Authors: Jingyao Wang, Luntian Mou, Changwen Zheng, Wen Gao
Handwriting authentication is a valuable tool used in various fields, such as fraud prevention and cultural heritage protection. However, it remains a challenging task due to the complex features, severe damage, and lack of supervision. In this paper, we propose a novel Contrastive Self-Supervised Learning framework for Robust Handwriting Authentication (CSSL-RHA) to address these issues. It can dynamically learn complex yet important features and accurately predict writer identities. Specifically, to remove the negative effects of imperfections and redundancy, we design an information-theoretic filter for pre-processing and propose a novel adaptive matching scheme to represent images as patches of local regions dominated by more important features. Through online optimization at inference time, the most informative patch embeddings are identified as the "most important" elements. Furthermore, we employ contrastive self-supervised training with a momentum-based paradigm to learn more general statistical structures of handwritten data without supervision. We conduct extensive experiments on five benchmark datasets and our manually annotated dataset EN-HA, which demonstrate the superiority of our CSSL-RHA compared to baselines. Additionally, we show that our proposed model can still effectively achieve authentication even under abnormal circumstances, such as data falsification and corruption.
Authors: Xingxuan Zhang, Renzhe Xu, Han Yu, Yancheng Dong, Pengfei Tian, Peng Cu
Domain generalization (DG) seeks to learn robust models that generalize well under unknown distribution shifts. As a critical aspect of DG, optimizer selection has not been explored in depth. Currently, most DG methods follow the widely used benchmark, DomainBed, and utilize Adam as the default optimizer for all datasets. However, we reveal that Adam is not necessarily the optimal choice for the majority of current DG methods and datasets. Based on the perspective of loss landscape flatness, we propose a novel approach, Flatness-Aware Minimization for Domain Generalization (FAD), which can efficiently optimize both zeroth-order and first-order flatness simultaneously for DG. We provide theoretical analyses of the FAD's out-of-distribution (OOD) generalization error and convergence. Our experimental results demonstrate the superiority of FAD on various DG datasets. Additionally, we confirm that FAD is capable of discovering flatter optima in comparison to other zeroth-order and first-order flatness-aware optimization methods.
Authors: Rita Pucci, Vincent J. Kalkman, Dan Stowell
Fine-grained classification is challenging due to the difficulty of finding discriminatory features. This problem is exacerbated when applied to identifying species within the same taxonomical class. This is because species are often sharing morphological characteristics that make them difficult to differentiate. We consider the taxonomical class of Insecta. The identification of insects is essential in biodiversity monitoring as they are one of the inhabitants at the base of many ecosystems. Citizen science is doing brilliant work of collecting images of insects in the wild giving the possibility to experts to create improved distribution maps in all countries. We have billions of images that need to be automatically classified and deep neural network algorithms are one of the main techniques explored for fine-grained tasks. At the SOTA, the field of deep learning algorithms is extremely fruitful, so how to identify the algorithm to use? We focus on Odonata and Coleoptera orders, and we propose an initial comparative study to analyse the two best-known layer structures for computer vision: transformer and convolutional layers. We compare the performance of T2TViT, a fully transformer-base, EfficientNet, a fully convolutional-base, and ViTAE, a hybrid. We analyse the performance of the three models in identical conditions evaluating the performance per species, per morph together with sex, the inference time, and the overall performance with unbalanced datasets of images from smartphones. Although we observe high performances with all three families of models, our analysis shows that the hybrid model outperforms the fully convolutional-base and fully transformer-base models on accuracy performance and the fully transformer-base model outperforms the others on inference speed and, these prove the transformer to be robust to the shortage of samples and to be faster at inference time.
Authors: Suttisak Wizadwongsa, Worameth Chinchuthakun, Pramook Khungurn, Amit Raj, Supasorn Suwajanakorn
Despite the remarkable success of diffusion models in image generation, slow sampling remains a persistent issue. To accelerate the sampling process, prior studies have reformulated diffusion sampling as an ODE/SDE and introduced higher-order numerical methods. However, these methods often produce divergence artifacts, especially with a low number of sampling steps, which limits the achievable acceleration. In this paper, we investigate the potential causes of these artifacts and suggest that the small stability regions of these methods could be the principal cause. To address this issue, we propose two novel techniques. The first technique involves the incorporation of Heavy Ball (HB) momentum, a well-known technique for improving optimization, into existing diffusion numerical methods to expand their stability regions. We also prove that the resulting methods have first-order convergence. The second technique, called Generalized Heavy Ball (GHVB), constructs a new high-order method that offers a variable trade-off between accuracy and artifact suppression. Experimental results show that our techniques are highly effective in reducing artifacts and improving image quality, surpassing state-of-the-art diffusion solvers on both pixel-based and latent-based diffusion models for low-step sampling. Our research provides novel insights into the design of numerical methods for future diffusion work.
Authors: Xueshen Li, Zhenxing Dong, Hongshan Liu, Jennifer J. Kang-Mieler, Yuye Ling, Yu Gan
Optical coherence tomography (OCT) has stimulated a wide range of medical image-based diagnosis and treatment in fields such as cardiology and ophthalmology. Such applications can be further facilitated by deep learning-based super-resolution technology, which improves the capability of resolving morphological structures. However, existing deep learning-based method only focuses on spatial distribution and disregard frequency fidelity in image reconstruction, leading to a frequency bias. To overcome this limitation, we propose a frequency-aware super-resolution framework that integrates three critical frequency-based modules (i.e., frequency transformation, frequency skip connection, and frequency alignment) and frequency-based loss function into a conditional generative adversarial network (cGAN). We conducted a large-scale quantitative study from an existing coronary OCT dataset to demonstrate the superiority of our proposed framework over existing deep learning frameworks. In addition, we confirmed the generalizability of our framework by applying it to fish corneal images and rat retinal images, demonstrating its capability to super-resolve morphological details in eye imaging.
Authors: Chintan Trivedi, Konstantinos Makantasis, Antonios Liapis, Georgios N. Yannakakis
On-screen game footage contains rich contextual information that players process when playing and experiencing a game. Learning pixel representations of games can benefit artificial intelligence across several downstream tasks including game-playing agents, procedural content generation, and player modelling. The generalizability of these methods, however, remains a challenge, as learned representations should ideally be shared across games with similar game mechanics. This could allow, for instance, game-playing agents trained on one game to perform well in similar games with no re-training. This paper explores how generalizable pre-trained computer vision encoders can be for such tasks, by decomposing the latent space into content embeddings and style embeddings. The goal is to minimize the domain gap between games of the same genre when it comes to game content critical for downstream tasks, and ignore differences in graphical style. We employ a pre-trained Vision Transformer encoder and a decomposition technique based on game genres to obtain separate content and style embeddings. Our findings show that the decomposed embeddings achieve style invariance across multiple games while still maintaining strong content extraction capabilities. We argue that the proposed decomposition of content and style offers better generalization capacities across game environments independently of the downstream task.
Authors: Zeyu Jiang, João P. C. Bertoldo, Etienne Decencière
Anomaly detection (AD) in images is a fundamental computer vision problem by deep learning neural network to identify images deviating significantly from normality. The deep features extracted from pretrained models have been proved to be essential for AD based on multivariate Gaussian distribution analysis. However, since models are usually pretrained on a large dataset for classification tasks such as ImageNet, they might produce lots of redundant features for AD, which increases computational cost and degrades the performance. We aim to do the dimension reduction of Negated Principal Component Analysis (NPCA) for these features. So we proposed some heuristic to choose hyperparameter of NPCA algorithm for getting as fewer components of features as possible while ensuring a good performance.
Authors: Xin Li, Sima Behpour, Thang Doan, Wenbin He, Liang Gou, Liu Ren
In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited annotation budget. Previous approaches to data pre-selection relied solely on visual features extracted from foundation models, such as CLIP and BLIP-2, but largely ignored the powerfulness of text features. In this work, we argue that, with proper design, the joint feature space of both vision and text can yield a better representation for data pre-selection. To this end, we introduce UP-DP, a simple yet effective unsupervised prompt learning approach that adapts vision-language models, like BLIP-2, for data pre-selection. Specifically, with the BLIP-2 parameters frozen, we train text prompts to extract the joint features with improved representation, ensuring a diverse cluster structure that covers the entire dataset. We extensively compare our method with the state-of-the-art using seven benchmark datasets in different settings, achieving up to a performance gain of 20%. Interestingly, the prompts learned from one dataset demonstrate significant generalizability and can be applied directly to enhance the feature extraction of BLIP-2 from other datasets. To the best of our knowledge, UP-DP is the first work to incorporate unsupervised prompt learning in a vision-language model for data pre-selection.
Authors: Enric Moreu, Eric Arazo, Kevin McGuinness, Noel E. O'Connor
Deep learning has shown excellent performance in analysing medical images. However, datasets are difficult to obtain due privacy issues, standardization problems, and lack of annotations. We address these problems by producing realistic synthetic images using a combination of 3D technologies and generative adversarial networks. We propose CUT-seg, a joint training where a segmentation model and a generative model are jointly trained to produce realistic images while learning to segment polyps. We take advantage of recent one-sided translation models because they use significantly less memory, allowing us to add a segmentation model in the training loop. CUT-seg performs better, is computationally less expensive, and requires less real images than other memory-intensive image translation approaches that require two stage training. Promising results are achieved on five real polyp segmentation datasets using only one real image and zero real annotations. As a part of this study we release Synth-Colon, an entirely synthetic dataset that includes 20000 realistic colon images and additional details about depth and 3D geometry: https://enric1994.github.io/synth-colon
Authors: Nikhil U. Shinde, Florian Richter, Michael C. Yip
The ability to envision future states is crucial to informed decision making while interacting with dynamic environments. With cameras providing a prevalent and information rich sensing modality, the problem of predicting future states from image sequences has garnered a lot of attention. Current state of the art methods typically train large parametric models for their predictions. Though often able to predict with accuracy, these models rely on the availability of large training datasets to converge to useful solutions. In this paper we focus on the problem of predicting future images of an image sequence from very little training data. To approach this problem, we use non-parametric models to take a probabilistic approach to image prediction. We generate probability distributions over sequentially predicted images and propagate uncertainty through time to generate a confidence metric for our predictions. Gaussian Processes are used for their data efficiency and ability to readily incorporate new training data online. We showcase our method by successfully predicting future frames of a smooth fluid simulation environment.
Authors: Anita Rau, Sophia Bano, Yueming Jin, Pablo Azagra, Javier Morlana, Edward Sanderson, Bogdan J. Matuszewski, Jae Young Lee, Dong-Jae Lee, Erez Posner, Netanel Frank, Varshini Elangovan, Sista Raviteja, Zhengwen Li, Jiquan Liu, Seenivasan Lalithkumar, Mobarakol Islam, Hongliang Ren, José M.M. Montiel, Danail Stoyanov
Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains unsolved due to numerous factors such as self-occlusion, reflective surfaces, lack of texture, and tissue deformation that limit feature-based methods. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. By establishing a benchmark, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction in virtual colonoscopy is robustly solvable, while pose estimation remains an open research question.
Authors: Debajyoti Chakraborty
Breast cancer is a leading cause of cancer-related deaths, but current programs are expensive and prone to false positives, leading to unnecessary follow-up and patient anxiety. This paper proposes a solution to automated breast cancer detection, to improve the efficiency and accuracy of screening programs. Different methodologies were tested against the RSNA dataset of radiographic breast images of roughly 20,000 female patients and yielded an average validation case pF1 score of 0.56 across methods.
Authors: Weiming Zhuang, Yonggang Wen, Lingjuan Lyu, Shuai Zhang
Federated learning (FL) is an emerging distributed machine learning method that empowers in-situ model training on decentralized edge devices. However, multiple simultaneous FL tasks could overload resource-constrained devices. In this work, we propose the first FL system to effectively coordinate and train multiple simultaneous FL tasks. We first formalize the problem of training simultaneous FL tasks. Then, we present our new approach, MAS (Merge and Split), to optimize the performance of training multiple simultaneous FL tasks. MAS starts by merging FL tasks into an all-in-one FL task with a multi-task architecture. After training for a few rounds, MAS splits the all-in-one FL task into two or more FL tasks by using the affinities among tasks measured during the all-in-one training. It then continues training each split of FL tasks based on model parameters from the all-in-one training. Extensive experiments demonstrate that MAS outperforms other methods while reducing training time by 2x and reducing energy consumption by 40%. We hope this work will inspire the community to further study and optimize training simultaneous FL tasks.
Authors: Ruyi Zha, Xuelian Cheng, Hongdong Li, Mehrtash Harandi, Zongyuan Ge
Reconstructing soft tissues from stereo endoscope videos is an essential prerequisite for many medical applications. Previous methods struggle to produce high-quality geometry and appearance due to their inadequate representations of 3D scenes. To address this issue, we propose a novel neural-field-based method, called EndoSurf, which effectively learns to represent a deforming surface from an RGBD sequence. In EndoSurf, we model surface dynamics, shape, and texture with three neural fields. First, 3D points are transformed from the observed space to the canonical space using the deformation field. The signed distance function (SDF) field and radiance field then predict their SDFs and colors, respectively, with which RGBD images can be synthesized via differentiable volume rendering. We constrain the learned shape by tailoring multiple regularization strategies and disentangling geometry and appearance. Experiments on public endoscope datasets demonstrate that EndoSurf significantly outperforms existing solutions, particularly in reconstructing high-fidelity shapes. Code is available at https://github.com/Ruyi-Zha/endosurf.git.
Authors: Zezeng Li, ShengHao Li, Zhanpeng Wang, Na Lei, Zhongxuan Luo, Xianfeng Gu
Sampling from diffusion probabilistic models (DPMs) can be viewed as a piecewise distribution transformation, which generally requires hundreds or thousands of steps of the inverse diffusion trajectory to get a high-quality image. Recent progress in designing fast samplers for DPMs achieves a trade-off between sampling speed and sample quality by knowledge distillation or adjusting the variance schedule or the denoising equation. However, it can't be optimal in both aspects and often suffer from mode mixture in short steps. To tackle this problem, we innovatively regard inverse diffusion as an optimal transport (OT) problem between latents at different stages and propose the DPM-OT, a unified learning framework for fast DPMs with a direct expressway represented by OT map, which can generate high-quality samples within around 10 function evaluations. By calculating the semi-discrete optimal transport map between the data latents and the white noise, we obtain an expressway from the prior distribution to the data distribution, while significantly alleviating the problem of mode mixture. In addition, we give the error bound of the proposed method, which theoretically guarantees the stability of the algorithm. Extensive experiments validate the effectiveness and advantages of DPM-OT in terms of speed and quality (FID and mode mixture), thus representing an efficient solution for generative modeling. Source codes are available at https://github.com/cognaclee/DPM-OT
Authors: Emily Mu, Kathleen M. Lewis, Adrian V. Dalca, John Guttag
Recent vision-language models outperform vision-only models on many image classification tasks. However, because of the absence of paired text/image descriptions, it remains difficult to fine-tune these models for fine-grained image classification. In this work, we propose a method, GIST, for generating image-specific fine-grained text descriptions from image-only datasets, and show that these text descriptions can be used to improve classification. Key parts of our method include 1. prompting a pretrained large language model with domain-specific prompts to generate diverse fine-grained text descriptions for each class and 2. using a pretrained vision-language model to match each image to label-preserving text descriptions that capture relevant visual features in the image. We demonstrate the utility of GIST by fine-tuning vision-language models on the image-and-generated-text pairs to learn an aligned vision-language representation space for improved classification. We evaluate our learned representation space in full-shot and few-shot scenarios across four diverse fine-grained classification datasets, each from a different domain. Our method achieves an average improvement of $4.1\%$ in accuracy over CLIP linear probes and an average of $1.1\%$ improvement in accuracy over the previous state-of-the-art image-text classification method on the full-shot datasets. Our method achieves similar improvements across few-shot regimes. Code is available at https://github.com/emu1729/GIST.
Authors: Karan Shah, Vishruth Veerendranath, Anushka Hebbar, Raghavendra Bhat
Streaming Linear Discriminant Analysis (LDA) while proven in Class-incremental Learning deployments at the edge with limited classes (upto 1000), has not been proven for deployment in extreme classification scenarios. In this paper, we present: (a) XLDA, a framework for Class-IL in edge deployment where LDA classifier is proven to be equivalent to FC layer including in extreme classification scenarios, and (b) optimizations to enable XLDA-based training and inference for edge deployment where there is a constraint on available compute resources. We show up to 42x speed up using a batched training approach and up to 5x inference speedup with nearest neighbor search on extreme datasets like AliProducts (50k classes) and Google Landmarks V2 (81k classes)
Authors: Kai Lei, Zhan Chen, Shuman Jia, Xiaoteng Zhang
In the field of autonomous driving, 3D object detection is a very important perception module. Although the current SOTA algorithm combines Camera and Lidar sensors, limited by the high price of Lidar, the current mainstream landing schemes are pure Camera sensors or Camera+Radar sensors. In this study, we propose a new detection algorithm called HVDetFusion, which is a multi-modal detection algorithm that not only supports pure camera data as input for detection, but also can perform fusion input of radar data and camera data. The camera stream does not depend on the input of Radar data, thus addressing the downside of previous methods. In the pure camera stream, we modify the framework of Bevdet4D for better perception and more efficient inference, and this stream has the whole 3D detection output. Further, to incorporate the benefits of Radar signals, we use the prior information of different object positions to filter the false positive information of the original radar data, according to the positioning information and radial velocity information recorded by the radar sensors to supplement and fuse the BEV features generated by the original camera data, and the effect is further improved in the process of fusion training. Finally, HVDetFusion achieves the new state-of-the-art 67.4\% NDS on the challenging nuScenes test set among all camera-radar 3D object detectors. The code is available at https://github.com/HVXLab/HVDetFusion
Authors: Qizhang Li, Yiwen Guo, Xiaochen Yang, Wangmeng Zuo, Hao Chen
This paper presents a substantial extension of our work published at ICLR. Our ICLR work advocated for enhancing transferability in adversarial examples by incorporating a Bayesian formulation into model parameters, which effectively emulates the ensemble of infinitely many deep neural networks, while, in this paper, we introduce a novel extension by incorporating the Bayesian formulation into the model input as well, enabling the joint diversification of both the model input and model parameters. Our empirical findings demonstrate that: 1) the combination of Bayesian formulations for both the model input and model parameters yields significant improvements in transferability; 2) by introducing advanced approximations of the posterior distribution over the model input, adversarial transferability achieves further enhancement, surpassing all state-of-the-arts when attacking without model fine-tuning. Moreover, we propose a principled approach to fine-tune model parameters in such an extended Bayesian formulation. The derived optimization objective inherently encourages flat minima in the parameter space and input space. Extensive experiments demonstrate that our method achieves a new state-of-the-art on transfer-based attacks, improving the average success rate on ImageNet and CIFAR-10 by 19.14% and 2.08%, respectively, when comparing with our ICLR basic Bayesian method. We will make our code publicly available.
Authors: Wenbo Hu, Yuling Wang, Lin Ma, Bangbang Yang, Lin Gao, Xiao Liu, Yuewen Ma
Despite the tremendous progress in neural radiance fields (NeRF), we still face a dilemma of the trade-off between quality and efficiency, e.g., MipNeRF presents fine-detailed and anti-aliased renderings but takes days for training, while Instant-ngp can accomplish the reconstruction in a few minutes but suffers from blurring or aliasing when rendering at various distances or resolutions due to ignoring the sampling area. To this end, we propose a novel Tri-Mip encoding that enables both instant reconstruction and anti-aliased high-fidelity rendering for neural radiance fields. The key is to factorize the pre-filtered 3D feature spaces in three orthogonal mipmaps. In this way, we can efficiently perform 3D area sampling by taking advantage of 2D pre-filtered feature maps, which significantly elevates the rendering quality without sacrificing efficiency. To cope with the novel Tri-Mip representation, we propose a cone-casting rendering technique to efficiently sample anti-aliased 3D features with the Tri-Mip encoding considering both pixel imaging and observing distance. Extensive experiments on both synthetic and real-world datasets demonstrate our method achieves state-of-the-art rendering quality and reconstruction speed while maintaining a compact representation that reduces 25% model size compared against Instant-ngp.
Authors: Quang Huy Che, Tung Do Thanh, Cuong Truong Van
Automatic License Plate Recognition (ALPR) is becoming a popular study area and is applied in many fields such as transportation or smart city. However, there are still several limitations when applying many current methods to practical problems due to the variation in real-world situations such as light changes, unclear License Plate (LP) characters, and image quality. Almost recent ALPR algorithms process on a single frame, which reduces accuracy in case of worse image quality. This paper presents methods to improve license plate recognition accuracy by tracking the license plate in multiple frames. First, the Adaptive License Plate Rotation algorithm is applied to correctly align the detected license plate. Second, we propose a method called Character Time-series Matching to recognize license plate characters from many consequence frames. The proposed method archives high performance in the UFPR-ALPR dataset which is \boldmath$96.7\%$ accuracy in real-time on RTX A5000 GPU card. We also deploy the algorithm for the Vietnamese ALPR system. The accuracy for license plate detection and character recognition are 0.881 and 0.979 $mAP^{test}$@.5 respectively. The source code is available at https://github.com/chequanghuy/Character-Time-series-Matching.git
Authors: Mingze Gao, Qilong Wang, Zhenyi Lin, Pengfei Zhu, Qinghua Hu, Jingbo Zhou
Recently, efficient fine-tuning of large-scale pre-trained models has attracted increasing research interests, where linear probing (LP) as a fundamental module is involved in exploiting the final representations for task-dependent classification. However, most of the existing methods focus on how to effectively introduce a few of learnable parameters, and little work pays attention to the commonly used LP module. In this paper, we propose a novel Moment Probing (MP) method to further explore the potential of LP. Distinguished from LP which builds a linear classification head based on the mean of final features (e.g., word tokens for ViT) or classification tokens, our MP performs a linear classifier on feature distribution, which provides the stronger representation ability by exploiting richer statistical information inherent in features. Specifically, we represent feature distribution by its characteristic function, which is efficiently approximated by using first- and second-order moments of features. Furthermore, we propose a multi-head convolutional cross-covariance (MHC$^3$) to compute second-order moments in an efficient and effective manner. By considering that MP could affect feature learning, we introduce a partially shared module to learn two recalibrating parameters (PSRP) for backbones based on MP, namely MP$_{+}$. Extensive experiments on ten benchmarks using various models show that our MP significantly outperforms LP and is competitive with counterparts at less training cost, while our MP$_{+}$ achieves state-of-the-art performance.
Authors: Daria Reshetova, Guanhang Wu, Marcel Puyat, Chunhui Gu, Huizhong Chen
Object detection is the key technique to a number of Computer Vision applications, but it often requires large amounts of annotated data to achieve decent results. Moreover, for pedestrian detection specifically, the collected data might contain some personally identifiable information (PII), which is highly restricted in many countries. This label intensive and privacy concerning task has recently led to an increasing interest in training the detection models using synthetically generated pedestrian datasets collected with a photo-realistic video game engine. The engine is able to generate unlimited amounts of data with precise and consistent annotations, which gives potential for significant gains in the real-world applications. However, the use of synthetic data for training introduces a synthetic-to-real domain shift aggravating the final performance. To close the gap between the real and synthetic data, we propose to use a Generative Adversarial Network (GAN), which performsparameterized unpaired image-to-image translation to generate more realistic images. The key benefit of using the GAN is its intrinsic preference of low-level changes to geometric ones, which means annotations of a given synthetic image remain accurate even after domain translation is performed thus eliminating the need for labeling real data. We extensively experimented with the proposed method using MOTSynth dataset to train and MOT17 and MOT20 detection datasets to test, with experimental results demonstrating the effectiveness of this method. Our approach not only produces visually plausible samples but also does not require any labels of the real domain thus making it applicable to the variety of downstream tasks.
Authors: Zhongping Ji, Feifei Che, Hanshuo Liu, Ziyi Zhao, Yu-Wei Zhang, Wenping Wang
In this paper, we propose a technique for making humans in photographs protrude like reliefs. Unlike previous methods which mostly focus on the face and head, our method aims to generate art works that describe the whole body activity of the character. One challenge is that there is no ground-truth for supervised deep learning. We introduce a sigmoid variant function to manipulate gradients tactfully and train our neural networks by equipping with a loss function defined in gradient domain. The second challenge is that actual photographs often across different light conditions. We used image-based rendering technique to address this challenge and acquire rendering images and depth data under different lighting conditions. To make a clear division of labor in network modules, a two-scale architecture is proposed to create high-quality relief from a single photograph. Extensive experimental results on a variety of scenes show that our method is a highly effective solution for generating digital 2.5D artwork from photographs.
Authors: Lorenzo Tronchin, Minh H. Vu, Paolo Soda, Tommy Löfstedt
Data Augmentation (DA) is a technique to increase the quantity and diversity of the training data, and by that alleviate overfitting and improve generalisation. However, standard DA produces synthetic data for augmentation with limited diversity. Generative Adversarial Networks (GANs) may unlock additional information in a dataset by generating synthetic samples having the appearance of real images. However, these models struggle to simultaneously address three key requirements: fidelity and high-quality samples; diversity and mode coverage; and fast sampling. Indeed, GANs generate high-quality samples rapidly, but have poor mode coverage, limiting their adoption in DA applications. We propose LatentAugment, a DA strategy that overcomes the low diversity of GANs, opening up for use in DA applications. Without external supervision, LatentAugment modifies latent vectors and moves them into latent space regions to maximise the synthetic images' diversity and fidelity. It is also agnostic to the dataset and the downstream task. A wide set of experiments shows that LatentAugment improves the generalisation of a deep model translating from MRI-to-CT beating both standard DA as well GAN-based sampling. Moreover, still in comparison with GAN-based sampling, LatentAugment synthetic samples show superior mode coverage and diversity. Code is available at: https://github.com/ltronchin/LatentAugment.
Authors: Yunhao Ge, Yuecheng Li, Shuo Ni, Jiaping Zhao, Ming-Hsuan Yang, Laurent Itti
Continual learning aims to emulate the human ability to continually accumulate knowledge over sequential tasks. The main challenge is to maintain performance on previously learned tasks after learning new tasks, i.e., to avoid catastrophic forgetting. We propose a Channel-wise Lightweight Reprogramming (CLR) approach that helps convolutional neural networks (CNNs) overcome catastrophic forgetting during continual learning. We show that a CNN model trained on an old task (or self-supervised proxy task) could be ``reprogrammed" to solve a new task by using our proposed lightweight (very cheap) reprogramming parameter. With the help of CLR, we have a better stability-plasticity trade-off to solve continual learning problems: To maintain stability and retain previous task ability, we use a common task-agnostic immutable part as the shared ``anchor" parameter set. We then add task-specific lightweight reprogramming parameters to reinterpret the outputs of the immutable parts, to enable plasticity and integrate new knowledge. To learn sequential tasks, we only train the lightweight reprogramming parameters to learn each new task. Reprogramming parameters are task-specific and exclusive to each task, which makes our method immune to catastrophic forgetting. To minimize the parameter requirement of reprogramming to learn new tasks, we make reprogramming lightweight by only adjusting essential kernels and learning channel-wise linear mappings from anchor parameters to task-specific domain knowledge. We show that, for general CNNs, the CLR parameter increase is less than 0.6\% for any new task. Our method outperforms 13 state-of-the-art continual learning baselines on a new challenging sequence of 53 image classification datasets. Code and data are available at https://github.com/gyhandy/Channel-wise-Lightweight-Reprogramming
Authors: Arne Schmidt, Pablo Morales-Álvarez, Rafael Molina
Medical image segmentation is a challenging task, particularly due to inter- and intra-observer variability, even between medical experts. In this paper, we propose a novel model, called Probabilistic Inter-Observer and iNtra-Observer variation NetwOrk (Pionono). It captures the labeling behavior of each rater with a multidimensional probability distribution and integrates this information with the feature maps of the image to produce probabilistic segmentation predictions. The model is optimized by variational inference and can be trained end-to-end. It outperforms state-of-the-art models such as STAPLE, Probabilistic U-Net, and models based on confusion matrices. Additionally, Pionono predicts multiple coherent segmentation maps that mimic the rater's expert opinion, which provides additional valuable information for the diagnostic process. Experiments on real-world cancer segmentation datasets demonstrate the high accuracy and efficiency of Pionono, making it a powerful tool for medical image analysis.
Authors: Isack Lee, Eungi Lee, Seok Bong Yoo
Most research on facial expression recognition (FER) is conducted in highly controlled environments, but its performance is often unacceptable when applied to real-world situations. This is because when unexpected objects occlude the face, the FER network faces difficulties extracting facial features and accurately predicting facial expressions. Therefore, occluded FER (OFER) is a challenging problem. Previous studies on occlusion-aware FER have typically required fully annotated facial images for training. However, collecting facial images with various occlusions and expression annotations is time-consuming and expensive. Latent-OFER, the proposed method, can detect occlusions, restore occluded parts of the face as if they were unoccluded, and recognize them, improving FER accuracy. This approach involves three steps: First, the vision transformer (ViT)-based occlusion patch detector masks the occluded position by training only latent vectors from the unoccluded patches using the support vector data description algorithm. Second, the hybrid reconstruction network generates the masking position as a complete image using the ViT and convolutional neural network (CNN). Last, the expression-relevant latent vector extractor retrieves and uses expression-related information from all latent vectors by applying a CNN-based class activation map. This mechanism has a significant advantage in preventing performance degradation from occlusion by unseen objects. The experimental results on several databases demonstrate the superiority of the proposed method over state-of-the-art methods.
Authors: Jian Ma, Junhao Liang, Chen Chen, Haonan Lu
Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}
Authors: Qiaoyi Su, Yuhong Chou, Yifan Hu, Jianing Li, Shijie Mei, Ziyang Zhang, Guoqi Li
Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics. Recently, deep SNNs trained directly have shown great success in achieving high performance on classification tasks with very few time steps. However, how to design a directly-trained SNN for the regression task of object detection still remains a challenging problem. To address this problem, we propose EMS-YOLO, a novel directly-trained SNN framework for object detection, which is the first trial to train a deep SNN with surrogate gradients for object detection rather than ANN-SNN conversion strategies. Specifically, we design a full-spike residual block, EMS-ResNet, which can effectively extend the depth of the directly-trained SNN with low power consumption. Furthermore, we theoretically analyze and prove the EMS-ResNet could avoid gradient vanishing or exploding. The results demonstrate that our approach outperforms the state-of-the-art ANN-SNN conversion methods (at least 500 time steps) in extremely fewer time steps (only 4 time steps). It is shown that our model could achieve comparable performance to the ANN with the same architecture while consuming 5.83 times less energy on the frame-based COCO Dataset and the event-based Gen1 Dataset.
Authors: Reuben Moyo, Stanley Ndebvu, Michael Zimba, Jimmy Mbelwa
Examinations are a crucial part of the learning process, and academic institutions invest significant resources into maintaining their integrity by preventing cheating from students or facilitators. However, cheating has become rampant in examination setups, compromising their integrity. The traditional method of relying on invigilators to monitor every student is impractical and ineffective. To address this issue, there is a need to continuously record exam sessions to monitor students for suspicious activities. However, these recordings are often too lengthy for invigilators to analyze effectively, and fatigue may cause them to miss significant details. To widen the coverage, invigilators could use fixed overhead or wearable cameras. This paper introduces a framework that uses automation to analyze videos and detect suspicious activities during examinations efficiently and effectively. We utilized the OpenPose framework and Convolutional Neural Network (CNN) to identify students exchanging objects during exams. This detection system is vital in preventing cheating and promoting academic integrity, fairness, and quality education for institutions.
Authors: Sungwon Hwang, Junha Hyung, Daejin Kim, Min-Jung Kim, Jaegul Choo
As recent advances in Neural Radiance Fields (NeRF) have enabled high-fidelity 3D face reconstruction and novel view synthesis, its manipulation also became an essential task in 3D vision. However, existing manipulation methods require extensive human labor, such as a user-provided semantic mask and manual attribute search unsuitable for non-expert users. Instead, our approach is designed to require a single text to manipulate a face reconstructed with NeRF. To do so, we first train a scene manipulator, a latent code-conditional deformable NeRF, over a dynamic scene to control a face deformation using the latent code. However, representing a scene deformation with a single latent code is unfavorable for compositing local deformations observed in different instances. As so, our proposed Position-conditional Anchor Compositor (PAC) learns to represent a manipulated scene with spatially varying latent codes. Their renderings with the scene manipulator are then optimized to yield high cosine similarity to a target text in CLIP embedding space for text-driven manipulation. To the best of our knowledge, our approach is the first to address the text-driven manipulation of a face reconstructed with NeRF. Extensive results, comparisons, and ablation studies demonstrate the effectiveness of our approach.
Authors: Tim Yarally, Luís Cruz, Daniel Feitosa, June Sallou, Arie van Deursen
The batch size is an essential parameter to tune during the development of new neural networks. Amongst other quality indicators, it has a large degree of influence on the model's accuracy, generalisability, training times and parallelisability. This fact is generally known and commonly studied. However, during the application phase of a deep learning model, when the model is utilised by an end-user for inference, we find that there is a disregard for the potential benefits of introducing a batch size. In this study, we examine the effect of input batching on the energy consumption and response times of five fully-trained neural networks for computer vision that were considered state-of-the-art at the time of their publication. The results suggest that batching has a significant effect on both of these metrics. Furthermore, we present a timeline of the energy efficiency and accuracy of neural networks over the past decade. We find that in general, energy consumption rises at a much steeper pace than accuracy and question the necessity of this evolution. Additionally, we highlight one particular network, ShuffleNetV2(2018), that achieved a competitive performance for its time while maintaining a much lower energy consumption. Nevertheless, we highlight that the results are model dependent.
Authors: Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
Due to the successful development of deep image generation technology, visual data forgery detection would play a more important role in social and economic security. Existing forgery detection methods suffer from unsatisfactory generalization ability to determine the authenticity in the unseen domain. In this paper, we propose a novel Attention Consistency Refined masked frequency forgery representation model toward generalizing face forgery detection algorithm (ACMF). Most forgery technologies always bring in high-frequency aware cues, which make it easy to distinguish source authenticity but difficult to generalize to unseen artifact types. The masked frequency forgery representation module is designed to explore robust forgery cues by randomly discarding high-frequency information. In addition, we find that the forgery attention map inconsistency through the detection network could affect the generalizability. Thus, the forgery attention consistency is introduced to force detectors to focus on similar attention regions for better generalization ability. Experiment results on several public face forgery datasets (FaceForensic++, DFD, Celeb-DF, and WDF datasets) demonstrate the superior performance of the proposed method compared with the state-of-the-art methods.
Authors: Guiping Cao, Shengda Luo, Wenjian Huang, Xiangyuan Lan, Dongmei Jiang, Yaowei Wang, Jianguo Zhang
Token interaction operation is one of the core modules in MLP-based models to exchange and aggregate information between different spatial locations. However, the power of token interaction on the spatial dimension is highly dependent on the spatial resolution of the feature maps, which limits the model's expressive ability, especially in deep layers where the feature are down-sampled to a small spatial size. To address this issue, we present a novel method called \textbf{Strip-MLP} to enrich the token interaction power in three ways. Firstly, we introduce a new MLP paradigm called Strip MLP layer that allows the token to interact with other tokens in a cross-strip manner, enabling the tokens in a row (or column) to contribute to the information aggregations in adjacent but different strips of rows (or columns). Secondly, a \textbf{C}ascade \textbf{G}roup \textbf{S}trip \textbf{M}ixing \textbf{M}odule (CGSMM) is proposed to overcome the performance degradation caused by small spatial feature size. The module allows tokens to interact more effectively in the manners of within-patch and cross-patch, which is independent to the feature spatial size. Finally, based on the Strip MLP layer, we propose a novel \textbf{L}ocal \textbf{S}trip \textbf{M}ixing \textbf{M}odule (LSMM) to boost the token interaction power in the local region. Extensive experiments demonstrate that Strip-MLP significantly improves the performance of MLP-based models on small datasets and obtains comparable or even better results on ImageNet. In particular, Strip-MLP models achieve higher average Top-1 accuracy than existing MLP-based models by +2.44\% on Caltech-101 and +2.16\% on CIFAR-100. The source codes will be available at~\href{https://github.com/Med-Process/Strip_MLP{https://github.com/Med-Process/Strip\_MLP}.
Authors: Yuwen Heng, Yihong Wu, Jiawen Chen, Srinandan Dasmahapatra, Hansung Kim
Achieving accurate material segmentation for 3-channel RGB images is challenging due to the considerable variation in a material's appearance. Hyperspectral images, which are sets of spectral measurements sampled at multiple wavelengths, theoretically offer distinct information for material identification, as variations in intensity of electromagnetic radiation reflected by a surface depend on the material composition of a scene. However, existing hyperspectral datasets are impoverished regarding the number of images and material categories for the dense material segmentation task, and collecting and annotating hyperspectral images with a spectral camera is prohibitively expensive. To address this, we propose a new model, the MatSpectNet to segment materials with recovered hyperspectral images from RGB images. The network leverages the principles of colour perception in modern cameras to constrain the reconstructed hyperspectral images and employs the domain adaptation method to generalise the hyperspectral reconstruction capability from a spectral recovery dataset to material segmentation datasets. The reconstructed hyperspectral images are further filtered using learned response curves and enhanced with human perception. The performance of MatSpectNet is evaluated on the LMD dataset as well as the OpenSurfaces dataset. Our experiments demonstrate that MatSpectNet attains a 1.60% increase in average pixel accuracy and a 3.42% improvement in mean class accuracy compared with the most recent publication. The project code is attached to the supplementary material and will be published on GitHub.
Authors: Jialiang Tang, Shuo Chen, Gang Niu, Masashi Sugiyama, Chen Gong
Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some privacy issues and data management considerations. Therefore, data-free knowledge distillation approaches proposed to collect training instances from the Internet. However, most of them have ignored the common distribution shift between the instances from original training data and webly collected data, affecting the reliability of the trained student network. To solve this problem, we propose a novel method dubbed ``Knowledge Distillation between Different Distributions" (KD$^{3}$), which consists of three components. Specifically, we first dynamically select useful training instances from the webly collected data according to the combined predictions of teacher network and student network. Subsequently, we align both the weighted features and classifier parameters of the two networks for knowledge memorization. Meanwhile, we also build a new contrastive learning block called MixDistribution to generate perturbed data with a new distribution for instance alignment, so that the student network can further learn a distribution-invariant representation. Intensive experiments on various benchmark datasets demonstrate that our proposed KD$^{3}$ can outperform the state-of-the-art data-free knowledge distillation approaches.
Authors: Hao Qi, Xinghui Dong
Underwater images normally suffer from degradation due to the transmission medium of water bodies. Both traditional prior-based approaches and deep learning-based methods have been used to address this problem. However, the inflexible assumption of the former often impairs their effectiveness in handling diverse underwater scenes, while the generalization of the latter to unseen images is usually weakened by insufficient data. In this study, we leverage both the physics-based underwater Image Formation Model (IFM) and deep learning techniques for Underwater Image Enhancement (UIE). To this end, we propose a novel Physics-Aware Dual-Stream Underwater Image Enhancement Network, i.e., PA-UIENet, which comprises a Transmission Estimation Steam (T-Stream) and an Ambient Light Estimation Stream (A-Stream). This network fulfills the UIE task by explicitly estimating the degradation parameters of the IFM. We also adopt an IFM-inspired semi-supervised learning framework, which exploits both the labeled and unlabeled images, to address the issue of insufficient data. Our method performs better than, or at least comparably to, eight baselines across five testing sets in the degradation estimation and UIE tasks. This should be due to the fact that it not only can model the degradation but also can learn the characteristics of diverse underwater scenes.
Authors: Jie Ma, Pinghui Wang, Dechen Kong, Zewei Wang, Jun Liu, Hongbin Pei, Junzhou Zhao
Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often exhibit a tendency to memorize biases present in the training data rather than learning proper behaviors, such as grounding images before predicting answers. Therefore, these methods usually achieve high in-distribution but poor out-of-distribution performance. In recent years, various datasets and debiasing methods have been proposed to evaluate and enhance the VQA robustness, respectively. This paper provides the first comprehensive survey focused on this emerging fashion. Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives. Then, we examine the evaluation metrics employed by these datasets. Thirdly, we propose a typology that presents the development process, similarities and differences, robustness comparison, and technical features of existing debiasing methods. Furthermore, we analyze and discuss the robustness of representative vision-and-language pre-training models on VQA. Finally, through a thorough review of the available literature and experimental analysis, we discuss the key areas for future research from various viewpoints.
Authors: Jinqing Zhang, Yanan Zhang, Qingjie Liu, Yunhong Wang
Recently, the pure camera-based Bird's-Eye-View (BEV) perception provides a feasible solution for economical autonomous driving. However, the existing BEV-based multi-view 3D detectors generally transform all image features into BEV features, without considering the problem that the large proportion of background information may submerge the object information. In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features. Accordingly, we propose BEV-Paste, an effective data augmentation strategy that closely matches with semantic-aware BEV feature. In addition, we design a Multi-Scale Cross-Task (MSCT) head, which combines task-specific and cross-task information to predict depth distribution and semantic segmentation more accurately, further improving the quality of semantic-aware BEV feature. Finally, we integrate the above modules into a novel multi-view 3D object detection framework, namely SA-BEV. Experiments on nuScenes show that SA-BEV achieves state-of-the-art performance. Code has been available at https://github.com/mengtan00/SA-BEV.git.
Authors: Yihan Wang, Qiao Yan
Most recent approaches for 3D object detection predominantly rely on point-view or bird's-eye view representations, with limited exploration of range-view-based methods. The range-view representation suffers from scale variation and surface texture deficiency, both of which pose significant limitations for developing corresponding methods. Notably, the surface texture loss problem has been largely ignored by all existing methods, despite its significant impact on the accuracy of range-view-based 3D object detection. In this study, we propose Redemption from Range-view R-CNN (R2 R-CNN), a novel and accurate approach that comprehensively explores the range-view representation. Our proposed method addresses scale variation through the HD Meta Kernel, which captures range-view geometry information in multiple scales. Additionally, we introduce Feature Points Redemption (FPR) to recover the lost 3D surface texture information from the range view, and Synchronous-Grid RoI Pooling (S-Grid RoI Pooling), a multi-scaled approach with multiple receptive fields for accurate box refinement. Our R2 R-CNN outperforms existing range-view-based methods, achieving state-of-the-art performance on both the KITTI benchmark and the Waymo Open Dataset. Our study highlights the critical importance of addressing the surface texture loss problem for accurate 3D object detection in range-view-based methods. Codes will be made publicly available.
Authors: Yi Gu, Yoshito Otake, Keisuke Uemura, Mazen Soufi, Masaki Takao, Hugues Talbot, Seiji Okada, Nobuhiko Sugano, Yoshinobu Sato
Osteoporosis is a prevalent bone disease that causes fractures in fragile bones, leading to a decline in daily living activities. Dual-energy X-ray absorptiometry (DXA) and quantitative computed tomography (QCT) are highly accurate for diagnosing osteoporosis; however, these modalities require special equipment and scan protocols. To frequently monitor bone health, low-cost, low-dose, and ubiquitously available diagnostic methods are highly anticipated. In this study, we aim to perform bone mineral density (BMD) estimation from a plain X-ray image for opportunistic screening, which is potentially useful for early diagnosis. Existing methods have used multi-stage approaches consisting of extraction of the region of interest and simple regression to estimate BMD, which require a large amount of training data. Therefore, we propose an efficient method that learns decomposition into projections of bone-segmented QCT for BMD estimation under limited datasets. The proposed method achieved high accuracy in BMD estimation, where Pearson correlation coefficients of 0.880 and 0.920 were observed for DXA-measured BMD and QCT-measured BMD estimation tasks, respectively, and the root mean square of the coefficient of variation values were 3.27 to 3.79% for four measurements with different poses. Furthermore, we conducted extensive validation experiments, including multi-pose, uncalibrated-CT, and compression experiments toward actual application in routine clinical practice.
Authors: Binglu Wang, Lei Zhang, Zhaozhong Wang, Yongqiang Zhao, Tianfei Zhou
This paper presents CORE, a conceptually simple, effective and communication-efficient model for multi-agent cooperative perception. It addresses the task from a novel perspective of cooperative reconstruction, based on two key insights: 1) cooperating agents together provide a more holistic observation of the environment, and 2) the holistic observation can serve as valuable supervision to explicitly guide the model learning how to reconstruct the ideal observation based on collaboration. CORE instantiates the idea with three major components: a compressor for each agent to create more compact feature representation for efficient broadcasting, a lightweight attentive collaboration component for cross-agent message aggregation, and a reconstruction module to reconstruct the observation based on aggregated feature representations. This learning-to-reconstruct idea is task-agnostic, and offers clear and reasonable supervision to inspire more effective collaboration, eventually promoting perception tasks. We validate CORE on OPV2V, a large-scale multi-agent percetion dataset, in two tasks, i.e., 3D object detection and semantic segmentation. Results demonstrate that the model achieves state-of-the-art performance on both tasks, and is more communication-efficient.
Authors: Emerson Sie, Zikun Liu, Deepak Vasisht
Unmanned aerial vehicles (UAVs) rely on optical sensors such as cameras and lidar for autonomous operation. However, such optical sensors are error-prone in bad lighting, inclement weather conditions including fog and smoke, and around textureless or transparent surfaces. In this paper, we ask: is it possible to fly UAVs without relying on optical sensors, i.e., can UAVs fly without seeing? We present BatMobility, a lightweight mmWave radar-only perception system for UAVs that eliminates the need for optical sensors. BatMobility enables two core functionalities for UAVs -- radio flow estimation (a novel FMCW radar-based alternative for optical flow based on surface-parallel doppler shift) and radar-based collision avoidance. We build BatMobility using commodity sensors and deploy it as a real-time system on a small off-the-shelf quadcopter running an unmodified flight controller. Our evaluation shows that BatMobility achieves comparable or better performance than commercial-grade optical sensors across a wide range of scenarios.
Authors: Fariha Tahosin Boishakhi, Ponkoj Chandra Shill, Md. Golam Rabiul Alam
With the continuous growth of internet users and media content, it is very hard to track down hateful speech in audio and video. Converting video or audio into text does not detect hate speech accurately as human sometimes uses hateful words as humorous or pleasant in sense and also uses different voice tones or show different action in the video. The state-ofthe-art hate speech detection models were mostly developed on a single modality. In this research, a combined approach of multimodal system has been proposed to detect hate speech from video contents by extracting feature images, feature values extracted from the audio, text and used machine learning and Natural language processing.
Authors: Ziyuan Luo, Qing Guo, Ka Chun Cheung, Simon See, Renjie Wan
Neural Radiance Fields (NeRF) have the potential to be a major representation of media. Since training a NeRF has never been an easy task, the protection of its model copyright should be a priority. In this paper, by analyzing the pros and cons of possible copyright protection solutions, we propose to protect the copyright of NeRF models by replacing the original color representation in NeRF with a watermarked color representation. Then, a distortion-resistant rendering scheme is designed to guarantee robust message extraction in 2D renderings of NeRF. Our proposed method can directly protect the copyright of NeRF models while maintaining high rendering quality and bit accuracy when compared among optional solutions.
Authors: Shouwei Ruan, Yinpeng Dong, Hang Su, Jianteng Peng, Ning Chen, Xingxing Wei
Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering the viewing directions can significantly impact predictions for the same object. While substantial efforts have been dedicated to making neural networks invariant to 2D image translations and rotations, viewpoint invariance is rarely investigated. Motivated by the success of adversarial training in enhancing model robustness, we propose Viewpoint-Invariant Adversarial Training (VIAT) to improve the viewpoint robustness of image classifiers. Regarding viewpoint transformation as an attack, we formulate VIAT as a minimax optimization problem, where the inner maximization characterizes diverse adversarial viewpoints by learning a Gaussian mixture distribution based on the proposed attack method GMVFool. The outer minimization obtains a viewpoint-invariant classifier by minimizing the expected loss over the worst-case viewpoint distributions that can share the same one for different objects within the same category. Based on GMVFool, we contribute a large-scale dataset called ImageNet-V+ to benchmark viewpoint robustness. Experimental results show that VIAT significantly improves the viewpoint robustness of various image classifiers based on the diversity of adversarial viewpoints generated by GMVFool. Furthermore, we propose ViewRS, a certified viewpoint robustness method that provides a certified radius and accuracy to demonstrate the effectiveness of VIAT from the theoretical perspective.
Authors: Zhaojie Fang, Zhanghao Chen, Pengxue Wei, Wangting Li, Shaochong Zhang, Ahmed Elazab, Gangyong Jia, Ruiquan Ge, Changmiao Wang
Fundus photography is an essential examination for clinical and differential diagnosis of fundus diseases. Recently, Ultra-Wide-angle Fundus (UWF) techniques, UWF Fluorescein Angiography (UWF-FA) and UWF Scanning Laser Ophthalmoscopy (UWF-SLO) have been gradually put into use. However, Fluorescein Angiography (FA) and UWF-FA require injecting sodium fluorescein which may have detrimental influences. To avoid negative impacts, cross-modality medical image generation algorithms have been proposed. Nevertheless, current methods in fundus imaging could not produce high-resolution images and are unable to capture tiny vascular lesion areas. This paper proposes a novel conditional generative adversarial network (UWAT-GAN) to synthesize UWF-FA from UWF-SLO. Using multi-scale generators and a fusion module patch to better extract global and local information, our model can generate high-resolution images. Moreover, an attention transmit module is proposed to help the decoder learn effectively. Besides, a supervised approach is used to train the network using multiple new weighted losses on different scales of data. Experiments on an in-house UWF image dataset demonstrate the superiority of the UWAT-GAN over the state-of-the-art methods. The source code is available at: https://github.com/Tinysqua/UWAT-GAN.
Authors: Ivano Donadi, Alberto Pretto
Object pose estimation is a fundamental computer vision task exploited in several robotics and augmented reality applications. Many established approaches rely on predicting 2D-3D keypoint correspondences using RANSAC (Random sample consensus) and estimating the object pose using the PnP (Perspective-n-Point) algorithm. Being RANSAC non-differentiable, correspondences cannot be directly learned in an end-to-end fashion. In this paper, we address the stereo image-based object pose estimation problem by (i) introducing a differentiable RANSAC layer into a well-known monocular pose estimation network; (ii) exploiting an uncertainty-driven multi-view PnP solver which can fuse information from multiple views. We evaluate our approach on a challenging public stereo object pose estimation dataset, yielding state-of-the-art results against other recent approaches. Furthermore, in our ablation study, we show that the differentiable RANSAC layer plays a significant role in the accuracy of the proposed method. We release with this paper the open-source implementation of our method.
Authors: Zunnan Xu, Zhihong Chen, Yong Zhang, Yibing Song, Xiang Wan, Guanbin Li
Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities. In this paper, we do an investigation of efficient tuning problems on referring image segmentation. We propose a novel adapter called Bridger to facilitate cross-modal information exchange and inject task-specific information into the pre-trained model. We also design a lightweight decoder for image segmentation. Our approach achieves comparable or superior performance with only 1.61\% to 3.38\% backbone parameter updates, evaluated on challenging benchmarks. The code is available at \url{https://github.com/kkakkkka/ETRIS}.
Authors: Arul Selvam Periyasamy, Arash Amini, Vladimir Tsaturyan, Sven Behnke
6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture originally proposed for natural language processing, is achieving state-of-the-art results in many computer vision tasks as well. Equipped with the multi-head self-attention mechanism, Transformers enable simple single-stage end-to-end architectures for learning object detection and 6D object pose estimation jointly. In this work, we propose YOLOPose (short form for You Only Look Once Pose estimation), a Transformer-based multi-object 6D pose estimation method based on keypoint regression and an improved variant of the YOLOPose model. In contrast to the standard heatmaps for predicting keypoints in an image, we directly regress the keypoints. Additionally, we employ a learnable orientation estimation module to predict the orientation from the keypoints. Along with a separate translation estimation module, our model is end-to-end differentiable. Our method is suitable for real-time applications and achieves results comparable to state-of-the-art methods. We analyze the role of object queries in our architecture and reveal that the object queries specialize in detecting objects in specific image regions. Furthermore, we quantify the accuracy trade-off of using datasets of smaller sizes to train our model.
Authors: Zhihong Chen, Ruifei Zhang, Yibing Song, Xiang Wan, Guanbin Li
Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities over their joint space. However, most existing VG datasets are constructed using simple description texts, which do not require sufficient reasoning over the images and texts. This has been demonstrated in a recent study~\cite{luo2022goes}, where a simple LSTM-based text encoder without pretraining can achieve state-of-the-art performance on mainstream VG datasets. Therefore, in this paper, we propose a novel benchmark of \underline{S}cene \underline{K}nowledge-guided \underline{V}isual \underline{G}rounding (SK-VG), where the image content and referring expressions are not sufficient to ground the target objects, forcing the models to have a reasoning ability on the long-form scene knowledge. To perform this task, we propose two approaches to accept the triple-type input, where the former embeds knowledge into the image features before the image-query interaction; the latter leverages linguistic structure to assist in computing the image-text matching. We conduct extensive experiments to analyze the above methods and show that the proposed approaches achieve promising results but still leave room for improvement, including performance and interpretability. The dataset and code are available at \url{https://github.com/zhjohnchan/SK-VG}.
Authors: Richard McKinley, Christian Rummel
The thickness of the cortical band is linked to various neurological and psychiatric conditions, and is often estimated through surface-based methods such as Freesurfer in MRI studies. The DiReCT method, which calculates cortical thickness using a diffeomorphic deformation of the gray-white matter interface towards the pial surface, offers an alternative to surface-based methods. Recent studies using a synthetic cortical thickness phantom have demonstrated that the combination of DiReCT and deep-learning-based segmentation is more sensitive to subvoxel cortical thinning than Freesurfer.
While anatomical segmentation of a T1-weighted image now takes seconds, existing implementations of DiReCT rely on iterative image registration methods which can take up to an hour per volume. On the other hand, learning-based deformable image registration methods like VoxelMorph have been shown to be faster than classical methods while improving registration accuracy. This paper proposes CortexMorph, a new method that employs unsupervised deep learning to directly regress the deformation field needed for DiReCT. By combining CortexMorph with a deep-learning-based segmentation model, it is possible to estimate region-wise thickness in seconds from a T1-weighted image, while maintaining the ability to detect cortical atrophy. We validate this claim on the OASIS-3 dataset and the synthetic cortical thickness phantom of Rusak et al.
Authors: Pierre Rougé, Nicolas Passat, Odyssée Merveille
Vessel segmentation and centerline extraction are two crucial preliminary tasks for many computer-aided diagnosis tools dealing with vascular diseases. Recently, deep-learning based methods have been widely applied to these tasks. However, classic deep-learning approaches struggle to capture the complex geometry and specific topology of vascular networks, which is of the utmost importance in most applications. To overcome these limitations, the clDice loss, a topological loss that focuses on the vessel centerlines, has been recently proposed. This loss requires computing, with a proposed soft-skeleton algorithm, the skeletons of both the ground truth and the predicted segmentation. However, the soft-skeleton algorithm provides suboptimal results on 3D images, which makes the clDice hardly suitable on 3D images. In this paper, we propose to replace the soft-skeleton algorithm by a U-Net which computes the vascular skeleton directly from the segmentation. We show that our method provides more accurate skeletons than the soft-skeleton algorithm. We then build upon this network a cascaded U-Net trained with the clDice loss to embed topological constraints during the segmentation. The resulting model is able to predict both the vessel segmentation and centerlines with a more accurate topology.
Authors: Qingyue Wei, Lequan Yu, Xianhang Li, Wei Shao, Cihang Xie, Lei Xing, Yuyin Zhou
Medical imaging has witnessed remarkable progress but usually requires a large amount of high-quality annotated data which is time-consuming and costly to obtain. To alleviate this burden, semi-supervised learning has garnered attention as a potential solution. In this paper, we present Meta-Learning for Bootstrapping Medical Image Segmentation (MLB-Seg), a novel method for tackling the challenge of semi-supervised medical image segmentation. Specifically, our approach first involves training a segmentation model on a small set of clean labeled images to generate initial labels for unlabeled data. To further optimize this bootstrapping process, we introduce a per-pixel weight mapping system that dynamically assigns weights to both the initialized labels and the model's own predictions. These weights are determined using a meta-process that prioritizes pixels with loss gradient directions closer to those of clean data, which is based on a small set of precisely annotated images. To facilitate the meta-learning process, we additionally introduce a consistency-based Pseudo Label Enhancement (PLE) scheme that improves the quality of the model's own predictions by ensembling predictions from various augmented versions of the same input. In order to improve the quality of the weight maps obtained through multiple augmentations of a single input, we introduce a mean teacher into the PLE scheme. This method helps to reduce noise in the weight maps and stabilize its generation process. Our extensive experimental results on public atrial and prostate segmentation datasets demonstrate that our proposed method achieves state-of-the-art results under semi-supervision. Our code is available at https://github.com/aijinrjinr/MLB-Seg.
Authors: Duojun Huang, Jichang Li, Weikai Chen, Junshi Huang, Zhenhua Chai, Guanbin Li
Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the existence of domain shift, and hence, fail to identify the truly valuable samples in the context of domain adaptation. To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions. We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. While sending the informative instances for annotation, DiaNA employs tailored learning strategies for the remaining categories. Furthermore, we propose an informativeness score that unifies the data partitioning criteria. This enables the use of a Gaussian mixture model (GMM) to automatically sample unlabeled data into the proposed four categories. Thanks to the "divideand-adapt" spirit, DiaNA can handle data with large variations of domain gap. In addition, we show that DiaNA can generalize to different domain adaptation settings, such as unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA), source-free domain adaptation (SFDA), etc.
Authors: Runjia Li, Shuyang Sun, Mohamed Elhoseiny, Philip Torr
This paper presents OxfordTVG-HIC (Humorous Image Captions), a large-scale dataset for humour generation and understanding. Humour is an abstract, subjective, and context-dependent cognitive construct involving several cognitive factors, making it a challenging task to generate and interpret. Hence, humour generation and understanding can serve as a new task for evaluating the ability of deep-learning methods to process abstract and subjective information. Due to the scarcity of data, humour-related generation tasks such as captioning remain under-explored. To address this gap, OxfordTVG-HIC offers approximately 2.9M image-text pairs with humour scores to train a generalizable humour captioning model. Contrary to existing captioning datasets, OxfordTVG-HIC features a wide range of emotional and semantic diversity resulting in out-of-context examples that are particularly conducive to generating humour. Moreover, OxfordTVG-HIC is curated devoid of offensive content. We also show how OxfordTVG-HIC can be leveraged for evaluating the humour of a generated text. Through explainability analysis of the trained models, we identify the visual and linguistic cues influential for evoking humour prediction (and generation). We observe qualitatively that these cues are aligned with the benign violation theory of humour in cognitive psychology.
Authors: Charlie Budd, Jianrong Qiu, Oscar MacCormac, Martin Huber, Christopher Mower, Mirek Janatka, Théo Trotouin, Jonathan Shapey, Mads S. Bergholt, Tom Vercauteren
Hyperspectral imaging (HSI) captures a greater level of spectral detail than traditional optical imaging, making it a potentially valuable intraoperative tool when precise tissue differentiation is essential. Hardware limitations of current optical systems used for handheld real-time video HSI result in a limited focal depth, thereby posing usability issues for integration of the technology into the operating room. This work integrates a focus-tunable liquid lens into a video HSI exoscope, and proposes novel video autofocusing methods based on deep reinforcement learning. A first-of-its-kind robotic focal-time scan was performed to create a realistic and reproducible testing dataset. We benchmarked our proposed autofocus algorithm against traditional policies, and found our novel approach to perform significantly ($p<0.05$) better than traditional techniques ($0.070\pm.098$ mean absolute focal error compared to $0.146\pm.148$). In addition, we performed a blinded usability trial by having two neurosurgeons compare the system with different autofocus policies, and found our novel approach to be the most favourable, making our system a desirable addition for intraoperative HSI.
Authors: Jiajun Zhang, Georgina Cosma, Sarah Bugby, Axel Finke, Jason Watkins
As the use of artificial intelligent (AI) models becomes more prevalent in industries such as engineering and manufacturing, it is essential that these models provide transparent reasoning behind their predictions. This paper proposes the AI-Reasoner, which extracts the morphological characteristics of defects (DefChars) from images and utilises decision trees to reason with the DefChar values. Thereafter, the AI-Reasoner exports visualisations (i.e. charts) and textual explanations to provide insights into outputs made by masked-based defect detection and classification models. It also provides effective mitigation strategies to enhance data pre-processing and overall model performance. The AI-Reasoner was tested on explaining the outputs of an IE Mask R-CNN model using a set of 366 images containing defects. The results demonstrated its effectiveness in explaining the IE Mask R-CNN model's predictions. Overall, the proposed AI-Reasoner provides a solution for improving the performance of AI models in industrial applications that require defect analysis.
Authors: Héctor Carrión, Narges Norouzi
Skin diseases affect millions of people worldwide, across all ethnicities. Increasing diagnosis accessibility requires fair and accurate segmentation and classification of dermatology images. However, the scarcity of annotated medical images, especially for rare diseases and underrepresented skin tones, poses a challenge to the development of fair and accurate models. In this study, we introduce a Fair, Efficient, and Diverse Diffusion-based framework for skin lesion segmentation and malignancy classification. FEDD leverages semantically meaningful feature embeddings learned through a denoising diffusion probabilistic backbone and processes them via linear probes to achieve state-of-the-art performance on Diverse Dermatology Images (DDI). We achieve an improvement in intersection over union of 0.18, 0.13, 0.06, and 0.07 while using only 5%, 10%, 15%, and 20% labeled samples, respectively. Additionally, FEDD trained on 10% of DDI demonstrates malignancy classification accuracy of 81%, 14% higher compared to the state-of-the-art. We showcase high efficiency in data-constrained scenarios while providing fair performance for diverse skin tones and rare malignancy conditions. Our newly annotated DDI segmentation masks and training code can be found on https://github.com/hectorcarrion/fedd.
Authors: Mayug Maniparambil, Chris Vorster, Derek Molloy, Noel Murphy, Kevin McGuinness, Noel E. O'Connor
Contrastive pretrained large Vision-Language Models (VLMs) like CLIP have revolutionized visual representation learning by providing good performance on downstream datasets. VLMs are 0-shot adapted to a downstream dataset by designing prompts that are relevant to the dataset. Such prompt engineering makes use of domain expertise and a validation dataset. Meanwhile, recent developments in generative pretrained models like GPT-4 mean they can be used as advanced internet search tools. They can also be manipulated to provide visual information in any structure. In this work, we show that GPT-4 can be used to generate text that is visually descriptive and how this can be used to adapt CLIP to downstream tasks. We show considerable improvements in 0-shot transfer accuracy on specialized fine-grained datasets like EuroSAT (~7%), DTD (~7%), SUN397 (~4.6%), and CUB (~3.3%) when compared to CLIP's default prompt. We also design a simple few-shot adapter that learns to choose the best possible sentences to construct generalizable classifiers that outperform the recently proposed CoCoOP by ~2% on average and by over 4% on 4 specialized fine-grained datasets. We will release the code, prompts, and auxiliary text dataset upon acceptance.
Authors: Jerome Revaud, Yohann Cabon, Romain Brégier, JongMin Lee, Philippe Weinzaepfel
Scene coordinates regression (SCR), i.e., predicting 3D coordinates for every pixel of a given image, has recently shown promising potential. However, existing methods remain mostly scene-specific or limited to small scenes and thus hardly scale to realistic datasets. In this paper, we propose a new paradigm where a single generic SCR model is trained once to be then deployed to new test scenes, regardless of their scale and without further finetuning. For a given query image, it collects inputs from off-the-shelf image retrieval techniques and Structure-from-Motion databases: a list of relevant database images with sparse pointwise 2D-3D annotations. The model is based on the transformer architecture and can take a variable number of images and sparse 2D-3D annotations as input. It is trained on a few diverse datasets and significantly outperforms other scene regression approaches on several benchmarks, including scene-specific models, for visual localization. In particular, we set a new state of the art on the Cambridge localization benchmark, even outperforming feature-matching-based approaches.
Authors: Eric Schneider, Sushanth Jayanth, Abhisesh Silwal, George Kantor
Robotic pruning of dormant grapevines is an area of active research in order to promote vine balance and grape quality, but so far robotic efforts have largely focused on planar, simplified vines not representative of commercial vineyards. This paper aims to advance the robotic perception capabilities necessary for pruning in denser and more complex vine structures by extending plant skeletonization techniques. The proposed pipeline generates skeletal grapevine models that have lower reprojection error and higher connectivity than baseline algorithms. We also show how 3D and skeletal information enables prediction accuracy of pruning weight for dense vines surpassing prior work, where pruning weight is an important vine metric influencing pruning site selection.
Authors: Yosuke Shinya
Scale-wise evaluation of object detectors is important for real-world applications. However, existing metrics are either coarse or not sufficiently reliable. In this paper, we propose novel scale-wise metrics that strike a balance between fineness and reliability, using a filter bank consisting of triangular and trapezoidal band-pass filters. We conduct experiments with two methods on two datasets and show that the proposed metrics can highlight the differences between the methods and between the datasets. Code is available at https://github.com/shinya7y/UniverseNet .
Authors: Willy Kuo, Diego Rossinelli, Georg Schulz, Roland H. Wenger, Simone Hieber, Bert Müller, Vartan Kurtcuoglu
The performance of machine learning algorithms, when used for segmenting 3D biomedical images, does not reach the level expected based on results achieved with 2D photos. This may be explained by the comparative lack of high-volume, high-quality training datasets, which require state-of-the-art imaging facilities, domain experts for annotation and large computational and personal resources. The HR-Kidney dataset presented in this work bridges this gap by providing 1.7 TB of artefact-corrected synchrotron radiation-based X-ray phase-contrast microtomography images of whole mouse kidneys and validated segmentations of 33 729 glomeruli, which corresponds to a one to two orders of magnitude increase over currently available biomedical datasets. The image sets also contain the underlying raw data, threshold- and morphology-based semi-automatic segmentations of renal vasculature and uriniferous tubules, as well as true 3D manual annotations. We therewith provide a broad basis for the scientific community to build upon and expand in the fields of image processing, data augmentation and machine learning, in particular unsupervised and semi-supervised learning investigations, as well as transfer learning and generative adversarial networks.
Authors: Amir Mohammadian, Foad Ghaderi
Building detection and change detection using remote sensing images can help urban and rescue planning. Moreover, they can be used for building damage assessment after natural disasters. Currently, most of the existing models for building detection use only one image (pre-disaster image) to detect buildings. This is based on the idea that post-disaster images reduce the model's performance because of presence of destroyed buildings. In this paper, we propose a siamese model, called SiamixFormer, which uses pre- and post-disaster images as input. Our model has two encoders and has a hierarchical transformer architecture. The output of each stage in both encoders is given to a temporal transformer for feature fusion in a way that query is generated from pre-disaster images and (key, value) is generated from post-disaster images. To this end, temporal features are also considered in feature fusion. Another advantage of using temporal transformers in feature fusion is that they can better maintain large receptive fields generated by transformer encoders compared with CNNs. Finally, the output of the temporal transformer is given to a simple MLP decoder at each stage. The SiamixFormer model is evaluated on xBD, and WHU datasets, for building detection and on LEVIR-CD and CDD datasets for change detection and could outperform the state-of-the-art.
Authors: Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain fixed at test time. In this work, we challenge this premise with a self-adaptive approach for semantic segmentation that adjusts the inference process to each input sample. Self-adaptation operates on two levels. First, it fine-tunes the parameters of convolutional layers to the input image using consistency regularization. Second, in Batch Normalization layers, self-adaptation interpolates between the training and the reference distribution derived from a single test sample. Despite both techniques being well known in the literature, their combination sets new state-of-the-art accuracy on synthetic-to-real generalization benchmarks. Our empirical study suggests that self-adaptation may complement the established practice of model regularization at training time for improving deep network generalization to out-of-domain data. Our code and pre-trained models are available at https://github.com/visinf/self-adaptive.
Authors: Chawin Sitawarin, Florian Tramèr, Nicholas Carlini
Decision-based attacks construct adversarial examples against a machine learning (ML) model by making only hard-label queries. These attacks have mainly been applied directly to standalone neural networks. However, in practice, ML models are just one component of a larger learning system. We find that by adding a single preprocessor in front of a classifier, state-of-the-art query-based attacks are up to 7$\times$ less effective at attacking a prediction pipeline than at attacking the model alone. We explain this discrepancy by the fact that most preprocessors introduce some notion of invariance to the input space. Hence, attacks that are unaware of this invariance inevitably waste a large number of queries to re-discover or overcome it. We, therefore, develop techniques to (i) reverse-engineer the preprocessor and then (ii) use this extracted information to attack the end-to-end system. Our preprocessors extraction method requires only a few hundred queries, and our preprocessor-aware attacks recover the same efficacy as when attacking the model alone. The code can be found at https://github.com/google-research/preprocessor-aware-black-box-attack.
Authors: Decheng Liu, Zhan Dang, Chunlei Peng, Yu Zheng, Shuang Li, Nannan Wang, Xinbo Gao
With the continuous development of deep learning in the field of image generation models, a large number of vivid forged faces have been generated and spread on the Internet. These high-authenticity artifacts could grow into a threat to society security. Existing face forgery detection methods directly utilize the obtained public shared or centralized data for training but ignore the personal privacy and security issues when personal data couldn't be centralizedly shared in real-world scenarios. Additionally, different distributions caused by diverse artifact types would further bring adverse influences on the forgery detection task. To solve the mentioned problems, the paper proposes a novel generalized residual Federated learning for face Forgery detection (FedForgery). The designed variational autoencoder aims to learn robust discriminative residual feature maps to detect forgery faces (with diverse or even unknown artifact types). Furthermore, the general federated learning strategy is introduced to construct distributed detection model trained collaboratively with multiple local decentralized devices, which could further boost the representation generalization. Experiments conducted on publicly available face forgery detection datasets prove the superior performance of the proposed FedForgery. The designed novel generalized face forgery detection protocols and source code would be publicly available.
Authors: Peng Xing, Hao Tang, Jinhui Tang, Zechao Li
Knowledge Distillation-based Anomaly Detection (KDAD) methods rely on the teacher-student paradigm to detect and segment anomalous regions by contrasting the unique features extracted by both networks. However, existing KDAD methods suffer from two main limitations: 1) the student network can effortlessly replicate the teacher network's representations, and 2) the features of the teacher network serve solely as a ``reference standard" and are not fully leveraged. Toward this end, we depart from the established paradigm and instead propose an innovative approach called Asymmetric Distillation Post-Segmentation (ADPS). Our ADPS employs an asymmetric distillation paradigm that takes distinct forms of the same image as the input of the teacher-student networks, driving the student network to learn discriminating representations for anomalous regions.
Meanwhile, a customized Weight Mask Block (WMB) is proposed to generate a coarse anomaly localization mask that transfers the distilled knowledge acquired from the asymmetric paradigm to the teacher network. Equipped with WMB, the proposed Post-Segmentation Module (PSM) is able to effectively detect and segment abnormal regions with fine structures and clear boundaries. Experimental results demonstrate that the proposed ADPS outperforms the state-of-the-art methods in detecting and segmenting anomalies. Surprisingly, ADPS significantly improves Average Precision (AP) metric by 9% and 20% on the MVTec AD and KolektorSDD2 datasets, respectively.
Authors: Quang-Huy Nguyen, Cuong Q. Nguyen, Dung D. Le, Hieu H. Pham
This paper addresses the few-shot image classification problem, where the classification task is performed on unlabeled query samples given a small amount of labeled support samples only. One major challenge of the few-shot learning problem is the large variety of object visual appearances that prevents the support samples to represent that object comprehensively. This might result in a significant difference between support and query samples, therefore undermining the performance of few-shot algorithms. In this paper, we tackle the problem by proposing Few-shot Cosine Transformer (FS-CT), where the relational map between supports and queries is effectively obtained for the few-shot tasks. The FS-CT consists of two parts, a learnable prototypical embedding network to obtain categorical representations from support samples with hard cases, and a transformer encoder to effectively achieve the relational map from two different support and query samples. We introduce Cosine Attention, a more robust and stable attention module that enhances the transformer module significantly and therefore improves FS-CT performance from 5% to over 20% in accuracy compared to the default scaled dot-product mechanism. Our method performs competitive results in mini-ImageNet, CUB-200, and CIFAR-FS on 1-shot learning and 5-shot learning tasks across backbones and few-shot configurations. We also developed a custom few-shot dataset for Yoga pose recognition to demonstrate the potential of our algorithm for practical application. Our FS-CT with cosine attention is a lightweight, simple few-shot algorithm that can be applied for a wide range of applications, such as healthcare, medical, and security surveillance. The official implementation code of our Few-shot Cosine Transformer is available at https://github.com/vinuni-vishc/Few-Shot-Cosine-Transformer
Authors: Shenghan Su, Lin Gu, Yue Yang, Zenghui Zhang, Tatsuya Harada
The long-standing theory that a colour-naming system evolves under dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies, including analysing four decades of diachronic data from the Nafaanra language. This inspires us to explore whether machine learning could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette; meanwhile the Palette Branch utilises a key-point detection way to find proper colours in the palette among the whole colour space. By interacting with colour annotation, CQFormer is able to balance both the machine vision accuracy and colour perceptual structure such as distinct and stable colour distribution for discovered colour system. Very interestingly, we even observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining high performance in high-level recognition tasks such as classification and detection. Extensive experiments demonstrate the superior performance of our method with extremely low bit-rate colours, showing potential to integrate into quantisation network to quantities from image to network activation. The source code is available at https://github.com/ryeocthiv/CQFormer
Authors: Yushan Han, Hui Zhang, Huifang Li, Yi Jin, Congyan Lang, Yidong Li
Collaborative perception is essential to address occlusion and sensor failure issues in autonomous driving. In recent years, theoretical and experimental investigations of novel works for collaborative perception have increased tremendously. So far, however, few reviews have focused on systematical collaboration modules and large-scale collaborative perception datasets. This work reviews recent achievements in this field to bridge this gap and motivate future research. We start with a brief overview of collaboration schemes. After that, we systematically summarize the collaborative perception methods for ideal scenarios and real-world issues. The former focuses on collaboration modules and efficiency, and the latter is devoted to addressing the problems in actual application. Furthermore, we present large-scale public datasets and summarize quantitative results on these benchmarks. Finally, we highlight gaps and overlook challenges between current academic research and real-world applications. The project page is https://github.com/CatOneTwo/Collaborative-Perception-in-Autonomous-Driving
Authors: Nicolas M. Müller, Simon Roschmann, Shahbaz Khan, Philip Sperl, Konstantin Böttinger
For real-world applications of machine learning (ML), it is essential that models make predictions based on well-generalizing features rather than spurious correlations in the data. The identification of such spurious correlations, also known as shortcuts, is a challenging problem and has so far been scarcely addressed. In this work, we present a novel approach to detect shortcuts in image and audio datasets by leveraging variational autoencoders (VAEs). The disentanglement of features in the latent space of VAEs allows us to discover feature-target correlations in datasets and semi-automatically evaluate them for ML shortcuts. We demonstrate the applicability of our method on several real-world datasets and identify shortcuts that have not been discovered before.
Authors: Ondrej Biza, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi, Gamaleldin F. Elsayed, Aravindh Mahendran, Thomas Kipf
Automatically discovering composable abstractions from raw perceptual data is a long-standing challenge in machine learning. Recent slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress in this direction. However, they typically fall short at adequately capturing spatial symmetries present in the visual world, which leads to sample inefficiency, such as when entangling object appearance and pose. In this paper, we present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We incorporate equivariance to per-object pose transformations into the attention and generation mechanism of Slot Attention by translating, scaling, and rotating position encodings. These changes result in little computational overhead, are easy to implement, and can result in large gains in terms of data efficiency and overall improvements to object discovery. We evaluate our method on a wide range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVRTex, Objects Room and MultiShapeNet, and show promising improvements on the challenging real-world Waymo Open dataset.
Authors: Stefan Thalhammer, Peter Hönig, Jean-Baptiste Weibel, Markus Vincze
Object pose estimation is a non-trivial task that enables robotic manipulation, bin picking, augmented reality, and scene understanding, to name a few use cases. Monocular object pose estimation gained considerable momentum with the rise of high-performing deep learning-based solutions and is particularly interesting for the community since sensors are inexpensive and inference is fast. Prior works establish the comprehensive state of the art for diverse pose estimation problems. Their broad scopes make it difficult to identify promising future directions. We narrow down the scope to the problem of single-shot monocular 6D object pose estimation, which is commonly used in robotics, and thus are able to identify such trends. By reviewing recent publications in robotics and computer vision, the state of the art is established at the union of both fields. Following that, we identify promising research directions in order to help researchers to formulate relevant research ideas and effectively advance the state of the art. Findings include that methods are sophisticated enough to overcome the domain shift and that occlusion handling is a fundamental challenge. We also highlight problems such as novel object pose estimation and challenging materials handling as central challenges to advance robotics.
Authors: Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Roldão, Dzmitry Tsishkou, Cyrille Migniot, Pascal Vasseur, Cédric Demonceaux
With the recent advances in autonomous driving and the decreasing cost of LiDARs, the use of multimodal sensor systems is on the rise. However, in order to make use of the information provided by a variety of complimentary sensors, it is necessary to accurately calibrate them. We take advantage of recent advances in computer graphics and implicit volumetric scene representation to tackle the problem of multi-sensor spatial and temporal calibration. Thanks to a new formulation of the Neural Radiance Field (NeRF) optimization, we are able to jointly optimize calibration parameters along with scene representation based on radiometric and geometric measurements. Our method enables accurate and robust calibration from data captured in uncontrolled and unstructured urban environments, making our solution more scalable than existing calibration solutions. We demonstrate the accuracy and robustness of our method in urban scenes typically encountered in autonomous driving scenarios.
Authors: Lea Bogensperger, Dominik Narnhofer, Filip Ilic, Thomas Pock
Medical image segmentation is a crucial task that relies on the ability to accurately identify and isolate regions of interest in medical images. Thereby, generative approaches allow to capture the statistical properties of segmentation masks that are dependent on the respective structures. In this work we propose a conditional score-based generative modeling framework to represent the signed distance function (SDF) leading to an implicit distribution of segmentation masks. The advantage of leveraging the SDF is a more natural distortion when compared to that of binary masks. By learning the score function of the conditional distribution of SDFs we can accurately sample from the distribution of segmentation masks, allowing for the evaluation of statistical quantities. Thus, this probabilistic representation allows for the generation of uncertainty maps represented by the variance, which can aid in further analysis and enhance the predictive robustness. We qualitatively and quantitatively illustrate competitive performance of the proposed method on a public nuclei and gland segmentation data set, highlighting its potential utility in medical image segmentation applications.
Authors: Shuai Yang, Liming Jiang, Ziwei Liu, Chen Change Loy
Recent advances in face manipulation using StyleGAN have produced impressive results. However, StyleGAN is inherently limited to cropped aligned faces at a fixed image resolution it is pre-trained on. In this paper, we propose a simple and effective solution to this limitation by using dilated convolutions to rescale the receptive fields of shallow layers in StyleGAN, without altering any model parameters. This allows fixed-size small features at shallow layers to be extended into larger ones that can accommodate variable resolutions, making them more robust in characterizing unaligned faces. To enable real face inversion and manipulation, we introduce a corresponding encoder that provides the first-layer feature of the extended StyleGAN in addition to the latent style code. We validate the effectiveness of our method using unaligned face inputs of various resolutions in a diverse set of face manipulation tasks, including facial attribute editing, super-resolution, sketch/mask-to-face translation, and face toonification.
Authors: Saikat Roy, Gregor Koehler, Constantin Ulrich, Michael Baumgartner, Jens Petersen, Fabian Isensee, Paul F. Jaeger, Klaus Maier-Hein
There has been exploding interest in embracing Transformer-based architectures for medical image segmentation. However, the lack of large-scale annotated medical datasets make achieving performances equivalent to those in natural images challenging. Convolutional networks, in contrast, have higher inductive biases and consequently, are easily trainable to high performance. Recently, the ConvNeXt architecture attempted to modernize the standard ConvNet by mirroring Transformer blocks. In this work, we improve upon this to design a modernized and scalable convolutional architecture customized to challenges of data-scarce medical settings. We introduce MedNeXt, a Transformer-inspired large kernel segmentation network which introduces - 1) A fully ConvNeXt 3D Encoder-Decoder Network for medical image segmentation, 2) Residual ConvNeXt up and downsampling blocks to preserve semantic richness across scales, 3) A novel technique to iteratively increase kernel sizes by upsampling small kernel networks, to prevent performance saturation on limited medical data, 4) Compound scaling at multiple levels (depth, width, kernel size) of MedNeXt. This leads to state-of-the-art performance on 4 tasks on CT and MRI modalities and varying dataset sizes, representing a modernized deep architecture for medical image segmentation. Our code is made publicly available at: https://github.com/MIC-DKFZ/MedNeXt.
Authors: Lucas Farndale, Robert Insall, Ke Yuan
Medical imaging technologies are generating increasingly large amounts of high-quality, information-dense data. Despite the progress, practical use of advanced imaging technologies for research and diagnosis remains limited by cost and availability, so information-sparse data such as H&E stains are relied on in practice. The study of diseased tissue requires methods which can leverage these information-dense data to extract more value from routine, information-sparse data. Using self-supervised deep learning, we demonstrate that it is possible to distil knowledge during training from information-dense data into models which only require information-sparse data for inference. This improves downstream classification accuracy on information-sparse data, making it comparable with the fully-supervised baseline. We find substantial effects on the learned representations, and this training process identifies subtle features which otherwise go undetected. This approach enables the design of models which require only routine images, but contain insights from state-of-the-art data, allowing better use of the available resources.
Authors: Ruihai Wu, Chuanruo Ning, Hao Dong
Understanding and manipulating deformable objects (e.g., ropes and fabrics) is an essential yet challenging task with broad applications. Difficulties come from complex states and dynamics, diverse configurations and high-dimensional action space of deformable objects. Besides, the manipulation tasks usually require multiple steps to accomplish, and greedy policies may easily lead to local optimal states. Existing studies usually tackle this problem using reinforcement learning or imitating expert demonstrations, with limitations in modeling complex states or requiring hand-crafted expert policies. In this paper, we study deformable object manipulation using dense visual affordance, with generalization towards diverse states, and propose a novel kind of foresightful dense affordance, which avoids local optima by estimating states' values for long-term manipulation. We propose a framework for learning this representation, with novel designs such as multi-stage stable learning and efficient self-supervised data collection without experts. Experiments demonstrate the superiority of our proposed foresightful dense affordance. Project page: https://hyperplane-lab.github.io/DeformableAffordance
Authors: Rui Yang, Lin Song, Yixiao Ge, Xiu Li
Box-supervised instance segmentation has gained much attention as it requires only simple box annotations instead of costly mask or polygon annotations. However, existing box-supervised instance segmentation models mainly focus on mask-based frameworks. We propose a new end-to-end training technique, termed BoxSnake, to achieve effective polygonal instance segmentation using only box annotations for the first time. Our method consists of two loss functions: (1) a point-based unary loss that constrains the bounding box of predicted polygons to achieve coarse-grained segmentation; and (2) a distance-aware pairwise loss that encourages the predicted polygons to fit the object boundaries. Compared with the mask-based weakly-supervised methods, BoxSnake further reduces the performance gap between the predicted segmentation and the bounding box, and shows significant superiority on the Cityscapes dataset.
Authors: Ludwig Bothmann, Lisa Wimmer, Omid Charrakh, Tobias Weber, Hendrik Edelhoff, Wibke Peters, Hien Nguyen, Caryl Benjamin, Annette Menzel
Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence systems can take over this task but usually need a large number of already-labeled training images to achieve sufficient performance. This requirement necessitates human expert labor and poses a particular challenge for projects with few cameras or short durations. We propose a label-efficient learning strategy that enables researchers with small or medium-sized image databases to leverage the potential of modern machine learning, thus freeing crucial resources for subsequent analyses.
Our methodological proposal is two-fold: (1) We improve current strategies of combining object detection and image classification by tuning the hyperparameters of both models. (2) We provide an active learning (AL) system that allows training deep learning models very efficiently in terms of required human-labeled training images. We supply a software package that enables researchers to use these methods directly and thereby ensure the broad applicability of the proposed framework in ecological practice.
We show that our tuning strategy improves predictive performance. We demonstrate how the AL pipeline reduces the amount of pre-labeled data needed to achieve a specific predictive performance and that it is especially valuable for improving out-of-sample predictive performance.
We conclude that the combination of tuning and AL increases predictive performance substantially. Furthermore, we argue that our work can broadly impact the community through the ready-to-use software package provided. Finally, the publication of our models tailored to European wildlife data enriches existing model bases mostly trained on data from Africa and North America.
Authors: Jie Chen, Hua Mao, Wai Lok Woo, Xi Peng
Multiview clustering (MVC) aims to reveal the underlying structure of multiview data by categorizing data samples into clusters. Deep learning-based methods exhibit strong feature learning capabilities on large-scale datasets. For most existing deep MVC methods, exploring the invariant representations of multiple views is still an intractable problem. In this paper, we propose a cross-view contrastive learning (CVCL) method that learns view-invariant representations and produces clustering results by contrasting the cluster assignments among multiple views. Specifically, we first employ deep autoencoders to extract view-dependent features in the pretraining stage. Then, a cluster-level CVCL strategy is presented to explore consistent semantic label information among the multiple views in the fine-tuning stage. Thus, the proposed CVCL method is able to produce more discriminative cluster assignments by virtue of this learning strategy. Moreover, we provide a theoretical analysis of soft cluster assignment alignment. Extensive experimental results obtained on several datasets demonstrate that the proposed CVCL method outperforms several state-of-the-art approaches.
Authors: Stefanos-Iordanis Papadopoulos, Christos Koutlis, Symeon Papadopoulos, Panagiotis C. Petrantonakis
Multimedia content has become ubiquitous on social media platforms, leading to the rise of multimodal misinformation (MM) and the urgent need for effective strategies to detect and prevent its spread. In recent years, the challenge of multimodal misinformation detection (MMD) has garnered significant attention by researchers and has mainly involved the creation of annotated, weakly annotated, or synthetically generated training datasets, along with the development of various deep learning MMD models. However, the problem of unimodal bias in MMD benchmarks -- where biased or unimodal methods outperform their multimodal counterparts on an inherently multimodal task -- has been overlooked. In this study, we systematically investigate and identify the presence of unimodal bias in widely-used MMD benchmarks (VMU-Twitter, COSMOS), raising concerns about their suitability for reliable evaluation. To address this issue, we introduce the "VERification of Image-TExtpairs" (VERITE) benchmark for MMD which incorporates real-world data, excludes "asymmetric multimodal misinformation" and utilizes "modality balancing". We conduct an extensive comparative study with a Transformer-based architecture that shows the ability of VERITE to effectively address unimodal bias, rendering it a robust evaluation framework for MMD. Furthermore, we introduce a new method -- termed Crossmodal HArd Synthetic MisAlignment (CHASMA) -- for generating realistic synthetic training data that preserve crossmodal relations between legitimate images and false human-written captions. By leveraging CHASMA in the training process, we observe consistent and notable improvements in predictive performance on VERITE; with a 9.2% increase in accuracy. We release our code at: https://github.com/stevejpapad/image-text-verification
Most generic object detectors are mainly built for standard object detection tasks such as COCO and PASCAL VOC. They might not work well and/or efficiently on tasks of other domains consisting of images that are visually different from standard datasets. To this end, many advances have been focused on adapting a general-purposed object detector with limited domain-specific designs. However, designing a successful task-specific detector requires extraneous manual experiments and parameter tuning through trial and error. In this paper, we first propose and examine a fully-automatic pipeline to design a fully-specialized detector (FSD) which mainly incorporates a neural-architectural-searched model by exploring ideal network structures over the backbone and task-specific head. On the DeepLesion dataset, extensive results show that FSD can achieve 3.1 mAP gain while using approximately 40% fewer parameters on binary lesion detection task and improved the mAP by around 10% on multi-type lesion detection task via our region-aware graph modeling compared with existing general-purposed medical lesion detection networks.
Authors: Xiaofeng Liu, Jiaxin Gao, Yaohua Liu, Risheng Liu, Nenggan Zheng
Recently significant progress has been made in human action recognition and behavior prediction using deep learning techniques, leading to improved vision-based semantic understanding. However, there is still a lack of high-quality motion datasets for small bio-robotics, which presents more challenging scenarios for long-term movement prediction and behavior control based on third-person observation. In this study, we introduce RatPose, a bio-robot motion prediction dataset constructed by considering the influence factors of individuals and environments based on predefined annotation rules. To enhance the robustness of motion prediction against these factors, we propose a Dual-stream Motion-Scenario Decoupling (\textit{DMSD}) framework that effectively separates scenario-oriented and motion-oriented features and designs a scenario contrast loss and motion clustering loss for overall training. With such distinctive architecture, the dual-branch feature flow information is interacted and compensated in a decomposition-then-fusion manner. Moreover, we demonstrate significant performance improvements of the proposed \textit{DMSD} framework on different difficulty-level tasks. We also implement long-term discretized trajectory prediction tasks to verify the generalization ability of the proposed dataset.
Authors: Zolnamar Dorjsembe, Hsing-Kuo Pao, Sodtavilan Odonchimed, Furen Xiao
The demand for artificial intelligence (AI) in healthcare is rapidly increasing. However, significant challenges arise from data scarcity and privacy concerns, particularly in medical imaging. While existing generative models have achieved success in image synthesis and image-to-image translation tasks, there remains a gap in the generation of 3D semantic medical images. To address this gap, we introduce Med-DDPM, a diffusion model specifically designed for semantic 3D medical image synthesis, effectively tackling data scarcity and privacy issues. The novelty of Med-DDPM lies in its incorporation of semantic conditioning, enabling precise control during the image generation process. Our model outperforms Generative Adversarial Networks (GANs) in terms of stability and performance, generating diverse and anatomically coherent images with high visual fidelity. Comparative analysis against state-of-the-art augmentation techniques demonstrates that Med-DDPM produces comparable results, highlighting its potential as a data augmentation tool for enhancing model accuracy. In conclusion, Med-DDPM pioneers 3D semantic medical image synthesis by delivering high-quality and anatomically coherent images. Furthermore, the integration of semantic conditioning with Med-DDPM holds promise for image anonymization in the field of biomedical imaging, showcasing the capabilities of the model in addressing challenges related to data scarcity and privacy concerns.
Authors: Yi Gu, Yoshito Otake, Keisuke Uemura, Masaki Takao, Mazen Soufi, Yuta Hiasa, Hugues Talbot, Seiji Okata, Nobuhiko Sugano, Yoshinobu Sato
Musculoskeletal diseases such as sarcopenia and osteoporosis are major obstacles to health during aging. Although dual-energy X-ray absorptiometry (DXA) and computed tomography (CT) can be used to evaluate musculoskeletal conditions, frequent monitoring is difficult due to the cost and accessibility (as well as high radiation exposure in the case of CT). We propose a method (named MSKdeX) to estimate fine-grained muscle properties from a plain X-ray image, a low-cost, low-radiation, and highly accessible imaging modality, through musculoskeletal decomposition leveraging fine-grained segmentation in CT. We train a multi-channel quantitative image translation model to decompose an X-ray image into projections of CT of individual muscles to infer the lean muscle mass and muscle volume. We propose the object-wise intensity-sum loss, a simple yet surprisingly effective metric invariant to muscle deformation and projection direction, utilizing information in CT and X-ray images collected from the same patient. While our method is basically an unpaired image-to-image translation, we also exploit the nature of the bone's rigidity, which provides the paired data through 2D-3D rigid registration, adding strong pixel-wise supervision in unpaired training. Through the evaluation using a 539-patient dataset, we showed that the proposed method significantly outperformed conventional methods. The average Pearson correlation coefficient between the predicted and CT-derived ground truth metrics was increased from 0.460 to 0.863. We believe our method opened up a new musculoskeletal diagnosis method and has the potential to be extended to broader applications in multi-channel quantitative image translation tasks. Our source code will be released soon.
Authors: Yixiao Zhang, Xinyi Li, Huimiao Chen, Alan Yuille, Yaoyao Liu, Zongwei Zhou
The ability to dynamically extend a model to new data and classes is critical for multiple organ and tumor segmentation. However, due to privacy regulations, accessing previous data and annotations can be problematic in the medical domain. This poses a significant barrier to preserving the high segmentation accuracy of the old classes when learning from new classes because of the catastrophic forgetting problem. In this paper, we first empirically demonstrate that simply using high-quality pseudo labels can fairly mitigate this problem in the setting of organ segmentation. Furthermore, we put forward an innovative architecture designed specifically for continuous organ and tumor segmentation, which incurs minimal computational overhead. Our proposed design involves replacing the conventional output layer with a suite of lightweight, class-specific heads, thereby offering the flexibility to accommodate newly emerging classes. These heads enable independent predictions for newly introduced and previously learned classes, effectively minimizing the impact of new classes on old ones during the course of continual learning. We further propose incorporating Contrastive Language-Image Pretraining (CLIP) embeddings into the organ-specific heads. These embeddings encapsulate the semantic information of each class, informed by extensive image-text co-training. The proposed method is evaluated on both in-house and public abdominal CT datasets under organ and tumor segmentation tasks. Empirical results suggest that the proposed design improves the segmentation performance of a baseline neural network on newly-introduced and previously-learned classes along the learning trajectory.
Authors: Shuo Li, Mehrdad Yaghoobi
Hyperspectral Image (HSI)s cover hundreds or thousands of narrow spectral bands, conveying a wealth of spatial and spectral information. However, due to the instrumental errors and the atmospheric changes, the HSI obtained in practice are often contaminated by noise and dead pixels(lines), resulting in missing information that may severely compromise the subsequent applications. We introduce here a novel HSI missing pixel prediction algorithm, called Low Rank and Sparsity Constraint Plug-and-Play (LRS-PnP). It is shown that LRS-PnP is able to predict missing pixels and bands even when all spectral bands of the image are missing. The proposed LRS-PnP algorithm is further extended to a self-supervised model by combining the LRS-PnP with the Deep Image Prior (DIP), called LRS-PnP-DIP. In a series of experiments with real data, It is shown that the LRS-PnP-DIP either achieves state-of-the-art inpainting performance compared to other learning-based methods, or outperforms them.
Authors: Junlong Cheng, Chengrui Gao, Fengjie Wang, Min Zhu
Recently, U-shaped networks have dominated the field of medical image segmentation due to their simple and easily tuned structure. However, existing U-shaped segmentation networks: 1) mostly focus on designing complex self-attention modules to compensate for the lack of long-term dependence based on convolution operation, which increases the overall number of parameters and computational complexity of the network; 2) simply fuse the features of encoder and decoder, ignoring the connection between their spatial locations. In this paper, we rethink the above problem and build a lightweight medical image segmentation network, called SegNetr. Specifically, we introduce a novel SegNetr block that can perform local-global interactions dynamically at any stage and with only linear complexity. At the same time, we design a general information retention skip connection (IRSC) to preserve the spatial location information of encoder features and achieve accurate fusion with the decoder features. We validate the effectiveness of SegNetr on four mainstream medical image segmentation datasets, with 59\% and 76\% fewer parameters and GFLOPs than vanilla U-Net, while achieving segmentation performance comparable to state-of-the-art methods. Notably, the components proposed in this paper can be applied to other U-shaped networks to improve their segmentation performance.
Authors: Paolo Soleni, Wouter B. Verschoof-van der Vaart, Žiga Kokalj, Arianna Traviglia, Marco Fiorucci
When applying deep learning to remote sensing data in archaeological research, a notable obstacle is the limited availability of suitable datasets for training models. The application of transfer learning is frequently employed to mitigate this drawback. However, there is still a need to explore its effectiveness when applied across different archaeological datasets. This paper compares the performance of various transfer learning configurations using two semantic segmentation deep neural networks on two LiDAR datasets. The experimental results indicate that transfer learning-based approaches in archaeology can lead to performance improvements, although a systematic enhancement has not yet been observed. We provide specific insights about the validity of such techniques that can serve as a baseline for future works.
Authors: Haoxuan Che, Yuhan Cheng, Haibo Jin, Hao Chen
Diabetic Retinopathy (DR) is a common complication of diabetes and a leading cause of blindness worldwide. Early and accurate grading of its severity is crucial for disease management. Although deep learning has shown great potential for automated DR grading, its real-world deployment is still challenging due to distribution shifts among source and target domains, known as the domain generalization problem. Existing works have mainly attributed the performance degradation to limited domain shifts caused by simple visual discrepancies, which cannot handle complex real-world scenarios. Instead, we present preliminary evidence suggesting the existence of three-fold generalization issues: visual and degradation style shifts, diagnostic pattern diversity, and data imbalance. To tackle these issues, we propose a novel unified framework named Generalizable Diabetic Retinopathy Grading Network (GDRNet). GDRNet consists of three vital components: fundus visual-artifact augmentation (FundusAug), dynamic hybrid-supervised loss (DahLoss), and domain-class-aware re-balancing (DCR). FundusAug generates realistic augmented images via visual transformation and image degradation, while DahLoss jointly leverages pixel-level consistency and image-level semantics to capture the diverse diagnostic patterns and build generalizable feature representations. Moreover, DCR mitigates the data imbalance from a domain-class view and avoids undesired over-emphasis on rare domain-class pairs. Finally, we design a publicly available benchmark for fair evaluations. Extensive comparison experiments against advanced methods and exhaustive ablation studies demonstrate the effectiveness and generalization ability of GDRNet.
Authors: Mingyuan Liu, Lu Xu, Jicong Zhang
Fueled by deep learning, computer-aided diagnosis achieves huge advances. However, out of controlled lab environments, algorithms could face multiple challenges. Open set recognition (OSR), as an important one, states that categories unseen in training could appear in testing. In medical fields, it could derive from incompletely collected training datasets and the constantly emerging new or rare diseases. OSR requires an algorithm to not only correctly classify known classes, but also recognize unknown classes and forward them to experts for further diagnosis. To tackle OSR, we assume that known classes could densely occupy small parts of the embedding space and the remaining sparse regions could be recognized as unknowns. Following it, we propose Open Margin Cosine Loss (OMCL) unifying two mechanisms. The former, called Margin Loss with Adaptive Scale (MLAS), introduces angular margin for reinforcing intra-class compactness and inter-class separability, together with an adaptive scaling factor to strengthen the generalization capacity. The latter, called Open-Space Suppression (OSS), opens the classifier by recognizing sparse embedding space as unknowns using proposed feature space descriptors. Besides, since medical OSR is still a nascent field, two publicly available benchmark datasets are proposed for comparison. Extensive ablation studies and feature visualization demonstrate the effectiveness of each design. Compared with state-of-the-art methods, MLAS achieves superior performances, measured by ACC, AUROC, and OSCR.
Authors: Marzieh Oghbaie, Teresa Araujo, Taha Emre, Ursula Schmidt-Erfurth, Hrvoje Bogunovic
The automatic classification of 3D medical data is memory-intensive. Also, variations in the number of slices between samples is common. Na\"ive solutions such as subsampling can solve these problems, but at the cost of potentially eliminating relevant diagnosis information. Transformers have shown promising performance for sequential data analysis. However, their application for long sequences is data, computationally, and memory demanding. In this paper, we propose an end-to-end Transformer-based framework that allows to classify volumetric data of variable length in an efficient fashion. Particularly, by randomizing the input volume-wise resolution(#slices) during training, we enhance the capacity of the learnable positional embedding assigned to each volume slice. Consequently, the accumulated positional information in each positional embedding can be generalized to the neighbouring slices, even for high-resolution volumes at the test time. By doing so, the model will be more robust to variable volume length and amenable to different computational budgets. We evaluated the proposed approach in retinal OCT volume classification and achieved 21.96% average improvement in balanced accuracy on a 9-class diagnostic task, compared to state-of-the-art video transformers. Our findings show that varying the volume-wise resolution of the input during training results in more informative volume representation as compared to training with fixed number of slices per volume.
Authors: Mritula Chandrasekaran, Jarek Francik, Dimitrios Makris
This paper focuses on addressing the problem of data scarcity for gait analysis. Standard augmentation methods may produce gait sequences that are not consistent with the biomechanical constraints of human walking. To address this issue, we propose a novel framework for gait data augmentation by using OpenSIM, a physics-based simulator, to synthesize biomechanically plausible walking sequences. The proposed approach is validated by augmenting the WBDS and CASIA-B datasets and then training gait-based classifiers for 3D gender gait classification and 2D gait person identification respectively. Experimental results indicate that our augmentation approach can improve the performance of model-based gait classifiers and deliver state-of-the-art results for gait-based person identification with an accuracy of up to 96.11% on the CASIA-B dataset.
Authors: Jinhong Wang, Yi Cheng, Jintai Chen, Tingting Chen, Danny Chen, Jian Wu
Ordinal regression refers to classifying object instances into ordinal categories. It has been widely studied in many scenarios, such as medical disease grading, movie rating, etc. Known methods focused only on learning inter-class ordinal relationships, but still incur limitations in distinguishing adjacent categories thus far. In this paper, we propose a simple sequence prediction framework for ordinal regression called Ord2Seq, which, for the first time, transforms each ordinal category label into a special label sequence and thus regards an ordinal regression task as a sequence prediction process. In this way, we decompose an ordinal regression task into a series of recursive binary classification steps, so as to subtly distinguish adjacent categories. Comprehensive experiments show the effectiveness of distinguishing adjacent categories for performance improvement and our new approach exceeds state-of-the-art performances in four different scenarios. Codes are available at https://github.com/wjh892521292/Ord2Seq.
Authors: Hao Yang, Liyuan Pan, Yan Yang, Miaomiao Liu
Recovering sharp images from dual-pixel (DP) pairs with disparity-dependent blur is a challenging task.~Existing blur map-based deblurring methods have demonstrated promising results. In this paper, we propose, to the best of our knowledge, the first framework to introduce the contrastive language-image pre-training framework (CLIP) to achieve accurate blur map estimation from DP pairs unsupervisedly. To this end, we first carefully design text prompts to enable CLIP to understand blur-related geometric prior knowledge from the DP pair. Then, we propose a format to input stereo DP pair to the CLIP without any fine-tuning, where the CLIP is pre-trained on monocular images. Given the estimated blur map, we introduce a blur-prior attention block, a blur-weighting loss and a blur-aware loss to recover the all-in-focus image. Our method achieves state-of-the-art performance in extensive experiments.
Authors: Hugo Latapie, Kristinn R. Thorisson, Shan Yu, Vahagn Petrosyan, Patrick Hammer, Pei Wang, Brandon Kynoch, Hanning Chen, Tangrui Li
Traditional computer vision models often require extensive manual effort for data acquisition, annotation and validation, particularly when detecting subtle behavioral nuances or events. The difficulty in distinguishing routine behaviors from potential risks in real-world applications, such as differentiating routine shopping from potential shoplifting, further complicates the process. Moreover, these models may demonstrate high false positive rates and imprecise event detection when exposed to real-world scenarios that differ significantly from the conditions of the training data.
To overcome these hurdles, we present Ethosight, a novel zero-shot computer vision system. Ethosight initiates with a clean slate based on user requirements and semantic knowledge of interest. Using localized label affinity calculations and a reasoning-guided iterative learning loop, Ethosight infers scene details and iteratively refines the label set. Reasoning mechanisms can be derived from large language models like GPT4, symbolic reasoners like OpenNARS\cite{wang2013}\cite{wang2006}, or hybrid systems.
Our evaluations demonstrate Ethosight's efficacy across 40 complex use cases, spanning domains such as health, safety, and security. Detailed results and case studies within the main body of this paper and an appendix underscore a promising trajectory towards enhancing the adaptability and resilience of computer vision models in detecting and extracting subtle and nuanced behaviors.
Authors: Sahar Almahfouz Nasser, Nihar Gupte, Amit Sethi
Retinal image matching plays a crucial role in monitoring disease progression and treatment response. However, datasets with matched keypoints between temporally separated pairs of images are not available in abundance to train transformer-based model. We propose a novel approach based on reverse knowledge distillation to train large models with limited data while preventing overfitting. Firstly, we propose architectural modifications to a CNN-based semi-supervised method called SuperRetina that help us improve its results on a publicly available dataset. Then, we train a computationally heavier model based on a vision transformer encoder using the lighter CNN-based model, which is counter-intuitive in the field knowledge-distillation research where training lighter models based on heavier ones is the norm. Surprisingly, such reverse knowledge distillation improves generalization even further. Our experiments suggest that high-dimensional fitting in representation space may prevent overfitting unlike training directly to match the final output. We also provide a public dataset with annotations for retinal image keypoint detection and matching to help the research community develop algorithms for retinal image applications.
Authors: Jiachun Pan, Jun Hao Liew, Vincent Y. F. Tan, Jiashi Feng, Hanshu Yan
Existing customization methods require access to multiple reference examples to align pre-trained diffusion probabilistic models (DPMs) with user-provided concepts. This paper aims to address the challenge of DPM customization when the only available supervision is a differentiable metric defined on the generated contents. Since the sampling procedure of DPMs involves recursive calls to the denoising UNet, na\"ive gradient backpropagation requires storing the intermediate states of all iterations, resulting in extremely high memory consumption. To overcome this issue, we propose a novel method AdjointDPM, which first generates new samples from diffusion models by solving the corresponding probability-flow ODEs. It then uses the adjoint sensitivity method to backpropagate the gradients of the loss to the models' parameters (including conditioning signals, network weights, and initial noises) by solving another augmented ODE. To reduce numerical errors in both the forward generation and gradient backpropagation processes, we further reparameterize the probability-flow ODE and augmented ODE as simple non-stiff ODEs using exponential integration. Finally, we demonstrate the effectiveness of AdjointDPM on three interesting tasks: converting visual effects into identification text embeddings, finetuning DPMs for specific types of stylization, and optimizing initial noise to generate adversarial samples for security auditing.
Authors: Guoqiang Zhang, J. P. Lewis, W. Bastiaan Kleijn
Recently, different methods have been proposed to address the inconsistency issue of DDIM inversion to enable image editing, such as EDICT \cite{Wallace23EDICT} and Null-text inversion \cite{Mokady23NullTestInv}. However, the above methods introduce considerable computational overhead. In this paper, we propose a new technique, named \emph{bi-directional integration approximation} (BDIA), to perform exact diffusion inversion with neglible computational overhead. Suppose we would like to estimate the next diffusion state $\boldsymbol{z}_{i-1}$ at timestep $t_i$ with the historical information $(i,\boldsymbol{z}_i)$ and $(i+1,\boldsymbol{z}_{i+1})$. We first obtain the estimated Gaussian noise $\hat{\boldsymbol{\epsilon}}(\boldsymbol{z}_i,i)$, and then apply the DDIM update procedure twice for approximating the ODE integration over the next time-slot $[t_i, t_{i-1}]$ in the forward manner and the previous time-slot $[t_i, t_{t+1}]$ in the backward manner. The DDIM step for the previous time-slot is used to refine the integration approximation made earlier when computing $\boldsymbol{z}_i$. One nice property with BDIA-DDIM is that the update expression for $\boldsymbol{z}_{i-1}$ is a linear combination of $(\boldsymbol{z}_{i+1}, \boldsymbol{z}_i, \hat{\boldsymbol{\epsilon}}(\boldsymbol{z}_i,i))$. This allows for exact backward computation of $\boldsymbol{z}_{i+1}$ given $(\boldsymbol{z}_i, \boldsymbol{z}_{i-1})$, thus leading to exact diffusion inversion. Experiments on both image reconstruction and image editing were conducted, confirming our statement. BDIA can also be applied to improve the performance of other ODE solvers in addition to DDIM. In our work, it is found that applying BDIA to the EDM sampling procedure produces slightly better FID score over CIFAR10.
Authors: R. El Jurdi, G. Varoquaux, O. Colliot
Medical segmentation models are evaluated empirically. As such an evaluation is based on a limited set of example images, it is unavoidably noisy. Beyond a mean performance measure, reporting confidence intervals is thus crucial. However, this is rarely done in medical image segmentation. The width of the confidence interval depends on the test set size and on the spread of the performance measure (its standard-deviation across of the test set). For classification, many test images are needed to avoid wide confidence intervals. Segmentation, however, has not been studied, and it differs by the amount of information brought by a given test image. In this paper, we study the typical confidence intervals in medical image segmentation. We carry experiments on 3D image segmentation using the standard nnU-net framework, two datasets from the Medical Decathlon challenge and two performance measures: the Dice accuracy and the Hausdorff distance. We show that the parametric confidence intervals are reasonable approximations of the bootstrap estimates for varying test set sizes and spread of the performance metric. Importantly, we show that the test size needed to achieve a given precision is often much lower than for classification tasks. Typically, a 1% wide confidence interval requires about 100-200 test samples when the spread is low (standard-deviation around 3%). More difficult segmentation tasks may lead to higher spreads and require over 1000 samples.