a pioneering investigation of the acceleration potential of classifier-free guidance (CFG) and reveal significant redundancy between conditional and unconditional features within the same timestep. Capitalizing on these observations, we introduce FasterCache to substantially accelerate diffusion-based video generation. Our key contributions include a dynamic feature reuse strategy that preserves both feature distinction and temporal continuity, and CFG-Cache which optimizes the reuse of conditional and unconditional outputs to further enhance inference speed without compromising video quality. We empirically evaluate FasterCache on recent video diffusion models. Experimental results show that FasterCache can significantly accelerate video generation (\eg 1.67$\times$ speedup on Vchitect-2.0) while keeping video quality comparable to the baseline, and consistently outperform existing methods in both inference speed and video quality.
Authors: Lakshmi Srinivas Panchananam, Praveen Kumar Chandaliya, Kishor Upla, Kiran Raja
Abstract: Abnormalities in the gastrointestinal tract significantly influence the patient's health and require a timely diagnosis for effective treatment. With such consideration, an effective automatic classification of these abnormalities from a video capsule endoscopy (VCE) frame is crucial for improvement in diagnostic workflows. The work presents the process of developing and evaluating a novel model designed to classify gastrointestinal anomalies from a VCE video frame. Integration of Omni Dimensional Gated Attention (OGA) mechanism and Wavelet transformation techniques into the model's architecture allowed the model to focus on the most critical areas in the endoscopy images, reducing noise and irrelevant features. This is particularly advantageous in capsule endoscopy, where images often contain a high degree of variability in texture and color. Wavelet transformations contributed by efficiently capturing spatial and frequency-domain information, improving feature extraction, especially for detecting subtle features from the VCE frames. Furthermore, the features extracted from the Stationary Wavelet Transform and Discrete Wavelet Transform are concatenated channel-wise to capture multiscale features, which are essential for detecting polyps, ulcerations, and bleeding. This approach improves classification accuracy on imbalanced capsule endoscopy datasets. The proposed model achieved 92.76% and 91.19% as training and validation accuracies respectively. At the same time, Training and Validation losses are 0.2057 and 0.2700. The proposed model achieved a Balanced Accuracy of 94.81%, AUC of 87.49%, F1-score of 91.11%, precision of 91.17%, recall of 91.19% and specificity of 98.44%. Additionally, the model's performance is benchmarked against two base models, VGG16 and ResNet50, demonstrating its enhanced ability to identify and classify a range of gastrointestinal abnormalities accurately.
Authors: Reuben Dorent, Nazim Haouchine, Alexandra Golby, Sarah Frisken, Tina Kapur, William Wells
Abstract: We propose a deep mixture of multimodal hierarchical variational auto-encoders called MMHVAE that synthesizes missing images from observed images in different modalities. MMHVAE's design focuses on tackling four challenges: (i) creating a complex latent representation of multimodal data to generate high-resolution images; (ii) encouraging the variational distributions to estimate the missing information needed for cross-modal image synthesis; (iii) learning to fuse multimodal information in the context of missing data; (iv) leveraging dataset-level information to handle incomplete data sets at training time. Extensive experiments are performed on the challenging problem of pre-operative brain multi-parametric magnetic resonance and intra-operative ultrasound imaging.
Authors: Yuekun Dai, Qinyue Li, Shangchen Zhou, Yihang Luo, Chongyi Li, Chen Change Loy
Abstract: Line art colorization plays a crucial role in hand-drawn animation production, where digital artists manually colorize segments using a paint bucket tool, guided by RGB values from character color design sheets. This process, often called paint bucket colorization, involves two main tasks: keyframe colorization, where colors are applied according to the character's color design sheet, and consecutive frame colorization, where these colors are replicated across adjacent frames. Current automated colorization methods primarily focus on reference-based and segment-matching approaches. However, reference-based methods often fail to accurately assign specific colors to each region, while matching-based methods are limited to consecutive frame colorization and struggle with issues like significant deformation and occlusion. In this work, we introduce inclusion matching, which allows the network to understand the inclusion relationships between segments, rather than relying solely on direct visual correspondences. By integrating this approach with segment parsing and color warping modules, our inclusion matching pipeline significantly improves performance in both keyframe colorization and consecutive frame colorization. To support our network's training, we have developed a unique dataset named PaintBucket-Character, which includes rendered line arts alongside their colorized versions and shading annotations for various 3D characters. To replicate industry animation data formats, we also created color design sheets for each character, with semantic information for each color and standard pose reference images. Experiments highlight the superiority of our method, demonstrating accurate and consistent colorization across both our proposed benchmarks and hand-drawn animations.
Authors: Francesc Net, Marc Folia, Pep Casals, Lluis Gomez
Abstract: This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.
Authors: Syed Sameen Ahmad Rizvi, Aryan Seth, Pratik Narang
Abstract: Automatically recognizing emotional intent using facial expression has been a thoroughly investigated topic in the realm of computer vision. Facial Expression Recognition (FER), being a supervised learning task, relies heavily on substantially large data exemplifying various socio-cultural demographic attributes. Over the past decade, several real-world in-the-wild FER datasets that have been proposed were collected through crowd-sourcing or web-scraping. However, most of these practically used datasets employ a manual annotation methodology for labeling emotional intent, which inherently propagates individual demographic biases. Moreover, these datasets also lack an equitable representation of various socio-cultural demographic groups, thereby inducing a class imbalance. Bias analysis and its mitigation have been investigated across multiple domains and problem settings, however, in the FER domain, this is a relatively lesser explored area. This work leverages representation learning based on latent spaces to mitigate bias in facial expression recognition systems, thereby enhancing a deep learning model's fairness and overall accuracy.
Authors: Yao Wu, Mingwei Xing, Yachao Zhang, Yuan Xie, Yanyun Qu
Abstract: In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mutually mimic cross-modal outputs in each domain, which enforces a class probability distribution that is agreeable in different domains. However, they overlook the complementarity brought by the heterogeneous fusion in cross-modal learning. In light of this, we propose a novel fusion-then-distillation (FtD++) method to explore cross-modal positive distillation of the source and target domains for 3D semantic segmentation. FtD++ realizes distribution consistency between outputs not only for 2D images and 3D point clouds but also for source-domain and augment-domain. Specially, our method contains three key ingredients. First, we present a model-agnostic feature fusion module to generate the cross-modal fusion representation for establishing a latent space. In this space, two modalities are enforced maximum correlation and complementarity. Second, the proposed cross-modal positive distillation preserves the complete information of multi-modal input and combines the semantic content of the source domain with the style of the target domain, thereby achieving domain-modality alignment. Finally, cross-modal debiased pseudo-labeling is devised to model the uncertainty of pseudo-labels via a self-training manner. Extensive experiments report state-of-the-art results on several domain adaptive scenarios under unsupervised and semi-supervised settings. Code is available at https://github.com/Barcaaaa/FtD-PlusPlus.
Authors: Nuthan Mummani, Simran Ketha, Venkatakrishnan Ramaswamy
Abstract: In the supervised classification setting, during inference, deep networks typically make multiple predictions. For a pair of such predictions (that are in the top-k predictions), two distinct possibilities might occur. On the one hand, each of the two predictions might be primarily driven by two distinct sets of entities in the input. On the other hand, it is possible that there is a single entity or set of entities that is driving the prediction for both the classes in question. This latter case, in effect, corresponds to the network making two separate guesses about the identity of a single entity type. Clearly, both the guesses cannot be true, i.e. both the labels cannot be present in the input. Current techniques in interpretability research do not readily disambiguate these two cases, since they typically consider input attributions for one class label at a time. Here, we present a framework and method to do so, leveraging modern segmentation and input attribution techniques. Notably, our framework also provides a simple counterfactual "proof" of each case, which can be verified for the input on the model (i.e. without running the method again). We demonstrate that the method performs well for a number of samples from the ImageNet validation set and on multiple models.
Authors: Weihang Liu, Xue Xian Zheng, Jingyi Yu, Xin Lou
Abstract: The recent popular radiance field models, exemplified by Neural Radiance Fields (NeRF), Instant-NGP and 3D Gaussian Splat?ting, are designed to represent 3D content by that training models for each individual scene. This unique characteristic of scene representation and per-scene training distinguishes radiance field models from other neural models, because complex scenes necessitate models with higher representational capacity and vice versa. In this paper, we propose content?aware radiance fields, aligning the model complexity with the scene intricacies through Adversarial Content-Aware Quantization (A-CAQ). Specifically, we make the bitwidth of parameters differentiable and train?able, tailored to the unique characteristics of specific scenes and requirements. The proposed framework has been assessed on Instant-NGP, a well-known NeRF variant and evaluated using various datasets. Experimental results demonstrate a notable reduction in computational complexity, while preserving the requisite reconstruction and rendering quality, making it beneficial for practical deployment of radiance fields models. Codes are available at https://github.com/WeihangLiu2024/Content_Aware_NeRF.
Authors: Vivek Parmar, Dwijay Bane, Syed Shakib Sarwar, Kleber Stangherlin, Barbara De Salvo, Manan Suri
Abstract: With the emergence of the Metaverse and focus on wearable devices in the recent years gesture based human-computer interaction has gained significance. To enable gesture recognition for VR/AR headsets and glasses several datasets focusing on egocentric i.e. first-person view have emerged in recent years. However, standard frame-based vision suffers from limitations in data bandwidth requirements as well as ability to capture fast motions. To overcome these limitation bio-inspired approaches such as event-based cameras present an attractive alternative. In this work, we present the first event-camera based egocentric gesture dataset for enabling neuromorphic, low-power solutions for XR-centric gesture recognition. The dataset has been made available publicly at the following URL: https://gitlab.com/NVM_IITD_Research/xrage.
Authors: Xin Shen, Heming Du, Hongwei Sheng, Shuyun Wang, Hui Chen, Huiqiang Chen, Zhuojie Wu, Xiaobiao Du, Jiaying Ying, Ruihan Lu, Qingzheng Xu, Xin Yu
Abstract: Isolated Sign Language Recognition (ISLR) focuses on identifying individual sign language glosses. Considering the diversity of sign languages across geographical regions, developing region-specific ISLR datasets is crucial for supporting communication and research. Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale word-level dataset for the ISLR task. To fill this gap, we curate \underline{\textbf{the first}} large-scale Multi-view Multi-modal Word-Level Australian Sign Language recognition dataset, dubbed MM-WLAuslan. Compared to other publicly available datasets, MM-WLAuslan exhibits three significant advantages: (1) the largest amount of data, (2) the most extensive vocabulary, and (3) the most diverse of multi-modal camera views. Specifically, we record 282K+ sign videos covering 3,215 commonly used Auslan glosses presented by 73 signers in a studio environment. Moreover, our filming system includes two different types of cameras, i.e., three Kinect-V2 cameras and a RealSense camera. We position cameras hemispherically around the front half of the model and simultaneously record videos using all four cameras. Furthermore, we benchmark results with state-of-the-art methods for various multi-modal ISLR settings on MM-WLAuslan, including multi-view, cross-camera, and cross-view. Experiment results indicate that MM-WLAuslan is a challenging ISLR dataset, and we hope this dataset will contribute to the development of Auslan and the advancement of sign languages worldwide. All datasets and benchmarks are available at MM-WLAuslan.
Authors: Hosam Elgendy, Ahmed Sharshar, Ahmed Aboeitta, Yasser Ashraf, Mohsen Guizani
Abstract: Detecting temporal changes in geographical landscapes is critical for applications like environmental monitoring and urban planning. While remote sensing data is abundant, existing vision-language models (VLMs) often fail to capture temporal dynamics effectively. This paper addresses these limitations by introducing an annotated dataset of video frame pairs to track evolving geographical patterns over time. Using fine-tuning techniques like Low-Rank Adaptation (LoRA), quantized LoRA (QLoRA), and model pruning on models such as Video-LLaVA and LLaVA-NeXT-Video, we significantly enhance VLM performance in processing remote sensing temporal changes. Results show significant improvements, with the best performance achieving a BERT score of 0.864 and ROUGE-1 score of 0.576, demonstrating superior accuracy in describing land-use transformations.
Authors: Rajat Modi, Vibhav Vineet, Yogesh Singh Rawat
Abstract: This paper explores the impact of occlusions in video action detection. We facilitate this study by introducing five new benchmark datasets namely O-UCF and O-JHMDB consisting of synthetically controlled static/dynamic occlusions, OVIS-UCF and OVIS-JHMDB consisting of occlusions with realistic motions and Real-OUCF for occlusions in realistic-world scenarios. We formally confirm an intuitive expectation: existing models suffer a lot as occlusion severity is increased and exhibit different behaviours when occluders are static vs when they are moving. We discover several intriguing phenomenon emerging in neural nets: 1) transformers can naturally outperform CNN models which might have even used occlusion as a form of data augmentation during training 2) incorporating symbolic-components like capsules to such backbones allows them to bind to occluders never even seen during training and 3) Islands of agreement can emerge in realistic images/videos without instance-level supervision, distillation or contrastive-based objectives2(eg. video-textual training). Such emergent properties allow us to derive simple yet effective training recipes which lead to robust occlusion models inductively satisfying the first two stages of the binding mechanism (grouping/segregation). Models leveraging these recipes outperform existing video action-detectors under occlusion by 32.3% on O-UCF, 32.7% on O-JHMDB & 2.6% on Real-OUCF in terms of the vMAP metric. The code for this work has been released at https://github.com/rajatmodi62/OccludedActionBenchmark.
URLs: https://github.com/rajatmodi62/OccludedActionBenchmark.
Authors: Shentong Mo, Shengbang Tong
Abstract: In recent advancements in unsupervised visual representation learning, the Joint-Embedding Predictive Architecture (JEPA) has emerged as a significant method for extracting visual features from unlabeled imagery through an innovative masking strategy. Despite its success, two primary limitations have been identified: the inefficacy of Exponential Moving Average (EMA) from I-JEPA in preventing entire collapse and the inadequacy of I-JEPA prediction in accurately learning the mean of patch representations. Addressing these challenges, this study introduces a novel framework, namely C-JEPA (Contrastive-JEPA), which integrates the Image-based Joint-Embedding Predictive Architecture with the Variance-Invariance-Covariance Regularization (VICReg) strategy. This integration is designed to effectively learn the variance/covariance for preventing entire collapse and ensuring invariance in the mean of augmented views, thereby overcoming the identified limitations. Through empirical and theoretical evaluations, our work demonstrates that C-JEPA significantly enhances the stability and quality of visual representation learning. When pre-trained on the ImageNet-1K dataset, C-JEPA exhibits rapid and improved convergence in both linear probing and fine-tuning performance metrics.
Authors: Tianyu Zhang, Guocheng Qian, Jin Xie, Jian Yang
Abstract: Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure. Prevailing techniques often rely on pre-trained motion estimators or intensive testing-time optimization, resulting in compromised interpolation accuracy or prolonged inference. This work presents FastPCI that introduces Pyramid Convolution-Transformer architecture for point cloud frame interpolation. Our hybrid Convolution-Transformer improves the local and long-range feature learning, while the pyramid network offers multilevel features and reduces the computation. In addition, FastPCI proposes a unique Dual-Direction Motion-Structure block for more accurate scene flow estimation. Our design is motivated by two facts: (1) accurate scene flow preserves 3D structure, and (2) point cloud at the previous timestep should be reconstructable using reverse motion from future timestep. Extensive experiments show that FastPCI significantly outperforms the state-of-the-art PointINet and NeuralPCI with notable gains (e.g. 26.6% and 18.3% reduction in Chamfer Distance in KITTI), while being more than 10x and 600x faster, respectively. Code is available at https://github.com/genuszty/FastPCI
Authors: Fanqi Pu, Yifan Wang, Jiru Deng, Wenming Yang
Abstract: Perspective projection has been extensively utilized in monocular 3D object detection methods. It introduces geometric priors from 2D bounding boxes and 3D object dimensions to reduce the uncertainty of depth estimation. However, due to depth errors originating from the object's visual surface, the height of the bounding box often fails to represent the actual projected central height, which undermines the effectiveness of geometric depth. Direct prediction for the projected height unavoidably results in a loss of 2D priors, while multi-depth prediction with complex branches does not fully leverage geometric depth. This paper presents a Transformer-based monocular 3D object detection method called MonoDGP, which adopts perspective-invariant geometry errors to modify the projection formula. We also try to systematically discuss and explain the mechanisms and efficacy behind geometry errors, which serve as a simple but effective alternative to multi-depth prediction. Additionally, MonoDGP decouples the depth-guided decoder and constructs a 2D decoder only dependent on visual features, providing 2D priors and initializing object queries without the disturbance of 3D detection. To further optimize and fine-tune input tokens of the transformer decoder, we also introduce a Region Segment Head (RSH) that generates enhanced features and segment embeddings. Our monocular method demonstrates state-of-the-art performance on the KITTI benchmark without extra data. Code is available at https://github.com/PuFanqi23/MonoDGP.
Authors: Alex Dils, David Raymond, Jack Spottiswood, Samay Kodige, Dylan Karmin, Rikhil Kokal, Win Cowger, Chris Sad\'ee
Abstract: Current methods for microplastic identification in water samples are costly and require expert analysis. Here, we propose a deep learning segmentation model to automatically identify microplastics in microscopic images. We labeled images of microplastic from the Moore Institute for Plastic Pollution Research and employ a Generative Adversarial Network (GAN) to supplement and generate diverse training data. To verify the validity of the generated data, we conducted a reader study where an expert was able to discern the generated microplastic from real microplastic at a rate of 68 percent. Our segmentation model trained on the combined data achieved an F1-Score of 0.91 on a diverse dataset, compared to the model without generated data's 0.82. With our findings we aim to enhance the ability of both experts and citizens to detect microplastic across diverse ecological contexts, thereby improving the cost and accessibility of microplastic analysis.
Authors: Kai-Yin Hong, Chieh-Chih Wang, Wen-Chieh Lin
Abstract: Recent years have seen a shift towards learning-based methods for trajectory prediction, with challenges remaining in addressing uncertainty and capturing multi-modal distributions. This paper introduces Temporal Ensembling with Learning-based Aggregation, a meta-algorithm designed to mitigate the issue of missing behaviors in trajectory prediction, which leads to inconsistent predictions across consecutive frames. Unlike conventional model ensembling, temporal ensembling leverages predictions from nearby frames to enhance spatial coverage and prediction diversity. By confirming predictions from multiple frames, temporal ensembling compensates for occasional errors in individual frame predictions. Furthermore, trajectory-level aggregation, often utilized in model ensembling, is insufficient for temporal ensembling due to a lack of consideration of traffic context and its tendency to assign candidate trajectories with incorrect driving behaviors to final predictions. We further emphasize the necessity of learning-based aggregation by utilizing mode queries within a DETR-like architecture for our temporal ensembling, leveraging the characteristics of predictions from nearby frames. Our method, validated on the Argoverse 2 dataset, shows notable improvements: a 4% reduction in minADE, a 5% decrease in minFDE, and a 1.16% reduction in the miss rate compared to the strongest baseline, QCNet, highlighting its efficacy and potential in autonomous driving.
Authors: Shenghao Fu, Junkai Yan, Qize Yang, Xihan Wei, Xiaohua Xie, Wei-Shi Zheng
Abstract: Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector's decoder by providing a compact context. Additionally, the patch tokens in foundation models can enrich the features in the detector's encoder by providing semantic details. Utilizing frozen foundation models as plug-and-play modules rather than the commonly used backbone can significantly enhance the detector's performance while preventing the problems caused by the architecture discrepancy between the detector's backbone and the foundation model. With such a novel paradigm, we boost the SOTA query-based detector DINO from 49.0% AP to 51.9% AP (+2.9% AP) and further to 53.8% AP (+4.8% AP) by integrating one or two foundation models respectively, on the COCO validation set after training for 12 epochs with R50 as the detector's backbone.
Authors: Junsheng Zhou, Weiqi Zhang, Yu-Shen Liu
Abstract: 3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness and unstructured nature. In this work, we propose DiffGS, a general Gaussian generator based on latent diffusion models. DiffGS is a powerful and efficient 3D generative model which is capable of generating Gaussian primitives at arbitrary numbers for high-fidelity rendering with rasterization. The key insight is to represent Gaussian Splatting in a disentangled manner via three novel functions to model Gaussian probabilities, colors and transforms. Through the novel disentanglement of 3DGS, we represent the discrete and unstructured 3DGS with continuous Gaussian Splatting functions, where we then train a latent diffusion model with the target of generating these Gaussian Splatting functions both unconditionally and conditionally. Meanwhile, we introduce a discretization algorithm to extract Gaussians at arbitrary numbers from the generated functions via octree-guided sampling and optimization. We explore DiffGS for various tasks, including unconditional generation, conditional generation from text, image, and partial 3DGS, as well as Point-to-Gaussian generation. We believe that DiffGS provides a new direction for flexibly modeling and generating Gaussian Splatting.
Authors: Chao Chen, Yu-Shen Liu, Zhizhong Han
Abstract: It is important to estimate an accurate signed distance function (SDF) from a point cloud in many computer vision applications. The latest methods learn neural SDFs using either a data-driven based or an overfitting-based strategy. However, these two kinds of methods are with either poor generalization or slow convergence, which limits their capability under challenging scenarios like highly noisy point clouds. To resolve this issue, we propose a method to promote pros of both data-driven based and overfitting-based methods for better generalization, faster inference, and higher accuracy in learning neural SDFs. We introduce a novel statistical reasoning algorithm in local regions which is able to finetune data-driven based priors without signed distance supervision, clean point cloud, or point normals. This helps our method start with a good initialization, and converge to a minimum in a much faster way. Our numerical and visual comparisons with the state-of-the-art methods show our superiority over these methods in surface reconstruction and point cloud denoising on widely used shape and scene benchmarks. The code is available at https://github.com/chenchao15/LocalN2NM.
Authors: Amit Das, Tanmay Shukla, Naofumi Tomita, Ryland Richards, Laura Vidis, Bing Ren, Saeed Hassanpour
Abstract: Grading inflammatory bowel disease (IBD) activity using standardized histopathological scoring systems remains challenging due to resource constraints and inter-observer variability. In this study, we developed a deep learning model to classify activity grades in hematoxylin and eosin-stained whole slide images (WSIs) from patients with IBD, offering a robust approach for general pathologists. We utilized 2,077 WSIs from 636 patients treated at Dartmouth-Hitchcock Medical Center in 2018 and 2019, scanned at 40x magnification (0.25 micron/pixel). Board-certified gastrointestinal pathologists categorized the WSIs into four activity classes: inactive, mildly active, moderately active, and severely active. A transformer-based model was developed and validated using five-fold cross-validation to classify IBD activity. Using HoVerNet, we examined neutrophil distribution across activity grades. Attention maps from our model highlighted areas contributing to its prediction. The model classified IBD activity with weighted averages of 0.871 [95% Confidence Interval (CI): 0.860-0.883] for the area under the curve, 0.695 [95% CI: 0.674-0.715] for precision, 0.697 [95% CI: 0.678-0.716] for recall, and 0.695 [95% CI: 0.674-0.714] for F1-score. Neutrophil distribution was significantly different across activity classes. Qualitative evaluation of attention maps by a gastrointestinal pathologist suggested their potential for improved interpretability. Our model demonstrates robust diagnostic performance and could enhance consistency and efficiency in IBD activity assessment.
Authors: Xiangyu Zeng, Kunchang Li, Chenting Wang, Xinhao Li, Tianxiang Jiang, Ziang Yan, Songze Li, Yansong Shi, Zhengrong Yue, Yi Wang, Yali Wang, Yu Qiao, Limin Wang
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a high-quality video dataset for grounded tuning of MLLMs, and a carefully-designed instruction tuning task to explicitly incorporate the grounding supervision in the traditional QA format. Specifically, based on VideoChat, we propose our long-video MLLM, coined as VideoChat-T, by implementing a token shuffling to compress long video tokens and introducing Temporal Adaptive Position Encoding (TAPE) to enhance the temporal awareness of visual representation. Meanwhile, we introduce the TimePro, a comprehensive grounding-centric instruction tuning dataset composed of 9 tasks and 349k high-quality grounded annotations. Notably, we design a new instruction tuning task type, called Temporal Grounded Caption, to peform detailed video descriptions with the corresponding time stamps prediction. This explicit temporal location prediction will guide MLLM to correctly attend on the visual content when generating description, and thus reduce the hallucination risk caused by the LLMs. Experimental results demonstrate that our TimeSuite provides a successful solution to enhance the long video understanding capability of short-form MLLM, achieving improvement of 5.6% and 6.8% on the benchmarks of Egoschema and VideoMME, respectively. In addition, VideoChat-T exhibits robust zero-shot temporal grounding capabilities, significantly outperforming the existing state-of-the-art MLLMs. After fine-tuning, it performs on par with the traditional supervised expert models.
Authors: George Stoica, Pratik Ramesh, Boglarka Ecsedi, Leshem Choshen, Judy Hoffman
Abstract: Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks without retraining. Yet, this success does not transfer well when merging LoRA finetuned models. We study this phenomenon and observe that the weights of LoRA finetuned models showcase a lower degree of alignment compared to their fully-finetuned counterparts. We hypothesize that improving this alignment is key to obtaining better LoRA model merges, and propose KnOTS to address this problem. KnOTS uses the SVD to jointly transform the weights of different LoRA models into an aligned space, where existing merging methods can be applied. In addition, we introduce a new benchmark that explicitly evaluates whether merged models are general models. Notably, KnOTS consistently improves LoRA merging by up to 4.3% across several vision and language benchmarks, including our new setting. We release our code at: https://github.com/gstoica27/KnOTS.
Authors: Ruoqi Liu, Yuelin Bai, Xiang Yue, Ping Zhang
Abstract: The electrocardiogram (ECG) is an essential non-invasive diagnostic tool for assessing cardiac conditions. Existing automatic interpretation methods suffer from limited generalizability, focusing on a narrow range of cardiac conditions, and typically depend on raw physiological signals, which may not be readily available in resource-limited settings where only printed or digital ECG images are accessible. Recent advancements in multimodal large language models (MLLMs) present promising opportunities for addressing these challenges. However, the application of MLLMs to ECG image interpretation remains challenging due to the lack of instruction tuning datasets and well-established ECG image benchmarks for quantitative evaluation. To address these challenges, we introduce ECGInstruct, a comprehensive ECG image instruction tuning dataset of over one million samples, covering a wide range of ECG-related tasks from diverse data sources. Using ECGInstruct, we develop PULSE, an MLLM tailored for ECG image comprehension. In addition, we curate ECGBench, a new evaluation benchmark covering four key ECG image interpretation tasks across nine different datasets. Our experiments show that PULSE sets a new state-of-the-art, outperforming general MLLMs with an average accuracy improvement of 15% to 30%. This work highlights the potential of PULSE to enhance ECG interpretation in clinical practice.
Authors: Aniket Das, Ayushman Singh, Nishant, Sharad Prakash
Abstract: Gastrointestinal (GI) diseases represent a significant global health concern, with Capsule Endoscopy (CE) offering a non-invasive method for diagnosis by capturing a large number of GI tract images. However, the sheer volume of video frames necessitates automated analysis to reduce the workload on doctors and increase the diagnostic accuracy. In this paper, we present CapsuleNet, a deep learning model developed for the Capsule Vision 2024 Challenge, aimed at classifying 10 distinct GI abnormalities. Using a highly imbalanced dataset, we implemented various data augmentation strategies, reducing the data imbalance to a manageable level. Our model leverages a pretrained EfficientNet-b7 backbone, tuned with additional layers for classification and optimized with PReLU activation functions. The model demonstrated superior performance on validation data, achieving a micro accuracy of 84.5% and outperforming the VGG16 baseline across most classes. Despite these advances, challenges remain in classifying certain abnormalities, such as Erythema. Our findings suggest that CNN-based models like CapsuleNet can provide an efficient solution for GI tract disease classification, particularly when inference time is a critical factor.
Authors: Basile Hurat, Zariluz Alvarado, Jerome Gilles
Abstract: The empirical wavelet transform is an adaptive multiresolution analysis tool based on the idea of building filters on a data-driven partition of the Fourier domain. However, existing 2D extensions are constrained by the shape of the detected partitioning. In this paper, we provide theoretical results that permits us to build 2D empirical wavelet filters based on an arbitrary partitioning of the frequency domain. We also propose an algorithm to detect such partitioning from an image spectrum by combining a scale-space representation to estimate the position of dominant harmonic modes and a watershed transform to find the boundaries of the different supports making the expected partition. This whole process allows us to define the empirical watershed wavelet transform. We illustrate the effectiveness and the advantages of such adaptive transform, first visually on toy images, and next on both unsupervised texture segmentation and image deconvolution applications.
Authors: Zixiao Zhao, Jing Sun, Zhiyuan Wei, Cheng-Hao Cai, Zhe Hou, Jin Song Dong
Abstract: In the field of automated programming, large language models (LLMs) have demonstrated foundational generative capabilities when given detailed task descriptions. However, their current functionalities are primarily limited to function-level development, restricting their effectiveness in complex project environments and specific application scenarios, such as complicated image-processing tasks. This paper presents a multi-agent framework that utilises a hybrid set of LLMs, including GPT-4o and locally deployed open-source models, which collaboratively complete auto-programming tasks. Each agent plays a distinct role in the software development cycle, collectively forming a virtual organisation that works together to produce software products. By establishing a tree-structured thought distribution and development mechanism across project, module, and function levels, this framework offers a cost-effective and efficient solution for code generation. We evaluated our approach using benchmark datasets, and the experimental results demonstrate that VisionCoder significantly outperforms existing methods in image processing auto-programming tasks.
Authors: Eric Cai, Octavian Donca, Ben Eisner, David Held
Abstract: The task of "relative placement" is to predict the placement of one object in relation to another, e.g. placing a mug onto a mug rack. Through explicit object-centric geometric reasoning, recent methods for relative placement have made tremendous progress towards data-efficient learning for robot manipulation while generalizing to unseen task variations. However, they have yet to represent deformable transformations, despite the ubiquity of non-rigid bodies in real world settings. As a first step towards bridging this gap, we propose ``cross-displacement" - an extension of the principles of relative placement to geometric relationships between deformable objects - and present a novel vision-based method to learn cross-displacement through dense diffusion. To this end, we demonstrate our method's ability to generalize to unseen object instances, out-of-distribution scene configurations, and multimodal goals on multiple highly deformable tasks (both in simulation and in the real world) beyond the scope of prior works. Supplementary information and videos can be found at our $\href{https://sites.google.com/view/tax3d-corl-2024}{\text{website}}$.
Authors: Liang Qiu, Liyue Shen, Lianli Liu, Junyan Liu, Yizheng Chen, Lei Xing
Abstract: During and after a course of therapy, imaging is routinely used to monitor the disease progression and assess the treatment responses. Despite of its significance, reliably capturing and predicting the spatial-temporal anatomic changes from a sequence of patient-specific image series presents a considerable challenge. Thus, the development of a computational framework becomes highly desirable for a multitude of practical applications. In this context, we propose a strategy of Spatial-Temporal Neural Representation learning with Prior embedding (ST-NeRP) for patient-specific imaging study. Our strategy involves leveraging an Implicit Neural Representation (INR) network to encode the image at the reference time point into a prior embedding. Subsequently, a spatial-temporally continuous deformation function is learned through another INR network. This network is trained using the whole patient-specific image sequence, enabling the prediction of deformation fields at various target time points. The efficacy of the ST-NeRP model is demonstrated through its application to diverse sequential image series, including 4D CT and longitudinal CT datasets within thoracic and abdominal imaging. The proposed ST-NeRP model exhibits substantial potential in enabling the monitoring of anatomical changes within a patient throughout the therapeutic journey.
Authors: Siyuan Dong, Zhuotong Cai, Gilbert Hangel, Wolfgang Bogner, Georg Widhalm, Yaqing Huang, Qinghao Liang, Chenyu You, Chathura Kumaragamage, Robert K. Fulbright, Amit Mahajan, Amin Karbasi, John A. Onofrey, Robin A. de Graaf, James S. Duncan
Abstract: Magnetic Resonance Spectroscopic Imaging (MRSI) is a non-invasive imaging technique for studying metabolism and has become a crucial tool for understanding neurological diseases, cancers and diabetes. High spatial resolution MRSI is needed to characterize lesions, but in practice MRSI is acquired at low resolution due to time and sensitivity restrictions caused by the low metabolite concentrations. Therefore, there is an imperative need for a post-processing approach to generate high-resolution MRSI from low-resolution data that can be acquired fast and with high sensitivity. Deep learning-based super-resolution methods provided promising results for improving the spatial resolution of MRSI, but they still have limited capability to generate accurate and high-quality images. Recently, diffusion models have demonstrated superior learning capability than other generative models in various tasks, but sampling from diffusion models requires iterating through a large number of diffusion steps, which is time-consuming. This work introduces a Flow-based Truncated Denoising Diffusion Model (FTDDM) for super-resolution MRSI, which shortens the diffusion process by truncating the diffusion chain, and the truncated steps are estimated using a normalizing flow-based network. The network is conditioned on upscaling factors to enable multi-scale super-resolution. To train and evaluate the deep learning models, we developed a 1H-MRSI dataset acquired from 25 high-grade glioma patients. We demonstrate that FTDDM outperforms existing generative models while speeding up the sampling process by over 9-fold compared to the baseline diffusion model. Neuroradiologists' evaluations confirmed the clinical advantages of our method, which also supports uncertainty estimation and sharpness adjustment, extending its potential clinical applications.
Authors: Jianning Chi, Zelan Li, Huixuan Wu, Wenjun Zhang, Ying Huang
Abstract: Weakly-supervised methods typically guided the pixel-wise training by comparing the predictions to single-level labels containing diverse segmentation-related information at once, but struggled to represent delicate feature differences between nodule and background regions and confused incorrect information, resulting in underfitting or overfitting in the segmentation predictions. In this work, we propose a weakly-supervised network that generates multi-level labels from four-point annotation to refine diverse constraints for delicate nodule segmentation. The Distance-Similarity Fusion Prior referring to the points annotations filters out information irrelevant to nodules. The bounding box and pure foreground/background labels, generated from the point annotation, guarantee the rationality of the prediction in the arrangement of target localization and the spatial distribution of target/background regions, respectively. Our proposed network outperforms existing weakly-supervised methods on two public datasets with respect to the accuracy and robustness, improving the applicability of deep-learning based segmentation in the clinical practice of thyroid nodule diagnosis.
Authors: Soojin Woo, Seong-Woo Kim
Abstract: In vision-based robot localization and SLAM, Visual Place Recognition (VPR) is essential. This paper addresses the problem of VPR, which involves accurately recognizing the location corresponding to a given query image. A popular approach to vision-based place recognition relies on low-level visual features. Despite significant progress in recent years, place recognition based on low-level visual features is challenging when there are changes in scene appearance. To address this, end-to-end training approaches have been proposed to overcome the limitations of hand-crafted features. However, these approaches still fail under drastic changes and require large amounts of labeled data to train models, presenting a significant limitation. Methods that leverage high-level semantic information, such as objects or categories, have been proposed to handle variations in appearance. In this paper, we introduce a novel VPR approach that remains robust to scene changes and does not require additional training. Our method constructs semantic image descriptors by extracting pixel-level embeddings using a zero-shot, language-driven semantic segmentation model. We validate our approach in challenging place recognition scenarios using real-world public dataset. The experiments demonstrate that our method outperforms non-learned image representation techniques and off-the-shelf convolutional neural network (CNN) descriptors. Our code is available at https: //github.com/woo-soojin/context-based-vlpr.
Authors: Zhenming Yu, Liming Cheng, Hongyu Huang, Wei Zhang, Liang Lin, Kun Xu
Abstract: Communication enables the expansion of human visual perception beyond the limitations of time and distance, while computational imaging overcomes the constraints of depth and breadth. Although impressive achievements have been witnessed with the two types of technologies, the occlusive information flow between the two domains is a bottleneck hindering their ulterior progression. Herein, we propose a novel framework that integrates communication and computational imaging (ICCI) to break through the inherent isolation between communication and computational imaging for remote perception. By jointly considering the sensing and transmitting of remote visual information, the ICCI framework performs a full-link information transfer optimization, aiming to minimize information loss from the generation of the information source to the execution of the final vision tasks. We conduct numerical analysis and experiments to demonstrate the ICCI framework by integrating communication systems and snapshot compressive imaging systems. Compared with straightforward combination schemes, which sequentially execute sensing and transmitting, the ICCI scheme shows greater robustness against channel noise and impairments while achieving higher data compression. Moreover, an 80 km 27-band hyperspectral video perception with a rate of 30 fps is experimentally achieved. This new ICCI remote perception paradigm offers a highefficiency solution for various real-time computer vision tasks.
Authors: Zixuan Gong, Guangyin Bao, Qi Zhang, Zhongwei Wan, Duoqian Miao, Shoujin Wang, Lei Zhu, Changwei Wang, Rongtao Xu, Liang Hu, Ke Liu, Yu Zhang
Abstract: Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. However, the research on fMRI-to-video reconstruction remains limited since decoding the spatiotemporal perception of continuous visual experiences is formidably challenging. We contend that the key to addressing these challenges lies in accurately decoding both high-level semantics and low-level perception flows, as perceived by the brain in response to video stimuli. To the end, we propose NeuroClips, an innovative framework to decode high-fidelity and smooth video from fMRI. NeuroClips utilizes a semantics reconstructor to reconstruct video keyframes, guiding semantic accuracy and consistency, and employs a perception reconstructor to capture low-level perceptual details, ensuring video smoothness. During inference, it adopts a pre-trained T2V diffusion model injected with both keyframes and low-level perception flows for video reconstruction. Evaluated on a publicly available fMRI-video dataset, NeuroClips achieves smooth high-fidelity video reconstruction of up to 6s at 8FPS, gaining significant improvements over state-of-the-art models in various metrics, e.g., a 128\% improvement in SSIM and an 81\% improvement in spatiotemporal metrics. Our project is available at https://github.com/gongzix/NeuroClips}{https://github.com/gongzix/NeuroClips.
URLs: https://github.com/gongzix/NeuroClips, https://github.com/gongzix/NeuroClips.
Authors: Pedro Martin, Ant\'onio Rodrigues, Jo\~ao Ascenso, Maria Paula Queluz
Abstract: Neural Radiance Fields (NeRF) have revolutionized the field of 3D visual representation by enabling highly realistic and detailed scene reconstructions from a sparse set of images. NeRF uses a volumetric functional representation that maps 3D points to their corresponding colors and opacities, allowing for photorealistic view synthesis from arbitrary viewpoints. Despite its advancements, the efficient streaming of NeRF content remains a significant challenge due to the large amount of data involved. This paper investigates the rate-distortion performance of two NeRF streaming strategies: pixel-based and neural network (NN) parameter-based streaming. While in the former, images are coded and then transmitted throughout the network, in the latter, the respective NeRF model parameters are coded and transmitted instead. This work also highlights the trade-offs in complexity and performance, demonstrating that the NN parameter-based strategy generally offers superior efficiency, making it suitable for one-to-many streaming scenarios.
Authors: Till Aczel, Roger Wattenhofer
Abstract: In lossy image compression, models face the challenge of either hallucinating details or generating out-of-distribution samples due to the information bottleneck. This implies that at times, introducing hallucinations is necessary to generate in-distribution samples. The optimal level of hallucination varies depending on image content, as humans are sensitive to small changes that alter the semantic meaning. We propose a novel compression method that dynamically balances the degree of hallucination based on content. We collect data and train a model to predict user preferences on hallucinations. By using this prediction to adjust the perceptual weight in the reconstruction loss, we develop a Conditionally Hallucinating compression model (ConHa) that outperforms state-of-the-art image compression methods. Code and images are available at https://polybox.ethz.ch/index.php/s/owS1k5JYs4KD4TA.
Authors: Branko Mitic, Philipp Seeb\"ock, Jennifer Straub, Helmut Prosch, Georg Langs
Abstract: Fast detection of emerging diseases is important for containing their spread and treating patients effectively. Local anomalies are relevant, but often novel diseases involve familiar disease patterns in new spatial distributions. Therefore, established local anomaly detection approaches may fail to identify them as new. Here, we present a novel approach to detect the emergence of new disease phenotypes exhibiting distinct patterns of the spatial distribution of lesions. We first identify anomalies in lung CT data, and then compare their distribution in a continually acquired new patient cohorts with historic patient population observed over a long prior period. We evaluate how accumulated evidence collected in the stream of patients is able to detect the onset of an emerging disease. In a gram-matrix based representation derived from the intermediate layers of a three-dimensional convolutional neural network, newly emerging clusters indicate emerging diseases.
Authors: Ilan Naiman, Nimrod Berman, Itai Pemper, Idan Arbiv, Gal Fadlon, Omri Azencot
Abstract: Lately, there has been a surge in interest surrounding generative modeling of time series data. Most existing approaches are designed either to process short sequences or to handle long-range sequences. This dichotomy can be attributed to gradient issues with recurrent networks, computational costs associated with transformers, and limited expressiveness of state space models. Towards a unified generative model for varying-length time series, we propose in this work to transform sequences into images. By employing invertible transforms such as the delay embedding and the short-time Fourier transform, we unlock three main advantages: i) We can exploit advanced diffusion vision models; ii) We can remarkably process short- and long-range inputs within the same framework; and iii) We can harness recent and established tools proposed in the time series to image literature. We validate the effectiveness of our method through a comprehensive evaluation across multiple tasks, including unconditional generation, interpolation, and extrapolation. We show that our approach achieves consistently state-of-the-art results against strong baselines. In the unconditional generation tasks, we show remarkable mean improvements of 58.17% over previous diffusion models in the short discriminative score and 132.61% in the (ultra-)long classification scores. Code is at https://github.com/azencot-group/ImagenTime.
Authors: Amir Dahari, Ronan Docherty, Steve Kench, Samuel J. Cooper
Abstract: In this study, we present a method for predicting the representativity of the phase fraction observed in a single image (2D or 3D) of a material. Traditional approaches often require large datasets and extensive statistical analysis to estimate the Integral Range, a key factor in determining the variance of microstructural properties. Our method leverages the Two-Point Correlation function to directly estimate the variance from a single image (2D or 3D), thereby enabling phase fraction prediction with associated confidence levels. We validate our approach using open-source datasets, demonstrating its efficacy across diverse microstructures. This technique significantly reduces the data requirements for representativity analysis, providing a practical tool for material scientists and engineers working with limited microstructural data. To make the method easily accessible, we have created a web-application, \url{www.imagerep.io}, for quick, simple and informative use of the method.
Authors: Xin Shen, Lei Shen, Shaozu Yuan, Heming Du, Haiyang Sun, Xin Yu
Abstract: Like spoken languages, a single sign language expression could correspond to multiple valid textual interpretations. Hence, learning a rigid one-to-one mapping for sign language translation (SLT) models might be inadequate, particularly in the case of limited data. In this work, we introduce a Diverse Sign Language Translation (DivSLT) task, aiming to generate diverse yet accurate translations for sign language videos. Firstly, we employ large language models (LLM) to generate multiple references for the widely-used CSL-Daily and PHOENIX14T SLT datasets. Here, native speakers are only invited to touch up inaccurate references, thus significantly improving the annotation efficiency. Secondly, we provide a benchmark model to spur research in this task. Specifically, we investigate multi-reference training strategies to enable our DivSLT model to achieve diverse translations. Then, to enhance translation accuracy, we employ the max-reward-driven reinforcement learning objective that maximizes the reward of the translated result. Additionally, we utilize multiple metrics to assess the accuracy, diversity, and semantic precision of the DivSLT task. Experimental results on the enriched datasets demonstrate that our DivSLT method achieves not only better translation performance but also diverse translation results.
Authors: Liviu Badea, Maria Popa
Abstract: Automating Multiple Sclerosis (MS) lesion segmentation would be of great benefit in initial diagnosis as well as monitoring disease progression. Deep learning based segmentation models perform well in many domains, but the state-of-the-art in MS lesion segmentation is still suboptimal. Complementary to previous MS lesion segmentation challenges which focused on optimizing the performance on a single evaluation dataset, this study aims to develop models that generalize across diverse evaluation datasets, mirroring real-world clinical scenarios that involve varied scanners, settings, and patient cohorts. To this end, we used all high-quality publicly-available MS lesion segmentation datasets on which we systematically trained a state-of-the-art UNet++ architecture. The resulting models demonstrate consistent performance across the remaining test datasets (are generalizable), with larger and more heterogeneous datasets leading to better models. To the best of our knowledge, this represents the most comprehensive cross-dataset evaluation of MS lesion segmentation models to date using publicly available datasets. Additionally, explicitly enhancing dataset size by merging datasets improved model performance. Specifically, a model trained on the combined MSSEG2016-train, ISBI2015, and 3D-MR-MS datasets surpasses the winner of the MICCAI-2016 competition. Moreover, we demonstrate that the generalizability of our models also relies on our original use of quantile normalization on MRI intensities.
Authors: Pranav Gupta, Pratham Gohil, Sridhar S
Abstract: The accurate prediction of danger levels in video content is critical for enhancing safety and security systems, particularly in environments where quick and reliable assessments are essential. In this study, we perform a comparative analysis of various machine learning and deep learning models to predict danger ratings in a custom dataset of 100 videos, each containing 50 frames, annotated with human-rated danger scores ranging from 0 to 10. The danger ratings are further classified into three categories: no alert (less than 7)and high alert (greater than equal to 7). Our evaluation covers classical machine learning models, such as Support Vector Machines, as well as Neural Networks, and transformer-based models. Model performance is assessed using standard metrics such as accuracy, F1-score, and mean absolute error (MAE), and the results are compared to identify the most robust approach. This research contributes to developing a more accurate and generalizable danger assessment framework for video-based risk detection.
Authors: Yucheng Zhou, Zhi Rao, Jun Wan, Jianbing Shen
Abstract: Large Vision-Language Models (LVLMs) excel in cross-model tasks but experience performance declines in long-context reasoning due to overreliance on textual information and reduced visual dependency. In this study, we empirically analyze LVLMs in long-context reasoning, revealing that increased context length leads to a higher dependence on language at the expense of visual dependency. To address this issue, we propose a novel training-free context pruning method that selectively removes less critical textual information. Our approach enhances visual dependency and reduces textual noise, thereby improving LVLM performance in long-context reasoning. We validate our method by constructing a long-context dataset, demonstrating its effectiveness across various LVLMs. Moreover, further analysis confirms the robustness of different token pruning strategies and preliminary explores scaling laws between pruning rates and context length.
Authors: Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos, Christos Diou
Abstract: Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using such data. However, most of them heavily rely on the availability of protected attribute labels in the dataset, which limits their applicability, while label-unaware approaches, i.e., approaches operating without such labels, exhibit considerably lower performance. To overcome these limitations, this work introduces FLAC, a methodology that minimizes mutual information between the features extracted by the model and a protected attribute, without the use of attribute labels. To do that, FLAC proposes a sampling strategy that highlights underrepresented samples in the dataset, and casts the problem of learning fair representations as a probability matching problem that leverages representations extracted by a bias-capturing classifier. It is theoretically shown that FLAC can indeed lead to fair representations, that are independent of the protected attributes. FLAC surpasses the current state-of-the-art on Biased-MNIST, CelebA, and UTKFace, by 29.1%, 18.1%, and 21.9%, respectively. Additionally, FLAC exhibits 2.2% increased accuracy on ImageNet-A and up to 4.2% increased accuracy on Corrupted-Cifar10. Finally, in most experiments, FLAC even outperforms the bias label-aware state-of-the-art methods.
Authors: Chenghao Li, Chaoning Zhang, Joseph Cho, Atish Waghwase, Lik-Hang Lee, Francois Rameau, Yang Yang, Sung-Ho Bae, Choong Seon Hong
Abstract: Generative AI has made significant progress in recent years, with text-guided content generation being the most practical as it facilitates interaction between human instructions and AI-generated content (AIGC). Thanks to advancements in text-to-image and 3D modeling technologies, like neural radiance field (NeRF), text-to-3D has emerged as a nascent yet highly active research field. Our work conducts a comprehensive survey on this topic and follows up on subsequent research progress in the overall field, aiming to help readers interested in this direction quickly catch up with its rapid development. First, we introduce 3D data representations, including both Structured and non-Structured data. Building on this pre-requisite, we introduce various core technologies to achieve satisfactory text-to-3D results. Additionally, we present mainstream baselines and research directions in recent text-to-3D technology, including fidelity, efficiency, consistency, controllability, diversity, and applicability. Furthermore, we summarize the usage of text-to-3D technology in various applications, including avatar generation, texture generation, scene generation and 3D editing. Finally, we discuss the agenda for the future development of text-to-3D.
Authors: Liangzhe Yuan, Nitesh Bharadwaj Gundavarapu, Long Zhao, Hao Zhou, Yin Cui, Lu Jiang, Xuan Yang, Menglin Jia, Tobias Weyand, Luke Friedman, Mikhail Sirotenko, Huisheng Wang, Florian Schroff, Hartwig Adam, Ming-Hsuan Yang, Ting Liu, Boqing Gong
Abstract: We evaluate the video understanding capabilities of existing foundation models (FMs) using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition,temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring an FM for downstream tasks. Furthermore, we jointly profile FMs' efficacy and efficiency when adapting to general video understanding tasks using cost measurements during both training and inference. Our main findings areas follows. First, task-specialized models significantly outperform the seven FMs studied in this work, in sharp contrast to what FMs have achieved in natural language and image understanding. Second, video-native FMs, whose pretraining data mainly contains the video modality, are generally better than image-native FMs in classifying motion-rich videos, localizing actions in time, and understanding a video of more than one action. Third, the video-native FMs can perform well on video tasks under light adaptations to downstream tasks (e.g., freezing the FM backbones), while image-native FMs win in full end-to-end finetuning. The first two observations reveal the need and tremendous opportunities to conduct research on video-focused FMs, and the last confirms that both tasks and adaptation methods matter when it comes to the evaluation of FMs. Our code is released under: https://github.com/tensorflow/models/tree/master/official/projects/videoglue.
URLs: https://github.com/tensorflow/models/tree/master/official/projects/videoglue.
Authors: Alloy Das, Sanket Biswas, Prasun Roy, Subhankar Ghosh, Umapada Pal, Michael Blumenstein, Joseph Llad\'os, Saumik Bhattacharya
Abstract: Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance.
Authors: Bencheng Liao, Shaoyu Chen, Yunchi Zhang, Bo Jiang, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang
Abstract: High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present \textbf{Map} \textbf{TR}ansformer, an end-to-end framework for online vectorized HD map construction. We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process. We design a hierarchical query embedding scheme to flexibly encode structured map information and perform hierarchical bipartite matching for map element learning. To speed up convergence, we further introduce auxiliary one-to-many matching and dense supervision. The proposed method well copes with various map elements with arbitrary shapes. It runs at real-time inference speed and achieves state-of-the-art performance on both nuScenes and Argoverse2 datasets. Abundant qualitative results show stable and robust map construction quality in complex and various driving scenes. Code and more demos are available at \url{https://github.com/hustvl/MapTR} for facilitating further studies and applications.
Authors: Jon Alvarez Justo, Alexandru Ghita, Daniel Kovac, Joseph L. Garrett, Mariana-Iuliana Georgescu, Jesus Gonzalez-Llorente, Radu Tudor Ionescu, Tor Arne Johansen
Abstract: Satellites are increasingly adopting on-board AI to optimize operations and increase autonomy through in-orbit inference. The use of Deep Learning (DL) models for segmentation in hyperspectral imagery offers advantages for remote sensing applications. In this work, we train and test 20 models for multi-class segmentation in hyperspectral imagery, selected for their potential in future space deployment. These models include 1D and 2D Convolutional Neural Networks (CNNs) and the latest vision transformers (ViTs). We propose a lightweight 1D-CNN model, 1D-Justo-LiuNet, which outperforms state-of-the-art models in the hypespectral domain. 1D-Justo-LiuNet exceeds the performance of 2D-CNN UNets and outperforms Apple's lightweight vision transformers designed for mobile inference. 1D-Justo-LiuNet achieves the highest accuracy (0.93) with the smallest model size (4,563 parameters) among all tested models, while maintaining fast inference. Unlike 2D-CNNs and ViTs, which encode both spectral and spatial information, 1D-Justo-LiuNet focuses solely on the rich spectral features in hyperspectral data, benefitting from the high-dimensional feature space. Our findings are validated across various satellite datasets, with the HYPSO-1 mission serving as the primary case study for sea, land, and cloud segmentation. We further confirm our conclusions through generalization tests on other hyperspectral missions, such as NASA's EO-1. Based on its superior performance and compact size, we conclude that 1D-Justo-LiuNet is highly suitable for in-orbit deployment, providing an effective solution for optimizing and automating satellite operations at edge.
Authors: Che Liu, Cheng Ouyang, Sibo Cheng, Anand Shah, Wenjia Bai, Rossella Arcucci
Abstract: Recently, medical vision-language pre-training (VLP) has reached substantial progress to learn global visual representation from medical images and their paired radiology reports. However, medical imaging tasks in real world usually require finer granularity in visual features. These tasks include visual localization tasks (e.g., semantic segmentation, object detection) and visual grounding task. Yet, current medical VLP methods face challenges in learning these fine-grained features, as they primarily focus on brute-force alignment between image patches and individual text tokens for local visual feature learning, which is suboptimal for downstream dense prediction tasks. In this work, we propose a new VLP framework, named \textbf{G}lobal to \textbf{D}ense level representation learning (G2D) that achieves significantly improved granularity and more accurate grounding for the learned features, compared to existing medical VLP approaches. In particular, G2D learns dense and semantically-grounded image representations via a pseudo segmentation task parallel with the global vision-language alignment. Notably, generating pseudo segmentation targets does not incur extra trainable parameters: they are obtained on the fly during VLP with a parameter-free processor. G2D achieves superior performance across 6 medical imaging tasks and 25 diseases, particularly in semantic segmentation, which necessitates fine-grained, semantically-grounded image features. In this task, G2D surpasses peer models even when fine-tuned with just 1\% of the training data, compared to the 100\% used by these models. The code can be found in https://github.com/cheliu-computation/G2D-NeurIPS24/tree/main.
URLs: https://github.com/cheliu-computation/G2D-NeurIPS24/tree/main.
Authors: Lennart Brocki, Jakub Binda, Neo Christopher Chung
Abstract: Importance estimators are explainability methods that quantify feature importance for deep neural networks (DNN). In vision transformers (ViT), the self-attention mechanism naturally leads to attention maps, which are sometimes interpreted as importance scores that indicate which input features ViT models are focusing on. However, attention maps do not account for signals from downstream tasks. To generate explanations that are sensitive to downstream tasks, we have developed class-discriminative attention maps (CDAM), a gradient-based extension that estimates feature importance with respect to a known class or a latent concept. CDAM scales attention scores by how relevant the corresponding tokens are for the predictions of a classifier head. In addition to targeting the supervised classifier, CDAM can explain an arbitrary concept shared by selected samples by measuring similarity in the latent space of ViT. Additionally, we introduce Smooth CDAM and Integrated CDAM, which average a series of CDAMs with slightly altered tokens. Our quantitative benchmarks include correctness, compactness, and class sensitivity, in comparison to 7 other importance estimators. Vanilla, Smooth, and Integrated CDAM excel across all three benchmarks. In particular, our results suggest that existing importance estimators may not provide sufficient class-sensitivity. We demonstrate the utility of CDAM in medical images by training and explaining malignancy and biomarker prediction models based on lung Computed Tomography (CT) scans. Overall, CDAM is shown to be highly class-discriminative and semantically relevant, while providing compact explanations.
Authors: Aditya Murali, Deepak Alapatt, Pietro Mascagni, Armine Vardazaryan, Alain Garcia, Nariaki Okamoto, Guido Costamagna, Didier Mutter, Jacques Marescaux, Bernard Dallemagne, Nicolas Padoy
Abstract: This technical report provides a detailed overview of Endoscapes, a dataset of laparoscopic cholecystectomy (LC) videos with highly intricate annotations targeted at automated assessment of the Critical View of Safety (CVS). Endoscapes comprises 201 LC videos with frames annotated sparsely but regularly with segmentation masks, bounding boxes, and CVS assessment by three different clinical experts. Altogether, there are 11090 frames annotated with CVS and 1933 frames annotated with tool and anatomy bounding boxes from the 201 videos, as well as an additional 422 frames from 50 of the 201 videos annotated with tool and anatomy segmentation masks. In this report, we provide detailed dataset statistics (size, class distribution, dataset splits, etc.) and a comprehensive performance benchmark for instance segmentation, object detection, and CVS prediction. The dataset and model checkpoints are publically available at https://github.com/CAMMA-public/Endoscapes.
Authors: Feihong He, Gang Li, Fuhui Sun, Mengyuan Zhang, Lingyu Si, Xiaoyan Wang, Li Shen
Abstract: The rapid development of generative diffusion models has significantly advanced the field of style transfer. However, most current style transfer methods based on diffusion models typically involve a slow iterative optimization process, e.g., model fine-tuning and textual inversion of style concept. In this paper, we introduce FreeStyle, an innovative style transfer method built upon a pre-trained large diffusion model, requiring no further optimization. Besides, our method enables style transfer only through a text description of the desired style, eliminating the necessity of style images. Specifically, we propose a dual-stream encoder and single-stream decoder architecture, replacing the conventional U-Net in diffusion models. In the dual-stream encoder, two distinct branches take the content image and style text prompt as inputs, achieving content and style decoupling. In the decoder, we further modulate features from the dual streams based on a given content image and the corresponding style text prompt for precise style transfer. Our experimental results demonstrate high-quality synthesis and fidelity of our method across various content images and style text prompts. Compared with state-of-the-art methods that require training, our FreeStyle approach notably reduces the computational burden by thousands of iterations, while achieving comparable or superior performance across multiple evaluation metrics including CLIP Aesthetic Score, CLIP Score, and Preference. We have released the code at: https://github.com/FreeStyleFreeLunch/FreeStyle.
Authors: Ant\'onio Filgueiras, Eduardo R. B. Marques, Lu\'is M. B. Lopes, Miguel Marques, Hugo Silva
Abstract: Machine-learning techniques, especially deep convolutional neural networks, are pivotal for image-based identification of biological species in many Citizen Science platforms. In this paper, we describe the construction of a dataset for the Portuguese native flora based on publicly available research-grade datasets, and the derivation of a high-accuracy model from it using off-the-shelf deep convolutional neural networks. We anchored the dataset in high-quality data provided by Sociedade Portuguesa de Bot\^anica and added further sampled data from research-grade datasets available from GBIF. We find that with a careful dataset design, off-the-shelf machine-learning cloud services such as Google's AutoML Vision produce accurate models, with results comparable to those of Pl@ntNet, a state-of-the-art citizen science platform. The best model we derived, dubbed Floralens, has been integrated into the public website of Project Biolens, where we gather models for other taxa as well. The dataset used to train the model is also publicly available on Zenodo.
Authors: Xiang Fan, Anand Bhattad, Ranjay Krishna
Abstract: We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative inpainting, to modify the first frame; it automatically propagates those changes, with semantic, spatial, and temporally consistent motion, to the remaining frames. Unlike existing methods that enable edits only through imprecise textual instructions, Videoshop allows users to add or remove objects, semantically change objects, insert stock photos into videos, etc. with fine-grained control over locations and appearance. We achieve this through image-based video editing by inverting latents with noise extrapolation, from which we generate videos conditioned on the edited image. Videoshop produces higher quality edits against 6 baselines on 2 editing benchmarks using 10 evaluation metrics.
Authors: Leslie Gu, Jason Ken Adhinarta, Mikhail Bessmeltsev, Jiancheng Yang, Yongjie Jessica Zhang, Wenjie Yin, Daniel Berger, Jeff Lichtman, Hanspeter Pfister, Donglai Wei
Abstract: Accurately segmenting 3D curvilinear structures in medical imaging remains challenging due to their complex geometry and the scarcity of diverse, large-scale datasets for algorithm development and evaluation. In this paper, we use dendritic spine segmentation as a case study and address these challenges by introducing a novel Frenet--Serret Frame-based Decomposition, which decomposes 3D curvilinear structures into a globally \( C^2 \) continuous curve that captures the overall shape, and a cylindrical primitive that encodes local geometric properties. This approach leverages Frenet--Serret Frames and arc length parameterization to preserve essential geometric features while reducing representational complexity, facilitating data-efficient learning, improved segmentation accuracy, and generalization on 3D curvilinear structures. To rigorously evaluate our method, we introduce two datasets: CurviSeg, a synthetic dataset for 3D curvilinear structure segmentation that validates our method's key properties, and DenSpineEM, a benchmark for dendritic spine segmentation, which comprises 4,476 manually annotated spines from 70 dendrites across three public electron microscopy datasets, covering multiple brain regions and species. Our experiments on DenSpineEM demonstrate exceptional cross-region and cross-species generalization: models trained on the mouse somatosensory cortex subset achieve 91.9\% Dice, maintaining strong performance in zero-shot segmentation on both mouse visual cortex (94.1\% Dice) and human frontal lobe (81.8\% Dice) subsets. Moreover, we test the generalizability of our method on the IntrA dataset, where it achieves 77.08\% Dice (5.29\% higher than prior arts) on intracranial aneurysm segmentation. These findings demonstrate the potential of our approach for accurately analyzing complex curvilinear structures across diverse medical imaging fields.
Authors: Li Mi, Xianjie Dai, Javiera Castillo-Navarro, Devis Tuia
Abstract: Image-based retrieval in large Earth observation archives is challenging because one needs to navigate across thousands of candidate matches only with the query image as a guide. By using text as information supporting the visual query, the retrieval system gains in usability, but at the same time faces difficulties due to the diversity of visual signals that cannot be summarized by a short caption only. For this reason, as a matching-based task, cross-modal text-image retrieval often suffers from information asymmetry between texts and images. To address this challenge, we propose a Knowledge-aware Text-Image Retrieval (KTIR) method for remote sensing images. By mining relevant information from an external knowledge graph, KTIR enriches the text scope available in the search query and alleviates the information gaps between texts and images for better matching. Moreover, by integrating domain-specific knowledge, KTIR also enhances the adaptation of pre-trained vision-language models to remote sensing applications. Experimental results on three commonly used remote sensing text-image retrieval benchmarks show that the proposed knowledge-aware method leads to varied and consistent retrievals, outperforming state-of-the-art retrieval methods.
Authors: Xiaowen Ma, Zhenliang Ni, Xinghao Chen
Abstract: Vanilla pixel-level classifiers for semantic segmentation are based on a certain paradigm, involving the inner product of fixed prototypes obtained from the training set and pixel features in the test image. This approach, however, encounters significant limitations, \ie, feature deviation in the semantic domain and information loss in the spatial domain. The former struggles with large intra-class variance among pixel features from different images, while the latter fails to utilize the structured information of semantic objects effectively. This leads to blurred mask boundaries as well as a deficiency of fine-grained recognition capability. In this paper, we propose a novel Semantic and Spatial Adaptive Classifier (SSA-Seg) to address the above challenges. Specifically, we employ the coarse masks obtained from the fixed prototypes as a guide to adjust the fixed prototype towards the center of the semantic and spatial domains in the test image. The adapted prototypes in semantic and spatial domains are then simultaneously considered to accomplish classification decisions. In addition, we propose an online multi-domain distillation learning strategy to improve the adaption process. Experimental results on three publicly available benchmarks show that the proposed SSA-Seg significantly improves the segmentation performance of the baseline models with only a minimal increase in computational cost. Code is available at https://github.com/xwmaxwma/SSA-Seg.
Authors: Zhixing Zhang, Yanyu Li, Yushu Wu, Yanwu Xu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin, Junli Cao, Dimitris Metaxas, Sergey Tulyakov, Jian Ren
Abstract: Diffusion-based video generation models have demonstrated remarkable success in obtaining high-fidelity videos through the iterative denoising process. However, these models require multiple denoising steps during sampling, resulting in high computational costs. In this work, we propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained video diffusion models. We show that, through the adversarial training, the multi-steps video diffusion model, i.e., Stable Video Diffusion (SVD), can be trained to perform single forward pass to synthesize high-quality videos, capturing both temporal and spatial dependencies in the video data. Extensive experiments demonstrate that our method achieves competitive generation quality of synthesized videos with significantly reduced computational overhead for the denoising process (i.e., around $23\times$ speedup compared with SVD and $6\times$ speedup compared with existing works, with even better generation quality), paving the way for real-time video synthesis and editing. More visualization results are made publicly available at https://snap-research.github.io/SF-V.
Authors: Dongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, Hai Zhao
Abstract: Advancements in multimodal learning, particularly in video understanding and generation, require high-quality video-text datasets for improved model performance. Vript addresses this issue with a meticulously annotated corpus of 12K high-resolution videos, offering detailed, dense, and script-like captions for over 420K clips. Each clip has a caption of ~145 words, which is over 10x longer than most video-text datasets. Unlike captions only documenting static content in previous datasets, we enhance video captioning to video scripting by documenting not just the content, but also the camera operations, which include the shot types (medium shot, close-up, etc) and camera movements (panning, tilting, etc). By utilizing the Vript, we explore three training paradigms of aligning more text with the video modality rather than clip-caption pairs. This results in Vriptor, a top-performing video captioning model among open-source models, comparable to GPT-4V in performance. Vriptor is also a powerful model capable of end-to-end generation of dense and detailed captions for long videos. Moreover, we introduce Vript-Hard, a benchmark consisting of three video understanding tasks that are more challenging than existing benchmarks: Vript-HAL is the first benchmark evaluating action and object hallucinations in video LLMs, Vript-RR combines reasoning with retrieval resolving question ambiguity in long-video QAs, and Vript-ERO is a new task to evaluate the temporal understanding of events in long videos rather than actions in short videos in previous works. All code, models, and datasets are available in https://github.com/mutonix/Vript. PS: We have included more video-text datasets (Vript_CN & Vript_Multilingual) in the Vript series.
Authors: Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang, Zhiqiang Tao
Abstract: Large Vision-Language Models (LVLMs) have shown significant potential in assisting medical diagnosis by leveraging extensive biomedical datasets. However, the advancement of medical image understanding and reasoning critically depends on building high-quality visual instruction data, which is costly and labor-intensive to obtain, particularly in the medical domain. To mitigate this data-starving issue, we introduce Self-Training Large Language and Vision Assistant for Medicine (STLLaVA-Med). The proposed method is designed to train a policy model (an LVLM) capable of auto-generating medical visual instruction data to improve data efficiency, guided through Direct Preference Optimization (DPO). Specifically, a more powerful and larger LVLM (e.g., GPT-4o) is involved as a biomedical expert to oversee the DPO fine-tuning process on the auto-generated data, encouraging the policy model to align efficiently with human preferences. We validate the efficacy and data efficiency of STLLaVA-Med across three major medical Visual Question Answering (VQA) benchmarks, demonstrating competitive zero-shot performance with the utilization of only 9% of the medical data.
Authors: Md Farhan Ishmam, Ishmam Tashdeed, Talukder Asir Saadat, Md Hamjajul Ashmafee, Abu Raihan Mostofa Kamal, Md. Azam Hossain
Abstract: Can Visual Question Answering (VQA) systems perform just as well when deployed in the real world? Or are they susceptible to realistic corruption effects e.g. image blur, which can be detrimental in sensitive applications, such as medical VQA? While linguistic or textual robustness has been thoroughly explored in the VQA literature, there has yet to be any significant work on the visual robustness of VQA models. We propose the first large-scale benchmark comprising 213,000 augmented images, challenging the visual robustness of multiple VQA models and assessing the strength of realistic visual corruptions. Additionally, we have designed several robustness evaluation metrics that can be aggregated into a unified metric and tailored to fit a variety of use cases. Our experiments reveal several insights into the relationships between model size, performance, and robustness with the visual corruptions. Our benchmark highlights the need for a balanced approach in model development that considers model performance without compromising the robustness.
Authors: Youngseok Yoon, Dainong Hu, Iain Weissburg, Yao Qin, Haewon Jeong
Abstract: The success of generative models has reached a unique threshold where their outputs are indistinguishable from real data, leading to the inevitable contamination of future data collection pipelines with synthetic data. While their potential to generate infinite samples initially offers promise for reducing data collection costs and addressing challenges in data-scarce fields, the severe degradation in performance has been observed when iterative loops of training and generation occur -- known as ``model collapse.'' This paper explores a practical scenario in which a pretrained text-to-image diffusion model is finetuned using synthetic images generated from a previous iteration, a process we refer to as the ``Chain of Diffusion.'' We first demonstrate the significant degradation in image quality caused by this iterative process and identify the key factor driving this decline through rigorous empirical investigations. Drawing an analogy between the Chain of Diffusion and biological evolution, we then introduce a novel theoretical analysis based on quantitative trait modeling. Our theoretical analysis aligns with empirical observations of the generated images in the Chain of Diffusion. Finally, we propose Reusable Diffusion Finetuning (ReDiFine), a simple yet effective strategy inspired by genetic mutations. ReDiFine mitigates model collapse without requiring any hyperparameter tuning, making it a plug-and-play solution for reusable image generation.
Authors: Ali Abdollahi, Mahdi Ghaznavi, Mohammad Reza Karimi Nejad, Arash Mari Oriyad, Reza Abbasi, Ali Salesi, Melika Behjati, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
Abstract: Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well in simple single-person scenarios, in real-world applications, we often face complex situations in which there are persons of different genders doing different activities. We show that in such cases, VLMs are biased towards identifying the individual with the expected gender (according to ingrained gender stereotypes in the model or other forms of sample selection bias) as the performer of the activity. We refer to this bias in associating an activity with the gender of its actual performer in an image or text as the Gender-Activity Binding (GAB) bias and analyze how this bias is internalized in VLMs. To assess this bias, we have introduced the GAB dataset with approximately 5500 AI-generated images that represent a variety of activities, addressing the scarcity of real-world images for some scenarios. To have extensive quality control, the generated images are evaluated for their diversity, quality, and realism. We have tested 12 renowned pre-trained VLMs on this dataset in the context of text-to-image and image-to-text retrieval to measure the effect of this bias on their predictions. Additionally, we have carried out supplementary experiments to quantify the bias in VLMs' text encoders and to evaluate VLMs' capability to recognize activities. Our experiments indicate that VLMs experience an average performance decline of about 13.2% when confronted with gender-activity binding bias.
Authors: Hao-Yun Hsu, Yi-Ching Cheng, Guan-Hua Huang
Abstract: This study explored the architecture of semantic segmentation and evaluated models that excel in polyp segmentation. We present an integrated framework that harnesses the advantages of different models to attain an optimal outcome. Specifically, in this framework, we fuse the learned features from convolutional and transformer models for prediction, thus engendering an ensemble technique to enhance model performance. Our experiments on polyp segmentation revealed that the proposed architecture surpassed other top models, exhibiting improved learning capacity and resilience. The code is available at https://github.com/HuangDLab/EnFormer.
Authors: Zifan Chen, Xinyu Nan, Jiazheng Li, Jie Zhao, Haifeng Li, Ziling Lin, Haoshen Li, Heyun Chen, Yiting Liu, Lei Tang, Li Zhang, Bin Dong
Abstract: Volumetric segmentation is important in medical imaging, but current methods face challenges like requiring lots of manual annotations and being tailored to specific tasks, which limits their versatility. General segmentation models used for natural images don't perform well with the unique features of medical images. There's a strong need for an adaptable approach that can effectively handle different 3D medical structures and imaging modalities. In this study, we present PAM (Propagating Anything Model), a segmentation approach that uses a 2D prompt, like a bounding box or sketch, to create a complete 3D segmentation of medical image volumes. PAM works by modeling relationships between slices, maintaining information flow across the 3D structure. It combines a CNN-based UNet for processing within slices and a Transformer-based attention module for propagating information between slices, leading to better generalizability across various imaging modalities. PAM significantly outperformed existing models like MedSAM and SegVol, with an average improvement of over 18.1% in dice similarity coefficient (DSC) across 44 medical datasets and various object types. It also showed stable performance despite prompt deviations and different propagation setups, and faster inference speeds compared to other models. PAM's one-view prompt design made it more efficient, reducing interaction time by about 63.6% compared to two-view prompts. Thanks to its focus on structural relationships, PAM handled unseen and complex objects well, showing a unique ability to generalize to new situations. PAM represents an advancement in medical image segmentation, effectively reducing the need for extensive manual work and specialized training. Its adaptability makes it a promising tool for more automated and reliable analysis in clinical settings.
Authors: Hu Wang, David Butler, Yuan Zhang, Jodie Avery, Steven Knox, Congbo Ma, Louise Hull, Gustavo Carneiro
Abstract: Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs of the disease using either laparoscopic surgery or the analysis of T1/T2 MRI images, with the latter being quicker and cheaper but less accurate. A key diagnostic sign of endometriosis is the obliteration of the Pouch of Douglas (POD). However, even experienced clinicians struggle with accurately classifying POD obliteration from MRI images, which complicates the training of reliable AI models. In this paper, we introduce the Human-AI Collaborative Multi-modal Multi-rater Learning (HAICOMM) methodology to address the challenge above. HAICOMM is the first method that explores three important aspects of this problem: 1) multi-rater learning to extract a cleaner label from the multiple "noisy" labels available per training sample; 2) multi-modal learning to leverage the presence of T1/T2 MRI images for training and testing; and 3) human-AI collaboration to build a system that leverages the predictions from clinicians and the AI model to provide more accurate classification than standalone clinicians and AI models. Presenting results on the multi-rater T1/T2 MRI endometriosis dataset that we collected to validate our methodology, the proposed HAICOMM model outperforms an ensemble of clinicians, noisy-label learning models, and multi-rater learning methods.
Authors: Bulat Gabdullin, Nina Konovalova, Nikolay Patakin, Dmitry Senushkin, Anton Konushin
Abstract: Despite recent success in discriminative approaches in monocular depth estimation its quality remains limited by training datasets. Generative approaches mitigate this issue by leveraging strong priors derived from training on internet-scale datasets. Recent studies have demonstrated that large text-to-image diffusion models achieve state-of-the-art results in depth estimation when fine-tuned on small depth datasets. Concurrently, autoregressive generative approaches, such as the Visual AutoRegressive modeling~(VAR), have shown promising results in conditioned image synthesis. Following the visual autoregressive modeling paradigm, we introduce the first autoregressive depth estimation model based on the visual autoregressive transformer. Our primary contribution is DepthART -- a novel training method formulated as Depth Autoregressive Refinement Task. Unlike the original VAR training procedure, which employs static targets, our method utilizes a dynamic target formulation that enables model self-refinement and incorporates multi-modal guidance during training. Specifically, we use model predictions as inputs instead of ground truth token maps during training, framing the objective as residual minimization. Our experiments demonstrate that the proposed training approach significantly outperforms visual autoregressive modeling via next-scale prediction in the depth estimation task. The Visual Autoregressive Transformer trained with our approach on Hypersim achieves superior results on a set of unseen benchmarks compared to other generative and discriminative baselines.
Authors: Haonan Lin, Wenbin An, Jiahao Wang, Yan Chen, Feng Tian, Mengmeng Wang, Guang Dai, Qianying Wang, Jingdong Wang
Abstract: Recent advancements have shown promise in applying traditional Semi-Supervised Learning strategies to the task of Generalized Category Discovery (GCD). Typically, this involves a teacher-student framework in which the teacher imparts knowledge to the student to classify categories, even in the absence of explicit labels. Nevertheless, GCD presents unique challenges, particularly the absence of priors for new classes, which can lead to the teacher's misguidance and unsynchronized learning with the student, culminating in suboptimal outcomes. In our work, we delve into why traditional teacher-student designs falter in open-world generalized category discovery as compared to their success in closed-world semi-supervised learning. We identify inconsistent pattern learning across attention layers as the crux of this issue and introduce FlipClass, a method that dynamically updates the teacher to align with the student's attention, instead of maintaining a static teacher reference. Our teacher-student attention alignment strategy refines the teacher's focus based on student feedback from an energy perspective, promoting consistent pattern recognition and synchronized learning across old and new classes. Extensive experiments on a spectrum of benchmarks affirm that FlipClass significantly surpasses contemporary GCD methods, establishing new standards for the field.
Authors: Kaichen Zhou, Yang Cao, Taewhan Kim, Hao Zhao, Hao Dong, Kai Ming Ting, Ye Zhu
Abstract: Recent advancements in industrial anomaly detection have been hindered by the lack of realistic datasets that accurately represent real-world conditions. Existing algorithms are often developed and evaluated using idealized datasets, which deviate significantly from real-life scenarios characterized by environmental noise and data corruption such as fluctuating lighting conditions, variable object poses, and unstable camera positions. To address this gap, we introduce the Realistic Anomaly Detection (RAD) dataset, the first multi-view RGB-based anomaly detection dataset specifically collected using a real robot arm, providing unique and realistic data scenarios. RAD comprises 4765 images across 13 categories and 4 defect types, collected from more than 50 viewpoints, providing a comprehensive and realistic benchmark. This multi-viewpoint setup mirrors real-world conditions where anomalies may not be detectable from every perspective. Moreover, by sampling varying numbers of views, the algorithm's performance can be comprehensively evaluated across different viewpoints. This approach enhances the thoroughness of performance assessment and helps improve the algorithm's robustness. Besides, to support 3D multi-view reconstruction algorithms, we propose a data augmentation method to improve the accuracy of pose estimation and facilitate the reconstruction of 3D point clouds. We systematically evaluate state-of-the-art RGB-based and point cloud-based models using RAD, identifying limitations and future research directions. The code and dataset could found at https://github.com/kaichen-z/RAD
Authors: Jente Vandersanden, Sascha Holl, Xingchang Huang, Gurprit Singh
Abstract: Classical generative diffusion models learn an isotropic Gaussian denoising process, treating all spatial regions uniformly, thus neglecting potentially valuable structural information in the data. Inspired by the long-established work on anisotropic diffusion in image processing, we present a novel edge-preserving diffusion model that is a generalization of denoising diffusion probablistic models (DDPM). In particular, we introduce an edge-aware noise scheduler that varies between edge-preserving and isotropic Gaussian noise. We show that our model's generative process converges faster to results that more closely match the target distribution. We demonstrate its capability to better learn the low-to-mid frequencies within the dataset, which plays a crucial role in representing shapes and structural information. Our edge-preserving diffusion process consistently outperforms state-of-the-art baselines in unconditional image generation. It is also more robust for generative tasks guided by a shape-based prior, such as stroke-to-image generation. We present qualitative and quantitative results showing consistent improvements (FID score) of up to 30% for both tasks. We provide source code and supplementary content via the public domain edge-preserving-diffusion.mpi-inf.mpg.de .
Authors: Danai Triantafyllidou, Sarah Parisot, Ales Leonardis, Steven McDonagh
Abstract: Visual domain gaps often impact object detection performance. Image-to-image translation can mitigate this effect, where contrastive approaches enable learning of the image-to-image mapping under unsupervised regimes. However, existing methods often fail to handle content-rich scenes with multiple object instances, which manifests in unsatisfactory detection performance. Sensitivity to such instance-level content is typically only gained through object annotations, which can be expensive to obtain. Towards addressing this issue, we present a novel image-to-image translation method that specifically targets cross-domain object detection. We formulate our approach as a contrastive learning framework with an inductive prior that optimises the appearance of object instances through spatial attention masks, implicitly delineating the scene into foreground regions associated with the target object instances and background non-object regions. Instead of relying on object annotations to explicitly account for object instances during translation, our approach learns to represent objects by contrasting local-global information. This affords investigation of an under-explored challenge: obtaining performant detection, under domain shifts, without relying on object annotations nor detector model fine-tuning. We experiment with multiple cross-domain object detection settings across three challenging benchmarks and report state-of-the-art performance. Project page: https://local-global-detection.github.io
Authors: Chenyue Li, Shuoyi Chen, Mang Ye
Abstract: Wildlife ReID involves utilizing visual technology to identify specific individuals of wild animals in different scenarios, holding significant importance for wildlife conservation, ecological research, and environmental monitoring. Existing wildlife ReID methods are predominantly tailored to specific species, exhibiting limited applicability. Although some approaches leverage extensively studied person ReID techniques, they struggle to address the unique challenges posed by wildlife. Therefore, in this paper, we present a unified, multi-species general framework for wildlife ReID. Given that high-frequency information is a consistent representation of unique features in various species, significantly aiding in identifying contours and details such as fur textures, we propose the Adaptive High-Frequency Transformer model with the goal of enhancing high-frequency information learning. To mitigate the inevitable high-frequency interference in the wilderness environment, we introduce an object-aware high-frequency selection strategy to adaptively capture more valuable high-frequency components. Notably, we unify the experimental settings of multiple wildlife datasets for ReID, achieving superior performance over state-of-the-art ReID methods. In domain generalization scenarios, our approach demonstrates robust generalization to unknown species.
Authors: Linhui Xiao, Xiaoshan Yang, Fang Peng, Yaowei Wang, Changsheng Xu
Abstract: Constrained by the separate encoding of vision and language, existing grounding and referring segmentation works heavily rely on bulky Transformer-based fusion en-/decoders and a variety of early-stage interaction technologies. Simultaneously, the current mask visual language modeling (MVLM) fails to capture the nuanced referential relationship between image-text in referring tasks. In this paper, we propose OneRef, a minimalist referring framework built on the modality-shared one-tower transformer that unifies the visual and linguistic feature spaces. To modeling the referential relationship, we introduce a novel MVLM paradigm called Mask Referring Modeling (MRefM), which encompasses both referring-aware mask image modeling and referring-aware mask language modeling. Both modules not only reconstruct modality-related content but also cross-modal referring content. Within MRefM, we propose a referring-aware dynamic image masking strategy that is aware of the referred region rather than relying on fixed ratios or generic random masking schemes. By leveraging the unified visual language feature space and incorporating MRefM's ability to model the referential relations, our approach enables direct regression of the referring results without resorting to various complex techniques. Our method consistently surpasses existing approaches and achieves SoTA performance on both grounding and segmentation tasks, providing valuable insights for future research. Our code and models are available at https://github.com/linhuixiao/OneRef.
Authors: Chen Xu, Qiming Huang, Yuqi Hou, Jiangxing Wu, Fan Zhang, Hyung Jin Chang, Jianbo Jiao
Abstract: Medical image segmentation poses challenges due to domain gaps, data modality variations, and dependency on domain knowledge or experts, especially for low- and middle-income countries (LMICs). Whereas for humans, given a few exemplars (with corresponding labels), we are able to segment different medical images even without exten-sive domain-specific clinical training. In addition, current SAM-based medical segmentation models use fine-grained visual prompts, such as the bounding rectangle generated from manually annotated target segmentation mask, as the bounding box (bbox) prompt during the testing phase. However, in actual clinical scenarios, no such precise prior knowledge is available. Our experimental results also reveal that previous models nearly fail to predict when given coarser bbox prompts. Considering these issues, in this paper, we introduce a domain-aware selective adaptation approach to adapt the general knowledge learned from a large model trained with natural images to the corresponding medical domains/modalities, with access to only a few (e.g. less than 5) exemplars. Our method mitigates the aforementioned limitations, providing an efficient and LMICs-friendly solution. Extensive experimental analysis showcases the effectiveness of our approach, offering potential advancements in healthcare diagnostics and clinical applications in LMICs.
Authors: Abdoul Aziz Amadou, Yue Zhang, Sebastien Piat, Paul Klein, Ingo Schmuecking, Tiziano Passerini, Puneet Sharma
Abstract: Quantitative evaluation of echocardiography is essential for precise assessment of cardiac condition, monitoring disease progression, and guiding treatment decisions. The diverse nature of echo images, including variations in probe types, manufacturers, and pathologies, poses challenges for developing artificial intelligent models that can generalize across different clinical practice. We introduce EchoApex, the first general-purpose vision foundation model echocardiography with applications on a variety of clinical practice. Leveraging self-supervised learning, EchoApex is pretrained on over 20 million echo images from 11 clinical centres. By incorporating task-specific decoders and adapter modules, we demonstrate the effectiveness of EchoApex on 4 different kind of clinical applications with 28 sub-tasks, including view classification, interactive structure segmentation, left ventricle hypertrophy detection and automated ejection fraction estimation from view sequences. Compared to state-of-the-art task-specific models, EchoApex attains improved performance with a unified image encoding architecture, demonstrating the benefits of model pretraining at scale with in-domain data. Furthermore, EchoApex illustrates the potential for developing a general-purpose vision foundation model tailored specifically for echocardiography, capable of addressing a diverse range of clinical applications with high efficiency and efficacy.
Authors: Cheng Yu, Haoyu Xie, Lei Shang, Yang Liu, Jun Dan, Liefeng Bo, Baigui Sun
Abstract: In the field of human-centric personalized image generation, the adapter-based method obtains the ability to customize and generate portraits by text-to-image training on facial data. This allows for identity-preserved personalization without additional fine-tuning in inference. Although there are improvements in efficiency and fidelity, there is often a significant performance decrease in test following ability, controllability, and diversity of generated faces compared to the base model. In this paper, we analyze that the performance degradation is attributed to the failure to decouple identity features from other attributes during extraction, as well as the failure to decouple the portrait generation training from the overall generation task. To address these issues, we propose the Face Adapter with deCoupled Training (FACT) framework, focusing on both model architecture and training strategy. To decouple identity features from others, we leverage a transformer-based face-export encoder and harness fine-grained identity features. To decouple the portrait generation training, we propose Face Adapting Increment Regularization~(FAIR), which effectively constrains the effect of face adapters on the facial region, preserving the generative ability of the base model. Additionally, we incorporate a face condition drop and shuffle mechanism, combined with curriculum learning, to enhance facial controllability and diversity. As a result, FACT solely learns identity preservation from training data, thereby minimizing the impact on the original text-to-image capabilities of the base model. Extensive experiments show that FACT has both controllability and fidelity in both text-to-image generation and inpainting solutions for portrait generation.
Authors: Yuxuan Cai, Jiangning Zhang, Haoyang He, Xinwei He, Ao Tong, Zhenye Gan, Chengjie Wang, Xiang Bai
Abstract: The success of Large Language Models (LLM) has led researchers to explore Multimodal Large Language Models (MLLM) for unified visual and linguistic understanding. However, the increasing model size and computational complexity of MLLM limit their use in resource-constrained environments. Small-scale MLLM (s-MLLM) aims to retain the capabilities of the large-scale model (l-MLLM) while reducing computational demands, but resulting in a significant decline in performance. To address the aforementioned issues, we propose a novel LLaVA-KD framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM, and Relation Distillation (RDist) to transfer l-MLLM's ability to model correlations between visual features. Additionally, we propose a three-stage training scheme to fully exploit the potential of s-MLLM: 1) Distilled Pre-Training to align visual-textual representations, 2) Supervised Fine-Tuning to equip the model with multimodal understanding, and 3) Distilled Fine-Tuning to further transfer l-MLLM capabilities. Our approach significantly improves performance without altering the small model's architecture. Extensive experiments and ablation studies validate the effectiveness of each proposed component. Code will be available at https://github.com/Fantasyele/LLaVA-KD.
Authors: Yizhe Tang, Yue Wang, Teng Hu, Ran Yi, Xin Tan, Lizhuang Ma, Yu-Kun Lai, Paul L. Rosin
Abstract: Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image. Recently, Neural Painting methods that utilize deep learning and reinforcement learning models to predict the stroke sequences have been developed, but suffer from longer inference time or unstable training. To address these issues, we propose AttentionPainter, an efficient and adaptive model for single-step neural painting. First, we propose a novel scalable stroke predictor, which predicts a large number of stroke parameters within a single forward process, instead of the iterative prediction of previous Reinforcement Learning or auto-regressive methods, which makes AttentionPainter faster than previous neural painting methods. To further increase the training efficiency, we propose a Fast Stroke Stacking algorithm, which brings 13 times acceleration for training. Moreover, we propose Stroke-density Loss, which encourages the model to use small strokes for detailed information, to help improve the reconstruction quality. Finally, we propose a new stroke diffusion model for both conditional and unconditional stroke-based generation, which denoises in the stroke parameter space and facilitates stroke-based inpainting and editing applications helpful for human artists design. Extensive experiments show that AttentionPainter outperforms the state-of-the-art neural painting methods.
Authors: Suchisrit Gangopadhyay, Xien Chen, Michael Chu, Patrick Rim, Hyoungseob Park, Alex Wong
Abstract: We propose UnCLe, a standardized benchmark for Unsupervised Continual Learning of a multimodal depth estimation task: Depth completion aims to infer a dense depth map from a pair of synchronized RGB image and sparse depth map. We benchmark depth completion models under the practical scenario of unsupervised learning over continuous streams of data. Existing methods are typically trained on a static, or stationary, dataset. However, when adapting to novel non-stationary distributions, they "catastrophically forget" previously learned information. UnCLe simulates these non-stationary distributions by adapting depth completion models to sequences of datasets containing diverse scenes captured from distinct domains using different visual and range sensors. We adopt representative methods from continual learning paradigms and translate them to enable unsupervised continual learning of depth completion. We benchmark these models for indoor and outdoor and investigate the degree of catastrophic forgetting through standard quantitative metrics. Furthermore, we introduce model inversion quality as an additional measure of forgetting. We find that unsupervised continual learning of depth completion is an open problem, and we invite researchers to leverage UnCLe as a development platform.
Authors: Lehan Wang, Haonan Wang, Honglong Yang, Jiaji Mao, Zehong Yang, Jun Shen, Xiaomeng Li
Abstract: Several medical Multimodal Large Languange Models (MLLMs) have been developed to address tasks involving visual images with textual instructions across various medical modalities, achieving impressive results. Most current medical generalist models are region-agnostic, treating the entire image as a holistic representation. However, they struggle to identify which specific regions they are focusing on when generating a sentence. To mimic the behavior of doctors, who typically begin by reviewing the entire image before concentrating on specific regions for a thorough evaluation, we aim to enhance the capability of medical MLLMs in understanding anatomical regions within entire medical scans. To achieve it, we first formulate Region-Centric tasks and construct a large-scale dataset, MedRegInstruct, to incorporate regional information into training. Combining our collected dataset with other medical multimodal corpora for training, we propose a Region-Aware medical MLLM, MedRegA, which is the first bilingual generalist medical AI system to simultaneously handle image-level and region-level medical vision-language tasks across a broad range of modalities. Our MedRegA not only enables three region-centric tasks, but also achieves the best performance for visual question answering, report generation and medical image classification over 8 modalities, showcasing significant versatility. Experiments demonstrate that our model can not only accomplish powerful performance across various medical vision-language tasks in bilingual settings, but also recognize and detect structures in multimodal medical scans, boosting the interpretability and user interactivity of medical MLLMs. Our project page is https://medrega.github.io.
Authors: Tom\'a\v{s} Pivo\v{n}ka, Libor P\v{r}eu\v{c}il
Abstract: Re-ranking is the second stage of a visual place recognition task, in which the system chooses the best-matching images from a pre-selected subset of candidates. Model-free approaches compute the image pair similarity based on a spatial comparison of corresponding local visual features, eliminating the need for computationally expensive estimation of a model describing transformation between images. The article focuses on model-free re-ranking based on standard local visual features and their applicability in long-term autonomy systems. It introduces three new model-free re-ranking methods that were designed primarily for deep-learned local visual features. These features evince high robustness to various appearance changes, which stands as a crucial property for use with long-term autonomy systems. All the introduced methods were employed in a new visual place recognition system together with the D2-net feature detector (Dusmanu, 2019) and experimentally tested with diverse, challenging public datasets. The obtained results are on par with current state-of-the-art methods, affirming that model-free approaches are a viable and worthwhile path for long-term visual place recognition.
Authors: Haonan Lin, Mengmeng Wang, Jiahao Wang, Wenbin An, Yan Chen, Yong Liu, Feng Tian, Guang Dai, Jingdong Wang, Qianying Wang
Abstract: Text-guided diffusion models have significantly advanced image editing, enabling high-quality and diverse modifications driven by text prompts. However, effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. These errors accumulate during the diffusion process, resulting in inferior content preservation and edit fidelity, especially with conditional inputs. We address these challenges by investigating the primary contributors to error accumulation in DDIM inversion and identify the singularity problem in traditional noise schedules as a key issue. To resolve this, we introduce the Logistic Schedule, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. This schedule reduces noise prediction errors, enabling more faithful editing that preserves the original content of the source image. Our approach requires no additional retraining and is compatible with various existing editing methods. Experiments across eight editing tasks demonstrate the Logistic Schedule's superior performance in content preservation and edit fidelity compared to traditional noise schedules, highlighting its adaptability and effectiveness.
Authors: Florentin Guth, Brice M\'enard, Gaspar Rochette, St\'ephane Mallat
Abstract: A central question in deep learning is to understand the functions learned by deep networks. What is their approximation class? Do the learned weights and representations depend on initialization? Previous empirical work has evidenced that kernels defined by network activations are similar across initializations. For shallow networks, this has been theoretically studied with random feature models, but an extension to deep networks has remained elusive. Here, we provide a deep extension of such random feature models, which we call the rainbow model. We prove that rainbow networks define deterministic (hierarchical) kernels in the infinite-width limit. The resulting functions thus belong to a data-dependent RKHS which does not depend on the weight randomness. We also verify numerically our modeling assumptions on deep CNNs trained on image classification tasks, and show that the trained networks approximately satisfy the rainbow hypothesis. In particular, rainbow networks sampled from the corresponding random feature model achieve similar performance as the trained networks. Our results highlight the central role played by the covariances of network weights at each layer, which are observed to be low-rank as a result of feature learning.
Authors: Yujin Oh, Sangjoon Park, Hwa Kyung Byun, Yeona Cho, Ik Jae Lee, Jin Sung Kim, Jong Chul Ye
Abstract: Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present a novel LLM-driven multimodal AI, namely LLMSeg, that utilizes the clinical text information and is applicable to the challenging task of target volume contouring for radiation therapy, and validate it within the context of breast cancer radiation therapy target volume contouring. Using external validation and data-insufficient environments, which attributes highly conducive to real-world applications, we demonstrate that the proposed model exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data efficiency. To our best knowledge, this is the first LLM-driven multimodal AI model that integrates the clinical text information into target volume delineation for radiation oncology.
Authors: Daxin Li, Yuanchao Bai, Kai Wang, Junjun Jiang, Xianming Liu
Abstract: Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and texture loss, thereby compromising perceptual quality of images. To address these issues, this study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss, to enhance the perceptual quality of image reconstructions. Additionally, we have implemented a latent refinement process to generate content-aware latent codes. These codes adhere to bit-rate constraints, balance the trade-off between distortion and fidelity, and prioritize bit allocation to regions of greater importance. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression. On CLIC2024 validation set, our approach achieves a 62% bitrate saving compared to MS-ILLM under FID metric.
Authors: Yipeng Sun, Linda-Sophie Schneider, Fuxin Fan, Mareike Thies, Mingxuan Gu, Siyuan Mei, Yuzhong Zhou, Siming Bayer, Andreas Maier
Abstract: In this study, we introduce a Fourier series-based trainable filter for computed tomography (CT) reconstruction within the filtered backprojection (FBP) framework. This method overcomes the limitation in noise reduction by optimizing Fourier series coefficients to construct the filter, maintaining computational efficiency with minimal increment for the trainable parameters compared to other deep learning frameworks. Additionally, we propose Gaussian edge-enhanced (GEE) loss function that prioritizes the $L_1$ norm of high-frequency magnitudes, effectively countering the blurring problems prevalent in mean squared error (MSE) approaches. The model's foundation in the FBP algorithm ensures excellent interpretability, as it relies on a data-driven filter with all other parameters derived through rigorous mathematical procedures. Designed as a plug-and-play solution, our Fourier series-based filter can be easily integrated into existing CT reconstruction models, making it an adaptable tool for a wide range of practical applications. Code and data are available at https://github.com/sypsyp97/Trainable-Fourier-Series.
Authors: Vishnu Sarukkai, Lu Yuan, Mia Tang, Maneesh Agrawala, Kayvon Fatahalian
Abstract: We introduce a novel sketch-to-image tool that aligns with the iterative refinement process of artists. Our tool lets users sketch blocking strokes to coarsely represent the placement and form of objects and detail strokes to refine their shape and silhouettes. We develop a two-pass algorithm for generating high-fidelity images from such sketches at any point in the iterative process. In the first pass we use a ControlNet to generate an image that strictly follows all the strokes (blocking and detail) and in the second pass we add variation by renoising regions surrounding blocking strokes. We also present a dataset generation scheme that, when used to train a ControlNet architecture, allows regions that do not contain strokes to be interpreted as not-yet-specified regions rather than empty space. We show that this partial-sketch-aware ControlNet can generate coherent elements from partial sketches that only contain a small number of strokes. The high-fidelity images produced by our approach serve as scaffolds that can help the user adjust the shape and proportions of objects or add additional elements to the composition. We demonstrate the effectiveness of our approach with a variety of examples and evaluative comparisons. Quantitatively, evaluative user feedback indicates that novice viewers prefer the quality of images from our algorithm over a baseline Scribble ControlNet for 84% of the pairs and found our images had less distortion in 81% of the pairs.
Authors: Jiaxu Xing, Angel Romero, Leonard Bauersfeld, Davide Scaramuzza
Abstract: Learning visuomotor policies for agile quadrotor flight presents significant difficulties, primarily from inefficient policy exploration caused by high-dimensional visual inputs and the need for precise and low-latency control. To address these challenges, we propose a novel approach that combines the performance of Reinforcement Learning (RL) and the sample efficiency of Imitation Learning (IL) in the task of vision-based autonomous drone racing. While RL provides a framework for learning high-performance controllers through trial and error, it faces challenges with sample efficiency and computational demands due to the high dimensionality of visual inputs. Conversely, IL efficiently learns from visual expert demonstrations, but it remains limited by the expert's performance and state distribution. To overcome these limitations, our policy learning framework integrates the strengths of both approaches. Our framework contains three phases: training a teacher policy using RL with privileged state information, distilling it into a student policy via IL, and adaptive fine-tuning via RL. Testing in both simulated and real-world scenarios shows our approach can not only learn in scenarios where RL from scratch fails but also outperforms existing IL methods in both robustness and performance, successfully navigating a quadrotor through a race course using only visual information.
Authors: Tianye Ding, Hongyu Li, Huaizu Jiang
Abstract: Obstacle detection and tracking represent a critical component in robot autonomous navigation. In this paper, we propose ODTFormer, a Transformer-based model to address both obstacle detection and tracking problems. For the detection task, our approach leverages deformable attention to construct a 3D cost volume, which is decoded progressively in the form of voxel occupancy grids. We further track the obstacles by matching the voxels between consecutive frames. The entire model can be optimized in an end-to-end manner. Through extensive experiments on DrivingStereo and KITTI benchmarks, our model achieves state-of-the-art performance in the obstacle detection task. We also report comparable accuracy to state-of-the-art obstacle tracking models while requiring only a fraction of their computation cost, typically ten-fold to twenty-fold less. The code and model weights will be publicly released.
Authors: Zhengsen Xu, Jonathan Li, Sibo Cheng, Xue Rui, Yu Zhao, Hongjie He, Linlin Xu
Abstract: Wildfires have significant impacts on global vegetation, wildlife, and humans. They destroy plant communities and wildlife habitats and contribute to increased emissions of carbon dioxide, nitrogen oxides, methane, and other pollutants. The prediction of wildfires relies on various independent variables combined with regression or machine learning methods. In this technical review, we describe the options for independent variables, data processing techniques, models, independent variables collinearity and importance estimation methods, and model performance evaluation metrics. First, we divide the independent variables into 4 aspects, including climate and meteorology conditions, socio-economical factors, terrain and hydrological features, and wildfire historical records. Second, preprocessing methods are described for different magnitudes, different spatial-temporal resolutions, and different formats of data. Third, the collinearity and importance evaluation methods of independent variables are also considered. Fourth, we discuss the application of statistical models, traditional machine learning models, and deep learning models in wildfire risk prediction. In this subsection, compared with other reviews, this manuscript particularly discusses the evaluation metrics and recent advancements in deep learning methods. Lastly, addressing the limitations of current research, this paper emphasizes the need for more effective deep learning time series forecasting algorithms, the utilization of three-dimensional data including ground and trunk fuel, extraction of more accurate historical fire point data, and improved model evaluation metrics.
Authors: Zheyuan Zhang, Elif Keles, Gorkem Durak, Yavuz Taktak, Onkar Susladkar, Vandan Gorade, Debesh Jha, Asli C. Ormeci, Alpay Medetalibeyoglu, Lanhong Yao, Bin Wang, Ilkin Sevgi Isler, Linkai Peng, Hongyi Pan, Camila Lopes Vendrami, Amir Bourhani, Yury Velichko, Boqing Gong, Concetto Spampinato, Ayis Pyrros, Pallavi Tiwari, Derk C. F. Klatte, Megan Engels, Sanne Hoogenboom, Candice W. Bolan, Emil Agarunov, Nassier Harfouch, Chenchan Huang, Marco J. Bruno, Ivo Schoots, Rajesh N. Keswani, Frank H. Miller, Tamas Gonda, Cemal Yazici, Temel Tirkes, Baris Turkbey, Michael B. Wallace, Ulas Bagci
Abstract: Automated volumetric segmentation of the pancreas on cross-sectional imaging is needed for diagnosis and follow-up of pancreatic diseases. While CT-based pancreatic segmentation is more established, MRI-based segmentation methods are understudied, largely due to a lack of publicly available datasets, benchmarking research efforts, and domain-specific deep learning methods. In this retrospective study, we collected a large dataset (767 scans from 499 participants) of T1-weighted (T1W) and T2-weighted (T2W) abdominal MRI series from five centers between March 2004 and November 2022. We also collected CT scans of 1,350 patients from publicly available sources for benchmarking purposes. We developed a new pancreas segmentation method, called PanSegNet, combining the strengths of nnUNet and a Transformer network with a new linear attention module enabling volumetric computation. We tested PanSegNet's accuracy in cross-modality (a total of 2,117 scans) and cross-center settings with Dice and Hausdorff distance (HD95) evaluation metrics. We used Cohen's kappa statistics for intra and inter-rater agreement evaluation and paired t-tests for volume and Dice comparisons, respectively. For segmentation accuracy, we achieved Dice coefficients of 88.3% (std: 7.2%, at case level) with CT, 85.0% (std: 7.9%) with T1W MRI, and 86.3% (std: 6.4%) with T2W MRI. There was a high correlation for pancreas volume prediction with R^2 of 0.91, 0.84, and 0.85 for CT, T1W, and T2W, respectively. We found moderate inter-observer (0.624 and 0.638 for T1W and T2W MRI, respectively) and high intra-observer agreement scores. All MRI data is made available at https://osf.io/kysnj/. Our source code is available at https://github.com/NUBagciLab/PaNSegNet.
URLs: https://osf.io/kysnj/., https://github.com/NUBagciLab/PaNSegNet.
Authors: Luca Savant Aira, Antonio Montanaro, Emanuele Aiello, Diego Valsesia, Enrico Magli
Abstract: Generating videos with realistic and physically plausible motion is one of the main recent challenges in computer vision. While diffusion models are achieving compelling results in image generation, video diffusion models are limited by heavy training and huge models, resulting in videos that are still biased to the training dataset. In this work we propose MotionCraft, a new zero-shot video generator to craft physics-based and realistic videos. MotionCraft is able to warp the noise latent space of an image diffusion model, such as Stable Diffusion, by applying an optical flow derived from a physics simulation. We show that warping the noise latent space results in coherent application of the desired motion while allowing the model to generate missing elements consistent with the scene evolution, which would otherwise result in artefacts or missing content if the flow was applied in the pixel space. We compare our method with the state-of-the-art Text2Video-Zero reporting qualitative and quantitative improvements, demonstrating the effectiveness of our approach to generate videos with finely-prescribed complex motion dynamics. Project page: https://mezzelfo.github.io/MotionCraft/
Authors: Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri Krishnan, Christopher Kanan
Abstract: Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing transferability and out-of-distribution (OOD) generalization of pre-trained DNN embeddings through the lens of the tunnel effect hypothesis, which is closely related to intermediate neural collapse. This hypothesis suggests that deeper DNN layers compress representations and hinder OOD generalization. Contrary to earlier work, our experiments show this is not a universal phenomenon. We comprehensively investigate the impact of DNN architecture, training data, image resolution, and augmentations on transferability. We identify that training with high-resolution datasets containing many classes greatly reduces representation compression and improves transferability. Our results emphasize the danger of generalizing findings from toy datasets to broader contexts.
Authors: Jianbiao Mei, Yukai Ma, Xuemeng Yang, Licheng Wen, Xinyu Cai, Xin Li, Daocheng Fu, Bo Zhang, Pinlong Cai, Min Dou, Botian Shi, Liang He, Yong Liu, Yu Qiao
Abstract: Autonomous driving has advanced significantly due to sensors, machine learning, and artificial intelligence improvements. However, prevailing methods struggle with intricate scenarios and causal relationships, hindering adaptability and interpretability in varied environments. To address the above problems, we introduce LeapAD, a novel paradigm for autonomous driving inspired by the human cognitive process. Specifically, LeapAD emulates human attention by selecting critical objects relevant to driving decisions, simplifying environmental interpretation, and mitigating decision-making complexities. Additionally, LeapAD incorporates an innovative dual-process decision-making module, which consists of an Analytic Process (System-II) for thorough analysis and reasoning, along with a Heuristic Process (System-I) for swift and empirical processing. The Analytic Process leverages its logical reasoning to accumulate linguistic driving experience, which is then transferred to the Heuristic Process by supervised fine-tuning. Through reflection mechanisms and a growing memory bank, LeapAD continuously improves itself from past mistakes in a closed-loop environment. Closed-loop testing in CARLA shows that LeapAD outperforms all methods relying solely on camera input, requiring 1-2 orders of magnitude less labeled data. Experiments also demonstrate that as the memory bank expands, the Heuristic Process with only 1.8B parameters can inherit the knowledge from a GPT-4 powered Analytic Process and achieve continuous performance improvement. Project page: https://pjlab-adg.github.io/LeapAD.
Authors: Wenbo Yu, Hao Fang, Bin Chen, Xiaohang Sui, Chuan Chen, Hao Wu, Shu-Tao Xia, Ke Xu
Abstract: Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients and have raised considerable privacy concerns. A majority of gradient inversion methods rely heavily on explicit prior knowledge (e.g., a well pre-trained generative model), which is often unavailable in realistic scenarios. To alleviate this issue, researchers have proposed to leverage the implicit prior knowledge of an over-parameterized network. However, they only utilize a fixed neural architecture for all the attack settings. This would hinder the adaptive use of implicit architectural priors and consequently limit the generalizability. In this paper, we further exploit such implicit prior knowledge by proposing Gradient Inversion via Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures. Extensive experiments verify that our proposed GI-NAS can achieve superior attack performance compared to state-of-the-art gradient inversion methods, even under more practical settings with high-resolution images, large-sized batches, and advanced defense strategies.
Authors: Aditya K Surikuchi, Raquel Fern\'andez, Sandro Pezzelle
Abstract: Visual storytelling consists in generating a natural language story given a temporally ordered sequence of images. This task is not only challenging for models, but also very difficult to evaluate with automatic metrics since there is no consensus about what makes a story 'good'. In this paper, we introduce a novel method that measures story quality in terms of human likeness regarding three key aspects highlighted in previous work: visual grounding, coherence, and repetitiveness. We then use this method to evaluate the stories generated by several models, showing that the foundation model LLaVA obtains the best result, but only slightly so compared to TAPM, a 50-times smaller visual storytelling model. Upgrading the visual and language components of TAPM results in a model that yields competitive performance with a relatively low number of parameters. Finally, we carry out a human evaluation study, whose results suggest that a 'good' story may require more than a human-like level of visual grounding, coherence, and repetition.
Authors: Bidur Khanal, Tianhong Dai, Binod Bhattarai, Cristian Linte
Abstract: The robustness of supervised deep learning-based medical image classification is significantly undermined by label noise. Although several methods have been proposed to enhance classification performance in the presence of noisy labels, they face some challenges: 1) a struggle with class-imbalanced datasets, leading to the frequent overlooking of minority classes as noisy samples; 2) a singular focus on maximizing performance using noisy datasets, without incorporating experts-in-the-loop for actively cleaning the noisy labels. To mitigate these challenges, we propose a two-phase approach that combines Learning with Noisy Labels (LNL) and active learning. This approach not only improves the robustness of medical image classification in the presence of noisy labels, but also iteratively improves the quality of the dataset by relabeling the important incorrect labels, under a limited annotation budget. Furthermore, we introduce a novel Variance of Gradients approach in LNL phase, which complements the loss-based sample selection by also sampling under-represented samples. Using two imbalanced noisy medical classification datasets, we demonstrate that that our proposed technique is superior to its predecessors at handling class imbalance by not misidentifying clean samples from minority classes as mostly noisy samples.
Authors: Marawan Elbatel, Hualiang Wang, Jixiang Chen, Hao Wang, Xiaomeng Li
Abstract: Federated semi-supervised learning (FedSemi) refers to scenarios where there may be clients with fully labeled data, clients with partially labeled, and even fully unlabeled clients while preserving data privacy. However, challenges arise from client drift due to undefined heterogeneous class distributions and erroneous pseudo-labels. Existing FedSemi methods typically fail to aggregate models from unlabeled clients due to their inherent unreliability, thus overlooking unique information from their heterogeneous data distribution, leading to sub-optimal results. In this paper, we enable unlabeled client aggregation through SemiAnAgg, a novel Semi-supervised Anchor-Based federated Aggregation. SemiAnAgg learns unlabeled client contributions via an anchor model, effectively harnessing their informative value. Our key idea is that by feeding local client data to the same global model and the same consistently initialized anchor model (i.e., random model), we can measure the importance of each unlabeled client accordingly. Extensive experiments demonstrate that SemiAnAgg achieves new state-of-the-art results on four widely used FedSemi benchmarks, leading to substantial performance improvements: a 9% increase in accuracy on CIFAR-100 and a 7.6% improvement in recall on the medical dataset ISIC-18, compared with prior state-of-the-art. Code is available at: https://github.com/xmed-lab/SemiAnAgg.
Authors: Ruoxuan Feng, Di Hu, Wenke Ma, Xuelong Li
Abstract: Humans possess a remarkable talent for flexibly alternating to different senses when interacting with the environment. Picture a chef skillfully gauging the timing of ingredient additions and controlling the heat according to the colors, sounds, and aromas, seamlessly navigating through every stage of the complex cooking process. This ability is founded upon a thorough comprehension of task stages, as achieving the sub-goal within each stage can necessitate the utilization of different senses. In order to endow robots with similar ability, we incorporate the task stages divided by sub-goals into the imitation learning process to accordingly guide dynamic multi-sensory fusion. We propose MS-Bot, a stage-guided dynamic multi-sensory fusion method with coarse-to-fine stage understanding, which dynamically adjusts the priority of modalities based on the fine-grained state within the predicted current stage. We train a robot system equipped with visual, auditory, and tactile sensors to accomplish challenging robotic manipulation tasks: pouring and peg insertion with keyway. Experimental results indicate that our approach enables more effective and explainable dynamic fusion, aligning more closely with the human fusion process than existing methods.
Authors: Anissa Alloula, Rima Mustafa, Daniel R McGowan, Bart{\l}omiej W. Papie\.z
Abstract: Recent work has uncovered alarming disparities in the performance of machine learning models in healthcare. In this study, we explore whether such disparities are present in the UK Biobank fundus retinal images by training and evaluating a disease classification model on these images. We assess possible disparities across various population groups and find substantial differences despite strong overall performance of the model. In particular, we discover unfair performance for certain assessment centres, which is surprising given the rigorous data standardisation protocol. We compare how these differences emerge and apply a range of existing bias mitigation methods to each one. A key insight is that each disparity has unique properties and responds differently to the mitigation methods. We also find that these methods are largely unable to enhance fairness, highlighting the need for better bias mitigation methods tailored to the specific type of bias.
Authors: Arthur Longuefosse, Baudouin Denis de Senneville, Gael Dournes, Ilyes Benlala, Pascal Desbarats, Fabien Baldacci
Abstract: In medical image synthesis, the precision of localized structural details is crucial, particularly when addressing specific clinical requirements such as the identification and measurement of fine structures. Traditional methods for image translation and synthesis are generally optimized for global image reconstruction but often fall short in providing the finesse required for detailed local analysis. This study represents a step toward addressing this challenge by introducing a novel anatomical feature-prioritized (AFP) loss function into the synthesis process. This method enhances reconstruction by focusing on clinically significant structures, utilizing features from a pre-trained model designed for a specific downstream task, such as the segmentation of particular anatomical regions. The AFP loss function can replace or complement global reconstruction methods, ensuring a balanced emphasis on both global image fidelity and local structural details. Various implementations of this loss function are explored, including its integration into different synthesis networks such as GAN-based and CNN-based models. Our approach is applied and evaluated in two contexts: lung MR to CT translation, focusing on high-quality reconstruction of bronchial structures, using a private dataset; and pelvis MR to CT synthesis, targeting the accurate representation of organs and muscles, utilizing a public dataset from the Synthrad2023 challenge. We leverage embeddings from pre-trained segmentation models specific to these anatomical regions to demonstrate the capability of the AFP loss to prioritize and accurately reconstruct essential features. This tailored approach shows promising potential for enhancing the specificity and practicality of medical image synthesis in clinical applications.
Authors: Liang Chen, Yong Zhang, Yibing Song, Zhiqiang Shen, Lingqiao Liu
Abstract: Domain generalization (DG) methods aim to maintain good performance in an unseen target domain by using training data from multiple source domains. While success on certain occasions are observed, enhancing the baseline across most scenarios remains challenging. This work introduces a simple yet effective framework, dubbed learning from multiple experts (LFME), that aims to make the target model an expert in all source domains to improve DG. Specifically, besides learning the target model used in inference, LFME will also train multiple experts specialized in different domains, whose output probabilities provide professional guidance by simply regularizing the logit of the target model. Delving deep into the framework, we reveal that the introduced logit regularization term implicitly provides effects of enabling the target model to harness more information, and mining hard samples from the experts during training. Extensive experiments on benchmarks from different DG tasks demonstrate that LFME is consistently beneficial to the baseline and can achieve comparable performance to existing arts. Code is available at~\url{https://github.com/liangchen527/LFME}.
Authors: Yanguang Zhao, Long Bai, Zhaoxi Zhang, Yanan Wu, Mobarakol Islam, Hongliang Ren
Abstract: Glioma, a common and deadly brain tumor, requires early diagnosis for improved prognosis. However, low-quality Magnetic Resonance Imaging (MRI) technology in Sub-Saharan Africa (SSA) hinders accurate diagnosis. This paper presents our work in the BraTS Challenge on SSA Adult Glioma. We adopt the model from the BraTS-GLI 2021 winning solution and utilize it with three training strategies: (1) initially training on the BraTS-GLI 2021 dataset with fine-tuning on the BraTS-Africa dataset, (2) training solely on the BraTS-Africa dataset, and (3) training solely on the BraTS-Africa dataset with 2x super-resolution enhancement. Results show that initial training on the BraTS-GLI 2021 dataset followed by fine-tuning on the BraTS-Africa dataset has yielded the best results. This suggests the importance of high-quality datasets in providing prior knowledge during training. Our top-performing model achieves Dice scores of 0.882, 0.840, and 0.926, and Hausdorff Distance (95%) scores of 15.324, 37.518, and 13.971 for enhancing tumor, tumor core, and whole tumor, respectively, in the validation phase. In the final phase of the competition, our approach successfully secured second place overall, reflecting the strength and effectiveness of our model and training strategies. Our approach provides insights into improving glioma diagnosis in SSA, showing the potential of deep learning in resource-limited settings and the importance of transfer learning from high-quality datasets.