Authors: Jiayu Huo, Yang Liu, Xi Ouyang, Alejandro Granados, Sebastien Ourselin, Rachel Sparks
Accurately segmenting brain lesions in MRI scans is critical for providing patients with prognoses and neurological monitoring. However, the performance of CNN-based segmentation methods is constrained by the limited training set size. Advanced data augmentation is an effective strategy to improve the model's robustness. However, they often introduce intensity disparities between foreground and background areas and boundary artifacts, which weakens the effectiveness of such strategies. In this paper, we propose a foreground harmonization framework (ARHNet) to tackle intensity disparities and make synthetic images look more realistic. In particular, we propose an Adaptive Region Harmonization (ARH) module to dynamically align foreground feature maps to the background with an attention mechanism. We demonstrate the efficacy of our method in improving the segmentation performance using real and synthetic images. Experimental results on the ATLAS 2.0 dataset show that ARHNet outperforms other methods for image harmonization tasks, and boosts the down-stream segmentation performance. Our code is publicly available at https://github.com/King-HAW/ARHNet.
Authors: Adnan Qayyum, Hassan Ali, Massimo Caputo, Hunaid Vohra, Taofeek Akinosho, Sofiat Abioye, Ilhem Berrou, Paweł Capik, Junaid Qadir, Muhammad Bilal
Over the past few years, surgical data science has attracted substantial interest from the machine learning (ML) community. Various studies have demonstrated the efficacy of emerging ML techniques in analysing surgical data, particularly recordings of procedures, for digitizing clinical and non-clinical functions like preoperative planning, context-aware decision-making, and operating skill assessment. However, this field is still in its infancy and lacks representative, well-annotated datasets for training robust models in intermediate ML tasks. Also, existing datasets suffer from inaccurate labels, hindering the development of reliable models. In this paper, we propose a systematic methodology for developing robust models for surgical tool detection using noisy data. Our methodology introduces two key innovations: (1) an intelligent active learning strategy for minimal dataset identification and label correction by human experts; and (2) an assembling strategy for a student-teacher model-based self-training framework to achieve the robust classification of 14 surgical tools in a semi-supervised fashion. Furthermore, we employ weighted data loaders to handle difficult class labels and address class imbalance issues. The proposed methodology achieves an average F1-score of 85.88\% for the ensemble model-based self-training with class weights, and 80.88\% without class weights for noisy labels. Also, our proposed method significantly outperforms existing approaches, which effectively demonstrates its effectiveness.
Authors: Tobias Goodwin-Allcock, Ting Gong, Robert Gray, Parashkev Nachev, Hui Zhang
We propose a new method, Patch-CNN, for diffusion tensor (DT) estimation from only six-direction diffusion weighted images (DWI). Deep learning-based methods have been recently proposed for dMRI parameter estimation, using either voxel-wise fully-connected neural networks (FCN) or image-wise convolutional neural networks (CNN). In the acute clinical context -- where pressure of time limits the number of imaged directions to a minimum -- existing approaches either require an infeasible number of training images volumes (image-wise CNNs), or do not estimate the fibre orientations (voxel-wise FCNs) required for tractogram estimation. To overcome these limitations, we propose Patch-CNN, a neural network with a minimal (non-voxel-wise) convolutional kernel (3$\times$3$\times$3). Compared with voxel-wise FCNs, this has the advantage of allowing the network to leverage local anatomical information. Compared with image-wise CNNs, the minimal kernel vastly reduces training data demand. Evaluated against both conventional model fitting and a voxel-wise FCN, Patch-CNN, trained with a single subject is shown to improve the estimation of both scalar dMRI parameters and fibre orientation from six-direction DWIs. The improved fibre orientation estimation is shown to produce improved tractogram.
Authors: Aniket Gupta, Yiming Xie, Hanumant Singh, Huaizu Jiang
Although deep neural networks endow the downsampled superpoints with discriminative feature representations, directly matching them is usually not used alone in state-of-the-art methods, mainly for two reasons. First, the correspondences are inevitably noisy, so RANSAC-like refinement is usually adopted. Such ad hoc postprocessing, however, is slow and not differentiable, which can not be jointly optimized with feature learning. Second, superpoints are sparse and thus more RANSAC iterations are needed. Existing approaches use the coarse-to-fine strategy to propagate the superpoints correspondences to the point level, which are not discriminative enough and further necessitates the postprocessing refinement. In this paper, we present a simple yet effective approach to extract correspondences by directly matching superpoints using a global softmax layer in an end-to-end manner, which are used to determine the rigid transformation between the source and target point cloud. Compared with methods that directly predict corresponding points, by leveraging the rich information from the superpoints matchings, we can obtain more accurate estimation of the transformation and effectively filter out outliers without any postprocessing refinement. As a result, our approach is not only fast, but also achieves state-of-the-art results on the challenging ModelNet and 3DMatch benchmarks. Our code and model weights will be publicly released.
Authors: Ritu Yadav, Andrea Nascetti, Yifang Ban
Accurate estimation of building heights is essential for urban planning, infrastructure management, and environmental analysis. In this study, we propose a supervised Multimodal Building Height Regression Network (MBHR-Net) for estimating building heights at 10m spatial resolution using Sentinel-1 (S1) and Sentinel-2 (S2) satellite time series. S1 provides Synthetic Aperture Radar (SAR) data that offers valuable information on building structures, while S2 provides multispectral data that is sensitive to different land cover types, vegetation phenology, and building shadows. Our MBHR-Net aims to extract meaningful features from the S1 and S2 images to learn complex spatio-temporal relationships between image patterns and building heights. The model is trained and tested in 10 cities in the Netherlands. Root Mean Squared Error (RMSE), Intersection over Union (IOU), and R-squared (R2) score metrics are used to evaluate the performance of the model. The preliminary results (3.73m RMSE, 0.95 IoU, 0.61 R2) demonstrate the effectiveness of our deep learning model in accurately estimating building heights, showcasing its potential for urban planning, environmental impact analysis, and other related applications.
Authors: Ye Bi, Leticia M.Campos, Jin Wang, Haipeng Yu, Mark D.Hanigan, Gota Morota
Monitoring cow body weight is crucial to support farm management decisions due to its direct relationship with the growth, nutritional status, and health of dairy cows. Cow body weight is a repeated trait, however, the majority of previous body weight prediction research only used data collected at a single point in time. Furthermore, the utility of deep learning-based segmentation for body weight prediction using videos remains unanswered. Therefore, the objectives of this study were to predict cow body weight from repeatedly measured video data, to compare the performance of the thresholding and Mask R-CNN deep learning approaches, to evaluate the predictive ability of body weight regression models, and to promote open science in the animal science community by releasing the source code for video-based body weight prediction. A total of 40,405 depth images and depth map files were obtained from 10 lactating Holstein cows and 2 non-lactating Jersey cows. Three approaches were investigated to segment the cow's body from the background, including single thresholding, adaptive thresholding, and Mask R-CNN. Four image-derived biometric features, such as dorsal length, abdominal width, height, and volume, were estimated from the segmented images. On average, the Mask-RCNN approach combined with a linear mixed model resulted in the best prediction coefficient of determination and mean absolute percentage error of 0.98 and 2.03%, respectively, in the forecasting cross-validation. The Mask-RCNN approach was also the best in the leave-three-cows-out cross-validation. The prediction coefficients of determination and mean absolute percentage error of the Mask-RCNN coupled with the linear mixed model were 0.90 and 4.70%, respectively. Our results suggest that deep learning-based segmentation improves the prediction performance of cow body weight from longitudinal depth video data.
Authors: Yunhui Guo, Youren Zhang, Yubei Chen, Stella X. Yu
Given an image set without any labels, our goal is to train a model that maps each image to a point in a feature space such that, not only proximity indicates visual similarity, but where it is located directly encodes how prototypical the image is according to the dataset.
Our key insight is to perform unsupervised feature learning in hyperbolic instead of Euclidean space, where the distance between points still reflect image similarity, and yet we gain additional capacity for representing prototypicality with the location of the point: The closer it is to the origin, the more prototypical it is. The latter property is simply emergent from optimizing the usual metric learning objective: The image similar to many training instances is best placed at the center of corresponding points in Euclidean space, but closer to the origin in hyperbolic space.
We propose an unsupervised feature learning algorithm in Hyperbolic space with sphere pACKing. HACK first generates uniformly packed particles in the Poincar\'e ball of hyperbolic space and then assigns each image uniquely to each particle. Images after congealing are regarded more typical of the dataset it belongs to. With our feature mapper simply trained to spread out training instances in hyperbolic space, we observe that images move closer to the origin with congealing, validating our idea of unsupervised prototypicality discovery. We demonstrate that our data-driven prototypicality provides an easy and superior unsupervised instance selection to reduce sample complexity, increase model generalization with atypical instances and robustness with typical ones.
Authors: Zhen Zhu, Yijun Li, Weijie Lyu, Krishna Kumar Singh, Zhixin Shu, Soeren Pirk, Derek Hoiem
We investigate how to generate multimodal image outputs, such as RGB, depth, and surface normals, with a single generative model. The challenge is to produce outputs that are realistic, and also consistent with each other. Our solution builds on the StyleGAN3 architecture, with a shared backbone and modality-specific branches in the last layers of the synthesis network, and we propose per-modality fidelity discriminators and a cross-modality consistency discriminator. In experiments on the Stanford2D3D dataset, we demonstrate realistic and consistent generation of RGB, depth, and normal images. We also show a training recipe to easily extend our pretrained model on a new domain, even with a few pairwise data. We further evaluate the use of synthetically generated RGB and depth pairs for training or fine-tuning depth estimators. Code will be available at https://github.com/jessemelpolio/MultimodalGAN.
Authors: Zhiyuan Yan, Yong Zhang, Xinhang Yuan, Siwei Lyu, Baoyuan Wu
A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. This issue leads to unfair performance comparisons and potentially misleading results. Specifically, there is a lack of uniformity in data processing pipelines, resulting in inconsistent data inputs for detection models. Additionally, there are noticeable differences in experimental settings, and evaluation strategies and metrics lack standardization. To fill this gap, we present the first comprehensive benchmark for deepfake detection, called DeepfakeBench, which offers three key contributions: 1) a unified data management system to ensure consistent input across all detectors, 2) an integrated framework for state-of-the-art methods implementation, and 3) standardized evaluation metrics and protocols to promote transparency and reproducibility. Featuring an extensible, modular-based codebase, DeepfakeBench contains 15 state-of-the-art detection methods, 9 deepfake datasets, a series of deepfake detection evaluation protocols and analysis tools, as well as comprehensive evaluations. Moreover, we provide new insights based on extensive analysis of these evaluations from various perspectives (e.g., data augmentations, backbones). We hope that our efforts could facilitate future research and foster innovation in this increasingly critical domain. All codes, evaluations, and analyses of our benchmark are publicly available at https://github.com/SCLBD/DeepfakeBench.
Authors: Zhen Zhu, Weijie Lyu, Yao Xiao, Derek Hoiem
We introduce a method for flexible continual learning in open-vocabulary image classification, drawing inspiration from the complementary learning systems observed in human cognition. We propose a "tree probe" method, an adaption of lazy learning principles, which enables fast learning from new examples with competitive accuracy to batch-trained linear models. Further, we propose a method to combine predictions from a CLIP zero-shot model and the exemplar-based model, using the zero-shot estimated probability that a sample's class is within any of the exemplar classes. We test in data incremental, class incremental, and task incremental settings, as well as ability to perform flexible inference on varying subsets of zero-shot and learned categories. Our proposed method achieves a good balance of learning speed, target task effectiveness, and zero-shot effectiveness.
Accurately matching local features between a pair of images is a challenging computer vision task. Previous studies typically use attention based graph neural networks (GNNs) with fully-connected graphs over keypoints within/across images for visual and geometric information reasoning. However, in the context of feature matching, considerable keypoints are non-repeatable due to occlusion and failure of the detector, and thus irrelevant for message passing. The connectivity with non-repeatable keypoints not only introduces redundancy, resulting in limited efficiency, but also interferes with the representation aggregation process, leading to limited accuracy. Targeting towards high accuracy and efficiency, we propose MaKeGNN, a sparse attention-based GNN architecture which bypasses non-repeatable keypoints and leverages matchable ones to guide compact and meaningful message passing. More specifically, our Bilateral Context-Aware Sampling Module first dynamically samples two small sets of well-distributed keypoints with high matchability scores from the image pair. Then, our Matchable Keypoint-Assisted Context Aggregation Module regards sampled informative keypoints as message bottlenecks and thus constrains each keypoint only to retrieve favorable contextual information from intra- and inter- matchable keypoints, evading the interference of irrelevant and redundant connectivity with non-repeatable ones. Furthermore, considering the potential noise in initial keypoints and sampled matchable ones, the MKACA module adopts a matchability-guided attentional aggregation operation for purer data-dependent context propagation. By these means, we achieve the state-of-the-art performance on relative camera estimation, fundamental matrix estimation, and visual localization, while significantly reducing computational and memory complexity compared to typical attentional GNNs.
Authors: Minh-Quan Dao, Julie Stephany Berrio, Vincent Frémont, Mao Shan, Elwan Héry, Stewart Worrall
In this paper, we improve the single-vehicle 3D object detection models using LiDAR by extending their capacity to process point cloud sequences instead of individual point clouds. In this step, we extend our previous work on rectification of the shadow effect in the concatenation of point clouds to boost the detection accuracy of multi-frame detection models. Our extension includes incorporating HD Map and distilling an Oracle model. Next, we further increase the performance of single-vehicle perception using multi-agent collaboration via Vehicle-to-everything (V2X) communication. We devise a simple yet effective collaboration method that achieves better bandwidth-performance tradeoffs than prior arts while minimizing changes made to single-vehicle detection models and assumptions on inter-agent synchronization. Experiments on the V2X-Sim dataset show that our collaboration method achieves 98% performance of the early collaboration while consuming the equivalent amount of bandwidth usage of late collaboration which is 0.03% of early collaboration. The code will be released at https://github.com/quan-dao/practical-collab-perception.
Authors: Helen Carson, Jason J. Ford, Michael Milford
While substantial progress has been made in the absolute performance of localization and Visual Place Recognition (VPR) techniques, it is becoming increasingly clear from translating these systems into applications that other capabilities like integrity and predictability are just as important, especially for safety- or operationally-critical autonomous systems. In this research we present a new, training-free approach to predicting the likely quality of localization estimates, and a novel method for using these predictions to bias a sequence-matching process to produce additional performance gains beyond that of a naive sequence matching approach. Our combined system is lightweight, runs in real-time and is agnostic to the underlying VPR technique. On extensive experiments across four datasets and three VPR techniques, we demonstrate our system improves precision performance, especially at the high-precision/low-recall operating point. We also present ablation and analysis identifying the performance contributions of the prediction and weighted sequence matching components in isolation, and the relationship between the quality of the prediction system and the benefits of the weighted sequential matcher.
Authors: Yunqing Zhao, Keshigeyan Chandrasegaran, Abdollahzadeh Milad, Chao Du, Tianyu Pang, Ruoteng Li, Henghui Ding, Ngai-Man Cheung
Few-shot image generation (FSIG) aims to learn to generate new and diverse images given few (e.g., 10) training samples. Recent work has addressed FSIG by leveraging a GAN pre-trained on a large-scale source domain and adapting it to the target domain with few target samples. Central to recent FSIG methods are knowledge preservation criteria, which select and preserve a subset of source knowledge to the adapted model. However, a major limitation of existing methods is that their knowledge preserving criteria consider only source domain/task and fail to consider target domain/adaptation in selecting source knowledge, casting doubt on their suitability for setups of different proximity between source and target domain. Our work makes two contributions. Firstly, we revisit recent FSIG works and their experiments. We reveal that under setups which assumption of close proximity between source and target domains is relaxed, many existing state-of-the-art (SOTA) methods which consider only source domain in knowledge preserving perform no better than a baseline method. As our second contribution, we propose Adaptation-Aware kernel Modulation (AdAM) for general FSIG of different source-target domain proximity. Extensive experiments show that AdAM consistently achieves SOTA performance in FSIG, including challenging setups where source and target domains are more apart.
Authors: Tatsuya Ishibashi, Kosuke Ono, Noriyuki Kugo, Yuji Sato
In this report, we describe the technical details of our approach for the Ego4D Long-Term Action Anticipation Challenge 2023. The aim of this task is to predict a sequence of future actions that will take place at an arbitrary time or later, given an input video. To accomplish this task, we introduce three improvements to the baseline model, which consists of an encoder that generates clip-level features from the video, an aggregator that integrates multiple clip-level features, and a decoder that outputs Z future actions. 1) Model ensemble of SlowFast and SlowFast-CLIP; 2) Label smoothing to relax order constraints for future actions; 3) Constraining the prediction of the action class (verb, noun) based on word co-occurrence. Our method outperformed the baseline performance and recorded as second place solution on the public leaderboard.
Authors: Chuanyu Pan, Guowei Yang, Taijiang Mu, Yu-Kun Lai
With the booming of virtual reality (VR) technology, there is a growing need for customized 3D avatars. However, traditional methods for 3D avatar modeling are either time-consuming or fail to retain similarity to the person being modeled. We present a novel framework to generate animatable 3D cartoon faces from a single portrait image. We first transfer an input real-world portrait to a stylized cartoon image with a StyleGAN. Then we propose a two-stage reconstruction method to recover the 3D cartoon face with detailed texture, which first makes a coarse estimation based on template models, and then refines the model by non-rigid deformation under landmark supervision. Finally, we propose a semantic preserving face rigging method based on manually created templates and deformation transfer. Compared with prior arts, qualitative and quantitative results show that our method achieves better accuracy, aesthetics, and similarity criteria. Furthermore, we demonstrate the capability of real-time facial animation of our 3D model.
Authors: Pavan Kumar Sharma, Pranamesh Chakraborty
Driver gaze plays an important role in different gaze-based applications such as driver attentiveness detection, visual distraction detection, gaze behavior understanding, and building driver assistance system. The main objective of this study is to perform a comprehensive summary of driver gaze fundamentals, methods to estimate driver gaze, and it's applications in real world driving scenarios. We first discuss the fundamentals related to driver gaze, involving head-mounted and remote setup based gaze estimation and the terminologies used for each of these data collection methods. Next, we list out the existing benchmark driver gaze datasets, highlighting the collection methodology and the equipment used for such data collection. This is followed by a discussion of the algorithms used for driver gaze estimation, which primarily involves traditional machine learning and deep learning based techniques. The estimated driver gaze is then used for understanding gaze behavior while maneuvering through intersections, on-ramps, off-ramps, lane changing, and determining the effect of roadside advertising structures. Finally, we have discussed the limitations in the existing literature, challenges, and the future scope in driver gaze estimation and gaze-based applications.
Authors: Raha Ahmadi, Mohammad Javad Rajabi, Mohamamd Khalooiem Mohammad Sabokrou
Deep learning models have demonstrated remarkable capabilities in learning complex patterns and concepts from training data. However, recent findings indicate that these models tend to rely heavily on simple and easily discernible features present in the background of images rather than the main concepts or objects they are intended to classify. This phenomenon poses a challenge to image classifiers as the crucial elements of interest in images may be overshadowed. In this paper, we propose a novel approach to address this issue and improve the learning of main concepts by image classifiers. Our central idea revolves around concurrently guiding the model's attention toward the foreground during the classification task. By emphasizing the foreground, which encapsulates the primary objects of interest, we aim to shift the focus of the model away from the dominant influence of the background. To accomplish this, we introduce a mechanism that encourages the model to allocate sufficient attention to the foreground. We investigate various strategies, including modifying the loss function or incorporating additional architectural components, to enable the classifier to effectively capture the primary concept within an image. Additionally, we explore the impact of different foreground attention mechanisms on model performance and provide insights into their effectiveness. Through extensive experimentation on benchmark datasets, we demonstrate the efficacy of our proposed approach in improving the classification accuracy of image classifiers. Our findings highlight the importance of foreground attention in enhancing model understanding and representation of the main concepts within images. The results of this study contribute to advancing the field of image classification and provide valuable insights for developing more robust and accurate deep-learning models.
Authors: Jun Shi, Hongyu Kan, Shulan Ruan, Ziqi Zhu, Minfan Zhao, Liang Qiao, Zhaohui Wang, Hong An, Xudong Xue
Recently, deep learning methods have been widely used for tumor segmentation of multimodal medical images with promising results. However, most existing methods are limited by insufficient representational ability, specific modality number and high computational complexity. In this paper, we propose a hybrid densely connected network for tumor segmentation, named H-DenseFormer, which combines the representational power of the Convolutional Neural Network (CNN) and the Transformer structures. Specifically, H-DenseFormer integrates a Transformer-based Multi-path Parallel Embedding (MPE) module that can take an arbitrary number of modalities as input to extract the fusion features from different modalities. Then, the multimodal fusion features are delivered to different levels of the encoder to enhance multimodal learning representation. Besides, we design a lightweight Densely Connected Transformer (DCT) block to replace the standard Transformer block, thus significantly reducing computational complexity. We conduct extensive experiments on two public multimodal datasets, HECKTOR21 and PI-CAI22. The experimental results show that our proposed method outperforms the existing state-of-the-art methods while having lower computational complexity. The source code is available at https://github.com/shijun18/H-DenseFormer.
Authors: Ryan Faulkner, Luke Haub, Simon Ratcliffe, Ian Reid, Tat-Jun Chin
LiDAR scanning for surveying applications acquire measurements over wide areas and long distances, which produces large-scale 3D point clouds with significant local density variations. While existing 3D semantic segmentation models conduct downsampling and upsampling to build robustness against varying point densities, they are less effective under the large local density variations characteristic of point clouds from surveying applications. To alleviate this weakness, we propose a novel architecture called HDVNet that contains a nested set of encoder-decoder pathways, each handling a specific point density range. Limiting the interconnections between the feature maps enables HDVNet to gauge the reliability of each feature based on the density of a point, e.g., downweighting high density features not existing in low density objects. By effectively handling input density variations, HDVNet outperforms state-of-the-art models in segmentation accuracy on real point clouds with inconsistent density, using just over half the weights.
Authors: Zhiqi Li, Zhiding Yu, David Austin, Mingsheng Fang, Shiyi Lan, Jan Kautz, Jose M. Alvarez
This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous Driving and CVPR 23 Workshop on Vision-Centric Autonomous Driving Workshop. Our proposed solution FB-OCC builds upon FB-BEV, a cutting-edge camera-based bird's-eye view perception design using forward-backward projection. On top of FB-BEV, we further study novel designs and optimization tailored to the 3D occupancy prediction task, including joint depth-semantic pre-training, joint voxel-BEV representation, model scaling up, and effective post-processing strategies. These designs and optimization result in a state-of-the-art mIoU score of 54.19% on the nuScenes dataset, ranking the 1st place in the challenge track. Code and models will be released at: https://github.com/NVlabs/FB-BEV.
Authors: Jacob J. Relle, Samuel Voß, Ramesch Raschidi, Regine Nessel, Johannes Görich, Mark O. Wielpütz, Thorsten Löffler, Vincent Heuveline, Friedrich Kallinowski, Philipp D. Lösel
Abdominal wall defects often lead to pain, discomfort, and recurrence of incisional hernias, resulting in significant morbidity and repeated surgical repairs worldwide. Mesh repair for large hernias is usually based on the defect area with a fixed overlap, without considering biomechanical aspects such as muscle activation, intra-abdominal pressure, tissue elasticity, and abdominal wall distention. To address this issue, we present a biomechanical approach to incisional hernia repair that takes into account the unstable abdominal wall. Additionally, we introduce HEDI, a tool that uses dynamic computed tomography with Valsalva maneuver to automatically detect and assess hernia size, volume, and abdominal wall instability. Our first clinical application of HEDI in the preoperative evaluation of 31 patients shows significantly improved success rates compared to reported rates, with all patients remaining pain-free and showing no hernia recurrence after three years of follow-up.
Authors: Sunder Ali Khowaja, Kapal Dev, Syed Muhammad Anwar, Marius George Linguraru
Self-supervised learning in federated learning paradigm has been gaining a lot of interest both in industry and research due to the collaborative learning capability on unlabeled yet isolated data. However, self-supervised based federated learning strategies suffer from performance degradation due to label scarcity and diverse data distributions, i.e., data heterogeneity. In this paper, we propose the SelfFed framework for Internet of Medical Things (IoMT). Our proposed SelfFed framework works in two phases. The first phase is the pre-training paradigm that performs augmentive modeling using Swin Transformer based encoder in a decentralized manner. The first phase of SelfFed framework helps to overcome the data heterogeneity issue. The second phase is the fine-tuning paradigm that introduces contrastive network and a novel aggregation strategy that is trained on limited labeled data for a target task in a decentralized manner. This fine-tuning stage overcomes the label scarcity problem. We perform our experimental analysis on publicly available medical imaging datasets and show that our proposed SelfFed framework performs better when compared to existing baselines concerning non-independent and identically distributed (IID) data and label scarcity. Our method achieves a maximum improvement of 8.8% and 4.1% on Retina and COVID-FL datasets on non-IID dataset. Further, our proposed method outperforms existing baselines even when trained on a few (10%) labeled instances.
Authors: Kaihui Cheng, Chule Yang
Few-shot classification aims to adapt to new tasks with limited labeled examples. To fully use the accessible data, recent methods explore suitable measures for the similarity between the query and support images and better high-dimensional features with meta-training and pre-training strategies. However, the potential of multi-modality information has barely been explored, which may bring promising improvement for few-shot classification. In this paper, we propose a Language-guided Prototypical Network (LPN) for few-shot classification, which leverages the complementarity of vision and language modalities via two parallel branches. Concretely, to introduce language modality with limited samples in the visual task, we leverage a pre-trained text encoder to extract class-level text features directly from class names while processing images with a conventional image encoder. Then, a language-guided decoder is introduced to obtain text features corresponding to each image by aligning class-level features with visual features. In addition, to take advantage of class-level features and prototypes, we build a refined prototypical head that generates robust prototypes in the text branch for follow-up measurement. Finally, we aggregate the visual and text logits to calibrate the deviation of a single modality. Extensive experiments demonstrate the competitiveness of LPN against state-of-the-art methods on benchmark datasets.
Authors: Joonkyo Shim, Hyunsoo Yoon
Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model outputs. However, previous approaches primarily focus on generating distorted outputs based on only predetermined target attributes, leading to a lack of robustness in real-world scenarios where target attributes are unknown. Additionally, the transferability of perturbations between two prominent generative models, Generative Adversarial Networks (GANs) and Diffusion Models, remains unexplored. In this paper, we emphasize the importance of target attribute-transferability and model-transferability for achieving robust deepfake disruption. To address this challenge, we propose a simple yet effective disruption method called Latent Ensemble ATtack (LEAT), which attacks the independent latent encoding process. By disrupting the latent encoding process, it generates distorted output images in subsequent generation processes, regardless of the given target attributes. This target attribute-agnostic attack ensures robust disruption even when the target attributes are unknown. Additionally, we introduce a Normalized Gradient Ensemble strategy that effectively aggregates gradients for iterative gradient attacks, enabling simultaneous attacks on various types of deepfake models, involving both GAN-based and Diffusion-based models. Moreover, we demonstrate the insufficiency of evaluating disruption quality solely based on pixel-level differences. As a result, we propose an alternative protocol for comprehensively evaluating the success of defense. Extensive experiments confirm the efficacy of our method in disrupting deepfakes in real-world scenarios, reporting a higher defense success rate compared to previous methods.
Authors: Ravi Kakaiya, Rakshith Sathish, Ramanathan Sethuraman
Autonomous vehicles and Advanced Driving Assistance Systems (ADAS) have the potential to radically change the way we travel. Many such vehicles currently rely on segmentation and object detection algorithms to detect and track objects around its surrounding. The data collected from the vehicles are often sent to cloud servers to facilitate continual/life-long learning of these algorithms. Considering the bandwidth constraints, the data is compressed before sending it to servers, where it is typically decompressed for training and analysis. In this work, we propose the use of a learning-based compression Codec to reduce the overhead in latency incurred for the decompression operation in the standard pipeline. We demonstrate that the learned compressed representation can also be used to perform tasks like semantic segmentation in addition to decompression to obtain the images. We experimentally validate the proposed pipeline on the Cityscapes dataset, where we achieve a compression factor up to $66 \times$ while preserving the information required to perform segmentation with a dice coefficient of $0.84$ as compared to $0.88$ achieved using decompressed images while reducing the overall compute by $11\%$.
Authors: Asim Khan, Taimur Hassan, Muhammad Shafay, Israa Fahmy, Naoufel Werghi, Lakmal Seneviratne, Irfan Hussain
Harvesting fully ripe tomatoes with mobile robots presents significant challenges in real-world scenarios. These challenges arise from factors such as occlusion caused by leaves and branches, as well as the color similarity between tomatoes and the surrounding foliage during the fruit development stage. The natural environment further compounds these issues with varying light conditions, viewing angles, occlusion factors, and different maturity levels. To overcome these obstacles, this research introduces a novel framework that leverages a convolutional transformer architecture to autonomously recognize and grade tomatoes, irrespective of their occlusion level, lighting conditions, and ripeness. The proposed model is trained and tested using carefully annotated images curated specifically for this purpose. The dataset is prepared under various lighting conditions, viewing perspectives, and employs different mobile camera sensors, distinguishing it from existing datasets such as Laboro Tomato and Rob2Pheno Annotated Tomato. The effectiveness of the proposed framework in handling cluttered and occluded tomato instances was evaluated using two additional public datasets, Laboro Tomato and Rob2Pheno Annotated Tomato, as benchmarks. The evaluation results across these three datasets demonstrate the exceptional performance of our proposed framework, surpassing the state-of-the-art by 58.14%, 65.42%, and 66.39% in terms of mean average precision scores for KUTomaData, Laboro Tomato, and Rob2Pheno Annotated Tomato, respectively. The results underscore the superiority of the proposed model in accurately detecting and delineating tomatoes compared to baseline methods and previous approaches. Specifically, the model achieves an F1-score of 80.14%, a Dice coefficient of 73.26%, and a mean IoU of 66.41% on the KUTomaData image dataset.
Authors: Anil Osman Tur, Nicola Dall'Asen, Cigdem Beyan, Elisa Ricci
This paper aims to address the unsupervised video anomaly detection (VAD) problem, which involves classifying each frame in a video as normal or abnormal, without any access to labels. To accomplish this, the proposed method employs conditional diffusion models, where the input data is the spatiotemporal features extracted from a pre-trained network, and the condition is the features extracted from compact motion representations that summarize a given video segment in terms of its motion and appearance. Our method utilizes a data-driven threshold and considers a high reconstruction error as an indicator of anomalous events. This study is the first to utilize compact motion representations for VAD and the experiments conducted on two large-scale VAD benchmarks demonstrate that they supply relevant information to the diffusion model, and consequently improve VAD performances w.r.t the prior art. Importantly, our method exhibits better generalization performance across different datasets, notably outperforming both the state-of-the-art and baseline methods. The code of our method is available at https://github.com/AnilOsmanTur/conditioned_video_anomaly_diffusion
Authors: Cédric Picron, Tinne Tuytelaars
Many two-stage instance segmentation heads predict a coarse 28x28 mask per instance, which is insufficient to capture the fine-grained details of many objects. To address this issue, PointRend and RefineMask predict a 112x112 segmentation mask resulting in higher quality segmentations. Both methods however have limitations by either not having access to neighboring features (PointRend) or by performing computation at all spatial locations instead of sparsely (RefineMask). In this work, we propose EffSeg performing fine-grained instance segmentation in an efficient way by using our Structure-Preserving Sparsity (SPS) method based on separately storing the active features, the passive features and a dense 2D index map containing the feature indices. The goal of the index map is to preserve the 2D spatial configuration or structure between the features such that any 2D operation can still be performed. EffSeg achieves similar performance on COCO compared to RefineMask, while reducing the number of FLOPs by 71% and increasing the FPS by 29%. Code will be released.
Authors: Mingjie Lu, Yuanxian Huang, Ji Liu, Jinzhang Peng, Lu Tian, Ashish Sirasao
Understanding driving scenarios is crucial to realizing autonomous driving. Previous works such as map learning and BEV lane detection neglect the connection relationship between lane instances, and traffic elements detection tasks usually neglect the relationship with lane lines. To address these issues, the task is presented which includes 4 sub-tasks, the detection of traffic elements, the detection of lane centerlines, reasoning connection relationships among lanes, and reasoning assignment relationships between lanes and traffic elements. We present Separated RoadTopoFormer to tackle the issues, which is an end-to-end framework that detects lane centerline and traffic elements with reasoning relationships among them. We optimize each module separately to prevent interaction with each other and aggregate them together with few finetunes. For two detection heads, we adopted a DETR-like architecture to detect objects, and for the relationship head, we concat two instance features from front detectors and feed them to the classifier to obtain relationship probability. Our final submission achieves 0.445 OLS, which is competitive in both sub-task and combined scores.
Authors: Franco Marchesoni-Acland, Jean-Michel Morel, Josselin Kherroubi, Gabriele Facciolo
Even though data annotation is extremely important for interpretability, research and development of artificial intelligence solutions, most research efforts such as active learning or few-shot learning focus on the sample efficiency problem. This paper studies the neglected complementary problem of getting annotated data given a predictor. For the simple binary classification setting, we present the spectrum ranging from optimal general solutions to practical efficient methods. The problem is framed as the full annotation of a binary classification dataset with the minimal number of yes/no questions when a predictor is available. For the case of general binary questions the solution is found in coding theory, where the optimal questioning strategy is given by the Huffman encoding of the possible labelings. However, this approach is computationally intractable even for small dataset sizes. We propose an alternative practical solution based on several heuristics and lookahead minimization of proxy cost functions. The proposed solution is analysed, compared with optimal solutions and evaluated on several synthetic and real-world datasets. On these datasets, the method allows a significant improvement ($23-86\%$) in annotation efficiency.
Authors: Franco Marchesoni-Acland, Gabriele Facciolo
This work proposes a strategy for training models while annotating data named Intelligent Annotation (IA). IA involves three modules: (1) assisted data annotation, (2) background model training, and (3) active selection of the next datapoints. Under this framework, we open-source the IAdet tool, which is specific for single-class object detection. Additionally, we devise a method for automatically evaluating such a human-in-the-loop system. For the PASCAL VOC dataset, the IAdet tool reduces the database annotation time by $25\%$ while providing a trained model for free. These results are obtained for a deliberately very simple IAdet design. As a consequence, IAdet is susceptible to multiple easy improvements, paving the way for powerful human-in-the-loop object detection systems.
Authors: Alex Gabel, Victoria Klein, Riccardo Valperga, Jeroen S. W. Lamb, Kevin Webster, Rick Quax, Efstratios Gavves
The problem of detecting and quantifying the presence of symmetries in datasets is useful for model selection, generative modeling, and data analysis, amongst others. While existing methods for hard-coding transformations in neural networks require prior knowledge of the symmetries of the task at hand, this work focuses on discovering and characterizing unknown symmetries present in the dataset, namely, Lie group symmetry transformations beyond the traditional ones usually considered in the field (rotation, scaling, and translation). Specifically, we consider a scenario in which a dataset has been transformed by a one-parameter subgroup of transformations with different parameter values for each data point. Our goal is to characterize the transformation group and the distribution of the parameter values. The results showcase the effectiveness of the approach in both these settings.
Authors: Samy Tafasca, Anshul Gupta, Jean-Marc Odobez
Gaze behaviors such as eye-contact or shared attention are important markers for diagnosing developmental disorders in children. While previous studies have looked at some of these elements, the analysis is usually performed on private datasets and is restricted to lab settings. Furthermore, all publicly available gaze target prediction benchmarks mostly contain instances of adults, which makes models trained on them less applicable to scenarios with young children. In this paper, we propose the first study for predicting the gaze target of children and interacting adults. To this end, we introduce the ChildPlay dataset: a curated collection of short video clips featuring children playing and interacting with adults in uncontrolled environments (e.g. kindergarten, therapy centers, preschools etc.), which we annotate with rich gaze information. We further propose a new model for gaze target prediction that is geometrically grounded by explicitly identifying the scene parts in the 3D field of view (3DFoV) of the person, leveraging recent geometry preserving depth inference methods. Our model achieves state of the art results on benchmark datasets and ChildPlay. Furthermore, results show that looking at faces prediction performance on children is much worse than on adults, and can be significantly improved by fine-tuning models using child gaze annotations. Our dataset and models will be made publicly available.
Authors: Ivica Dimitrovski, Ivan Kitanovski, Nikola Simidjievski, Dragi Kocev
Self-supervised learning (SSL) has emerged as a promising approach for remote sensing image classification due to its ability to leverage large amounts of unlabeled data. In contrast to traditional supervised learning, SSL aims to learn representations of data without the need for explicit labels. This is achieved by formulating auxiliary tasks that can be used to create pseudo-labels for the unlabeled data and learn pre-trained models. The pre-trained models can then be fine-tuned on downstream tasks such as remote sensing image scene classification. The paper analyzes the effectiveness of SSL pre-training using Million AID - a large unlabeled remote sensing dataset on various remote sensing image scene classification datasets as downstream tasks. More specifically, we evaluate the effectiveness of SSL pre-training using the iBOT framework coupled with Vision transformers (ViT) in contrast to supervised pre-training of ViT using the ImageNet dataset. The comprehensive experimental work across 14 datasets with diverse properties reveals that in-domain SSL leads to improved predictive performance of models compared to the supervised counterparts.
Authors: Jonas-Dario Troles, Richard Nieding, Sonia Simons, Ute Schmid
Climate crisis and correlating prolonged, more intense periods of drought threaten tree health in cities and forests. In consequence, arborists and foresters suffer from increasing workloads and, in the best case, a consistent but often declining workforce. To optimise workflows and increase productivity, we propose a novel open-source end-to-end approach that generates helpful information and improves task planning of those who care for trees in and around cities. Our approach is based on RGB and multispectral UAV data, which is used to create tree inventories of city parks and forests and to deduce tree vitality assessments through statistical indices and Deep Learning. Due to EU restrictions regarding flying drones in urban areas, we will also use multispectral satellite data and fifteen soil moisture sensors to extend our tree vitality-related basis of data. Furthermore, Bamberg already has a georeferenced tree cadastre of around 15,000 solitary trees in the city area, which is also used to generate helpful information. All mentioned data is then joined and visualised in an interactive web application allowing arborists and foresters to generate individual and flexible evaluations, thereby improving daily task planning.
Authors: Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez, Paula Delgado-Santos, Giuseppe Stragapede, Julian Fierrez, Javier Ortega-Garcia
The application of mobile biometrics as a user-friendly authentication method has increased in the last years. Recent studies have proposed novel behavioral biometric recognition systems based on Transformers, which currently outperform the state of the art in several application scenarios. On-line handwritten signature verification aims to verify the identity of subjects, based on their biometric signatures acquired using electronic devices such as tablets or smartphones. This paper investigates the suitability of architectures based on recent Transformers for on-line signature verification. In particular, four different configurations are studied, two of them rely on the Vanilla Transformer encoder, and the two others have been successfully applied to the tasks of gait and activity recognition. We evaluate the four proposed configurations according to the experimental protocol proposed in the SVC-onGoing competition. The results obtained in our experiments are promising, and promote the use of Transformers for on-line signature verification.
Authors: Prabin Sharma, Joanna C. Justus, Govinda R. Poudel
Mental fatigue is a leading cause of motor vehicle accidents, medical errors, loss of workplace productivity, and student disengagements in e-learning environment. Development of sensors and systems that can reliably track mental fatigue can prevent accidents, reduce errors, and help increase workplace productivity. This review provides a critical summary of theoretical models of mental fatigue, a description of key enabling sensor technologies, and a systematic review of recent studies using biosensor-based systems for tracking mental fatigue in humans. We conducted a systematic search and review of recent literature which focused on detection and tracking of mental fatigue in humans. The search yielded 57 studies (N=1082), majority of which used electroencephalography (EEG) based sensors for tracking mental fatigue. We found that EEG-based sensors can provide a moderate to good sensitivity for fatigue detection. Notably, we found no incremental benefit of using high-density EEG sensors for application in mental fatigue detection. Given the findings, we provide a critical discussion on the integration of wearable EEG and ambient sensors in the context of achieving real-world monitoring. Future work required to advance and adapt the technologies toward widespread deployment of wearable sensors and systems for fatigue monitoring in semi-autonomous and autonomous industries is examined.
Authors: Weijian Luo, Hao Jiang, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Zhihua Zhang
Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an irreconcilable trade-off between the computational burden and the validity of the CD. Running MCMCs till convergence is computationally intensive. On the other hand, short-run MCMC brings in an extra non-negligible parameter gradient term that is difficult to handle. In this paper, we provide a general interpretation of CD, viewing it as a special instance of our proposed Diffusion Contrastive Divergence (DCD) family. By replacing the Langevin dynamic used in CD with other EBM-parameter-free diffusion processes, we propose a more efficient divergence. We show that the proposed DCDs are both more computationally efficient than the CD and are not limited to a non-negligible gradient term. We conduct intensive experiments, including both synthesis data modeling and high-dimensional image denoising and generation, to show the advantages of the proposed DCDs. On the synthetic data learning and image denoising experiments, our proposed DCD outperforms CD by a large margin. In image generation experiments, the proposed DCD is capable of training an energy-based model for generating the Celab-A $32\times 32$ dataset, which is comparable to existing EBMs.
Authors: Guy Berger, Aviv Navon, Ethan Fetaya
In computer vision and machine learning, a crucial challenge is to lower the computation and memory demands for neural network inference. A commonplace solution to address this challenge is through the use of binarization. By binarizing the network weights and activations, one can significantly reduce computational complexity by substituting the computationally expensive floating operations with faster bitwise operations. This leads to a more efficient neural network inference that can be deployed on low-resource devices. In this work, we extend previous approaches that trained networks with discrete weights using the local reparameterization trick to also allow for discrete activations. The original approach optimized a distribution over the discrete weights and uses the central limit theorem to approximate the pre-activation with a continuous Gaussian distribution. Here we show that the probabilistic modeling can also allow effective training of networks with discrete activation as well. This further reduces runtime and memory footprint at inference time with state-of-the-art results for networks with binary activations.
Authors: Man Yao, Jiakui Hu, Zhaokun Zhou, Li Yuan, Yonghong Tian, Bo Xu, Guoqi Li
Spiking Neural Networks (SNNs) provide an energy-efficient deep learning option due to their unique spike-based event-driven (i.e., spike-driven) paradigm. In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: 1) Event-driven, no calculation is triggered when the input of Transformer is zero; 2) Binary spike communication, all matrix multiplications associated with the spike matrix can be transformed into sparse additions; 3) Self-attention with linear complexity at both token and channel dimensions; 4) The operations between spike-form Query, Key, and Value are mask and addition. Together, there are only sparse addition operations in the Spike-driven Transformer. To this end, we design a novel Spike-Driven Self-Attention (SDSA), which exploits only mask and addition operations without any multiplication, and thus having up to $87.2\times$ lower computation energy than vanilla self-attention. Especially in SDSA, the matrix multiplication between Query, Key, and Value is designed as the mask operation. In addition, we rearrange all residual connections in the vanilla Transformer before the activation functions to ensure that all neurons transmit binary spike signals. It is shown that the Spike-driven Transformer can achieve 77.1\% top-1 accuracy on ImageNet-1K, which is the state-of-the-art result in the SNN field. The source code is available at https://github.com/BICLab/Spike-Driven-Transformer.
Authors: Qiyu Sun, Pavlo Melnyk, Michael Felsberg, Yang Tang
Domain generalized semantic segmentation (DGSS) is an essential but highly challenging task, in which the model is trained only on source data and any target data is not available. Previous DGSS methods can be partitioned into augmentation-based and normalization-based ones. The former either introduces extra biased data or only conducts channel-wise adjustments for data augmentation, and the latter may discard beneficial visual information, both of which lead to limited performance in DGSS. Contrarily, our method performs inter-channel transformation and meanwhile evades domain-specific biases, thus diversifying data and enhancing model generalization performance. Specifically, our method consists of two modules: random image color augmentation (RICA) and random feature distribution augmentation (RFDA). RICA converts images from RGB to the CIELAB color model and randomizes color maps in a perception-based way for image enhancement purposes. We further this augmentation by extending it beyond color to feature space using a CycleGAN-based generative network, which complements RICA and further boosts generalization capability. We conduct extensive experiments, and the generalization results from the synthetic GTAV and SYNTHIA to the real Cityscapes, BDDS, and Mapillary datasets show that our method achieves state-of-the-art performance in DGSS.
Authors: Peng Tang, Yang Nan, Tobias Lasser
Many skin lesion analysis (SLA) methods recently focused on developing a multi-modal-based multi-label classification method due to two factors. The first is multi-modal data, i.e., clinical and dermoscopy images, which can provide complementary information to obtain more accurate results than single-modal data. The second one is that multi-label classification, i.e., seven-point checklist (SPC) criteria as an auxiliary classification task can not only boost the diagnostic accuracy of melanoma in the deep learning (DL) pipeline but also provide more useful functions to the clinical doctor as it is commonly used in clinical dermatologist's diagnosis. However, most methods only focus on designing a better module for multi-modal data fusion; few methods explore utilizing the label correlation between SPC and skin disease for performance improvement. This study fills the gap that introduces a Graph Convolution Network (GCN) to exploit prior co-occurrence between each category as a correlation matrix into the DL model for the multi-label classification. However, directly applying GCN degraded the performances in our experiments; we attribute this to the weak generalization ability of GCN in the scenario of insufficient statistical samples of medical data. We tackle this issue by proposing a Graph-Ensemble Learning Model (GELN) that views the prediction from GCN as complementary information of the predictions from the fusion model and adaptively fuses them by a weighted averaging scheme, which can utilize the valuable information from GCN while avoiding its negative influences as much as possible. To evaluate our method, we conduct experiments on public datasets. The results illustrate that our GELN can consistently improve the classification performance on different datasets and that the proposed method can achieve state-of-the-art performance in SPC and diagnosis classification.
Authors: Changjian Shui, Justin Szeto, Raghav Mehta, Douglas Arnold, Tal Arbel
Trustworthy deployment of deep learning medical imaging models into real-world clinical practice requires that they be calibrated. However, models that are well calibrated overall can still be poorly calibrated for a sub-population, potentially resulting in a clinician unwittingly making poor decisions for this group based on the recommendations of the model. Although methods have been shown to successfully mitigate biases across subgroups in terms of model accuracy, this work focuses on the open problem of mitigating calibration biases in the context of medical image analysis. Our method does not require subgroup attributes during training, permitting the flexibility to mitigate biases for different choices of sensitive attributes without re-training. To this end, we propose a novel two-stage method: Cluster-Focal to first identify poorly calibrated samples, cluster them into groups, and then introduce group-wise focal loss to improve calibration bias. We evaluate our method on skin lesion classification with the public HAM10000 dataset, and on predicting future lesional activity for multiple sclerosis (MS) patients. In addition to considering traditional sensitive attributes (e.g. age, sex) with demographic subgroups, we also consider biases among groups with different image-derived attributes, such as lesion load, which are required in medical image analysis. Our results demonstrate that our method effectively controls calibration error in the worst-performing subgroups while preserving prediction performance, and outperforming recent baselines.
Authors: Jianhai Zhang, Tonghua Wan, Ethan MacDonald, Aravind Ganesh, Qiu Wu
Stroke lesion volume is a key radiologic measurement for assessing the prognosis of Acute Ischemic Stroke (AIS) patients, which is challenging to be automatically measured on Non-Contrast CT (NCCT) scans. Recent diffusion probabilistic models have shown potentials of being used for image segmentation. In this paper, a novel Synchronous image-label Diffusion Probability Model (SDPM) is proposed for stroke lesion segmentation on NCCT using Markov diffusion process. The proposed SDPM is fully based on a Latent Variable Model (LVM), offering a complete probabilistic elaboration. An additional net-stream, parallel with a noise prediction stream, is introduced to obtain initial noisy label estimates for efficiently inferring the final labels. By optimizing the specified variational boundaries, the trained model can infer multiple label estimates for reference given the input images with noises. The proposed model was assessed on three stroke lesion datasets including one public and two private datasets. Compared to several U-net and transformer-based segmentation methods, our proposed SDPM model is able to achieve state-of-the-art performance. The code is publicly available.
Authors: Michael Mommert, Nicolas Kesseli, Joëlle Hanna, Linus Scheibenreif, Damian Borth, Begüm Demir
Deep learning methods have proven to be a powerful tool in the analysis of large amounts of complex Earth observation data. However, while Earth observation data are multi-modal in most cases, only single or few modalities are typically considered. In this work, we present the ben-ge dataset, which supplements the BigEarthNet-MM dataset by compiling freely and globally available geographical and environmental data. Based on this dataset, we showcase the value of combining different data modalities for the downstream tasks of patch-based land-use/land-cover classification and land-use/land-cover segmentation. ben-ge is freely available and expected to serve as a test bed for fully supervised and self-supervised Earth observation applications.
Authors: Zhijie Rao, Jingcai Guo, Luyao Tang, Yue Huang, Xinghao Ding, Song Guo
This paper provides a novel framework for single-domain generalized object detection (i.e., Single-DGOD), where we are interested in learning and maintaining the semantic structures of self-augmented compound cross-domain samples to enhance the model's generalization ability. Different from DGOD trained on multiple source domains, Single-DGOD is far more challenging to generalize well to multiple target domains with only one single source domain. Existing methods mostly adopt a similar treatment from DGOD to learn domain-invariant features by decoupling or compressing the semantic space. However, there may have two potential limitations: 1) pseudo attribute-label correlation, due to extremely scarce single-domain data; and 2) the semantic structural information is usually ignored, i.e., we found the affinities of instance-level semantic relations in samples are crucial to model generalization. In this paper, we introduce Semantic Reasoning with Compound Domains (SRCD) for Single-DGOD. Specifically, our SRCD contains two main components, namely, the texture-based self-augmentation (TBSA) module, and the local-global semantic reasoning (LGSR) module. TBSA aims to eliminate the effects of irrelevant attributes associated with labels, such as light, shadow, color, etc., at the image level by a light-yet-efficient self-augmentation. Moreover, LGSR is used to further model the semantic relationships on instance features to uncover and maintain the intrinsic semantic structures. Extensive experiments on multiple benchmarks demonstrate the effectiveness of the proposed SRCD.
Authors: Alexey Protopopov
K-complexes are an important marker of brain activity and are used both in clinical practice to perform sleep scoring, and in research. However, due to the size of electroencephalography (EEG) records, as well as the subjective nature of K-complex detection performed by somnologists, it is reasonable to automate K-complex detection. Previous works in this field of research have relied on the values of true positive rate and false positive rate to quantify the effectiveness of proposed methods, however this set of metrics may be misleading. The objective of the present research is to find a more accurate set of metrics and use them to develop a new method of K-complex detection, which would not rely on neural networks. Thus, the present article proposes two new methods for K-complex detection based on the fast Fourier transform. The results achieved demonstrated that the proposed methods offered a quality of K-complex detection that is either similar or superior to the quality of the methods demonstrated in previous works, including the methods employing neural networks, while requiring less computational power, meaning that K-complex detection does not require the use of neural networks. The proposed methods were evaluated using a new set of metrics, which is more representative of the quality of K-complex detection.
Authors: Lucas Mahler, Qi Wang, Julius Steiglechner, Florian Birk, Samuel Heczko, Klaus Scheffler, Gabriele Lohmann
Autism spectrum disorder (ASD) is a prevalent psychiatric condition characterized by atypical cognitive, emotional, and social patterns. Timely and accurate diagnosis is crucial for effective interventions and improved outcomes in individuals with ASD. In this study, we propose a novel Multi-Atlas Enhanced Transformer framework, METAFormer, ASD classification. Our framework utilizes resting-state functional magnetic resonance imaging data from the ABIDE I dataset, comprising 406 ASD and 476 typical control (TC) subjects. METAFormer employs a multi-atlas approach, where flattened connectivity matrices from the AAL, CC200, and DOS160 atlases serve as input to the transformer encoder. Notably, we demonstrate that self-supervised pretraining, involving the reconstruction of masked values from the input, significantly enhances classification performance without the need for additional or separate training data. Through stratified cross-validation, we evaluate the proposed framework and show that it surpasses state-of-the-art performance on the ABIDE I dataset, with an average accuracy of 83.7% and an AUC-score of 0.832. The code for our framework is available at https://github.com/Lugges991/METAFormer
Authors: Darlington Akogo, Issah Samori, Cyril Akafia, Harriet Fiagbor, Andrews Kangah, Donald Kwame Asiedu, Kwabena Fuachie, Luis Oala
The Ghana Cashew Disease Identification with Artificial Intelligence (CADI AI) project demonstrates the importance of sound data work as a precondition for the delivery of useful, localized datacentric solutions for public good tasks such as agricultural productivity and food security. Drone collected data and machine learning are utilized to determine crop stressors. Data, model and the final app are developed jointly and made available to local farmers via a desktop application.
Authors: Zhanhao Hu, Wenda Chu, Xiaopei Zhu, Hui Zhang, Bo Zhang, Xiaolin Hu
Recent works have proposed to craft adversarial clothes for evading person detectors, while they are either only effective at limited viewing angles or very conspicuous to humans. We aim to craft adversarial texture for clothes based on 3D modeling, an idea that has been used to craft rigid adversarial objects such as a 3D-printed turtle. Unlike rigid objects, humans and clothes are non-rigid, leading to difficulties in physical realization. In order to craft natural-looking adversarial clothes that can evade person detectors at multiple viewing angles, we propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes, camouflage textures. We leverage the Voronoi diagram and Gumbel-softmax trick to parameterize the camouflage textures and optimize the parameters via 3D modeling. Moreover, we propose an efficient augmentation pipeline on 3D meshes combining topologically plausible projection (TopoProj) and Thin Plate Spline (TPS) to narrow the gap between digital and real-world objects. We printed the developed 3D texture pieces on fabric materials and tailored them into T-shirts and trousers. Experiments show high attack success rates of these clothes against multiple detectors.
Authors: Xiaojiao Xiao, Qinmin Hu, Guanghui Wang
Simultaneous multi-index quantification, segmentation, and uncertainty estimation of liver tumors on multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for accurate diagnosis. However, existing methods lack an effective mechanism for multi-modality NCMRI fusion and accurate boundary information capture, making these tasks challenging. To address these issues, this paper proposes a unified framework, namely edge-aware multi-task network (EaMtNet), to associate multi-index quantification, segmentation, and uncertainty of liver tumors on the multi-modality NCMRI. The EaMtNet employs two parallel CNN encoders and the Sobel filters to extract local features and edge maps, respectively. The newly designed edge-aware feature aggregation module (EaFA) is used for feature fusion and selection, making the network edge-aware by capturing long-range dependency between feature and edge maps. Multi-tasking leverages prediction discrepancy to estimate uncertainty and improve segmentation and quantification performance. Extensive experiments are performed on multi-modality NCMRI with 250 clinical subjects. The proposed model outperforms the state-of-the-art by a large margin, achieving a dice similarity coefficient of 90.01$\pm$1.23 and a mean absolute error of 2.72$\pm$0.58 mm for MD. The results demonstrate the potential of EaMtNet as a reliable clinical-aided tool for medical image analysis.
Authors: Afshin Khadangi
In this paper, we propose a novel learning paradigm called "DeepFlorist" for flower classification using ensemble learning as a meta-classifier. DeepFlorist combines the power of deep learning with the robustness of ensemble methods to achieve accurate and reliable flower classification results. The proposed network architecture leverages a combination of dense convolutional and convolutional neural networks (DCNNs and CNNs) to extract high-level features from flower images, followed by a fully connected layer for classification. To enhance the performance and generalization of DeepFlorist, an ensemble learning approach is employed, incorporating multiple diverse models to improve the classification accuracy. Experimental results on benchmark flower datasets demonstrate the effectiveness of DeepFlorist, outperforming state-of-the-art methods in terms of accuracy and robustness. The proposed framework holds significant potential for automated flower recognition systems in real-world applications, enabling advancements in plant taxonomy, conservation efforts, and ecological studies.
Authors: Zheyuan Zhou, Jiachen Lu, Yihan Zeng, Hang Xu, Li Zhang
3D object detection from LiDAR point cloud is of critical importance for autonomous driving and robotics. While sequential point cloud has the potential to enhance 3D perception through temporal information, utilizing these temporal features effectively and efficiently remains a challenging problem. Based on the observation that the foreground information is sparsely distributed in LiDAR scenes, we believe sufficient knowledge can be provided by sparse format rather than dense maps. To this end, we propose to learn Significance-gUided Information for 3D Temporal detection (SUIT), which simplifies temporal information as sparse features for information fusion across frames. Specifically, we first introduce a significant sampling mechanism that extracts information-rich yet sparse features based on predicted object centroids. On top of that, we present an explicit geometric transformation learning technique, which learns the object-centric transformations among sparse features across frames. We evaluate our method on large-scale nuScenes and Waymo dataset, where our SUIT not only significantly reduces the memory and computation cost of temporal fusion, but also performs well over the state-of-the-art baselines.
Authors: Jiangbei Yue, Dinesh Manocha, He Wang
Human trajectory forecasting helps to understand and predict human behaviors, enabling applications from social robots to self-driving cars, and therefore has been heavily investigated. Most existing methods can be divided into model-free and model-based methods. Model-free methods offer superior prediction accuracy but lack explainability, while model-based methods provide explainability but cannot predict well. Combining both methodologies, we propose a new Bayesian Neural Stochastic Differential Equation model BNSP-SFM, where a behavior SDE model is combined with Bayesian neural networks (BNNs). While the NNs provide superior predictive power, the SDE offers strong explainability with quantifiable uncertainty in behavior and observation. We show that BNSP-SFM achieves up to a 50% improvement in prediction accuracy, compared with 11 state-of-the-art methods. BNSP-SFM also generalizes better to drastically different scenes with different environments and crowd densities (~ 20 times higher than the testing data). Finally, BNSP-SFM can provide predictions with confidence to better explain potential causes of behaviors. The code will be released upon acceptance.
Authors: Shentong Mo, Enze Xie, Ruihang Chu, Lewei Yao, Lanqing Hong, Matthias Nießner, Zhenguo Li
Recent Diffusion Transformers (e.g., DiT) have demonstrated their powerful effectiveness in generating high-quality 2D images. However, it is still being determined whether the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, namely DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers. Compared to existing U-Net approaches, our DiT-3D is more scalable in model size and produces much higher quality generations. Specifically, the DiT-3D adopts the design philosophy of DiT but modifies it by incorporating 3D positional and patch embeddings to adaptively aggregate input from voxelized point clouds. To reduce the computational cost of self-attention in 3D shape generation, we incorporate 3D window attention into Transformer blocks, as the increased 3D token length resulting from the additional dimension of voxels can lead to high computation. Finally, linear and devoxelization layers are used to predict the denoised point clouds. In addition, our transformer architecture supports efficient fine-tuning from 2D to 3D, where the pre-trained DiT-2D checkpoint on ImageNet can significantly improve DiT-3D on ShapeNet. Experimental results on the ShapeNet dataset demonstrate that the proposed DiT-3D achieves state-of-the-art performance in high-fidelity and diverse 3D point cloud generation. In particular, our DiT-3D decreases the 1-Nearest Neighbor Accuracy of the state-of-the-art method by 4.59 and increases the Coverage metric by 3.51 when evaluated on Chamfer Distance.
Authors: Giorgos Sfikas, George Retsinas
We study matrix forms of quaternionic versions of the Fourier Transform and Convolution operations. Quaternions offer a powerful representation unit, however they are related to difficulties in their use that stem foremost from non-commutativity of quaternion multiplication, and due to that $\mu^2 = -1$ posseses infinite solutions in the quaternion domain. Handling of quaternionic matrices is consequently complicated in several aspects (definition of eigenstructure, determinant, etc.). Our research findings clarify the relation of the Quaternion Fourier Transform matrix to the standard (complex) Discrete Fourier Transform matrix, and the extend on which well-known complex-domain theorems extend to quaternions. We focus especially on the relation of Quaternion Fourier Transform matrices to Quaternion Circulant matrices (representing quaternionic convolution), and the eigenstructure of the latter. A proof-of-concept application that makes direct use of our theoretical results is presented, where we produce a method to bound the spectral norm of a Quaternionic Convolution.
Authors: Anjith George, Christophe Ecabert, Hatef Otroshi Shahreza, Ketan Kotwal, Sebastien Marcel
In this paper, we present EdgeFace, a lightweight and efficient face recognition network inspired by the hybrid architecture of EdgeNeXt. By effectively combining the strengths of both CNN and Transformer models, and a low rank linear layer, EdgeFace achieves excellent face recognition performance optimized for edge devices. The proposed EdgeFace network not only maintains low computational costs and compact storage, but also achieves high face recognition accuracy, making it suitable for deployment on edge devices. Extensive experiments on challenging benchmark face datasets demonstrate the effectiveness and efficiency of EdgeFace in comparison to state-of-the-art lightweight models and deep face recognition models. Our EdgeFace model with 1.77M parameters achieves state of the art results on LFW (99.73%), IJB-B (92.67%), and IJB-C (94.85%), outperforming other efficient models with larger computational complexities. The code to replicate the experiments will be made available publicly.
Authors: Duong Q. Nguyen, Thinh D. Le, Phuong D. Nguyen, H. Nguyen-Xuan
Facial wound segmentation plays a crucial role in preoperative planning and optimizing patient outcomes in various medical applications. In this paper, we propose an efficient approach for automating 3D facial wound segmentation using a two-stream graph convolutional network. Our method leverages the Cir3D-FaIR dataset and addresses the challenge of data imbalance through extensive experimentation with different loss functions. To achieve accurate segmentation, we conducted thorough experiments and selected a high-performing model from the trained models. The selected model demonstrates exceptional segmentation performance for complex 3D facial wounds. Furthermore, based on the segmentation model, we propose an improved approach for extracting 3D facial wound fillers and compare it to the results of the previous study. Our method achieved a remarkable accuracy of 0.9999986\% on the test suite, surpassing the performance of the previous method. From this result, we use 3D printing technology to illustrate the shape of the wound filling. The outcomes of this study have significant implications for physicians involved in preoperative planning and intervention design. By automating facial wound segmentation and improving the accuracy of wound-filling extraction, our approach can assist in carefully assessing and optimizing interventions, leading to enhanced patient outcomes. Additionally, it contributes to advancing facial reconstruction techniques by utilizing machine learning and 3D bioprinting for printing skin tissue implants. Our source code is available at \url{https://github.com/SIMOGroup/WoundFilling3D}.
Authors: Hailin Li, Raghavendra Ramachandra
The rapid evolution of high-end smartphones with advanced high-resolution cameras has resulted in contactless capture of fingerprint biometrics that are more reliable and suitable for verification. Similar to other biometric systems, contactless fingerprint-verification systems are vulnerable to presentation attacks. In this paper, we present a comparative study on the generalizability of seven different pre-trained Convolutional Neural Networks (CNN) and a Vision Transformer (ViT) to reliably detect presentation attacks. Extensive experiments were carried out on publicly available smartphone-based presentation attack datasets using four different Presentation Attack Instruments (PAI). The detection performance of the eighth deep feature technique was evaluated using the leave-one-out protocol to benchmark the generalization performance for unseen PAI. The obtained results indicated the best generalization performance with the ResNet50 CNN.
Authors: Korcan Uyanik, S. Faegheh Yeganli, Ivan V. Bajić
Collaborative intelligence (CI) involves dividing an artificial intelligence (AI) model into two parts: front-end, to be deployed on an edge device, and back-end, to be deployed in the cloud. The deep feature tensors produced by the front-end are transmitted to the cloud through a communication channel, which may be subject to packet loss. To address this issue, in this paper, we propose a novel approach to enhance the resilience of the CI system in the presence of packet loss through Unequal Loss Protection (ULP). The proposed ULP approach involves a feature importance estimator, which estimates the importance of feature packets produced by the front-end, and then selectively applies Forward Error Correction (FEC) codes to protect important packets. Experimental results demonstrate that the proposed approach can significantly improve the reliability and robustness of the CI system in the presence of packet loss.
Authors: Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, Haibin Yan
Equipping embodied agents with commonsense is important for robots to successfully complete complex human instructions in general environments. Recent large language models (LLM) can embed rich semantic knowledge for agents in plan generation of complex tasks, while they lack the information about the realistic world and usually yield infeasible action sequences. In this paper, we propose a TAsk Planing Agent (TaPA) in embodied tasks for grounded planning with physical scene constraint, where the agent generates executable plans according to the existed objects in the scene by aligning LLMs with the visual perception models. Specifically, we first construct a multimodal dataset containing triplets of indoor scenes, instructions and action plans, where we provide the designed prompts and the list of existing objects in the scene for GPT-3.5 to generate a large number of instructions and corresponding planned actions. The generated data is leveraged for grounded plan tuning of pre-trained LLMs. During inference, we discover the objects in the scene by extending open-vocabulary object detectors to multi-view RGB images collected in different achievable locations. Experimental results show that the generated plan from our TaPA framework can achieve higher success rate than LLaVA and GPT-3.5 by a sizable margin, which indicates the practicality of embodied task planning in general and complex environments.
Authors: Xiang Li, Varun Belagali, Jinghuan Shang, Michael S. Ryoo
Sequence modeling approaches have shown promising results in robot imitation learning. Recently, diffusion models have been adopted for behavioral cloning, benefiting from their exceptional capabilities in modeling complex data distribution. In this work, we propose Crossway Diffusion, a method to enhance diffusion-based visuomotor policy learning by using an extra self-supervised learning (SSL) objective. The standard diffusion-based policy generates action sequences from random noise conditioned on visual observations and other low-dimensional states. We further extend this by introducing a new decoder that reconstructs raw image pixels (and other state information) from the intermediate representations of the reverse diffusion process, and train the model jointly using the SSL loss. Our experiments demonstrate the effectiveness of Crossway Diffusion in various simulated and real-world robot tasks, confirming its advantages over the standard diffusion-based policy. We demonstrate that such self-supervised reconstruction enables better representation for policy learning, especially when the demonstrations have different proficiencies.
Authors: Marios Loizou, Siddhant Garg, Dmitry Petrov, Melinos Averkiou, Evangelos Kalogerakis
We present a deep learning method that propagates point-wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross-shape attention mechanism to enable interactions between a shape's point-wise features and those of other shapes. The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation. Our method also proposes a shape retrieval measure to select suitable shapes for cross-shape attention operations for each test shape. Our experiments demonstrate that our approach yields state-of-the-art results in the popular PartNet dataset.
Authors: Yongquan Yang, Yiming Yang, Jie Chen, Jiayi Zheng, Zhongxi Zheng
Learning from noisy labels is an important concern because of the lack of accurate ground-truth labels in plenty of real-world scenarios. In practice, various approaches for this concern first make some corrections corresponding to potentially noisy-labeled instances, and then update predictive model with information of the made corrections. However, in specific areas, such as medical histopathology whole slide image analysis (MHWSIA), it is often difficult or even impossible for experts to manually achieve the noisy-free ground-truth labels which leads to labels with complex noise. This situation raises two more difficult problems: 1) the methodology of approaches making corrections corresponding to potentially noisy-labeled instances has limitations due to the complex noise existing in labels; and 2) the appropriate evaluation strategy for validation/testing is unclear because of the great difficulty in collecting the noisy-free ground-truth labels. In this paper, we focus on alleviating these two problems. For the problem 1), we present one-step abductive multi-target learning (OSAMTL) that imposes a one-step logical reasoning upon machine learning via a multi-target learning procedure to constrain the predictions of the learning model to be subject to our prior knowledge about the true target. For the problem 2), we propose a logical assessment formula (LAF) that evaluates the logical rationality of the outputs of an approach by estimating the consistencies between the predictions of the learning model and the logical facts narrated from the results of the one-step logical reasoning of OSAMTL. Applying OSAMTL and LAF to the Helicobacter pylori (H. pylori) segmentation task in MHWSIA, we show that OSAMTL is able to enable the machine learning model achieving logically more rational predictions, which is beyond various state-of-the-art approaches in handling complex noisy labels.
Authors: Ce Zheng, Wenhan Wu, Chen Chen, Taojiannan Yang, Sijie Zhu, Ju Shen, Nasser Kehtarnavaz, Mubarak Shah
Human pose estimation aims to locate the human body parts and build human body representation (e.g., body skeleton) from input data such as images and videos. It has drawn increasing attention during the past decade and has been utilized in a wide range of applications including human-computer interaction, motion analysis, augmented reality, and virtual reality. Although the recently developed deep learning-based solutions have achieved high performance in human pose estimation, there still remain challenges due to insufficient training data, depth ambiguities, and occlusion. The goal of this survey paper is to provide a comprehensive review of recent deep learning-based solutions for both 2D and 3D pose estimation via a systematic analysis and comparison of these solutions based on their input data and inference procedures. More than 250 research papers since 2014 are covered in this survey. Furthermore, 2D and 3D human pose estimation datasets and evaluation metrics are included. Quantitative performance comparisons of the reviewed methods on popular datasets are summarized and discussed. Finally, the challenges involved, applications, and future research directions are concluded. A regularly updated project page is provided: \url{https://github.com/zczcwh/DL-HPE}
Authors: Wei Lian, Wangmeng Zuo
In many applications, we need algorithms which can align partially overlapping point sets and are invariant to the corresponding transformations. In this work, a method possessing such properties is realized by minimizing the objective of the robust point matching (RPM) algorithm. We first show that the RPM objective is a cubic polynomial. We then utilize the convex envelopes of trilinear and bilinear monomials to derive its lower bound function. The resulting lower bound problem has the merit that it can be efficiently solved via linear assignment and low dimensional convex quadratic programming. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently. Experimental results demonstrated better robustness of the proposed method against non-rigid deformation, positional noise and outliers in case that outliers are not mixed with inliers when compared with the state-of-the-art approaches. They also showed that it has competitive efficiency and scales well with problem size.
Authors: Haipeng Li, Shuaicheng Liu, Jue Wang
Mobile captured images can be aligned using their gyroscope sensors. Optical image stabilizer (OIS) terminates this possibility by adjusting the images during the capturing. In this work, we propose a deep network that compensates the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the OIS cameras. To achieve this, first, we record both videos and gyroscopes with an OIS camera as training data. Then, we convert gyroscope readings into motion fields. Second, we propose a Fundamental Mixtures motion model for rolling shutter cameras, where an array of rotations within a frame are extracted as the ground-truth guidance. Third, we train a convolutional neural network with gyroscope motions as input to compensate for the OIS motion. Once finished, the compensation network can be applied for other scenes, where the image alignment is purely based on gyroscopes with no need for images contents, delivering strong robustness. Experiments show that our results are comparable with that of non-OIS cameras, and outperform image-based alignment results with a relatively large margin. Code and dataset are available at https://github.com/lhaippp/DeepOIS
Authors: Alon Shoshan, Nadav Bhonker, Igor Kviatkovsky, Matan Fintz, Gerard Medioni
Recent breakthroughs in synthetic data generation approaches made it possible to produce highly photorealistic images which are hardly distinguishable from real ones. Furthermore, synthetic generation pipelines have the potential to generate an unlimited number of images. The combination of high photorealism and scale turn synthetic data into a promising candidate for improving various machine learning (ML) pipelines. Thus far, a large body of research in this field has focused on using synthetic images for training, by augmenting and enlarging training data. In contrast to using synthetic data for training, in this work we explore whether synthetic data can be beneficial for model selection. Considering the task of image classification, we demonstrate that when data is scarce, synthetic data can be used to replace the held out validation set, thus allowing to train on a larger dataset. We also introduce a novel method to calibrate the synthetic error estimation to fit that of the real domain. We show that such calibration significantly improves the usefulness of synthetic data for model selection.
Authors: Jiezhang Cao, Yawei Li, Kai Zhang, Luc Van Gool
Video super-resolution (VSR), with the aim to restore a high-resolution video from its corresponding low-resolution version, is a spatial-temporal sequence prediction problem. Recently, Transformer has been gaining popularity due to its parallel computing ability for sequence-to-sequence modeling. Thus, it seems to be straightforward to apply the vision Transformer to solve VSR. However, the typical block design of Transformer with a fully connected self-attention layer and a token-wise feed-forward layer does not fit well for VSR due to the following two reasons. First, the fully connected self-attention layer neglects to exploit the data locality because this layer relies on linear layers to compute attention maps. Second, the token-wise feed-forward layer lacks the feature alignment which is important for VSR since this layer independently processes each of the input token embeddings without any interaction among them. In this paper, we make the first attempt to adapt Transformer for VSR. Specifically, to tackle the first issue, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information. For the second issue, we design a bidirectional optical flow-based feed-forward layer to discover the correlations across different video frames and also align features. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed method. The code will be available at https://github.com/caojiezhang/VSR-Transformer.
Authors: Bingyuan Liu, Ismail Ben Ayed, Adrian Galdran, Jose Dolz
In spite of the dominant performances of deep neural networks, recent works have shown that they are poorly calibrated, resulting in over-confident predictions. Miscalibration can be exacerbated by overfitting due to the minimization of the cross-entropy during training, as it promotes the predicted softmax probabilities to match the one-hot label assignments. This yields a pre-softmax activation of the correct class that is significantly larger than the remaining activations. Recent evidence from the literature suggests that loss functions that embed implicit or explicit maximization of the entropy of predictions yield state-of-the-art calibration performances. We provide a unifying constrained-optimization perspective of current state-of-the-art calibration losses. Specifically, these losses could be viewed as approximations of a linear penalty (or a Lagrangian) imposing equality constraints on logit distances. This points to an important limitation of such underlying equality constraints, whose ensuing gradients constantly push towards a non-informative solution, which might prevent from reaching the best compromise between the discriminative performance and calibration of the model during gradient-based optimization. Following our observations, we propose a simple and flexible generalization based on inequality constraints, which imposes a controllable margin on logit distances. Comprehensive experiments on a variety of image classification, semantic segmentation and NLP benchmarks demonstrate that our method sets novel state-of-the-art results on these tasks in terms of network calibration, without affecting the discriminative performance. The code is available at https://github.com/by-liu/MbLS .
Authors: Michael P. J. Camilleri, Li Zhang, Rasneer S. Bains, Andrew Zisserman, Christopher K. I. Williams
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse's location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the object identification problem as an assignment problem (solved using Integer Linear Programming), and (b) a novel probabilistic model of the affinity between tracklets and RFID data. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden.
Authors: Yunfan Ye, Renjiao Yi, Zhiping Cai, Kai Xu
Learning-based edge detection has hereunto been strongly supervised with pixel-wise annotations which are tedious to obtain manually. We study the problem of self-training edge detection, leveraging the untapped wealth of large-scale unlabeled image datasets. We design a self-supervised framework with multi-layer regularization and self-teaching. In particular, we impose a consistency regularization which enforces the outputs from each of the multiple layers to be consistent for the input image and its perturbed counterpart. We adopt L0-smoothing as the 'perturbation' to encourage edge prediction lying on salient boundaries following the cluster assumption in self-supervised learning. Meanwhile, the network is trained with multi-layer supervision by pseudo labels which are initialized with Canny edges and then iteratively refined by the network as the training proceeds. The regularization and self-teaching together attain a good balance of precision and recall, leading to a significant performance boost over supervised methods, with lightweight refinement on the target dataset. Furthermore, our method demonstrates strong cross-dataset generality. For example, it attains 4.8% improvement for ODS and 5.8% for OIS when tested on the unseen BIPED dataset, compared to the state-of-the-art methods.
Authors: Ekin Akyürek, Jacob Andreas
In tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that enforce a compositional process of sentence interpretation. In this paper, we present a domain-general and model-agnostic formulation of compositionality as a constraint on symmetries of data distributions rather than models. Informally, we prove that whenever a task can be solved by a compositional model, there is a corresponding data augmentation scheme -- a procedure for transforming examples into other well formed examples -- that imparts compositional inductive bias on any model trained to solve the same task. We describe a procedure called LEXSYM that discovers these transformations automatically, then applies them to training data for ordinary neural sequence models. Unlike existing compositional data augmentation procedures, LEXSYM can be deployed agnostically across text, structured data, and even images. It matches or surpasses state-of-the-art, task-specific models on COGS semantic parsing, SCAN and ALCHEMY instruction following, and CLEVR-COGENT visual question answering datasets.
Authors: Zeyad Khalifa, Syed Afaq Ali Shah
The physical and textural attributes of objects have been widely studied for recognition, detection and segmentation tasks in computer vision.~A number of datasets, such as large scale ImageNet, have been proposed for feature learning using data hungry deep neural networks and for hand-crafted feature extraction. To intelligently interact with objects, robots and intelligent machines need the ability to infer beyond the traditional physical/textural attributes, and understand/learn visual cues, called visual affordances, for affordance recognition, detection and segmentation. To date there is no publicly available large dataset for visual affordance understanding and learning. In this paper, we introduce a large scale multi-view RGBD visual affordance learning dataset, a benchmark of 47210 RGBD images from 37 object categories, annotated with 15 visual affordance categories. To the best of our knowledge, this is the first ever and the largest multi-view RGBD visual affordance learning dataset. We benchmark the proposed dataset for affordance segmentation and recognition tasks using popular Vision Transformer and Convolutional Neural Networks. Several state-of-the-art deep learning networks are evaluated each for affordance recognition and segmentation tasks. Our experimental results showcase the challenging nature of the dataset and present definite prospects for new and robust affordance learning algorithms. The dataset is publicly available at https://sites.google.com/view/afaqshah/dataset.
Authors: Xin Zhang, Xiaohua Xie, Jianhuang Lai, Wei-Shi Zheng
We are concerned with retrieving a query person from multiple videos captured by a non-overlapping camera network. Existing methods often rely on purely visual matching or consider temporal constraints but ignore the spatial information of the camera network. To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information. To obtain pedestrian trajectories, we propose a novel cross-camera spatio-temporal model that integrates pedestrians' walking habits and the path layout between cameras to form a joint probability distribution. Such a spatio-temporal model among a camera network can be specified using sparsely sampled pedestrian data. Based on the spatio-temporal model, cross-camera trajectories can be extracted by the conditional random field model and further optimized by restricted non-negative matrix factorization. Finally, a trajectory re-ranking technique is proposed to improve the pedestrian retrieval results. To verify the effectiveness of our method, we construct the first cross-camera pedestrian trajectory dataset, the Person Trajectory Dataset, in real surveillance scenarios. Extensive experiments verify the effectiveness and robustness of the proposed method.
Authors: Lalita Kumari, Sukhdeep Singh, Vaibhav Varish Singh Rathore, Anuj Sharma
In this study, we have presented an efficient procedure using two state-of-the-art approaches from the literature of handwritten text recognition as Vertical Attention Network and Word Beam Search. The attention module is responsible for internal line segmentation that consequently processes a page in a line-by-line manner. At the decoding step, we have added a connectionist temporal classification-based word beam search decoder as a post-processing step. In this study, an end-to-end paragraph recognition system is presented with a lexicon decoder as a post-processing step. Our procedure reports state-of-the-art results on standard datasets. The reported character error rate is 3.24% on the IAM dataset with 27.19% improvement, 1.13% on RIMES with 40.83% improvement and 2.43% on the READ-16 dataset with 32.31% improvement from existing literature and the word error rate is 8.29% on IAM dataset with 43.02% improvement, 2.94% on RIMES dataset with 56.25% improvement and 7.35% on READ-2016 dataset with 47.27% improvement from the existing results. The character error rate and word error rate reported in this work surpass the results reported in the literature.
Authors: Qiang Zhang, Seung-Hwan Baek, Szymon Rusinkiewicz, Felix Heide
We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in memory and runtime, both in training and inference. The method begins with a uniformly-sampled random point cloud and learns per-point position and view-dependent appearance, using a differentiable splat-based renderer to evolve the model to match a set of input images. Our method is up to 300x faster than NeRF in both training and inference, with only a marginal sacrifice in quality, while using less than 10~MB of memory for a static scene. For dynamic scenes, our method trains two orders of magnitude faster than STNeRF and renders at near interactive rate, while maintaining high image quality and temporal coherence even without imposing any temporal-coherency regularizers.
Authors: Li Zhang, Jiachen Lu, Junge Zhang, Xiatian Zhu, Jianfeng Feng, Tao Xiang
Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory usage. This motivates the development of approximating the self-attention at linear complexity. However, an in-depth analysis in this work reveals that existing methods are either theoretically flawed or empirically ineffective for visual recognition. We identify that their limitations are rooted in the inheritance of softmax-based self-attention during approximations, that is, normalizing the scaled dot-product between token feature vectors using the softmax function. As preserving the softmax operation challenges any subsequent linearization efforts. By this insight, a family of Softmax-Free Transformers (SOFT) are proposed. Specifically, a Gaussian kernel function is adopted to replace the dot-product similarity, enabling a full self-attention matrix to be approximated under low-rank matrix decomposition. For computational robustness, we estimate the Moore-Penrose inverse using an iterative Newton-Raphson method in the forward process only, while calculating its theoretical gradients only once in the backward process. To further expand applicability (e.g., dense prediction tasks), an efficient symmetric normalization technique is introduced. Extensive experiments on ImageNet, COCO, and ADE20K show that our SOFT significantly improves the computational efficiency of existing ViT variants. With linear complexity, much longer token sequences are permitted by SOFT, resulting in superior trade-off between accuracy and complexity. Code and models are available at https://github.com/fudan-zvg/SOFT.
Authors: Awet Haileslassie Gebrehiwot, Patrik Vacek, David Hurych, Karel Zimmermann, Patrick Perez, Tomáš Svoboda
Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are large, and manual labeling is very challenging. We propose to leverage sequences of point clouds to boost the pseudolabeling technique in a teacher-student setup via training multiple teachers, each with access to different temporal information. This set of teachers, dubbed Concordance, provides higher quality pseudo-labels for student training than standard methods. The output of multiple teachers is combined via a novel pseudo label confidence-guided criterion. Our experimental evaluation focuses on the 3D point cloud domain and urban driving scenarios. We show the performance of our method applied to 3D semantic segmentation and 3D object detection on three benchmark datasets. Our approach, which uses only 20% manual labels, outperforms some fully supervised methods. A notable performance boost is achieved for classes rarely appearing in training data.
Authors: David Bruggemann, Christos Sakaridis, Prune Truong, Luc Van Gool
Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images. UDA adapts models trained on normal conditions to the target adverse-condition domains. Meanwhile, multiple datasets with driving scenes provide corresponding images of the same scenes across multiple conditions, which can serve as a form of weak supervision for domain adaptation. We propose Refign, a generic extension to self-training-based UDA methods which leverages these cross-domain correspondences. Refign consists of two steps: (1) aligning the normal-condition image to the corresponding adverse-condition image using an uncertainty-aware dense matching network, and (2) refining the adverse prediction with the normal prediction using an adaptive label correction mechanism. We design custom modules to streamline both steps and set the new state of the art for domain-adaptive semantic segmentation on several adverse-condition benchmarks, including ACDC and Dark Zurich. The approach introduces no extra training parameters, minimal computational overhead -- during training only -- and can be used as a drop-in extension to improve any given self-training-based UDA method. Code is available at https://github.com/brdav/refign.
Authors: Youpeng Zhao, Huadong Tang, Yingying Jiang, Yong A, Qiang Wu
Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to learn visual representations, but these networks are spatially local. ViTs can learn global representations with their self-attention mechanism, but they are usually heavy-weight and unsuitable for mobile devices. In this paper, we propose cross feature attention (XFA) to bring down computation cost for transformers, and combine efficient mobile CNNs to form a novel efficient light-weight CNN-ViT hybrid model, XFormer, which can serve as a general-purpose backbone to learn both global and local representation. Experimental results show that XFormer outperforms numerous CNN and ViT-based models across different tasks and datasets. On ImageNet1K dataset, XFormer achieves top-1 accuracy of 78.5% with 5.5 million parameters, which is 2.2% and 6.3% more accurate than EfficientNet-B0 (CNN-based) and DeiT (ViT-based) for similar number of parameters. Our model also performs well when transferring to object detection and semantic segmentation tasks. On MS COCO dataset, XFormer exceeds MobileNetV2 by 10.5 AP (22.7 -> 33.2 AP) in YOLOv3 framework with only 6.3M parameters and 3.8G FLOPs. On Cityscapes dataset, with only a simple all-MLP decoder, XFormer achieves mIoU of 78.5 and FPS of 15.3, surpassing state-of-the-art lightweight segmentation networks.
Authors: Zhipeng Du, Miaojing Shi, Jiankang Deng, Stefanos Zafeiriou
Perspective distortions and crowd variations make crowd counting a challenging task in computer vision. To tackle it, many previous works have used multi-scale architecture in deep neural networks (DNNs). Multi-scale branches can be either directly merged (e.g. by concatenation) or merged through the guidance of proxies (e.g. attentions) in the DNNs. Despite their prevalence, these combination methods are not sophisticated enough to deal with the per-pixel performance discrepancy over multi-scale density maps. In this work, we redesign the multi-scale neural network by introducing a hierarchical mixture of density experts, which hierarchically merges multi-scale density maps for crowd counting. Within the hierarchical structure, an expert competition and collaboration scheme is presented to encourage contributions from all scales; pixel-wise soft gating nets are introduced to provide pixel-wise soft weights for scale combinations in different hierarchies. The network is optimized using both the crowd density map and the local counting map, where the latter is obtained by local integration on the former. Optimizing both can be problematic because of their potential conflicts. We introduce a new relative local counting loss based on relative count differences among hard-predicted local regions in an image, which proves to be complementary to the conventional absolute error loss on the density map. Experiments show that our method achieves the state-of-the-art performance on five public datasets, i.e. ShanghaiTech, UCF_CC_50, JHU-CROWD++, NWPU-Crowd and Trancos.
Authors: Zecheng Liu, Jia Wei, Rui Li, Jianlong Zhou
People perceive the world with different senses, such as sight, hearing, smell, and touch. Processing and fusing information from multiple modalities enables Artificial Intelligence to understand the world around us more easily. However, when there are missing modalities, the number of available modalities is different in diverse situations, which leads to an N-to-One fusion problem. To solve this problem, we propose a self-attention based fusion block called SFusion. Different from preset formulations or convolution based methods, the proposed block automatically learns to fuse available modalities without synthesizing or zero-padding missing ones. Specifically, the feature representations extracted from upstream processing model are projected as tokens and fed into self-attention module to generate latent multimodal correlations. Then, a modal attention mechanism is introduced to build a shared representation, which can be applied by the downstream decision model. The proposed SFusion can be easily integrated into existing multimodal analysis networks. In this work, we apply SFusion to different backbone networks for human activity recognition and brain tumor segmentation tasks. Extensive experimental results show that the SFusion block achieves better performance than the competing fusion strategies. Our code is available at https://github.com/scut-cszcl/SFusion.
Authors: Jingru Li, Sheng Zhou, Liangcheng Li, Haishuai Wang, Zhi Yu, Jiajun Bu
Data-free knowledge distillation (DFKD) is a widely-used strategy for Knowledge Distillation (KD) whose training data is not available. It trains a lightweight student model with the aid of a large pretrained teacher model without any access to training data. However, existing DFKD methods suffer from inadequate and unstable training process, as they do not adjust the generation target dynamically based on the status of the student model during learning. To address this limitation, we propose a novel DFKD method called CuDFKD. It teaches students by a dynamic strategy that gradually generates easy-to-hard pseudo samples, mirroring how humans learn. Besides, CuDFKD adapts the generation target dynamically according to the status of student model. Moreover, We provide a theoretical analysis of the majorization minimization (MM) algorithm and explain the convergence of CuDFKD. To measure the robustness and fidelity of DFKD methods, we propose two more metrics, and experiments shows CuDFKD has comparable performance to state-of-the-art (SOTA) DFKD methods on all datasets. Experiments also present that our CuDFKD has the fastest convergence and best robustness over other SOTA DFKD methods.
Authors: Grégoire Petit, Adrian Popescu, Eden Belouadah, David Picard, Bertrand Delezoide
Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging when no memory buffer is available. Mainstream methods need to store two deep models since they integrate new classes using fine-tuning with knowledge distillation from the previous incremental state. We propose a method which has similar number of parameters but distributes them differently in order to find a better balance between plasticity and stability. Following an approach already deployed by transfer-based incremental methods, we freeze the feature extractor after the initial state. Classes in the oldest incremental states are trained with this frozen extractor to ensure stability. Recent classes are predicted using partially fine-tuned models in order to introduce plasticity. Our proposed plasticity layer can be incorporated to any transfer-based method designed for exemplar-free incremental learning, and we apply it to two such methods. Evaluation is done with three large-scale datasets. Results show that performance gains are obtained in all tested configurations compared to existing methods.
Authors: Yashowardhan Shinde, Kishore Kulkarni, Sachin Kuberkar
Document denoising is considered one of the most challenging tasks in computer vision. There exist millions of documents that are still to be digitized, but problems like document degradation due to natural and man-made factors make this task very difficult. This paper introduces a supervised approach for cleaning dirty documents using a new fully convolutional auto-encoder architecture. This paper focuses on restoring documents with discrepancies like deformities caused due to aging of a document, creases left on the pages that were xeroxed, random black patches, lightly visible text, etc., and also improving the quality of the image for better optical character recognition system (OCR) performance. Removing noise from scanned documents is a very important step before the documents as this noise can severely affect the performance of an OCR system. The experiments in this paper have shown promising results as the model is able to learn a variety of ordinary as well as unusual noises and rectify them efficiently.
Authors: Keita Mason, Joshua Knights, Milad Ramezani, Peyman Moghadam, Dimity Miller
State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments. To address this issue, we investigate the task of uncertainty-aware lidar place recognition, where each predicted place must have an associated uncertainty that can be used to identify and reject incorrect predictions. We introduce a novel evaluation protocol and present the first comprehensive benchmark for this task, testing across five uncertainty estimation techniques and three large-scale datasets. Our results show that an Ensembles approach is the highest performing technique, consistently improving the performance of lidar place recognition and uncertainty estimation in novel environments, though it incurs a computational cost. Code is publicly available at https://github.com/csiro-robotics/Uncertainty-LPR.
Authors: Dani Valevski, Matan Kalman, Eyal Molad, Eyal Segalis, Yossi Matias, Yaniv Leviathan
Text-driven image generation methods have shown impressive results recently, allowing casual users to generate high quality images by providing textual descriptions. However, similar capabilities for editing existing images are still out of reach. Text-driven image editing methods usually need edit masks, struggle with edits that require significant visual changes and cannot easily keep specific details of the edited portion. In this paper we make the observation that image-generation models can be converted to image-editing models simply by fine-tuning them on a single image. We also show that initializing the stochastic sampler with a noised version of the base image before the sampling and interpolating relevant details from the base image after sampling further increase the quality of the edit operation. Combining these observations, we propose UniTune, a novel image editing method. UniTune gets as input an arbitrary image and a textual edit description, and carries out the edit while maintaining high fidelity to the input image. UniTune does not require additional inputs, like masks or sketches, and can perform multiple edits on the same image without retraining. We test our method using the Imagen model in a range of different use cases. We demonstrate that it is broadly applicable and can perform a surprisingly wide range of expressive editing operations, including those requiring significant visual changes that were previously impossible.
Authors: Yidong Ouyang, Liyan Xie, Guang Cheng
Synthetic data generation has become an emerging tool to help improve the adversarial robustness in classification tasks since robust learning requires a significantly larger amount of training samples compared with standard classification tasks. Among various deep generative models, the diffusion model has been shown to produce high-quality synthetic images and has achieved good performance in improving the adversarial robustness. However, diffusion-type methods are typically slow in data generation as compared with other generative models. Although different acceleration techniques have been proposed recently, it is also of great importance to study how to improve the sample efficiency of generated data for the downstream task. In this paper, we first analyze the optimality condition of synthetic distribution for achieving non-trivial robust accuracy. We show that enhancing the distinguishability among the generated data is critical for improving adversarial robustness. Thus, we propose the Contrastive-Guided Diffusion Process (Contrastive-DP), which adopts the contrastive loss to guide the diffusion model in data generation. We verify our theoretical results using simulations and demonstrate the good performance of Contrastive-DP on image datasets.
Authors: Prateek Yadav, Mohit Bansal
Continual Learning (CL) methods focus on accumulating knowledge over time while avoiding catastrophic forgetting. Recently, Wortsman et al. (2020) proposed a CL method, SupSup, which uses a randomly initialized, fixed base network (model) and finds a supermask for each new task that selectively keeps or removes each weight to produce a subnetwork. They prevent forgetting as the network weights are not being updated. Although there is no forgetting, the performance of SupSup is sub-optimal because fixed weights restrict its representational power. Furthermore, there is no accumulation or transfer of knowledge inside the model when new tasks are learned. Hence, we propose ExSSNeT (Exclusive Supermask SubNEtwork Training), that performs exclusive and non-overlapping subnetwork weight training. This avoids conflicting updates to the shared weights by subsequent tasks to improve performance while still preventing forgetting. Furthermore, we propose a novel KNN-based Knowledge Transfer (KKT) module that utilizes previously acquired knowledge to learn new tasks better and faster. We demonstrate that ExSSNeT outperforms strong previous methods on both NLP and Vision domains while preventing forgetting. Moreover, ExSSNeT is particularly advantageous for sparse masks that activate 2-10% of the model parameters, resulting in an average improvement of 8.3% over SupSup. Furthermore, ExSSNeT scales to a large number of tasks (100). Our code is available at https://github.com/prateeky2806/exessnet.
Authors: Wing-Fung Ku, Wan-Chi Siu, Xi Cheng, H. Anthony Chan
Have you ever thought that you can be an intelligent painter? This means that you can paint a picture with a few expected objects in mind, or with a desirable scene. This is different from normal inpainting approaches for which the location of specific objects cannot be determined. In this paper, we present an intelligent painter that generate a person's imaginary scene in one go, given explicit hints. We propose a resampling strategy for Denoising Diffusion Probabilistic Model (DDPM) to intelligently compose unconditional harmonized pictures according to the input subjects at specific locations. By exploiting the diffusion property, we resample efficiently to produce realistic pictures. Experimental results show that our resampling method favors the semantic meaning of the generated output efficiently and generates less blurry output. Quantitative analysis of image quality assessment shows that our method produces higher perceptual quality images compared with the state-of-the-art methods.
Authors: Simon Welker, Henry N. Chapman, Timo Gerkmann
In this work, we utilize the high-fidelity generation abilities of diffusion models to solve blind JPEG restoration at high compression levels. We propose an elegant modification of the forward stochastic differential equation of diffusion models to adapt them to this restoration task and name our method DriftRec. Comparing DriftRec against an $L_2$ regression baseline with the same network architecture and two state-of-the-art techniques for JPEG restoration, we show that our approach can escape the tendency of other methods to generate blurry images, and recovers the distribution of clean images significantly more faithfully. For this, only a dataset of clean/corrupted image pairs and no knowledge about the corruption operation is required, enabling wider applicability to other restoration tasks. In contrast to other conditional and unconditional diffusion models, we utilize the idea that the distributions of clean and corrupted images are much closer to each other than each is to the usual Gaussian prior of the reverse process in diffusion models. Our approach therefore requires only low levels of added noise, and needs comparatively few sampling steps even without further optimizations. We show that DriftRec naturally generalizes to realistic and difficult scenarios such as unaligned double JPEG compression and blind restoration of JPEGs found online, without having encountered such examples during training.
Authors: Alexander Bigalke, Lasse Hansen, Jasper Diesel, Carlotta Hennigs, Philipp Rostalski, Mattias P. Heinrich
3D human pose estimation is a key component of clinical monitoring systems. The clinical applicability of deep pose estimation models, however, is limited by their poor generalization under domain shifts along with their need for sufficient labeled training data. As a remedy, we present a novel domain adaptation method, adapting a model from a labeled source to a shifted unlabeled target domain. Our method comprises two complementary adaptation strategies based on prior knowledge about human anatomy. First, we guide the learning process in the target domain by constraining predictions to the space of anatomically plausible poses. To this end, we embed the prior knowledge into an anatomical loss function that penalizes asymmetric limb lengths, implausible bone lengths, and implausible joint angles. Second, we propose to filter pseudo labels for self-training according to their anatomical plausibility and incorporate the concept into the Mean Teacher paradigm. We unify both strategies in a point cloud-based framework applicable to unsupervised and source-free domain adaptation. Evaluation is performed for in-bed pose estimation under two adaptation scenarios, using the public SLP dataset and a newly created dataset. Our method consistently outperforms various state-of-the-art domain adaptation methods, surpasses the baseline model by 31%/66%, and reduces the domain gap by 65%/82%. Source code is available at https://github.com/multimodallearning/da-3dhpe-anatomy.
Authors: Junhyun Nam, Sangwoo Mo, Jaeho Lee, Jinwoo Shin
To capture the relationship between samples and labels, conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to another latent attribute. To mitigate this issue, which we call spurious causality of conditional generation, we propose a general two-step strategy. (a) Fairness Intervention (FI): emphasize the minority samples that are hard to generate due to the spurious correlation in the training dataset. (b) Corrective Sampling (CS): explicitly filter the generated samples and ensure that they follow the desired latent attribute distribution. We have designed the fairness intervention to work for various degrees of supervision on the spurious attribute, including unsupervised, weakly-supervised, and semi-supervised scenarios. Our experimental results demonstrate that FICS can effectively resolve spurious causality of conditional generation across various datasets.
Authors: Hyekang Kevin Joo, Khoa Vo, Kashu Yamazaki, Ngan Le
Video anomaly detection (VAD) -- commonly formulated as a multiple-instance learning problem in a weakly-supervised manner due to its labor-intensive nature -- is a challenging problem in video surveillance where the frames of anomaly need to be localized in an untrimmed video. In this paper, we first propose to utilize the ViT-encoded visual features from CLIP, in contrast with the conventional C3D or I3D features in the domain, to efficiently extract discriminative representations in the novel technique. We then model temporal dependencies and nominate the snippets of interest by leveraging our proposed Temporal Self-Attention (TSA). The ablation study confirms the effectiveness of TSA and ViT feature. The extensive experiments show that our proposed CLIP-TSA outperforms the existing state-of-the-art (SOTA) methods by a large margin on three commonly-used benchmark datasets in the VAD problem (UCF-Crime, ShanghaiTech Campus, and XD-Violence). Our source code is available at https://github.com/joos2010kj/CLIP-TSA.
Authors: Junyan Cao, Yan Hong, Li Niu
Image harmonization aims to produce visually harmonious composite images by adjusting the foreground appearance to be compatible with the background. When the composite image has photographic foreground and painterly background, the task is called painterly image harmonization. There are only few works on this task, which are either time-consuming or weak in generating well-harmonized results. In this work, we propose a novel painterly harmonization network consisting of a dual-domain generator and a dual-domain discriminator, which harmonizes the composite image in both spatial domain and frequency domain. The dual-domain generator performs harmonization by using AdaIN modules in the spatial domain and our proposed ResFFT modules in the frequency domain. The dual-domain discriminator attempts to distinguish the inharmonious patches based on the spatial feature and frequency feature of each patch, which can enhance the ability of generator in an adversarial manner. Extensive experiments on the benchmark dataset show the effectiveness of our method. Our code and model are available at https://github.com/bcmi/PHDNet-Painterly-Image-Harmonization.
Authors: Korrawe Karunratanakul, Sergey Prokudin, Otmar Hilliges, Siyu Tang
We present HARP (HAnd Reconstruction and Personalization), a personalized hand avatar creation approach that takes a short monocular RGB video of a human hand as input and reconstructs a faithful hand avatar exhibiting a high-fidelity appearance and geometry. In contrast to the major trend of neural implicit representations, HARP models a hand with a mesh-based parametric hand model, a vertex displacement map, a normal map, and an albedo without any neural components. As validated by our experiments, the explicit nature of our representation enables a truly scalable, robust, and efficient approach to hand avatar creation. HARP is optimized via gradient descent from a short sequence captured by a hand-held mobile phone and can be directly used in AR/VR applications with real-time rendering capability. To enable this, we carefully design and implement a shadow-aware differentiable rendering scheme that is robust to high degree articulations and self-shadowing regularly present in hand motion sequences, as well as challenging lighting conditions. It also generalizes to unseen poses and novel viewpoints, producing photo-realistic renderings of hand animations performing highly-articulated motions. Furthermore, the learned HARP representation can be used for improving 3D hand pose estimation quality in challenging viewpoints. The key advantages of HARP are validated by the in-depth analyses on appearance reconstruction, novel-view and novel pose synthesis, and 3D hand pose refinement. It is an AR/VR-ready personalized hand representation that shows superior fidelity and scalability.
Authors: Rohan Pandey, Rulin Shao, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
Despite recent progress towards scaling up multimodal vision-language models, these models are still known to struggle on compositional generalization benchmarks such as Winoground. We find that a critical component lacking from current vision-language models is relation-level alignment: the ability to match directional semantic relations in text (e.g., "mug in grass") with spatial relationships in the image (e.g., the position of the mug relative to the grass). To tackle this problem, we show that relation alignment can be enforced by encouraging the directed language attention from 'mug' to 'grass' (capturing the semantic relation 'in') to match the directed visual attention from the mug to the grass. Tokens and their corresponding objects are softly identified using the cross-modal attention. We prove that this notion of soft relation alignment is equivalent to enforcing congruence between vision and language attention matrices under a 'change of basis' provided by the cross-modal attention matrix. Intuitively, our approach projects visual attention into the language attention space to calculate its divergence from the actual language attention, and vice versa. We apply our Cross-modal Attention Congruence Regularization (CACR) loss to UNITER and improve on the state-of-the-art approach to Winoground.
Authors: Chengxi Zeng, Xinyu Yang, David Smithard, Majid Mirmehdi, Alberto M Gambaruto, Tilo Burghardt
This paper presents a deep learning framework for medical video segmentation. Convolution neural network (CNN) and transformer-based methods have achieved great milestones in medical image segmentation tasks due to their incredible semantic feature encoding and global information comprehension abilities. However, most existing approaches ignore a salient aspect of medical video data - the temporal dimension. Our proposed framework explicitly extracts features from neighbouring frames across the temporal dimension and incorporates them with a temporal feature blender, which then tokenises the high-level spatio-temporal feature to form a strong global feature encoded via a Swin Transformer. The final segmentation results are produced via a UNet-like encoder-decoder architecture. Our model outperforms other approaches by a significant margin and improves the segmentation benchmarks on the VFSS2022 dataset, achieving a dice coefficient of 0.8986 and 0.8186 for the two datasets tested. Our studies also show the efficacy of the temporal feature blending scheme and cross-dataset transferability of learned capabilities. Code and models are fully available at https://github.com/SimonZeng7108/Video-SwinUNet.
Authors: Ramin Nakhli, Puria Azadi Moghadam, Haoyang Mi, Hossein Farahani, Alexander Baras, Blake Gilks, Ali Bashashati
Processing giga-pixel whole slide histopathology images (WSI) is a computationally expensive task. Multiple instance learning (MIL) has become the conventional approach to process WSIs, in which these images are split into smaller patches for further processing. However, MIL-based techniques ignore explicit information about the individual cells within a patch. In this paper, by defining the novel concept of shared-context processing, we designed a multi-modal Graph Transformer (AMIGO) that uses the celluar graph within the tissue to provide a single representation for a patient while taking advantage of the hierarchical structure of the tissue, enabling a dynamic focus between cell-level and tissue-level information. We benchmarked the performance of our model against multiple state-of-the-art methods in survival prediction and showed that ours can significantly outperform all of them including hierarchical Vision Transformer (ViT). More importantly, we show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data. Finally, in two different cancer datasets, we demonstrated that our model was able to stratify the patients into low-risk and high-risk groups while other state-of-the-art methods failed to achieve this goal. We also publish a large dataset of immunohistochemistry images (InUIT) containing 1,600 tissue microarray (TMA) cores from 188 patients along with their survival information, making it one of the largest publicly available datasets in this context.
Authors: Zikang Xu, Shang Zhao, Quan Quan, Qingsong Yao, S. Kevin Zhou
Deep learning is becoming increasingly ubiquitous in medical research and applications while involving sensitive information and even critical diagnosis decisions. Researchers observe a significant performance disparity among subgroups with different demographic attributes, which is called model unfairness, and put lots of effort into carefully designing elegant architectures to address unfairness, which poses heavy training burden, brings poor generalization, and reveals the trade-off between model performance and fairness. To tackle these issues, we propose FairAdaBN by making batch normalization adaptive to sensitive attribute. This simple but effective design can be adopted to several classification backbones that are originally unaware of fairness. Additionally, we derive a novel loss function that restrains statistical parity between subgroups on mini-batches, encouraging the model to converge with considerable fairness. In order to evaluate the trade-off between model performance and fairness, we propose a new metric, named Fairness-Accuracy Trade-off Efficiency (FATE), to compute normalized fairness improvement over accuracy drop. Experiments on two dermatological datasets show that our proposed method outperforms other methods on fairness criteria and FATE.
Authors: Shilong Zhang, Xinjiang Wang, Jiaqi Wang, Jiangmiao Pang, Chengqi Lyu, Wenwei Zhang, Ping Luo, Kai Chen
One-to-one label assignment in object detection has successfully obviated the need for non-maximum suppression (NMS) as postprocessing and makes the pipeline end-to-end. However, it triggers a new dilemma as the widely used sparse queries cannot guarantee a high recall, while dense queries inevitably bring more similar queries and encounter optimization difficulties. As both sparse and dense queries are problematic, then what are the expected queries in end-to-end object detection? This paper shows that the solution should be Dense Distinct Queries (DDQ). Concretely, we first lay dense queries like traditional detectors and then select distinct ones for one-to-one assignments. DDQ blends the advantages of traditional and recent end-to-end detectors and significantly improves the performance of various detectors including FCN, R-CNN, and DETRs. Most impressively, DDQ-DETR achieves 52.1 AP on MS-COCO dataset within 12 epochs using a ResNet-50 backbone, outperforming all existing detectors in the same setting. DDQ also shares the benefit of end-to-end detectors in crowded scenes and achieves 93.8 AP on CrowdHuman. We hope DDQ can inspire researchers to consider the complementarity between traditional methods and end-to-end detectors. The source code can be found at \url{https://github.com/jshilong/DDQ}.
Authors: Amandeep Kumar, Ankan kumar Bhunia, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Jorma Laaksonen, Fahad Shahbaz Khan
In this work, we propose a few-shot colorectal tissue image generation method for addressing the scarcity of histopathological training data for rare cancer tissues. Our few-shot generation method, named XM-GAN, takes one base and a pair of reference tissue images as input and generates high-quality yet diverse images. Within our XM-GAN, a novel controllable fusion block densely aggregates local regions of reference images based on their similarity to those in the base image, resulting in locally consistent features. To the best of our knowledge, we are the first to investigate few-shot generation in colorectal tissue images. We evaluate our few-shot colorectral tissue image generation by performing extensive qualitative, quantitative and subject specialist (pathologist) based evaluations. Specifically, in specialist-based evaluation, pathologists could differentiate between our XM-GAN generated tissue images and real images only 55% time. Moreover, we utilize these generated images as data augmentation to address the few-shot tissue image classification task, achieving a gain of 4.4% in terms of mean accuracy over the vanilla few-shot classifier. Code: \url{https://github.com/VIROBO-15/XM-GAN}
Authors: Kun Han, Yifeng Xiong, Chenyu You, Pooya Khosravi, Shanlin Sun, Xiangyi Yan, James Duncan, Xiaohui Xie
Acquiring and annotating sufficient labeled data is crucial in developing accurate and robust learning-based models, but obtaining such data can be challenging in many medical image segmentation tasks. One promising solution is to synthesize realistic data with ground-truth mask annotations. However, no prior studies have explored generating complete 3D volumetric images with masks. In this paper, we present MedGen3D, a deep generative framework that can generate paired 3D medical images and masks. First, we represent the 3D medical data as 2D sequences and propose the Multi-Condition Diffusion Probabilistic Model (MC-DPM) to generate multi-label mask sequences adhering to anatomical geometry. Then, we use an image sequence generator and semantic diffusion refiner conditioned on the generated mask sequences to produce realistic 3D medical images that align with the generated masks. Our proposed framework guarantees accurate alignment between synthetic images and segmentation maps. Experiments on 3D thoracic CT and brain MRI datasets show that our synthetic data is both diverse and faithful to the original data, and demonstrate the benefits for downstream segmentation tasks. We anticipate that MedGen3D's ability to synthesize paired 3D medical images and masks will prove valuable in training deep learning models for medical imaging tasks.
Authors: Huanhuan Li, Xuechao Zou, Yu-an Zhang, Jiangcai Zhaba, Guomei Li, Lamao Yongga
The Three-River-Source region is a highly significant natural reserve in China that harbors a plethora of untamed botanical resources. To meet the practical requirements of botanical research and intelligent plant management, we construct a large-scale dataset for Plant detection in the Three-River-Source region (PTRS). This dataset comprises 6965 high-resolution images of 2160*3840 pixels, captured by diverse sensors and platforms, and featuring objects of varying shapes and sizes. Subsequently, a team of botanical image interpretation experts annotated these images with 21 commonly occurring object categories. The fully annotated PTRS images contain 122, 300 instances of plant leaves, each labeled by a horizontal rectangle. The PTRS presents us with challenges such as dense occlusion, varying leaf resolutions, and high feature similarity among plants, prompting us to develop a novel object detection network named PlantDet. This network employs a window-based efficient self-attention module (ST block) to generate robust feature representation at multiple scales, improving the detection efficiency for small and densely-occluded objects. Our experimental results validate the efficacy of our proposed plant detection benchmark, with a precision of 88.1%, a mean average precision (mAP) of 77.6%, and a higher recall compared to the baseline. Additionally, our method effectively overcomes the issue of missing small objects. We intend to share our data and code with interested parties to advance further research in this field.
Authors: Chen Zhao, Wei-Ling Cai, Zheng Yuan, Cheng-Wei Hu
Recently, unsupervised image-to-image translation methods based on contrastive learning have achieved state-of-the-art results in many tasks. However, in the previous works, the negatives are sampled from the input image itself, which inspires us to design a data augmentation method to improve the quality of the selected negatives. Moreover, the previous methods only preserve the content consistency via patch-wise contrastive learning in the embedding space, which ignores the domain consistency between the generated images and the real images of the target domain. In this paper, we propose a novel unsupervised image-to-image translation framework based on multi-cropping contrastive learning and domain consistency, called MCDUT. Specifically, we obtain the multi-cropping views via the center-cropping and the random-cropping with the aim of further generating the high-quality negative examples. To constrain the embeddings in the deep feature space, we formulate a new domain consistency loss, which encourages the generated images to be close to the real images in the embedding space of the same domain. Furthermore, we present a dual coordinate attention network by embedding positional information into the channel, which called DCA. We employ the DCA network in the design of generator, which makes the generator capture the horizontal and vertical global information of dependency. In many image-to-image translation tasks, our method achieves state-of-the-art results, and the advantages of our method have been proven through extensive comparison experiments and ablation research.
Authors: Lucas Prado Osco, Eduardo Lopes de Lemos, Wesley Nunes Gonçalves, Ana Paula Marques Ramos, José Marcato Junior
Recent advancements in Natural Language Processing (NLP), particularly in Large Language Models (LLMs), associated with deep learning-based computer vision techniques, have shown substantial potential for automating a variety of tasks. One notable model is Visual ChatGPT, which combines ChatGPT's LLM capabilities with visual computation to enable effective image analysis. The model's ability to process images based on textual inputs can revolutionize diverse fields. However, its application in the remote sensing domain remains unexplored. This is the first paper to examine the potential of Visual ChatGPT, a cutting-edge LLM founded on the GPT architecture, to tackle the aspects of image processing related to the remote sensing domain. Among its current capabilities, Visual ChatGPT can generate textual descriptions of images, perform canny edge and straight line detection, and conduct image segmentation. These offer valuable insights into image content and facilitate the interpretation and extraction of information. By exploring the applicability of these techniques within publicly available datasets of satellite images, we demonstrate the current model's limitations in dealing with remote sensing images, highlighting its challenges and future prospects. Although still in early development, we believe that the combination of LLMs and visual models holds a significant potential to transform remote sensing image processing, creating accessible and practical application opportunities in the field.
Authors: C. S. Sonali, Chinmayi B S, Ahana Balasubramanian
Audio classification is vital in areas such as speech and music recognition. Feature extraction from the audio signal, such as Mel-Spectrograms and MFCCs, is a critical step in audio classification. These features are transformed into spectrograms for classification. Researchers have explored various techniques, including traditional machine and deep learning methods to classify spectrograms, but these can be computationally expensive. To simplify this process, a more straightforward approach inspired by sequence classification in NLP can be used. This paper proposes a Transformer-encoder-based model for audio classification using MFCCs. The model was benchmarked against the ESC-50, Speech Commands v0.02 and UrbanSound8k datasets and has shown strong performance, with the highest accuracy of 95.2% obtained upon training the model on the UrbanSound8k dataset. The model consisted of a mere 127,544 total parameters, making it light-weight yet highly efficient at the audio classification task.
Authors: Elia Bonetto, Aamir Ahmad
Nowadays, there is a wide availability of datasets that enable the training of common object detectors or human detectors. These come in the form of labelled real-world images and require either a significant amount of human effort, with a high probability of errors such as missing labels, or very constrained scenarios, e.g. VICON systems. On the other hand, uncommon scenarios, like aerial views, animals, like wild zebras, or difficult-to-obtain information, such as human shapes, are hardly available. To overcome this, synthetic data generation with realistic rendering technologies has recently gained traction and advanced research areas such as target tracking and human pose estimation. However, subjects such as wild animals are still usually not well represented in such datasets. In this work, we first show that a pre-trained YOLO detector can not identify zebras in real images recorded from aerial viewpoints. To solve this, we present an approach for training an animal detector using only synthetic data. We start by generating a novel synthetic zebra dataset using GRADE, a state-of-the-art framework for data generation. The dataset includes RGB, depth, skeletal joint locations, pose, shape and instance segmentations for each subject. We use this to train a YOLO detector from scratch. Through extensive evaluations of our model with real-world data from i) limited datasets available on the internet and ii) a new one collected and manually labelled by us, we show that we can detect zebras by using only synthetic data during training. The code, results, trained models, and both the generated and training data are provided as open-source at https://eliabntt.github.io/grade-rr.
Authors: Juanjuan Weng, Zhiming Luo, Dazhen Lin, Shaozi Li, Zhun Zhong
Recent research has shown that Deep Neural Networks (DNNs) are highly vulnerable to adversarial samples, which are highly transferable and can be used to attack other unknown black-box models. To improve the transferability of adversarial samples, several feature-based adversarial attack methods have been proposed to disrupt neuron activation in the middle layers. However, current state-of-the-art feature-based attack methods typically require additional computation costs for estimating the importance of neurons. To address this challenge, we propose a Singular Value Decomposition (SVD)-based feature-level attack method. Our approach is inspired by the discovery that eigenvectors associated with the larger singular values decomposed from the middle layer features exhibit superior generalization and attention properties. Specifically, we conduct the attack by retaining the decomposed Top-1 singular value-associated feature for computing the output logits, which are then combined with the original logits to optimize adversarial examples. Our extensive experimental results verify the effectiveness of our proposed method, which can be easily integrated into various baselines to significantly enhance the transferability of adversarial samples for disturbing normally trained CNNs and advanced defense strategies. The source code of this study is available at https://github.com/WJJLL/SVD-SSA
Authors: Songning Lai, Xifeng Hu, Haoxuan Xu, Zhaoxia Ren, Zhi Liu
Multimodal sentiment analysis has become an important research area in the field of artificial intelligence. With the latest advances in deep learning, this technology has reached new heights. It has great potential for both application and research, making it a popular research topic. This review provides an overview of the definition, background, and development of multimodal sentiment analysis. It also covers recent datasets and advanced models, emphasizing the challenges and future prospects of this technology. Finally, it looks ahead to future research directions. It should be noted that this review provides constructive suggestions for promising research directions and building better performing multimodal sentiment analysis models, which can help researchers in this field.
Authors: Jinxiang Liu, Yu Wang, Chen Ju, Chaofan Ma, Ya Zhang, Weidi Xie
The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks. To tackle the task, it involves a comprehensive consideration of both the data and model aspects. In this paper, first, we initiate a novel pipeline for generating artificial data for the AVS task without human annotating. We leverage existing image segmentation and audio datasets to match the image-mask pairs with its corresponding audio samples with the linkage of category labels, that allows us to effortlessly compose (image, audio, mask) triplets for training AVS models. The pipeline is annotation-free and scalable to cover a large number of categories. Additionally, we introduce a lightweight approach SAMA-AVS to adapt the pre-trained segment anything model~(SAM) to the AVS task. By introducing only a small number of trainable parameters with adapters, the proposed model can effectively achieve adequate audio-visual fusion and interaction in the encoding stage with vast majority of parameters fixed. We conduct extensive experiments, and the results show our proposed model remarkably surpasses other competing methods. Moreover, by using the proposed model pretrained with our synthetic data, the performance on real AVSBench data is further improved, achieving 83.17 mIoU on S4 subset and 66.95 mIoU on MS3 set.
Authors: Tomoki Inoue, Koyo Kubota, Tsubasa Ikami, Yasuhiro Egami, Hiroki Nagai, Takahiro Kashikawa, Koichi Kimura, Yu Matsuda
Time-series clustering serves as a powerful data mining technique for time-series data in the absence of prior knowledge about clusters. A large amount of time-series data with large size has been acquired and used in various research fields. Hence, clustering method with low computational cost is required. Given that a quantum-inspired computing technology, such as a simulated annealing machine, surpasses conventional computers in terms of fast and accurately solving combinatorial optimization problems, it holds promise for accomplishing clustering tasks that are challenging to achieve using existing methods. This study proposes a novel time-series clustering method that leverages an annealing machine. The proposed method facilitates an even classification of time-series data into clusters close to each other while maintaining robustness against outliers. Moreover, its applicability extends to time-series images. We compared the proposed method with a standard existing method for clustering an online distributed dataset. In the existing method, the distances between each data are calculated based on the Euclidean distance metric, and the clustering is performed using the k-means++ method. We found that both methods yielded comparable results. Furthermore, the proposed method was applied to a flow measurement image dataset containing noticeable noise with a signal-to-noise ratio of approximately 1. Despite a small signal variation of approximately 2%, the proposed method effectively classified the data without any overlap among the clusters. In contrast, the clustering results by the standard existing method and the conditional image sampling (CIS) method, a specialized technique for flow measurement data, displayed overlapping clusters. Consequently, the proposed method provides better results than the other two methods, demonstrating its potential as a superior clustering method.
Authors: Hui Li, Yongbiao Xiao, Chunyang Cheng, Zhongwei Shen, Xiaoning Song
Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are suffering from the issues of texture loss and edge information deficiency, which result in suboptimal fusion results. Meanwhile, the straight-forward up-sampling operator can not well preserve the source information from multi-scale features. To address these issues, a novel fusion network based on the decomposition pooling (de-pooling) manner is proposed, termed as DePF. Specifically, a de-pooling based encoder is designed to extract multi-scale image and detail features of source images at the same time. In addition, the spatial attention model is used to aggregate these salient features. After that, the fused features will be reconstructed by the decoder, in which the up-sampling operator is replaced by the de-pooling reversed operation. Different from the common max-pooling technique, image features after the de-pooling layer can retain abundant details information, which is benefit to the fusion process. In this case, rich texture information and multi-scale information are maintained during the reconstruction phase. The experimental results demonstrate that the proposed method exhibits superior fusion performance over the state-of-the-arts on multiple image fusion benchmarks.
Authors: Yuxin Wen, John Kirchenbauer, Jonas Geiping, Tom Goldstein
Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs. Unlike existing methods that perform post-hoc modifications to images after sampling, Tree-Ring Watermarking subtly influences the entire sampling process, resulting in a model fingerprint that is invisible to humans. The watermark embeds a pattern into the initial noise vector used for sampling. These patterns are structured in Fourier space so that they are invariant to convolutions, crops, dilations, flips, and rotations. After image generation, the watermark signal is detected by inverting the diffusion process to retrieve the noise vector, which is then checked for the embedded signal. We demonstrate that this technique can be easily applied to arbitrary diffusion models, including text-conditioned Stable Diffusion, as a plug-in with negligible loss in FID. Our watermark is semantically hidden in the image space and is far more robust than watermarking alternatives that are currently deployed. Code is available at https://github.com/YuxinWenRick/tree-ring-watermark.
Authors: Debesh Jha, Nikhil Kumar Tomar, Debayan Bhattacharya, Ulas Bagci
Out-of-distribution (OOD) generalization is a critical challenge in deep learning. It is specifically important when the test samples are drawn from a different distribution than the training data. We develop a novel real-time deep learning based architecture, TransRUPNet that is based on a Transformer and residual upsampling network for colorectal polyp segmentation to improve OOD generalization. The proposed architecture, TransRUPNet, is an encoder-decoder network that consists of three encoder blocks, three decoder blocks, and some additional upsampling blocks at the end of the network. With the image size of $256\times256$, the proposed method achieves an excellent real-time operation speed of \textbf{47.07} frames per second with an average mean dice coefficient score of 0.7786 and mean Intersection over Union of 0.7210 on the out-of-distribution polyp datasets. The results on the publicly available PolypGen dataset (OOD dataset in our case) suggest that TransRUPNet can give real-time feedback while retaining high accuracy for in-distribution dataset. Furthermore, we demonstrate the generalizability of the proposed method by showing that it significantly improves performance on OOD datasets compared to the existing methods.
Authors: Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau, Wieland Brendel, Been Kim
How do neural networks extract patterns from pixels? Feature visualizations attempt to answer this important question by visualizing highly activating patterns through optimization. Today, visualization methods form the foundation of our knowledge about the internal workings of neural networks, as a type of mechanistic interpretability. Here we ask: How reliable are feature visualizations? We start our investigation by developing network circuits that trick feature visualizations into showing arbitrary patterns that are completely disconnected from normal network behavior on natural input. We then provide evidence for a similar phenomenon occurring in standard, unmanipulated networks: feature visualizations are processed very differently from standard input, casting doubt on their ability to "explain" how neural networks process natural images. We underpin this empirical finding by theory proving that the set of functions that can be reliably understood by feature visualization is extremely small and does not include general black-box neural networks. Therefore, a promising way forward could be the development of networks that enforce certain structures in order to ensure more reliable feature visualizations.
Authors: Renjun Xu, Kaifan Yang, Ke Liu, Fengxiang He
Vision Transformer (ViT) has achieved remarkable performance in computer vision. However, positional encoding in ViT makes it substantially difficult to learn the intrinsic equivariance in data. Initial attempts have been made on designing equivariant ViT but are proved defective in some cases in this paper. To address this issue, we design a Group Equivariant Vision Transformer (GE-ViT) via a novel, effective positional encoding operator. We prove that GE-ViT meets all the theoretical requirements of an equivariant neural network. Comprehensive experiments are conducted on standard benchmark datasets, demonstrating that GE-ViT significantly outperforms non-equivariant self-attention networks. The code is available at https://github.com/ZJUCDSYangKaifan/GEVit.
Authors: Weizhen He, Shixiang Tang, Yiheng Deng, Qihao Chen, Qingsong Xie, Yizhou Wang, Lei Bai, Feng Zhu, Rui Zhao, Wanli Ouyang, Donglian Qi, Yunfeng Yan
Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which limits the applications in the real world. This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions.Our instruct-ReID is a more general ReID setting, where existing ReID tasks can be viewed as special cases by designing different instructions. We propose a large-scale OmniReID benchmark and an adaptive triplet loss as a baseline method to facilitate research in this new setting. Experimental results show that the baseline model trained on our OmniReID benchmark can improve +0.6%, +1.4%, 0.2% mAP on Market1501, CUHK03, MSMT17 for traditional ReID, +0.8%, +2.0%, +13.4% mAP on PRCC, VC-Clothes, LTCC for clothes-changing ReID, +11.7% mAP on COCAS+ real2 for clothestemplate based clothes-changing ReID when using only RGB images, +25.4% mAP on COCAS+ real2 for our newly defined language-instructed ReID. The dataset, model, and code will be available at https://github.com/hwz-zju/Instruct-ReID.
Authors: Lian Zhang, Zhengliang Liu, Lu Zhang, Zihao Wu, Xiaowei Yu, Jason Holmes, Hongying Feng, Haixing Dai, Xiang Li, Quanzheng Li, Dajiang Zhu, Tianming Liu, Wei Liu
In this study, we evaluate the performance of the Segment Anything Model (SAM) in clinical radiotherapy. Our results indicate that SAM's 'segment anything' mode can achieve clinically acceptable segmentation results in most organs-at-risk (OARs) with Dice scores higher than 0.7. SAM's 'box prompt' mode further improves the Dice scores by 0.1 to 0.5. Considering the size of the organ and the clarity of its boundary, SAM displays better performance for large organs with clear boundaries but performs worse for smaller organs with unclear boundaries. Given that SAM, a model pre-trained purely on natural images, can handle the delineation of OARs from medical images with clinically acceptable accuracy, these results highlight SAM's robust generalization capabilities with consistent accuracy in automatic segmentation for radiotherapy. In other words, SAM can achieve delineation of different OARs at different sites using a generic automatic segmentation model. SAM's generalization capabilities across different disease sites suggest that it is technically feasible to develop a generic model for automatic segmentation in radiotherapy.
Authors: Jianghui Wang, Yang Chen, Xingyu Xie, Cong Fang, Zhouchen Lin
Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy holds when pre-training a foundation model. However, the foundation model may not uniformly behave well for a series of related downstream tasks. This happens, for example, when conducting mask recovery regression where the recovery ability or the training instances diverge like pattern features are extracted dominantly on pre-training, but semantic features are also required on a downstream task. This paper considers pre-training a model that guarantees a uniformly good performance over the downstream tasks. We call this goal as $\textit{downstream-task robustness}$. Our method first separates the upstream task into several representative ones and applies a simple minimax loss for pre-training. We then design an efficient algorithm to solve the minimax loss and prove its convergence in the convex setting. In the experiments, we show both on large-scale natural language processing and computer vision datasets our method increases the metrics on worse-case downstream tasks. Additionally, some theoretical explanations for why our loss is beneficial are provided. Specifically, we show fewer samples are inherently required for the most challenging downstream task in some cases.
Authors: Hang Jung Ling, Olivier Bernard, Nicolas Ducros, Damien Garcia
Color Doppler echocardiography is a widely used non-invasive imaging modality that provides real-time information about the intracardiac blood flow. In an apical long-axis view of the left ventricle, color Doppler is subject to phase wrapping, or aliasing, especially during cardiac filling and ejection. When setting up quantitative methods based on color Doppler, it is necessary to correct this wrapping artifact. We developed an unfolded primal-dual network to unwrap (dealias) color Doppler echocardiographic images and compared its effectiveness against two state-of-the-art segmentation approaches based on nnU-Net and transformer models. We trained and evaluated the performance of each method on an in-house dataset and found that the nnU-Net-based method provided the best dealiased results, followed by the primal-dual approach and the transformer-based technique. Noteworthy, the primal-dual network, which had significantly fewer trainable parameters, performed competitively with respect to the other two methods, demonstrating the high potential of deep unfolding methods. Our results suggest that deep learning-based methods can effectively remove aliasing artifacts in color Doppler echocardiographic images, outperforming DeAN, a state-of-the-art semi-automatic technique. Overall, our results show that deep learning-based methods have the potential to effectively preprocess color Doppler images for downstream quantitative analysis.
Authors: Alexander Bigalke, Mattias P. Heinrich
Point cloud-based medical registration promises increased computational efficiency, robustness to intensity shifts, and anonymity preservation but is limited by the inefficacy of unsupervised learning with similarity metrics. Supervised training on synthetic deformations is an alternative but, in turn, suffers from the domain gap to the real domain. In this work, we aim to tackle this gap through domain adaptation. Self-training with the Mean Teacher is an established approach to this problem but is impaired by the inherent noise of the pseudo labels from the teacher. As a remedy, we present a denoised teacher-student paradigm for point cloud registration, comprising two complementary denoising strategies. First, we propose to filter pseudo labels based on the Chamfer distances of teacher and student registrations, thus preventing detrimental supervision by the teacher. Second, we make the teacher dynamically synthesize novel training pairs with noise-free labels by warping its moving inputs with the predicted deformations. Evaluation is performed for inhale-to-exhale registration of lung vessel trees on the public PVT dataset under two domain shifts. Our method surpasses the baseline Mean Teacher by 13.5/62.8%, consistently outperforms diverse competitors, and sets a new state-of-the-art accuracy (TRE=2.31mm). Code is available at https://github.com/multimodallearning/denoised_mt_pcd_reg.
Authors: Louis Mahon, Thomas Lukasiewicz
Existing image complexity metrics cannot distinguish meaningful content from noise. This means that white noise images, which contain no meaningful information, are judged as highly complex. We present a new image complexity metric through hierarchical clustering of patches. We use the minimum description length principle to determine the number of clusters and designate certain points as outliers and, hence, correctly assign white noise a low score. The presented method has similarities to theoretical ideas for measuring meaningful complexity. We conduct experiments on seven different sets of images, which show that our method assigns the most accurate scores to all images considered. Additionally, comparing the different levels of the hierarchy of clusters can reveal how complexity manifests at different scales, from local detail to global structure. We then present ablation studies showing the contribution of the components of our method, and that it continues to assign reasonable scores when the inputs are modified in certain ways, including the addition of Gaussian noise and the lowering of the resolution.
Authors: Nikolaos Stathoulopoulos, Anton Koval, George Nikolakopoulos
Change detection and irregular object extraction in 3D point clouds is a challenging task that is of high importance not only for autonomous navigation but also for updating existing digital twin models of various industrial environments. This article proposes an innovative approach for change detection in 3D point clouds using deep learned place recognition descriptors and irregular object extraction based on voxel-to-point comparison. The proposed method first aligns the bi-temporal point clouds using a map-merging algorithm in order to establish a common coordinate frame. Then, it utilizes deep learning techniques to extract robust and discriminative features from the 3D point cloud scans, which are used to detect changes between consecutive point cloud frames and therefore find the changed areas. Finally, the altered areas are sampled and compared between the two time instances to extract any obstructions that caused the area to change. The proposed method was successfully evaluated in real-world field experiments, where it was able to detect different types of changes in 3D point clouds, such as object or muck-pile addition and displacement, showcasing the effectiveness of the approach. The results of this study demonstrate important implications for various applications, including safety and security monitoring in construction sites, mapping and exploration and suggests potential future research directions in this field.
Authors: Xue-Feng Zhu, Tianyang Xu, Jian Zhao, Jia-Wei Liu, Kai Wang, Gang Wang, Jianan Li, Qiang Wang, Lei Jin, Zheng Zhu, Junliang Xing, Xiao-Jun Wu
Unmanned Aerial Vehicles (UAVs) have been widely used in many areas, including transportation, surveillance, and military. However, their potential for safety and privacy violations is an increasing issue and highly limits their broader applications, underscoring the critical importance of UAV perception and defense (anti-UAV). Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i.e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance). In this paper, we first formulate a new and practical anti-UAV problem featuring the UAVs perception in complex scenes without prior UAVs information. To benchmark such a challenging task, we propose the largest UAV dataset dubbed AntiUAV600 and a new evaluation metric. The AntiUAV600 comprises 600 video sequences of challenging scenes with random, fast, and small-scale UAVs, with over 723K thermal infrared frames densely annotated with bounding boxes. Finally, we develop a novel anti-UAV approach via an evidential collaboration of global UAVs detection and local UAVs tracking, which effectively tackles the proposed problem and can serve as a strong baseline for future research. Extensive experiments show our method outperforms SOTA approaches and validate the ability of AntiUAV600 to enhance UAV perception performance due to its large scale and complexity. Our dataset, pretrained models, and source codes will be released publically.
Authors: Enzhe Zhao, Zhichang Guo, Yao Li, Dazhi Zhang
Hyperspectral images (HSI) captured from earth observing satellites and aircraft is becoming increasingly important for applications in agriculture, environmental monitoring, mining, etc. Due to the limited available hyperspectral datasets, the pixel-wise random sampling is the most commonly used training-test dataset partition approach, which has significant overlap between samples in training and test datasets. Furthermore, our experimental observations indicates that regions with larger overlap often exhibit higher classification accuracy. Consequently, the pixel-wise random sampling approach poses a risk of data leakage. Thus, we propose a block-wise sampling method to minimize the potential for data leakage. Our experimental findings also confirm the presence of data leakage in models such as 2DCNN. Further, We propose a spectral-spatial axial aggregation transformer model, namely SaaFormer, to address the challenges associated with hyperspectral image classifier that considers HSI as long sequential three-dimensional images. The model comprises two primary components: axial aggregation attention and multi-level spectral-spatial extraction. The axial aggregation attention mechanism effectively exploits the continuity and correlation among spectral bands at each pixel position in hyperspectral images, while aggregating spatial dimension features. This enables SaaFormer to maintain high precision even under block-wise sampling. The multi-level spectral-spatial extraction structure is designed to capture the sensitivity of different material components to specific spectral bands, allowing the model to focus on a broader range of spectral details. The results on six publicly available datasets demonstrate that our model exhibits comparable performance when using random sampling, while significantly outperforming other methods when employing block-wise sampling partition.
Authors: Fangqiang Ding, Zhen Luo, Peijun Zhao, Chris Xiaoxuan Lu
Approaching the era of ubiquitous computing, human motion sensing plays a crucial role in smart systems for decision making, user interaction, and personalized services. Extensive research has been conducted on human tracking, pose estimation, gesture recognition, and activity recognition, which are predominantly based on cameras in traditional methods. However, the intrusive nature of cameras limits their use in smart home applications. To address this, mmWave radars have gained popularity due to their privacy-friendly features. In this work, we propose \textit{milliFlow}, a novel deep learning method for scene flow estimation as a complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting downstream human motion sensing tasks. Experimental results demonstrate the superior performance of our method with an average 3D endpoint error of 4.6cm, significantly surpassing the competing approaches. Furthermore, by incorporating scene flow information, we achieve remarkable improvements in human activity recognition, human parsing, and human body part tracking. To foster further research in this area, we provide our codebase and dataset for open access.
Authors: Jina Kim, Zekun Li, Yijun Lin, Min Namgung, Leeje Jang, Yao-Yi Chiang
Scanned historical maps in libraries and archives are valuable repositories of geographic data that often do not exist elsewhere. Despite the potential of machine learning tools like the Google Vision APIs for automatically transcribing text from these maps into machine-readable formats, they do not work well with large-sized images (e.g., high-resolution scanned documents), cannot infer the relation between the recognized text and other datasets, and are challenging to integrate with post-processing tools. This paper introduces the mapKurator system, an end-to-end system integrating machine learning models with a comprehensive data processing pipeline. mapKurator empowers automated extraction, post-processing, and linkage of text labels from large numbers of large-dimension historical map scans. The output data, comprising bounding polygons and recognized text, is in the standard GeoJSON format, making it easily modifiable within Geographic Information Systems (GIS). The proposed system allows users to quickly generate valuable data from large numbers of historical maps for in-depth analysis of the map content and, in turn, encourages map findability, accessibility, interoperability, and reusability (FAIR principles). We deployed the mapKurator system and enabled the processing of over 60,000 maps and over 100 million text/place names in the David Rumsey Historical Map collection. We also demonstrated a seamless integration of mapKurator with a collaborative web platform to enable accessing automated approaches for extracting and linking text labels from historical map scans and collective work to improve the results.
Authors: Huiming Sun, Lan Fu, Jinlong Li, Qing Guo, Zibo Meng, Tianyun Zhang, Yuewei Lin, Hongkai Yu
Detecting the salient objects in a remote sensing image has wide applications for the interdisciplinary research. Many existing deep learning methods have been proposed for Salient Object Detection (SOD) in remote sensing images and get remarkable results. However, the recent adversarial attack examples, generated by changing a few pixel values on the original remote sensing image, could result in a collapse for the well-trained deep learning based SOD model. Different with existing methods adding perturbation to original images, we propose to jointly tune adversarial exposure and additive perturbation for attack and constrain image close to cloudy image as Adversarial Cloud. Cloud is natural and common in remote sensing images, however, camouflaging cloud based adversarial attack and defense for remote sensing images are not well studied before. Furthermore, we design DefenseNet as a learn-able pre-processing to the adversarial cloudy images so as to preserve the performance of the deep learning based remote sensing SOD model, without tuning the already deployed deep SOD model. By considering both regular and generalized adversarial examples, the proposed DefenseNet can defend the proposed Adversarial Cloud in white-box setting and other attack methods in black-box setting. Experimental results on a synthesized benchmark from the public remote sensing SOD dataset (EORSSD) show the promising defense against adversarial cloud attacks.
Authors: Yi Guo, Che Sun, Yunde Jia, Yuwei Wu
Neural 3D scene reconstruction methods have achieved impressive performance when reconstructing complex geometry and low-textured regions in indoor scenes. However, these methods heavily rely on 3D data which is costly and time-consuming to obtain in real world. In this paper, we propose a novel neural reconstruction method that reconstructs scenes using sparse depth under the plane constraints without 3D supervision. We introduce a signed distance function field, a color field, and a probability field to represent a scene. We optimize these fields to reconstruct the scene by using differentiable ray marching with accessible 2D images as supervision. We improve the reconstruction quality of complex geometry scene regions with sparse depth obtained by using the geometric constraints. The geometric constraints project 3D points on the surface to similar-looking regions with similar features in different 2D images. We impose the plane constraints to make large planes parallel or vertical to the indoor floor. Both two constraints help reconstruct accurate and smooth geometry structures of the scene. Without 3D supervision, our method achieves competitive performance compared with existing methods that use 3D supervision on the ScanNet dataset.
Authors: Ammar Chouchane, Abdelmalik Ouamane, Yassine Himeur, Wathiq Mansoor, Shadi Atalla, Afaf Benzaibak, Chahrazed Boudellal
Person re-identification (PRe-ID) is a crucial task in security, surveillance, and retail analysis, which involves identifying an individual across multiple cameras and views. However, it is a challenging task due to changes in illumination, background, and viewpoint. Efficient feature extraction and metric learning algorithms are essential for a successful PRe-ID system. This paper proposes a novel approach for PRe-ID, which combines a Convolutional Neural Network (CNN) based feature extraction method with Cross-view Quadratic Discriminant Analysis (XQDA) for metric learning. Additionally, a matching algorithm that employs Mahalanobis distance and a score normalization process to address inconsistencies between camera scores is implemented. The proposed approach is tested on four challenging datasets, including VIPeR, GRID, CUHK01, and PRID450S, and promising results are obtained. For example, without normalization, the rank-20 rate accuracies of the GRID, CUHK01, VIPeR and PRID450S datasets were 61.92%, 83.90%, 92.03%, 96.22%; however, after score normalization, they have increased to 64.64%, 89.30%, 92.78%, and 98.76%, respectively. Accordingly, the promising results on four challenging datasets indicate the effectiveness of the proposed approach.
Authors: Zhongjin Luo, Dong Du, Heming Zhu, Yizhou Yu, Hongbo Fu, Xiaoguang Han
Modeling 3D avatars benefits various application scenarios such as AR/VR, gaming, and filming. Character faces contribute significant diversity and vividity as a vital component of avatars. However, building 3D character face models usually requires a heavy workload with commercial tools, even for experienced artists. Various existing sketch-based tools fail to support amateurs in modeling diverse facial shapes and rich geometric details. In this paper, we present SketchMetaFace - a sketching system targeting amateur users to model high-fidelity 3D faces in minutes. We carefully design both the user interface and the underlying algorithm. First, curvature-aware strokes are adopted to better support the controllability of carving facial details. Second, considering the key problem of mapping a 2D sketch map to a 3D model, we develop a novel learning-based method termed "Implicit and Depth Guided Mesh Modeling" (IDGMM). It fuses the advantages of mesh, implicit, and depth representations to achieve high-quality results with high efficiency. In addition, to further support usability, we present a coarse-to-fine 2D sketching interface design and a data-driven stroke suggestion tool. User studies demonstrate the superiority of our system over existing modeling tools in terms of the ease to use and visual quality of results. Experimental analyses also show that IDGMM reaches a better trade-off between accuracy and efficiency. SketchMetaFace is available at https://zhongjinluo.github.io/SketchMetaFace/.
Authors: Shengyi Gao, Zhe Chen, Guo Chen, Wenhai Wang, Tong Lu
The combination of audio and vision has long been a topic of interest in the multi-modal community. Recently, a new audio-visual segmentation (AVS) task has been introduced, aiming to locate and segment the sounding objects in a given video. This task demands audio-driven pixel-level scene understanding for the first time, posing significant challenges. In this paper, we propose AVSegFormer, a novel framework for AVS tasks that leverages the transformer architecture. Specifically, we introduce audio queries and learnable queries into the transformer decoder, enabling the network to selectively attend to interested visual features. Besides, we present an audio-visual mixer, which can dynamically adjust visual features by amplifying relevant and suppressing irrelevant spatial channels. Additionally, we devise an intermediate mask loss to enhance the supervision of the decoder, encouraging the network to produce more accurate intermediate predictions. Extensive experiments demonstrate that AVSegFormer achieves state-of-the-art results on the AVS benchmark. The code is available at https://github.com/vvvb-github/AVSegFormer.
Authors: Chuer Pan, Brian Okorn, Harry Zhang, Ben Eisner, David Held
How do we imbue robots with the ability to efficiently manipulate unseen objects and transfer relevant skills based on demonstrations? End-to-end learning methods often fail to generalize to novel objects or unseen configurations. Instead, we focus on the task-specific pose relationship between relevant parts of interacting objects. We conjecture that this relationship is a generalizable notion of a manipulation task that can transfer to new objects in the same category; examples include the relationship between the pose of a pan relative to an oven or the pose of a mug relative to a mug rack. We call this task-specific pose relationship "cross-pose" and provide a mathematical definition of this concept. We propose a vision-based system that learns to estimate the cross-pose between two objects for a given manipulation task using learned cross-object correspondences. The estimated cross-pose is then used to guide a downstream motion planner to manipulate the objects into the desired pose relationship (placing a pan into the oven or the mug onto the mug rack). We demonstrate our method's capability to generalize to unseen objects, in some cases after training on only 10 demonstrations in the real world. Results show that our system achieves state-of-the-art performance in both simulated and real-world experiments across a number of tasks. Supplementary information and videos can be found at https://sites.google.com/view/tax-pose/home.
Authors: Kevin Kasa, Graham W. Taylor
Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to degrade under distribution shift and long-tailed class distributions, which are often present in real world applications. Here, we characterize the performance of several post-hoc and training-based conformal prediction methods under these settings, providing the first empirical evaluation on large-scale datasets and models. We show that across numerous conformal methods and neural network families, performance greatly degrades under distribution shifts violating safety guarantees. Similarly, we show that in long-tailed settings the guarantees are frequently violated on many classes. Understanding the limitations of these methods is necessary for deployment in real world and safety-critical applications.