Authors: Anjith George, Sebastien Marcel
Heterogeneous Face Recognition (HFR) aims to match face images across different domains, such as thermal and visible spectra, expanding the applicability of Face Recognition (FR) systems to challenging scenarios. However, the domain gap and limited availability of large-scale datasets in the target domain make training robust and invariant HFR models from scratch difficult. In this work, we treat different modalities as distinct styles and propose a framework to adapt feature maps, bridging the domain gap. We introduce a novel Conditional Adaptive Instance Modulation (CAIM) module that can be integrated into pre-trained FR networks, transforming them into HFR networks. The CAIM block modulates intermediate feature maps, to adapt the style of the target modality effectively bridging the domain gap. Our proposed method allows for end-to-end training with a minimal number of paired samples. We extensively evaluate our approach on multiple challenging benchmarks, demonstrating superior performance compared to state-of-the-art methods. The source code and protocols for reproducing the findings will be made publicly available.
Authors: Deressa Wodajo, Solomon Atnafu, Zahid Akhtar
Deepfakes have raised significant concerns due to their potential to spread false information and compromise digital media integrity. In this work, we propose a Generative Convolutional Vision Transformer (GenConViT) for deepfake video detection. Our model combines ConvNeXt and Swin Transformer models for feature extraction, and it utilizes Autoencoder and Variational Autoencoder to learn from the latent data distribution. By learning from the visual artifacts and latent data distribution, GenConViT achieves improved performance in detecting a wide range of deepfake videos. The model is trained and evaluated on DFDC, FF++, DeepfakeTIMIT, and Celeb-DF v2 datasets, achieving high classification accuracy, F1 scores, and AUC values. The proposed GenConViT model demonstrates robust performance in deepfake video detection, with an average accuracy of 95.8% and an AUC value of 99.3% across the tested datasets. Our proposed model addresses the challenge of generalizability in deepfake detection by leveraging visual and latent features and providing an effective solution for identifying a wide range of fake videos while preserving media integrity. The code for GenConViT is available at https://github.com/erprogs/GenConViT.
Authors: Neel Dey, S. Mazdak Abulnaga, Benjamin Billot, Esra Abaci Turk, P. Ellen Grant, Adrian V. Dalca, Polina Golland
Star-convex shapes arise across bio-microscopy and radiology in the form of nuclei, nodules, metastases, and other units. Existing instance segmentation networks for such structures train on densely labeled instances for each dataset, which requires substantial and often impractical manual annotation effort. Further, significant reengineering or finetuning is needed when presented with new datasets and imaging modalities due to changes in contrast, shape, orientation, resolution, and density. We present AnyStar, a domain-randomized generative model that simulates synthetic training data of blob-like objects with randomized appearance, environments, and imaging physics to train general-purpose star-convex instance segmentation networks. As a result, networks trained using our generative model do not require annotated images from unseen datasets. A single network trained on our synthesized data accurately 3D segments C. elegans and P. dumerilii nuclei in fluorescence microscopy, mouse cortical nuclei in micro-CT, zebrafish brain nuclei in EM, and placental cotyledons in human fetal MRI, all without any retraining, finetuning, transfer learning, or domain adaptation. Code is available at https://github.com/neel-dey/AnyStar.
Authors: Jorge Gonzalez-Zapata, Francisco Lopez-Tiro, Elias Villalvazo-Avila, Daniel Flores-Araiza, Jacques Hubert, Andres Mendez-Vazquez, Gilberto Ochoa-Ruiz, Christian Daul
Several Deep Learning (DL) methods have recently been proposed for an automated identification of kidney stones during an ureteroscopy to enable rapid therapeutic decisions. Even if these DL approaches led to promising results, they are mainly appropriate for kidney stone types for which numerous labelled data are available. However, only few labelled images are available for some rare kidney stone types. This contribution exploits Deep Metric Learning (DML) methods i) to handle such classes with few samples, ii) to generalize well to out of distribution samples, and iii) to cope better with new classes which are added to the database. The proposed Guided Deep Metric Learning approach is based on a novel architecture which was designed to learn data representations in an improved way. The solution was inspired by Few-Shot Learning (FSL) and makes use of a teacher-student approach. The teacher model (GEMINI) generates a reduced hypothesis space based on prior knowledge from the labeled data, and is used it as a guide to a student model (i.e., ResNet50) through a Knowledge Distillation scheme. Extensive tests were first performed on two datasets separately used for the recognition, namely a set of images acquired for the surfaces of the kidney stone fragments, and a set of images of the fragment sections. The proposed DML-approach improved the identification accuracy by 10% and 12% in comparison to DL-methods and other DML-approaches, respectively. Moreover, model embeddings from the two dataset types were merged in an organized way through a multi-view scheme to simultaneously exploit the information of surface and section fragments. Test with the resulting mixed model improves the identification accuracy by at least 3% and up to 30% with respect to DL-models and shallow machine learning methods, respectively.
Authors: He Huang, Jagadeesh Balam, Boris Ginsburg
We study speech intent classification and slot filling (SICSF) by proposing to use an encoder pretrained on speech recognition (ASR) to initialize an end-to-end (E2E) Conformer-Transformer model, which achieves the new state-of-the-art results on the SLURP dataset, with 90.14% intent accuracy and 82.27% SLURP-F1. We compare our model with encoders pretrained on self-supervised learning (SSL), and show that ASR pretraining is much more effective than SSL for SICSF. To explore parameter efficiency, we freeze the encoder and add Adapter modules, and show that parameter efficiency is only achievable with an ASR-pretrained encoder, while the SSL encoder needs full finetuning to achieve comparable results. In addition, we provide an in-depth comparison on end-to-end models versus cascading models (ASR+NLU), and show that E2E models are better than cascaded models unless an oracle ASR model is provided. Last but not least, our model is the first E2E model that achieves the same performance as cascading models with oracle ASR. Code, checkpoints and configs are available.
Authors: Yiren Jian, Chongyang Gao, Soroush Vosoughi
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current paradigm uses visual features as prompts to guide language models, with a focus on determining the most relevant visual features for corresponding text. Our approach diverges by concentrating on the language component, specifically identifying the optimal prompts to align with visual features. We introduce the Prompt-Transformer (P-Former), a model that predicts these ideal prompts, which is trained exclusively on linguistic data, bypassing the need for image-text pairings. This strategy subtly bifurcates the end-to-end VL training process into an additional, separate stage. Our experiments reveal that our framework significantly enhances the performance of a robust image-to-text baseline (BLIP-2), and effectively narrows the performance gap between models trained with either 4M or 129M image-text pairs. Importantly, our framework is modality-agnostic and flexible in terms of architectural design, as validated by its successful application in a video learning task using varied base modules. The code is available at https://github.com/yiren-jian/BLIText
Authors: Runwei Guan, Shanliang Yao, Xiaohui Zhu, Ka Lok Man, Eng Gee Lim, Jeremy Smith, Yong Yue, Yutao Yue
Current perception models for different tasks usually exist in modular forms on Unmanned Surface Vehicles (USVs), which infer extremely slowly in parallel on edge devices, causing the asynchrony between perception results and USV position, and leading to error decisions of autonomous navigation. Compared with Unmanned Ground Vehicles (UGVs), the robust perception of USVs develops relatively slowly. Moreover, most current multi-task perception models are huge in parameters, slow in inference and not scalable. Oriented on this, we propose Achelous, a low-cost and fast unified panoptic perception framework for water-surface perception based on the fusion of a monocular camera and 4D mmWave radar. Achelous can simultaneously perform five tasks, detection and segmentation of visual targets, drivable-area segmentation, waterline segmentation and radar point cloud segmentation. Besides, models in Achelous family, with less than around 5 million parameters, achieve about 18 FPS on an NVIDIA Jetson AGX Xavier, 11 FPS faster than HybridNets, and exceed YOLOX-Tiny and Segformer-B0 on our collected dataset about 5 mAP$_{\text{50-95}}$ and 0.7 mIoU, especially under situations of adverse weather, dark environments and camera failure. To our knowledge, Achelous is the first comprehensive panoptic perception framework combining vision-level and point-cloud-level tasks for water-surface perception. To promote the development of the intelligent transportation community, we release our codes in \url{https://github.com/GuanRunwei/Achelous}.
Authors: Minseok Seo, Youngtack Oh, Doyi Kim, Dongmin Kang, Yeji Choi
Driven by rapid climate change, the frequency and intensity of flood events are increasing. Electro-Optical (EO) satellite imagery is commonly utilized for rapid response. However, its utilities in flood situations are hampered by issues such as cloud cover and limitations during nighttime, making accurate assessment of damage challenging. Several alternative flood detection techniques utilizing Synthetic Aperture Radar (SAR) data have been proposed. Despite the advantages of SAR over EO in the aforementioned situations, SAR presents a distinct drawback: human analysts often struggle with data interpretation. To tackle this issue, this paper introduces a novel framework, Diffusion-Based SAR to EO Image Translation (DSE). The DSE framework converts SAR images into EO images, thereby enhancing the interpretability of flood insights for humans. Experimental results on the Sen1Floods11 and SEN12-FLOOD datasets confirm that the DSE framework not only delivers enhanced visual information but also improves performance across all tested flood segmentation baselines.
Authors: Xiaoyan Yang, Dingbo Lu, Yang Li, Chenhui Li, Changbo Wang
In recent years, novel view synthesis has gained popularity in generating high-fidelity images. While demonstrating superior performance in the task of synthesizing novel views, the majority of these methods are still based on the conventional multi-layer perceptron for scene embedding. Furthermore, light field models suffer from geometric blurring during pixel rendering, while radiance field-based volume rendering methods have multiple solutions for a certain target of density distribution integration. To address these issues, we introduce the Convolutional Neural Radiance Fields to model the derivatives of radiance along rays. Based on 1D convolutional operations, our proposed method effectively extracts potential ray representations through a structured neural network architecture. Besides, with the proposed ray modeling, a proposed recurrent module is employed to solve geometric ambiguity in the fully neural rendering process. Extensive experiments demonstrate the promising results of our proposed model compared with existing state-of-the-art methods.
Authors: Gongxin Yao, Yixin Xuan, Yiwei Chen, Yu Pan
In the context of image-to-point cloud registration, acquiring point-to-pixel correspondences presents a challenging task since the similarity between individual points and pixels is ambiguous due to the visual differences in data modalities. Nevertheless, the same object present in the two data formats can be readily identified from the local perspective of point sets and pixel patches. Motivated by this intuition, we propose a coarse-to-fine framework that emphasizes the establishment of correspondences between local point sets and pixel patches, followed by the refinement of results at both the point and pixel levels. On a coarse scale, we mimic the classic Visual Transformer to translate both image and point cloud into two sequences of local representations, namely point and pixel proxies, and employ attention to capture global and cross-modal contexts. To supervise the coarse matching, we propose a novel projected point proportion loss, which guides to match point sets with pixel patches where more points can be projected into. On a finer scale, point-to-pixel correspondences are then refined from a smaller search space (i.e., the coarsely matched sets and patches) via well-designed sampling, attentional learning and fine matching, where sampling masks are embedded in the last two steps to mitigate the negative effect of sampling. With the high-quality correspondences, the registration problem is then resolved by EPnP algorithm within RANSAC. Experimental results on large-scale outdoor benchmarks demonstrate our superiority over existing methods.
Authors: Kaylene C. Stocking, Zak Murez, Vijay Badrinarayanan, Jamie Shotton, Alex Kendall, Claire Tomlin, Christopher P. Burgess
Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this decouples perception from the downstream driving task and could harm generalization. In this work we adapt a self-supervised object-centric vision model to perform object decomposition using only RGB video and the pose of the vehicle as inputs. We demonstrate that our method obtains promising results on the Waymo Open perception dataset. While object mask quality lags behind supervised methods or alternatives that use more privileged information, we find that our model is capable of learning a representation that fuses multiple camera viewpoints over time and successfully tracks many vehicles and pedestrians in the dataset. Code for our model is available at https://github.com/wayveai/SOCS.
Authors: Ryosuke Korekata, Motonari Kambara, Yu Yoshida, Shintaro Ishikawa, Yosuke Kawasaki, Masaki Takahashi, Komei Sugiura
This paper describes a domestic service robot (DSR) that fetches everyday objects and carries them to specified destinations according to free-form natural language instructions. Given an instruction such as "Move the bottle on the left side of the plate to the empty chair," the DSR is expected to identify the bottle and the chair from multiple candidates in the environment and carry the target object to the destination. Most of the existing multimodal language understanding methods are impractical in terms of computational complexity because they require inferences for all combinations of target object candidates and destination candidates. We propose Switching Head-Tail Funnel UNITER, which solves the task by predicting the target object and the destination individually using a single model. Our method is validated on a newly-built dataset consisting of object manipulation instructions and semi photo-realistic images captured in a standard Embodied AI simulator. The results show that our method outperforms the baseline method in terms of language comprehension accuracy. Furthermore, we conduct physical experiments in which a DSR delivers standardized everyday objects in a standardized domestic environment as requested by instructions with referring expressions. The experimental results show that the object grasping and placing actions are achieved with success rates of more than 90%.
Authors: Olukorede Fakorede, Ashutosh Kumar Nirala, Modeste Atsague, Jin Tian
Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most variants of AT algorithms treat every training example equally. However, recent works have shown that better performance is achievable by treating them unequally. In addition, it has been observed that AT exerts an uneven influence on different classes in a training set and unfairly hurts examples corresponding to classes that are inherently harder to classify. Consequently, various reweighting schemes have been proposed that assign unequal weights to robust losses of individual examples in a training set. In this work, we propose a novel instance-wise reweighting scheme. It considers the vulnerability of each natural example and the resulting information loss on its adversarial counterpart occasioned by adversarial attacks. Through extensive experiments, we show that our proposed method significantly improves over existing reweighting schemes, especially against strong white and black-box attacks.
Authors: Jingna Qiu, Frauke Wilm, Mathias Öttl, Maja Schlereth, Chang Liu, Tobias Heimann, Marc Aubreville, Katharina Breininger
The process of annotating histological gigapixel-sized whole slide images (WSIs) at the pixel level for the purpose of training a supervised segmentation model is time-consuming. Region-based active learning (AL) involves training the model on a limited number of annotated image regions instead of requesting annotations of the entire images. These annotation regions are iteratively selected, with the goal of optimizing model performance while minimizing the annotated area. The standard method for region selection evaluates the informativeness of all square regions of a specified size and then selects a specific quantity of the most informative regions. We find that the efficiency of this method highly depends on the choice of AL step size (i.e., the combination of region size and the number of selected regions per WSI), and a suboptimal AL step size can result in redundant annotation requests or inflated computation costs. This paper introduces a novel technique for selecting annotation regions adaptively, mitigating the reliance on this AL hyperparameter. Specifically, we dynamically determine each region by first identifying an informative area and then detecting its optimal bounding box, as opposed to selecting regions of a uniform predefined shape and size as in the standard method. We evaluate our method using the task of breast cancer metastases segmentation on the public CAMELYON16 dataset and show that it consistently achieves higher sampling efficiency than the standard method across various AL step sizes. With only 2.6\% of tissue area annotated, we achieve full annotation performance and thereby substantially reduce the costs of annotating a WSI dataset. The source code is available at https://github.com/DeepMicroscopy/AdaptiveRegionSelection.
Authors: Weidong Huang, Jiaming Ji, Borong Zhang, Chunhe Xia, Yaodong Yang
The widespread application of Reinforcement Learning (RL) in real-world situations is yet to come to fruition, largely as a result of its failure to satisfy the essential safety demands of such systems. Existing safe reinforcement learning (SafeRL) methods, employing cost functions to enhance safety, fail to achieve zero-cost in complex scenarios, including vision-only tasks, even with comprehensive data sampling and training. To address this, we introduce Safe DreamerV3, a novel algorithm that integrates both Lagrangian-based and planning-based methods within a world model. Our methodology represents a significant advancement in SafeRL as the first algorithm to achieve nearly zero-cost in both low-dimensional and vision-only tasks within the Safety-Gymnasium benchmark. Our project website can be found in: https://sites.google.com/view/safedreamerv3.
Authors: Linfeng Liu, Junyan Lyu, Siyu Liu, Xiaoying Tang, Shekhar S. Chandra, Fatima A. Nasrallah
The prediction of mild cognitive impairment (MCI) conversion to Alzheimer's disease (AD) is important for early treatment to prevent or slow the progression of AD. To accurately predict the MCI conversion to stable MCI or progressive MCI, we propose Triformer, a novel transformer-based framework with three specialized transformers to incorporate multi-model data. Triformer uses I) an image transformer to extract multi-view image features from medical scans, II) a clinical transformer to embed and correlate multi-modal clinical data, and III) a modality fusion transformer that produces an accurate prediction based on fusing the outputs from the image and clinical transformers. Triformer is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ANDI)1 and ADNI2 datasets and outperforms previous state-of-the-art single and multi-modal methods.
Authors: Chia-Yuan Chang, Yu-Neng Chuang, Guanchu Wang, Mengnan Du, Zou Na
Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains. However, existing domain generalization approaches often bring in prediction-irrelevant noise or require the collection of domain labels. To address these challenges, we consider the domain generalization problem from a different perspective by categorizing underlying feature groups into domain-shared and domain-specific features. Nevertheless, the domain-specific features are difficult to be identified and distinguished from the input data. In this work, we propose DomaIn-SPEcific Liberating (DISPEL), a post-processing fine-grained masking approach that can filter out undefined and indistinguishable domain-specific features in the embedding space. Specifically, DISPEL utilizes a mask generator that produces a unique mask for each input data to filter domain-specific features. The DISPEL framework is highly flexible to be applied to any fine-tuned models. We derive a generalization error bound to guarantee the generalization performance by optimizing a designed objective loss. The experimental results on five benchmarks demonstrate DISPEL outperforms existing methods and can further generalize various algorithms.
Authors: Fan Ni, Xu Zhang, Jianhui Wu, Guan-Nan Dong, Aichun Zhu, Hui Liu, Yue Zhang
Most existing methods for text-based person retrieval focus on text-to-image person retrieval. Nevertheless, due to the lack of dynamic information provided by isolated frames, the performance is hampered when the person is obscured in isolated frames or variable motion details are given in the textual description. In this paper, we propose a new task called Text-to-Video Person Retrieval(TVPR) which aims to effectively overcome the limitations of isolated frames. Since there is no dataset or benchmark that describes person videos with natural language, we construct a large-scale cross-modal person video dataset containing detailed natural language annotations, such as person's appearance, actions and interactions with environment, etc., termed as Text-to-Video Person Re-identification (TVPReid) dataset, which will be publicly available. To this end, a Text-to-Video Person Retrieval Network (TVPRN) is proposed. Specifically, TVPRN acquires video representations by fusing visual and motion representations of person videos, which can deal with temporal occlusion and the absence of variable motion details in isolated frames. Meanwhile, we employ the pre-trained BERT to obtain caption representations and the relationship between caption and video representations to reveal the most relevant person videos. To evaluate the effectiveness of the proposed TVPRN, extensive experiments have been conducted on TVPReid dataset. To the best of our knowledge, TVPRN is the first successful attempt to use video for text-based person retrieval task and has achieved state-of-the-art performance on TVPReid dataset. The TVPReid dataset will be publicly available to benefit future research.
Authors: Neng Dong, Liyan Zhang, Shuanglin Yan, Hao Tang, Jinhui Tang
Occlusion perturbation presents a significant challenge in person re-identification (re-ID), and existing methods that rely on external visual cues require additional computational resources and only consider the issue of missing information caused by occlusion. In this paper, we propose a simple yet effective framework, termed Erasing, Transforming, and Noising Defense Network (ETNDNet), which treats occlusion as a noise disturbance and solves occluded person re-ID from the perspective of adversarial defense. In the proposed ETNDNet, we introduce three strategies: Firstly, we randomly erase the feature map to create an adversarial representation with incomplete information, enabling adversarial learning of identity loss to protect the re-ID system from the disturbance of missing information. Secondly, we introduce random transformations to simulate the position misalignment caused by occlusion, training the extractor and classifier adversarially to learn robust representations immune to misaligned information. Thirdly, we perturb the feature map with random values to address noisy information introduced by obstacles and non-target pedestrians, and employ adversarial gaming in the re-ID system to enhance its resistance to occlusion noise. Without bells and whistles, ETNDNet has three key highlights: (i) it does not require any external modules with parameters, (ii) it effectively handles various issues caused by occlusion from obstacles and non-target pedestrians, and (iii) it designs the first GAN-based adversarial defense paradigm for occluded person re-ID. Extensive experiments on five public datasets fully demonstrate the effectiveness, superiority, and practicality of the proposed ETNDNet. The code will be released at \url{https://github.com/nengdong96/ETNDNet}.
Authors: Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
For smart vehicles driving through signalised intersections, it is crucial to determine whether the vehicle has right of way given the state of the traffic lights. To address this issue, camera based sensors can be used to determine whether the vehicle has permission to proceed straight, turn left or turn right. This paper proposes a novel end to end intersection right of way recognition model called LightFormer to generate right of way status for available driving directions in complex urban intersections. The model includes a spatial temporal inner structure with an attention mechanism, which incorporates features from past image to contribute to the classification of the current frame right of way status. In addition, a modified, multi weight arcface loss is introduced to enhance the model classification performance. Finally, the proposed LightFormer is trained and tested on two public traffic light datasets with manually augmented labels to demonstrate its effectiveness.
Authors: Alessandro Flaborea, Luca Collorone, Guido D'Amely, Stefano D'Arrigo, Bardh Prenkaj, Fabio Galasso
Anomalies are rare and anomaly detection is often therefore framed as One-Class Classification (OCC), i.e. trained solely on normalcy. Leading OCC techniques constrain the latent representations of normal motions to limited volumes and detect as abnormal anything outside, which accounts satisfactorily for the openset'ness of anomalies. But normalcy shares the same openset'ness property, since humans can perform the same action in several ways, which the leading techniques neglect. We propose a novel generative model for video anomaly detection (VAD), which assumes that both normality and abnormality are multimodal. We consider skeletal representations and leverage state-of-the-art diffusion probabilistic models to generate multimodal future human poses. We contribute a novel conditioning on the past motion of people, and exploit the improved mode coverage capabilities of diffusion processes to generate different-but-plausible future motions. Upon the statistical aggregation of future modes, anomaly is detected when the generated set of motions is not pertinent to the actual future. We validate our model on 4 established benchmarks: UBnormal, HR-UBnormal, HR-STC, and HR-Avenue, with extensive experiments surpassing state-of-the-art results.
Authors: Jiayin Sun, Hong Wang, Qiulei Dong
Open-set image recognition is a challenging topic in computer vision. Most of the existing works in literature focus on learning more discriminative features from the input images, however, they are usually insensitive to the high- or low-frequency components in features, resulting in a decreasing performance on fine-grained image recognition. To address this problem, we propose a Complementary Frequency-varying Awareness Network that could better capture both high-frequency and low-frequency information, called CFAN. The proposed CFAN consists of three sequential modules: (i) a feature extraction module is introduced for learning preliminary features from the input images; (ii) a frequency-varying filtering module is designed to separate out both high- and low-frequency components from the preliminary features in the frequency domain via a frequency-adjustable filter; (iii) a complementary temporal aggregation module is designed for aggregating the high- and low-frequency components via two Long Short-Term Memory networks into discriminative features. Based on CFAN, we further propose an open-set fine-grained image recognition method, called CFAN-OSFGR, which learns image features via CFAN and classifies them via a linear classifier. Experimental results on 3 fine-grained datasets and 2 coarse-grained datasets demonstrate that CFAN-OSFGR performs significantly better than 9 state-of-the-art methods in most cases.
Authors: Annika Reinke, Georg Grab, Lena Maier-Hein
While clinical trials are the state-of-the-art methods to assess the effect of new medication in a comparative manner, benchmarking in the field of medical image analysis is performed by so-called challenges. Recently, comprehensive analysis of multiple biomedical image analysis challenges revealed large discrepancies between the impact of challenges and quality control of the design and reporting standard. This work aims to follow up on these results and attempts to address the specific question of the reproducibility of the participants methods. In an effort to determine whether alternative interpretations of the method description may change the challenge ranking, we reproduced the algorithms submitted to the 2019 Robust Medical Image Segmentation Challenge (ROBUST-MIS). The leaderboard differed substantially between the original challenge and reimplementation, indicating that challenge rankings may not be sufficiently reproducible.
Authors: Bincheng Yang, Gangshan Wu
While transformer models have been demonstrated to be effective for natural language processing tasks and high-level vision tasks, only a few attempts have been made to use powerful transformer models for single image super-resolution. Because transformer models have powerful representation capacity and the in-built self-attention mechanisms in transformer models help to leverage self-similarity prior in input low-resolution image to improve performance for single image super-resolution, we present a single image super-resolution model based on recent hybrid vision transformer of MaxViT, named as MaxSR. MaxSR consists of four parts, a shallow feature extraction block, multiple cascaded adaptive MaxViT blocks to extract deep hierarchical features and model global self-similarity from low-level features efficiently, a hierarchical feature fusion block, and finally a reconstruction block. The key component of MaxSR, i.e., adaptive MaxViT block, is based on MaxViT block which mixes MBConv with squeeze-and-excitation, block attention and grid attention. In order to achieve better global modelling of self-similarity in input low-resolution image, we improve block attention and grid attention in MaxViT block to adaptive block attention and adaptive grid attention which do self-attention inside each window across all grids and each grid across all windows respectively in the most efficient way. We instantiate proposed model for classical single image super-resolution (MaxSR) and lightweight single image super-resolution (MaxSR-light). Experiments show that our MaxSR and MaxSR-light establish new state-of-the-art performance efficiently.
Authors: Tianyi Shi, Xiaohuan Ding, Liang Zhang, Xin Yang
Curvilinear object segmentation is critical for many applications. However, manually annotating curvilinear objects is very time-consuming and error-prone, yielding insufficiently available annotated datasets for existing supervised methods and domain adaptation methods. This paper proposes a self-supervised curvilinear object segmentation method that learns robust and distinctive features from fractals and unlabeled images (FreeCOS). The key contributions include a novel Fractal-FDA synthesis (FFS) module and a geometric information alignment (GIA) approach. FFS generates curvilinear structures based on the parametric Fractal L-system and integrates the generated structures into unlabeled images to obtain synthetic training images via Fourier Domain Adaptation. GIA reduces the intensity differences between the synthetic and unlabeled images by comparing the intensity order of a given pixel to the values of its nearby neighbors. Such image alignment can explicitly remove the dependency on absolute intensity values and enhance the inherent geometric characteristics which are common in both synthetic and real images. In addition, GIA aligns features of synthetic and real images via the prediction space adaptation loss (PSAL) and the curvilinear mask contrastive loss (CMCL). Extensive experimental results on four public datasets, i.e., XCAD, DRIVE, STARE and CrackTree demonstrate that our method outperforms the state-of-the-art unsupervised methods, self-supervised methods and traditional methods by a large margin. The source code of this work is available at https://github.com/TY-Shi/FreeCOS.
Authors: Xiaofei Chen, Yuting He, Cheng Xue, Rongjun Ge, Shuo Li, Guanyu Yang
The foundation models based on pre-training technology have significantly advanced artificial intelligence from theoretical to practical applications. These models have facilitated the feasibility of computer-aided diagnosis for widespread use. Medical contrastive vision-language pre-training, which does not require human annotations, is an effective approach for guiding representation learning using description information in diagnostic reports. However, the effectiveness of pre-training is limited by the large-scale semantic overlap and shifting problems in medical field. To address these issues, we propose the Knowledge-Boosting Contrastive Vision-Language Pre-training framework (KoBo), which integrates clinical knowledge into the learning of vision-language semantic consistency. The framework uses an unbiased, open-set sample-wise knowledge representation to measure negative sample noise and supplement the correspondence between vision-language mutual information and clinical knowledge. Extensive experiments validate the effect of our framework on eight tasks including classification, segmentation, retrieval, and semantic relatedness, achieving comparable or better performance with the zero-shot or few-shot settings. Our code is open on https://github.com/ChenXiaoFei-CS/KoBo.
Authors: Byung-Kwan Lee, Junho Kim, Yong Man Ro
Adversarial examples derived from deliberately crafted perturbations on visual inputs can easily harm decision process of deep neural networks. To prevent potential threats, various adversarial training-based defense methods have grown rapidly and become a de facto standard approach for robustness. Despite recent competitive achievements, we observe that adversarial vulnerability varies across targets and certain vulnerabilities remain prevalent. Intriguingly, such peculiar phenomenon cannot be relieved even with deeper architectures and advanced defense methods. To address this issue, in this paper, we introduce a causal approach called Adversarial Double Machine Learning (ADML), which allows us to quantify the degree of adversarial vulnerability for network predictions and capture the effect of treatments on outcome of interests. ADML can directly estimate causal parameter of adversarial perturbations per se and mitigate negative effects that can potentially damage robustness, bridging a causal perspective into the adversarial vulnerability. Through extensive experiments on various CNN and Transformer architectures, we corroborate that ADML improves adversarial robustness with large margins and relieve the empirical observation.
Authors: Silvia D. Almeida, Carsten T. Lüth, Tobias Norajitra, Tassilo Wald, Marco Nolden, Paul F. Jaeger, Claus P. Heussel, Jürgen Biederer, Oliver Weinheimer, Klaus Maier-Hein
Classification of heterogeneous diseases is challenging due to their complexity, variability of symptoms and imaging findings. Chronic Obstructive Pulmonary Disease (COPD) is a prime example, being underdiagnosed despite being the third leading cause of death. Its sparse, diffuse and heterogeneous appearance on computed tomography challenges supervised binary classification. We reformulate COPD binary classification as an anomaly detection task, proposing cOOpD: heterogeneous pathological regions are detected as Out-of-Distribution (OOD) from normal homogeneous lung regions. To this end, we learn representations of unlabeled lung regions employing a self-supervised contrastive pretext model, potentially capturing specific characteristics of diseased and healthy unlabeled regions. A generative model then learns the distribution of healthy representations and identifies abnormalities (stemming from COPD) as deviations. Patient-level scores are obtained by aggregating region OOD scores. We show that cOOpD achieves the best performance on two public datasets, with an increase of 8.2% and 7.7% in terms of AUROC compared to the previous supervised state-of-the-art. Additionally, cOOpD yields well-interpretable spatial anomaly maps and patient-level scores which we show to be of additional value in identifying individuals in the early stage of progression. Experiments in artificially designed real-world prevalence settings further support that anomaly detection is a powerful way of tackling COPD classification.
Authors: Asif Hanif, Muzammal Naseer, Salman Khan, Mubarak Shah, Fahad Shahbaz Khan
It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these models cannot be deployed for real-world applications immediately due to their vulnerability to adversarial attacks. We present a 3D frequency domain adversarial attack for volumetric medical image segmentation models and demonstrate its advantages over conventional input or voxel domain attacks. Using our proposed attack, we introduce a novel frequency domain adversarial training approach for optimizing a robust model against voxel and frequency domain attacks. Moreover, we propose frequency consistency loss to regulate our frequency domain adversarial training that achieves a better tradeoff between model's performance on clean and adversarial samples. Code is publicly available at https://github.com/asif-hanif/vafa.
Authors: Artur Miroszewski, Jakub Mielczarek, Filip Szczepanek, Grzegorz Czelusta, Bartosz Grabowski, Bertrand Le Saux, Jakub Nalepa
Support vector machines (SVMs) are a well-established classifier effectively deployed in an array of pattern recognition and classification tasks. In this work, we consider extending classic SVMs with quantum kernels and applying them to satellite data analysis. The design and implementation of SVMs with quantum kernels (hybrid SVMs) is presented. It consists of the Quantum Kernel Estimation (QKE) procedure combined with a classic SVM training routine. The pixel data are mapped to the Hilbert space using ZZ-feature maps acting on the parameterized ansatz state. The parameters are optimized to maximize the kernel target alignment. We approach the problem of cloud detection in satellite image data, which is one of the pivotal steps in both on-the-ground and on-board satellite image analysis processing chains. The experiments performed over the benchmark Landsat-8 multispectral dataset revealed that the simulated hybrid SVM successfully classifies satellite images with accuracy on par with classic SVMs.
Authors: Siyuan Yang, Jun Liu, Shijian Lu, Er Meng Hwa, Alex C. Kot
One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and it outperforms the state-of-the-art consistently by large margins.
Authors: ShangQi Deng, RuoCheng Wu, Liang-Jian Deng, Ran Ran, Tai-Xiang Jiang
Multispectral and Hyperspectral Image Fusion (MHIF) is a practical task that aims to fuse a high-resolution multispectral image (HR-MSI) and a low-resolution hyperspectral image (LR-HSI) of the same scene to obtain a high-resolution hyperspectral image (HR-HSI). Benefiting from powerful inductive bias capability, CNN-based methods have achieved great success in the MHIF task. However, they lack certain interpretability and require convolution structures be stacked to enhance performance. Recently, Implicit Neural Representation (INR) has achieved good performance and interpretability in 2D tasks due to its ability to locally interpolate samples and utilize multimodal content such as pixels and coordinates. Although INR-based approaches show promise, they require extra construction of high-frequency information (\emph{e.g.,} positional encoding). In this paper, inspired by previous work of MHIF task, we realize that HR-MSI could serve as a high-frequency detail auxiliary input, leading us to propose a novel INR-based hyperspectral fusion function named Implicit Neural Feature Fusion Function (INF). As an elaborate structure, it solves the MHIF task and addresses deficiencies in the INR-based approaches. Specifically, our INF designs a Dual High-Frequency Fusion (DHFF) structure that obtains high-frequency information twice from HR-MSI and LR-HSI, then subtly fuses them with coordinate information. Moreover, the proposed INF incorporates a parameter-free method named INR with cosine similarity (INR-CS) that uses cosine similarity to generate local weights through feature vectors. Based on INF, we construct an Implicit Neural Fusion Network (INFN) that achieves state-of-the-art performance for MHIF tasks of two public datasets, \emph{i.e.,} CAVE and Harvard. The code will soon be made available on GitHub.
Authors: Yuhao Huang, Gangrong Qu, Youran Ge
Video Compressed Sensing (VCS) aims to reconstruct multiple frames from one single captured measurement, thus achieving high-speed scene recording with a low-frame-rate sensor. Although there have been impressive advances in VCS recently, those state-of-the-art (SOTA) methods also significantly increase model complexity and suffer from poor generality and robustness, which means that those networks need to be retrained to accommodate the new system. Such limitations hinder the real-time imaging and practical deployment of models. In this work, we propose a Sampling-Priors-Augmented Deep Unfolding Network (SPA-DUN) for efficient and robust VCS reconstruction. Under the optimization-inspired deep unfolding framework, a lightweight and efficient U-net is exploited to downsize the model while improving overall performance. Moreover, the prior knowledge from the sampling model is utilized to dynamically modulate the network features to enable single SPA-DUN to handle arbitrary sampling settings, augmenting interpretability and generality. Extensive experiments on both simulation and real datasets demonstrate that SPA-DUN is not only applicable for various sampling settings with one single model but also achieves SOTA performance with incredible efficiency.
Authors: Marcel Beetz, Yilong Yang, Abhirup Banerjee, Lei Li, Vicente Grau
Myocardial infarction (MI) is one of the most prevalent cardiovascular diseases with associated clinical decision-making typically based on single-valued imaging biomarkers. However, such metrics only approximate the complex 3D structure and physiology of the heart and hence hinder a better understanding and prediction of MI outcomes. In this work, we investigate the utility of complete 3D cardiac shapes in the form of point clouds for an improved detection of MI events. To this end, we propose a fully automatic multi-step pipeline consisting of a 3D cardiac surface reconstruction step followed by a point cloud classification network. Our method utilizes recent advances in geometric deep learning on point clouds to enable direct and efficient multi-scale learning on high-resolution surface models of the cardiac anatomy. We evaluate our approach on 1068 UK Biobank subjects for the tasks of prevalent MI detection and incident MI prediction and find improvements of ~13% and ~5% respectively over clinical benchmarks. Furthermore, we analyze the role of each ventricle and cardiac phase for 3D shape-based MI detection and conduct a visual analysis of the morphological and physiological patterns typically associated with MI outcomes.
Authors: Oscar Carlsson, Jan E. Gerken, Hampus Linander, Heiner Spieß, Fredrik Ohlsson, Christoffer Petersson, Daniel Persson
High-resolution wide-angle fisheye images are becoming more and more important for robotics applications such as autonomous driving. However, using ordinary convolutional neural networks or vision transformers on this data is problematic due to projection and distortion losses introduced when projecting to a rectangular grid on the plane. We introduce the HEAL-SWIN transformer, which combines the highly uniform Hierarchical Equal Area iso-Latitude Pixelation (HEALPix) grid used in astrophysics and cosmology with the Hierarchical Shifted-Window (SWIN) transformer to yield an efficient and flexible model capable of training on high-resolution, distortion-free spherical data. In HEAL-SWIN, the nested structure of the HEALPix grid is used to perform the patching and windowing operations of the SWIN transformer, resulting in a one-dimensional representation of the spherical data with minimal computational overhead. We demonstrate the superior performance of our model for semantic segmentation and depth regression tasks on both synthetic and real automotive datasets. Our code is available at https://github.com/JanEGerken/HEAL-SWIN.
Authors: Zhili Ng, Haozhe Wang, Zhengshen Zhang, Francis Tay Eng Hock, Marcelo H. Ang Jr
In this work, we present SynTable, a unified and flexible Python-based dataset generator built using NVIDIA's Isaac Sim Replicator Composer for generating high-quality synthetic datasets for unseen object amodal instance segmentation of cluttered tabletop scenes. Our dataset generation tool can render a complex 3D scene containing object meshes, materials, textures, lighting, and backgrounds. Metadata, such as modal and amodal instance segmentation masks, occlusion masks, depth maps, bounding boxes, and material properties, can be generated to automatically annotate the scene according to the users' requirements. Our tool eliminates the need for manual labeling in the dataset generation process while ensuring the quality and accuracy of the dataset. In this work, we discuss our design goals, framework architecture, and the performance of our tool. We demonstrate the use of a sample dataset generated using SynTable by ray tracing for training a state-of-the-art model, UOAIS-Net. The results show significantly improved performance in Sim-to-Real transfer when evaluated on the OSD-Amodal dataset. We offer this tool as an open-source, easy-to-use, photorealistic dataset generator for advancing research in deep learning and synthetic data generation.
Authors: Kaiwen Cai, Chris Xiaoxuan Lu, Xingyu Zhao, Xiaowei Huang
Most image retrieval research focuses on improving predictive performance, but they may fall short in scenarios where the reliability of the prediction is crucial. Though uncertainty quantification can help by assessing uncertainty for query and database images, this method can provide only a heuristic estimate rather than an guarantee. To address these limitations, we present Risk Controlled Image Retrieval (RCIR), which generates retrieval sets that are guaranteed to contain the ground truth samples with a predefined probability. RCIR can be easily plugged into any image retrieval method, agnostic to data distribution and model selection. To the best of our knowledge, this is the first work that provides coverage guarantees for image retrieval. The validity and efficiency of RCIR is demonstrated on four real-world image retrieval datasets, including the Stanford CAR-196 (Krause et al. 2013), CUB-200 (Wah et al. 2011), the Pittsburgh dataset (Torii et al. 2013) and the ChestX-Det dataset (Lian et al. 2021).
Authors: Zixin Guo, Tzu-Jui Julius Wang, Selen Pehlivan, Abduljalil Radman, Jorma Laaksonen
Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on a huge amount of image-text pairs, which requires tedious and costly curation. On the contrary, weakly-supervised VLP (W-VLP) explores means with object tags generated by a pre-trained object detector (OD) from images. Yet, they still require paired information, i.e. images and object-level annotations, as supervision to train an OD.
To further reduce the amount of supervision, we propose Prompts-in-The-Loop (PiTL) that prompts knowledge from large language models (LLMs) to describe images. Concretely, given a category label of an image, e.g. refinery, the knowledge, e.g. a refinery could be seen with large storage tanks, pipework, and ..., extracted by LLMs is used as the language counterpart. The knowledge supplements, e.g. the common relations among entities most likely appearing in a scene. We create IN14K, a new VL dataset of 9M images and 1M descriptions of 14K categories from ImageNet21K with PiTL. Empirically, the VL models pre-trained with PiTL-generated pairs are strongly favored over other W-VLP works on image-to-text (I2T) and text-to-image (T2I) retrieval tasks, with less supervision. The results reveal the effectiveness of PiTL-generated pairs for VLP.
Authors: Aoxiong Yin, Tianyun Zhong, Li Tang, Weike Jin, Tao Jin, Zhou Zhao
Most sign language translation (SLT) methods to date require the use of gloss annotations to provide additional supervision information, however, the acquisition of gloss is not easy. To solve this problem, we first perform an analysis of existing models to confirm how gloss annotations make SLT easier. We find that it can provide two aspects of information for the model, 1) it can help the model implicitly learn the location of semantic boundaries in continuous sign language videos, 2) it can help the model understand the sign language video globally. We then propose \emph{gloss attention}, which enables the model to keep its attention within video segments that have the same semantics locally, just as gloss helps existing models do. Furthermore, we transfer the knowledge of sentence-to-sentence similarity from the natural language model to our gloss attention SLT network (GASLT) to help it understand sign language videos at the sentence level. Experimental results on multiple large-scale sign language datasets show that our proposed GASLT model significantly outperforms existing methods. Our code is provided in \url{https://github.com/YinAoXiong/GASLT}.
Authors: Zhaoyi Sun, Mingquan Lin, Qingqing Zhu, Qianqian Xie, Fei Wang, Zhiyong Lu, Yifan Peng
Computer-assisted diagnostic and prognostic systems of the future should be capable of simultaneously processing multimodal data. Multimodal deep learning (MDL), which involves the integration of multiple sources of data, such as images and text, has the potential to revolutionize the analysis and interpretation of biomedical data. However, it only caught researchers' attention recently. To this end, there is a critical need to conduct a systematic review on this topic, identify the limitations of current work, and explore future directions. In this scoping review, we aim to provide a comprehensive overview of the current state of the field and identify key concepts, types of studies, and research gaps with a focus on biomedical images and texts joint learning, mainly because these two were the most commonly available data types in MDL research. This study reviewed the current uses of multimodal deep learning on five tasks: (1) Report generation, (2) Visual question answering, (3) Cross-modal retrieval, (4) Computer-aided diagnosis, and (5) Semantic segmentation. Our results highlight the diverse applications and potential of MDL and suggest directions for future research in the field. We hope our review will facilitate the collaboration of natural language processing (NLP) and medical imaging communities and support the next generation of decision-making and computer-assisted diagnostic system development.
Authors: Guoyun Tu, Ying Liu, Vladimir Vlassov
Image captioning is a significant field across computer vision and natural language processing. We propose and present AIC-AB NET, a novel Attribute-Information-Combined Attention-Based Network that combines spatial attention architecture and text attributes in an encoder-decoder. For caption generation, adaptive spatial attention determines which image region best represents the image and whether to attend to the visual features or the visual sentinel. Text attribute information is synchronously fed into the decoder to help image recognition and reduce uncertainty. We have tested and evaluated our AICAB NET on the MS COCO dataset and a new proposed Fashion dataset. The Fashion dataset is employed as a benchmark of single-object images. The results show the superior performance of the proposed model compared to the state-of-the-art baseline and ablated models on both the images from MSCOCO and our single-object images. Our AIC-AB NET outperforms the baseline adaptive attention network by 0.017 (CIDEr score) on the MS COCO dataset and 0.095 (CIDEr score) on the Fashion dataset.
Authors: Xiao Liu, Alessandra Mileo, Alan F. Smeaton
The development of computer vision and in-situ monitoring using visual sensors allows the collection of large datasets from the additive manufacturing (AM) process. Such datasets could be used with machine learning techniques to improve the quality of AM. This paper examines two scenarios: first, using convolutional neural networks (CNNs) to accurately classify defects in an image dataset from AM and second, applying active learning techniques to the developed classification model. This allows the construction of a human-in-the-loop mechanism to reduce the size of the data required to train and generate training data.
Authors: Yasar Abbas Ur Rehman, Yan Gao, Pedro Porto Buarque de Gusmão, Mina Alibeigi, Jiajun Shen, Nicholas D. Lane
The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of the learned visual representations without needing to move data around. However, client bias and divergence during FL aggregation caused by data heterogeneity limits the performance of learned visual representations on downstream tasks. In this paper, we propose a new aggregation strategy termed Layer-wise Divergence Aware Weight Aggregation (L-DAWA) to mitigate the influence of client bias and divergence during FL aggregation. The proposed method aggregates weights at the layer-level according to the measure of angular divergence between the clients' model and the global model. Extensive experiments with cross-silo and cross-device settings on CIFAR-10/100 and Tiny ImageNet datasets demonstrate that our methods are effective and obtain new SOTA performance on both contrastive and non-contrastive SSL approaches.
Authors: Zhengbo Wang, Jian Liang, Ran He, Nan Xu, Zilei Wang, Tieniu Tan
With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising results, most existing methods require labeled data for all classes, which may not hold in real-world applications due to the long tail and Zipf's law. For example, some classes may lack labeled data entirely, such as emerging concepts. To address this problem, we propose a plug-and-play generative approach called \textbf{S}ynt\textbf{H}es\textbf{I}zed \textbf{P}rompts~(\textbf{SHIP}) to improve existing fine-tuning methods. Specifically, we follow variational autoencoders to introduce a generator that reconstructs the visual features by inputting the synthesized prompts and the corresponding class names to the textual encoder of CLIP. In this manner, we easily obtain the synthesized features for the remaining label-only classes. Thereafter, we fine-tune CLIP with off-the-shelf methods by combining labeled and synthesized features. Extensive experiments on base-to-new generalization, cross-dataset transfer learning, and generalized zero-shot learning demonstrate the superiority of our approach. The code is available at \url{https://github.com/mrflogs/SHIP}.
Authors: Fei Zhang, Yunjie Ye, Lei Feng, Zhongwen Rao, Jieming Zhu, Marcus Kalander, Chen Gong, Jianye Hao, Bo Han
This paper studies a new problem, \emph{active learning with partial labels} (ALPL). In this setting, an oracle annotates the query samples with partial labels, relaxing the oracle from the demanding accurate labeling process. To address ALPL, we first build an intuitive baseline that can be seamlessly incorporated into existing AL frameworks. Though effective, this baseline is still susceptible to the \emph{overfitting}, and falls short of the representative partial-label-based samples during the query process. Drawing inspiration from human inference in cognitive science, where accurate inferences can be explicitly derived from \emph{counter-examples} (CEs), our objective is to leverage this human-like learning pattern to tackle the \emph{overfitting} while enhancing the process of selecting representative samples in ALPL. Specifically, we construct CEs by reversing the partial labels for each instance, and then we propose a simple but effective WorseNet to directly learn from this complementary pattern. By leveraging the distribution gap between WorseNet and the predictor, this adversarial evaluation manner could enhance both the performance of the predictor itself and the sample selection process, allowing the predictor to capture more accurate patterns in the data. Experimental results on five real-world datasets and four benchmark datasets show that our proposed method achieves comprehensive improvements over ten representative AL frameworks, highlighting the superiority of WorseNet. The source code will be available at \url{https://github.com/Ferenas/APLL}.
Authors: W. Zhao, F. Yin, H. Ma, Q. Wu, J. Gomez-Dans, P. Lewis
The Leaf Area Index (LAI) is vital for predicting winter wheat yield. Acquisition of crop conditions via Sentinel-2 remote sensing images can be hindered by persistent clouds, affecting yield predictions. Synthetic Aperture Radar (SAR) provides all-weather imagery, and the ratio between its cross- and co-polarized channels (C-band) shows a high correlation with time series LAI over winter wheat regions. This study evaluates the use of time series Sentinel-1 VH/VV for LAI imputation, aiming to increase spatial-temporal density. We utilize a bidirectional LSTM (BiLSTM) network to impute time series LAI and use half mean squared error for each time step as the loss function. We trained models on data from southern Germany and the North China Plain using only LAI data generated by Sentinel-1 VH/VV and Sentinel-2. Experimental results show BiLSTM outperforms traditional regression methods, capturing nonlinear dynamics between multiple time series. It proves robust in various growing conditions and is effective even with limited Sentinel-2 images. BiLSTM's performance surpasses that of LSTM, particularly over the senescence period. Therefore, BiLSTM can be used to impute LAI with time-series Sentinel-1 VH/VV and Sentinel-2 data, and this method could be applied to other time-series imputation issues.
Authors: Sophie Starck, Yadunandan Vivekanand Kini, Jessica Johanna Maria Ritter, Rickmer Braren, Daniel Rueckert, Tamara Mueller
Age prediction is an important part of medical assessments and research. It can aid in detecting diseases as well as abnormal ageing by highlighting the discrepancy between chronological and biological age. To gain a comprehensive understanding of age-related changes observed in various body parts, we investigate them on a larger scale by using whole-body images. We utilise the Grad-CAM interpretability method to determine the body areas most predictive of a person's age. We expand our analysis beyond individual subjects by employing registration techniques to generate population-wide interpretability maps. Furthermore, we set state-of-the-art whole-body age prediction with a model that achieves a mean absolute error of 2.76 years. Our findings reveal three primary areas of interest: the spine, the autochthonous back muscles, and the cardiac region, which exhibits the highest importance.
Authors: Yuhang Wen, Zixuan Tang, Yunsheng Pang, Beichen Ding, Mengyuan Liu
Recognizing interactive action plays an important role in human-robot interaction and collaboration. Previous methods use late fusion and co-attention mechanism to capture interactive relations, which have limited learning capability or inefficiency to adapt to more interacting entities. With assumption that priors of each entity are already known, they also lack evaluations on a more general setting addressing the diversity of subjects. To address these problems, we propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Specifically, our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. By extending the entity dimension, ISTs provide better interactive representations. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations. When modeling correlations, a strict entity ordering is usually irrelevant for recognizing interactive actions. To this end, Entity Rearrangement is proposed to eliminate the orderliness in ISTs for interchangeable entities. Extensive experiments on four datasets verify the effectiveness of ISTA-Net by outperforming state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/ISTA-Net
Authors: Simon Holdenried-Krafft, Peter Somers, Ivonne A. Montes-Majarro, Diana Silimon, Cristina Tarín, Falko Fend, Hendrik P. A. Lensch
Whole slide image (WSI) assessment is a challenging and crucial step in cancer diagnosis and treatment planning. WSIs require high magnifications to facilitate sub-cellular analysis. Precise annotations for patch- or even pixel-level classifications in the context of gigapixel WSIs are tedious to acquire and require domain experts. Coarse-grained labels, on the other hand, are easily accessible, which makes WSI classification an ideal use case for multiple instance learning (MIL). In our work, we propose a novel embedding-based Dual-Query MIL pipeline (DQ-MIL). We contribute to both the embedding and aggregation steps. Since all-purpose visual feature representations are not yet available, embedding models are currently limited in terms of generalizability. With our work, we explore the potential of dynamic meta-embedding based on cutting-edge self-supervised pre-trained models in the context of MIL. Moreover, we propose a new MIL architecture capable of combining MIL-attention with correlated self-attention. The Dual-Query Perceiver design of our approach allows us to leverage the concept of self-distillation and to combine the advantages of a small model in the context of a low data regime with the rich feature representation of a larger model. We demonstrate the superior performance of our approach on three histopathological datasets, where we show improvement of up to 10% over state-of-the-art approaches.
Authors: Gorjan Radevski, Dusan Grujicic, Marie-Francine Moens, Matthew Blaschko, Tinne Tuytelaars
The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perform well. However, their performance improves further by employing additional input modalities that provide complementary cues, such as object detections, optical flow, audio, etc. The added complexity of the modality-specific modules, on the other hand, makes these models impractical for deployment. The goal of this work is to retain the performance of such a multimodal approach, while using only the RGB frames as input at inference time. We demonstrate that for egocentric action recognition on the Epic-Kitchens and the Something-Something datasets, students which are taught by multimodal teachers tend to be more accurate and better calibrated than architecturally equivalent models trained on ground truth labels in a unimodal or multimodal fashion. We further adopt a principled multimodal knowledge distillation framework, allowing us to deal with issues which occur when applying multimodal knowledge distillation in a naive manner. Lastly, we demonstrate the achieved reduction in computational complexity, and show that our approach maintains higher performance with the reduction of the number of input views.
Authors: Daiqing Li, Huan Ling, Amlan Kar, David Acuna, Seung Wook Kim, Karsten Kreis, Antonio Torralba, Sanja Fidler
In this work, we introduce a self-supervised feature representation learning framework DreamTeacher that utilizes generative networks for pre-training downstream image backbones. We propose to distill knowledge from a trained generative model into standard image backbones that have been well engineered for specific perception tasks. We investigate two types of knowledge distillation: 1) distilling learned generative features onto target image backbones as an alternative to pretraining these backbones on large labeled datasets such as ImageNet, and 2) distilling labels obtained from generative networks with task heads onto logits of target backbones. We perform extensive analyses on multiple generative models, dense prediction benchmarks, and several pre-training regimes. We empirically find that our DreamTeacher significantly outperforms existing self-supervised representation learning approaches across the board. Unsupervised ImageNet pre-training with DreamTeacher leads to significant improvements over ImageNet classification pre-training on downstream datasets, showcasing generative models, and diffusion generative models specifically, as a promising approach to representation learning on large, diverse datasets without requiring manual annotation.
Authors: Dapeng Hu, Jian Liang, Xinchao Wang, Chuan-Sheng Foo
Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. However, the calibration of predictive uncertainty in the target domain, a crucial aspect of the safe deployment of UDA models, has received limited attention. The conventional in-domain calibration method, \textit{temperature scaling} (TempScal), encounters challenges due to domain distribution shifts and the absence of labeled target domain data. Recent approaches have employed importance-weighting techniques to estimate the target-optimal temperature based on re-weighted labeled source data. Nonetheless, these methods require source data and suffer from unreliable density estimates under severe domain shifts, rendering them unsuitable for source-free UDA settings. To overcome these limitations, we propose PseudoCal, a source-free calibration method that exclusively relies on unlabeled target data. Unlike previous approaches that treat UDA calibration as a \textit{covariate shift} problem, we consider it as an unsupervised calibration problem specific to the target domain. Motivated by the factorization of the negative log-likelihood (NLL) objective in TempScal, we generate a labeled pseudo-target set that captures the structure of the real target. By doing so, we transform the unsupervised calibration problem into a supervised one, enabling us to effectively address it using widely-used in-domain methods like TempScal. Finally, we thoroughly evaluate the calibration performance of PseudoCal by conducting extensive experiments on 10 UDA methods, considering both traditional UDA settings and recent source-free UDA scenarios. The experimental results consistently demonstrate the superior performance of PseudoCal, exhibiting significantly reduced calibration error compared to existing calibration methods.
Authors: Yuting Xu, Jian Liang, Gengyun Jia, Ziming Yang, Yanhao Zhang, Ran He
The growing threats of deepfakes to society and cybersecurity have raised enormous public concerns, and increasing efforts have been devoted to this critical topic of deepfake video detection. Existing video methods achieve good performance but are computationally intensive. This paper introduces a simple yet effective strategy named Thumbnail Layout (TALL), which transforms a video clip into a pre-defined layout to realize the preservation of spatial and temporal dependencies. Specifically, consecutive frames are masked in a fixed position in each frame to improve generalization, then resized to sub-images and rearranged into a pre-defined layout as the thumbnail. TALL is model-agnostic and extremely simple by only modifying a few lines of code. Inspired by the success of vision transformers, we incorporate TALL into Swin Transformer, forming an efficient and effective method TALL-Swin. Extensive experiments on intra-dataset and cross-dataset validate the validity and superiority of TALL and SOTA TALL-Swin. TALL-Swin achieves 90.79$\%$ AUC on the challenging cross-dataset task, FaceForensics++ $\to$ Celeb-DF. The code is available at https://github.com/rainy-xu/TALL4Deepfake.
Authors: Aupam Hamran, Marzieh Vaeztourshizi, Amirhossein Esmaili, Massoud Pedram
In this paper, we present different architectures of Convolutional Neural Networks (CNN) to analyze and classify the brain tumors into benign and malignant types using the Magnetic Resonance Imaging (MRI) technique. Different CNN architecture optimization techniques such as widening and deepening of the network and adding skip connections are applied to improve the accuracy of the network. Results show that a subset of these techniques can judiciously be used to outperform a baseline CNN model used for the same purpose.
Authors: Nilesh Kulkarni, Davis Rempe, Kyle Genova, Abhijit Kundu, Justin Johnson, David Fouhey, Leonidas Guibas
We address the problem of generating realistic 3D motions of humans interacting with objects in a scene. Our key idea is to create a neural interaction field attached to a specific object, which outputs the distance to the valid interaction manifold given a human pose as input. This interaction field guides the sampling of an object-conditioned human motion diffusion model, so as to encourage plausible contacts and affordance semantics. To support interactions with scarcely available data, we propose an automated synthetic data pipeline. For this, we seed a pre-trained motion model, which has priors for the basics of human movement, with interaction-specific anchor poses extracted from limited motion capture data. Using our guided diffusion model trained on generated synthetic data, we synthesize realistic motions for sitting and lifting with several objects, outperforming alternative approaches in terms of motion quality and successful action completion. We call our framework NIFTY: Neural Interaction Fields for Trajectory sYnthesis.
Authors: Xiaomeng Dong, Michael Potter, Gaurav Kumar, Yun-Chan Tsai, V. Ratna Saripalli, Theodore Trafalis
It is no secret amongst deep learning researchers that finding the optimal data augmentation strategy during training can mean the difference between state-of-the-art performance and a run-of-the-mill result. To that end, the community has seen many efforts to automate the process of finding the perfect augmentation procedure for any task at hand. Unfortunately, even recent cutting-edge methods bring massive computational overhead, requiring as many as 100 full model trainings to settle on an ideal configuration. We show how to achieve equivalent performance using just 6 trainings with Random Unidimensional Augmentation. Source code is available at https://github.com/fastestimator/RUA/tree/v1.0
Authors: Sungmin Woo, Dogyoon Lee, Sangwon Hwang, Woojin Kim, Sangyoun Lee
Despite the remarkable success of deep learning, an optimal convolution operation on point clouds remains elusive owing to their irregular data structure. Existing methods mainly focus on designing an effective continuous kernel function that can handle an arbitrary point in continuous space. Various approaches exhibiting high performance have been proposed, but we observe that the standard pointwise feature is represented by 1D channels and can become more informative when its representation involves additional spatial feature dimensions. In this paper, we present Multidimensional Kernel Convolution (MKConv), a novel convolution operator that learns to transform the point feature representation from a vector to a multidimensional matrix. Unlike standard point convolution, MKConv proceeds via two steps. (i) It first activates the spatial dimensions of local feature representation by exploiting multidimensional kernel weights. These spatially expanded features can represent their embedded information through spatial correlation as well as channel correlation in feature space, carrying more detailed local structure information. (ii) Then, discrete convolutions are applied to the multidimensional features which can be regarded as a grid-structured matrix. In this way, we can utilize the discrete convolutions for point cloud data without voxelization that suffers from information loss. Furthermore, we propose a spatial attention module, Multidimensional Local Attention (MLA), to provide comprehensive structure awareness within the local point set by reweighting the spatial feature dimensions. We demonstrate that MKConv has excellent applicability to point cloud processing tasks including object classification, object part segmentation, and scene semantic segmentation with superior results.
Authors: Shuanglin Yan, Hao Tang, Liyan Zhang, Jinhui Tang
Text-based person search (TBPS) is a challenging task that aims to search pedestrian images with the same identity from an image gallery given a query text. In recent years, TBPS has made remarkable progress and state-of-the-art methods achieve superior performance by learning local fine-grained correspondence between images and texts. However, most existing methods rely on explicitly generated local parts to model fine-grained correspondence between modalities, which is unreliable due to the lack of contextual information or the potential introduction of noise. Moreover, existing methods seldom consider the information inequality problem between modalities caused by image-specific information. To address these limitations, we propose an efficient joint Multi-level Alignment Network (MANet) for TBPS, which can learn aligned image/text feature representations between modalities at multiple levels, and realize fast and effective person search. Specifically, we first design an image-specific information suppression module, which suppresses image background and environmental factors by relation-guided localization and channel attention filtration respectively. This module effectively alleviates the information inequality problem and realizes the alignment of information volume between images and texts. Secondly, we propose an implicit local alignment module to adaptively aggregate all pixel/word features of image/text to a set of modality-shared semantic topic centers and implicitly learn the local fine-grained correspondence between modalities without additional supervision and cross-modal interactions. And a global alignment is introduced as a supplement to the local perspective. The cooperation of global and local alignment modules enables better semantic alignment between modalities. Extensive experiments on multiple databases demonstrate the effectiveness and superiority of our MANet.
Authors: Zainy M. Malakan, Ghulam Mubashar Hassan, Ajmal Mian
Visual Story-Telling is the process of forming a multi-sentence story from a set of images. Appropriately including visual variation and contextual information captured inside the input images is one of the most challenging aspects of visual storytelling. Consequently, stories developed from a set of images often lack cohesiveness, relevance, and semantic relationship. In this paper, we propose a novel Vision Transformer Based Model for describing a set of images as a story. The proposed method extracts the distinct features of the input images using a Vision Transformer (ViT). Firstly, input images are divided into 16X16 patches and bundled into a linear projection of flattened patches. The transformation from a single image to multiple image patches captures the visual variety of the input visual patterns. These features are used as input to a Bidirectional-LSTM which is part of the sequence encoder. This captures the past and future image context of all image patches. Then, an attention mechanism is implemented and used to increase the discriminatory capacity of the data fed into the language model, i.e. a Mogrifier-LSTM. The performance of our proposed model is evaluated using the Visual Story-Telling dataset (VIST), and the results show that our model outperforms the current state of the art models.
Authors: Sehwan Choi, Jungho Kim, Junyong Yun, Jun Won Choi
Predicting the future motion of dynamic agents is of paramount importance to ensuring safety and assessing risks in motion planning for autonomous robots. In this study, we propose a two-stage motion prediction method, called R-Pred, designed to effectively utilize both scene and interaction context using a cascade of the initial trajectory proposal and trajectory refinement networks. The initial trajectory proposal network produces M trajectory proposals corresponding to the M modes of the future trajectory distribution. The trajectory refinement network enhances each of the M proposals using 1) tube-query scene attention (TQSA) and 2) proposal-level interaction attention (PIA) mechanisms. TQSA uses tube-queries to aggregate local scene context features pooled from proximity around trajectory proposals of interest. PIA further enhances the trajectory proposals by modeling inter-agent interactions using a group of trajectory proposals selected by their distances from neighboring agents. Our experiments conducted on Argoverse and nuScenes datasets demonstrate that the proposed refinement network provides significant performance improvements compared to the single-stage baseline and that R-Pred achieves state-of-the-art performance in some categories of the benchmarks.
Authors: Florent Chiaroni, Jose Dolz, Ziko Imtiaz Masud, Amar Mitiche, Ismail Ben Ayed
We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem. Specifically, we propose a bi-level optimization formulation, which explores a parameterized family of objective functions, each evaluating a weighted mutual information between the features and the latent labels, subject to supervision constraints from the labeled samples. Our formulation mitigates the class-balance bias encoded in standard information maximization approaches, thereby handling effectively both short-tailed and long-tailed data sets. We report extensive experiments and comparisons demonstrating that our PIM model consistently sets new state-of-the-art performances in GCD across six different datasets, more so when dealing with challenging fine-grained problems.
Authors: Peng Tu, Xu Xie, Guo AI, Yuexiang Li, Yawen Huang, Yefeng Zheng
Efficient detectors for edge devices are often optimized for metrics like parameters or speed counts, which remain weak correlation with the energy of detectors. However, among vision applications of convolutional neural networks (CNNs), some, such as always-on surveillance cameras, are critical for energy constraints. This paper aims to serve as a baseline by designing detectors to reach tradeoffs between energy and performance from two perspectives: 1) We extensively analyze various CNNs to identify low-energy architectures, including the selection of activation functions, convolutions operators, and feature fusion structures on necks. These underappreciated details in past works seriously affect the energy consumption of detectors; 2) To break through the dilemmatic energy-performance problem, we propose a balanced detector driven by energy using discovered low-energy components named \textit{FemtoDet}. In addition to the novel construction, we further improve FemtoDet by considering convolutions and training strategy optimizations. Specifically, we develop a new instance boundary enhancement (IBE) module for convolution optimization to overcome the contradiction between the limited capacity of CNNs and detection tasks in diverse spatial representations, and propose a recursive warm-restart (RecWR) for optimizing training strategy to escape the sub-optimization of light-weight detectors, considering the data shift produced in popular augmentations. As a result, FemtoDet with only 68.77k parameters achieves a competitive score of 46.3 AP50 on PASCAL VOC and power of 7.83W on RTX 3090. Extensive experiments on COCO and TJU-DHD datasets indicate that the proposed method achieves competitive results in diverse scenes.
Authors: Yang Shu, Xingzhuo Guo, Jialong Wu, Ximei Wang, Jianmin Wang, Mingsheng Long
Out-of-distribution (OOD) generalization, where the model needs to handle distribution shifts from training, is a major challenge of machine learning. Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. This paper aims at generalizing CLIP to out-of-distribution test data on downstream tasks. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on the unseen test data. To exploit the semantic relations between classes from the text modality, CLIPood introduces a new training objective, margin metric softmax (MMS), with class adaptive margins for fine-tuning. To incorporate both pre-trained zero-shot model and fine-tuned task-adaptive model, CLIPood leverages a new optimization strategy, Beta moving average (BMA), to maintain a temporal ensemble weighted by Beta distribution. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.
Authors: Ričards Marcinkevičs, Patricia Reis Wolfertstetter, Ugne Klimiene, Kieran Chin-Cheong, Alyssia Paschke, Julia Zerres, Markus Denzinger, David Niederberger, Sven Wellmann, Ece Ozkan, Christian Knorr, Julia E. Vogt
Appendicitis is among the most frequent reasons for pediatric abdominal surgeries. With recent advances in machine learning, data-driven decision support could help clinicians diagnose and manage patients while reducing the number of non-critical surgeries. Previous decision support systems for appendicitis focused on clinical, laboratory, scoring and computed tomography data, mainly ignoring abdominal ultrasound, a noninvasive and readily available diagnostic modality. To this end, we developed and validated interpretable machine learning models for predicting the diagnosis, management and severity of suspected appendicitis using ultrasound images. Our models were trained on a dataset comprising 579 pediatric patients with 1709 ultrasound images accompanied by clinical and laboratory data. Our methodological contribution is the generalization of concept bottleneck models to prediction problems with multiple views and incomplete concept sets. Notably, such models lend themselves to interpretation and interaction via high-level concepts understandable to clinicians without sacrificing performance or requiring time-consuming image annotation when deployed.
Authors: Toan Nguyen, Minh Nhat Vu, An Vuong, Dzung Nguyen, Thieu Vo, Ngan Le, Anh Nguyen
Affordance detection is a challenging problem with a wide variety of robotic applications. Traditional affordance detection methods are limited to a predefined set of affordance labels, hence potentially restricting the adaptability of intelligent robots in complex and dynamic environments. In this paper, we present the Open-Vocabulary Affordance Detection (OpenAD) method, which is capable of detecting an unbounded number of affordances in 3D point clouds. By simultaneously learning the affordance text and the point feature, OpenAD successfully exploits the semantic relationships between affordances. Therefore, our proposed method enables zero-shot detection and can be able to detect previously unseen affordances without a single annotation example. Intensive experimental results show that OpenAD works effectively on a wide range of affordance detection setups and outperforms other baselines by a large margin. Additionally, we demonstrate the practicality of the proposed OpenAD in real-world robotic applications with a fast inference speed (~100ms). Our project is available at https://openad2023.github.io.
Authors: Nitzan Bitton-Guetta, Yonatan Bitton, Jack Hessel, Ludwig Schmidt, Yuval Elovici, Gabriel Stanovsky, Roy Schwartz
Weird, unusual, and uncanny images pique the curiosity of observers because they challenge commonsense. For example, an image released during the 2022 world cup depicts the famous soccer stars Lionel Messi and Cristiano Ronaldo playing chess, which playfully violates our expectation that their competition should occur on the football field. Humans can easily recognize and interpret these unconventional images, but can AI models do the same? We introduce WHOOPS!, a new dataset and benchmark for visual commonsense. The dataset is comprised of purposefully commonsense-defying images created by designers using publicly-available image generation tools like Midjourney. We consider several tasks posed over the dataset. In addition to image captioning, cross-modal matching, and visual question answering, we introduce a difficult explanation generation task, where models must identify and explain why a given image is unusual. Our results show that state-of-the-art models such as GPT3 and BLIP2 still lag behind human performance on WHOOPS!. We hope our dataset will inspire the development of AI models with stronger visual commonsense reasoning abilities. Data, models and code are available at the project website: whoops-benchmark.github.io
Authors: Lukas Zbinden, Lars Doorenbos, Theodoros Pissas, Adrian Thomas Huber, Raphael Sznitman, Pablo Márquez-Neila
Semantic segmentation has made significant progress in recent years thanks to deep neural networks, but the common objective of generating a single segmentation output that accurately matches the image's content may not be suitable for safety-critical domains such as medical diagnostics and autonomous driving. Instead, multiple possible correct segmentation maps may be required to reflect the true distribution of annotation maps. In this context, stochastic semantic segmentation methods must learn to predict conditional distributions of labels given the image, but this is challenging due to the typically multimodal distributions, high-dimensional output spaces, and limited annotation data. To address these challenges, we propose a conditional categorical diffusion model (CCDM) for semantic segmentation based on Denoising Diffusion Probabilistic Models. Our model is conditioned to the input image, enabling it to generate multiple segmentation label maps that account for the aleatoric uncertainty arising from divergent ground truth annotations. Our experimental results show that CCDM achieves state-of-the-art performance on LIDC, a stochastic semantic segmentation dataset, and outperforms established baselines on the classical segmentation dataset Cityscapes.
Authors: Sauradip Nag, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song, Tao Xiang
We propose a new formulation of temporal action detection (TAD) with denoising diffusion, DiffTAD in short. Taking as input random temporal proposals, it can yield action proposals accurately given an untrimmed long video. This presents a generative modeling perspective, against previous discriminative learning manners. This capability is achieved by first diffusing the ground-truth proposals to random ones (i.e., the forward/noising process) and then learning to reverse the noising process (i.e., the backward/denoising process). Concretely, we establish the denoising process in the Transformer decoder (e.g., DETR) by introducing a temporal location query design with faster convergence in training. We further propose a cross-step selective conditioning algorithm for inference acceleration. Extensive evaluations on ActivityNet and THUMOS show that our DiffTAD achieves top performance compared to previous art alternatives. The code will be made available at https://github.com/sauradip/DiffusionTAD.
Authors: Dmitrii Torbunov, Yi Huang, Huan-Hsin Tseng, Haiwang Yu, Jin Huang, Shinjae Yoo, Meifeng Lin, Brett Viren, Yihui Ren
An unpaired image-to-image (I2I) translation technique seeks to find a mapping between two domains of data in a fully unsupervised manner. While the initial solutions to the I2I problem were provided by the generative adversarial neural networks (GANs), currently, diffusion models (DM) hold the state-of-the-art status on the I2I translation benchmarks in terms of FID. Yet, they suffer from some limitations, such as not using data from the source domain during the training, or maintaining consistency of the source and translated images only via simple pixel-wise errors. This work revisits the classic CycleGAN model and equips it with recent advancements in model architectures and model training procedures. The revised model is shown to significantly outperform other advanced GAN- and DM-based competitors on a variety of benchmarks. In the case of Male2Female translation of CelebA, the model achieves over 40% improvement in FID score compared to the state-of-the-art results. This work also demonstrates the ineffectiveness of the pixel-wise I2I translation faithfulness metrics and suggests their revision. The code and trained models are available at https://github.com/LS4GAN/uvcgan2
Authors: Tingting Liu, Yuan Liu, Chuncheng Zhang, Yuan Liyin, Xiubao Sui, Qian Chen
Since the number of incident energies is limited, it is difficult to directly acquire hyperspectral images (HSI) with high spatial resolution. Considering the high dimensionality and correlation of HSI, super-resolution (SR) of HSI remains a challenge in the absence of auxiliary high-resolution images. Furthermore, it is very important to extract the spatial features effectively and make full use of the spectral information. This paper proposes a novel HSI super-resolution algorithm, termed dual-domain network based on hybrid convolution (SRDNet). Specifically, a dual-domain network is designed to fully exploit the spatial-spectral and frequency information among the hyper-spectral data. To capture inter-spectral self-similarity, a self-attention learning mechanism (HSL) is devised in the spatial domain. Meanwhile the pyramid structure is applied to increase the acceptance field of attention, which further reinforces the feature representation ability of the network. Moreover, to further improve the perceptual quality of HSI, a frequency loss(HFL) is introduced to optimize the model in the frequency domain. The dynamic weighting mechanism drives the network to gradually refine the generated frequency and excessive smoothing caused by spatial loss. Finally, In order to better fully obtain the mapping relationship between high-resolution space and low-resolution space, a hybrid module of 2D and 3D units with progressive upsampling strategy is utilized in our method. Experiments on a widely used benchmark dataset illustrate that the proposed SRDNet method enhances the texture information of HSI and is superior to state-of-the-art methods.
Authors: Tang Tao, Longfei Gao, Guangrun Wang, Yixing Lao, Peng Chen, Hengshuang Zhao, Dayang Hao, Xiaodan Liang, Mathieu Salzmann, Kaicheng Yu
We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns because the renderers rely on explicit 3D reconstruction and exploit game engines, that ignore important attributes of LiDAR points. We address this challenge by formulating, to the best of our knowledge, the first differentiable end-to-end LiDAR rendering framework, LiDAR-NeRF, leveraging a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points. However, simply employing NeRF cannot achieve satisfactory results, as it only focuses on learning individual pixels while ignoring local information, especially at low texture areas, resulting in poor geometry. To this end, we have taken steps to address this issue by introducing a structural regularization method to preserve local structural details. To evaluate the effectiveness of our approach, we establish an object-centric multi-view LiDAR dataset, dubbed NeRF-MVL. It contains observations of objects from 9 categories seen from 360-degree viewpoints captured with multiple LiDAR sensors. Our extensive experiments on the scene-level KITTI-360 dataset, and on our object-level NeRF-MVL show that our LiDAR-NeRF surpasses the model-based algorithms significantly.
Authors: Azmine Toushik Wasi, Karlo Šerbetar, Raima Islam, Taki Hasan Rafi, Dong-Kyu Chae
In this paper, we introduce a framework ARBEx, a novel attentive feature extraction framework driven by Vision Transformer with reliability balancing to cope against poor class distributions, bias, and uncertainty in the facial expression learning (FEL) task. We reinforce several data pre-processing and refinement methods along with a window-based cross-attention ViT to squeeze the best of the data. We also employ learnable anchor points in the embedding space with label distributions and multi-head self-attention mechanism to optimize performance against weak predictions with reliability balancing, which is a strategy that leverages anchor points, attention scores, and confidence values to enhance the resilience of label predictions. To ensure correct label classification and improve the models' discriminative power, we introduce anchor loss, which encourages large margins between anchor points. Additionally, the multi-head self-attention mechanism, which is also trainable, plays an integral role in identifying accurate labels. This approach provides critical elements for improving the reliability of predictions and has a substantial positive effect on final prediction capabilities. Our adaptive model can be integrated with any deep neural network to forestall challenges in various recognition tasks. Our strategy outperforms current state-of-the-art methodologies, according to extensive experiments conducted in a variety of contexts.
Authors: Danilo A. Jesus, Eric F. Thee, Tim Doekemeijer, Daniel Luttikhuizen, Caroline Klaver, Stefan Klein, Theo van Walsum, Hans Vingerling, Luisa Sanchez
To study whether it is possible to differentiate intermediate age-related macular degeneration (AMD) from healthy controls using partial optical coherence tomography (OCT) data, that is, restricting the input B-scans to certain pre-defined regions of interest (ROIs). A total of 15744 B-scans from 269 intermediate AMD patients and 115 normal subjects were used in this study (split on subject level in 80% train, 10% validation and 10% test). From each OCT B-scan, three ROIs were extracted: retina, complex between retinal pigment epithelium (RPE) and Bruch membrane (BM), and choroid (CHO). These ROIs were obtained using two different methods: masking and cropping. In addition to the six ROIs, the whole OCT B-scan and the binary mask corresponding to the segmentation of the RPE-BM complex were used. For each subset, a convolutional neural network (based on VGG16 architecture and pre-trained on ImageNet) was trained and tested. The performance of the models was evaluated using the area under the receiver operating characteristic (AUROC), accuracy, sensitivity, and specificity. All trained models presented an AUROC, accuracy, sensitivity, and specificity equal to or higher than 0.884, 0.816, 0.685, and 0.644, respectively. The model trained on the whole OCT B-scan presented the best performance (AUROC = 0.983, accuracy = 0.927, sensitivity = 0.862, specificity = 0.913). The models trained on the ROIs obtained with the cropping method led to significantly higher outcomes than those obtained with masking, with the exception of the retinal tissue, where no statistically significant difference was observed between cropping and masking (p = 0.47). This study demonstrated that while using the complete OCT B-scan provided the highest accuracy in classifying intermediate AMD, models trained on specific ROIs such as the RPE-BM complex or the choroid can still achieve high performance.
Authors: Chia-Hao Kao, Ying-Chieh Weng, Yi-Hsin Chen, Wei-Chen Chiu, Wen-Hsiao Peng
This paper proposes a transformer-based learned image compression system. It is capable of achieving variable-rate compression with a single model while supporting the region-of-interest (ROI) functionality. Inspired by prompt tuning, we introduce prompt generation networks to condition the transformer-based autoencoder of compression. Our prompt generation networks generate content-adaptive tokens according to the input image, an ROI mask, and a rate parameter. The separation of the ROI mask and the rate parameter allows an intuitive way to achieve variable-rate and ROI coding simultaneously. Extensive experiments validate the effectiveness of our proposed method and confirm its superiority over the other competing methods.
Authors: Tuhin Chakrabarty, Arkadiy Saakyan, Olivia Winn, Artemis Panagopoulou, Yue Yang, Marianna Apidianaki, Smaranda Muresan
Visual metaphors are powerful rhetorical devices used to persuade or communicate creative ideas through images. Similar to linguistic metaphors, they convey meaning implicitly through symbolism and juxtaposition of the symbols. We propose a new task of generating visual metaphors from linguistic metaphors. This is a challenging task for diffusion-based text-to-image models, such as DALL$\cdot$E 2, since it requires the ability to model implicit meaning and compositionality. We propose to solve the task through the collaboration between Large Language Models (LLMs) and Diffusion Models: Instruct GPT-3 (davinci-002) with Chain-of-Thought prompting generates text that represents a visual elaboration of the linguistic metaphor containing the implicit meaning and relevant objects, which is then used as input to the diffusion-based text-to-image models.Using a human-AI collaboration framework, where humans interact both with the LLM and the top-performing diffusion model, we create a high-quality dataset containing 6,476 visual metaphors for 1,540 linguistic metaphors and their associated visual elaborations. Evaluation by professional illustrators shows the promise of LLM-Diffusion Model collaboration for this task . To evaluate the utility of our Human-AI collaboration framework and the quality of our dataset, we perform both an intrinsic human-based evaluation and an extrinsic evaluation using visual entailment as a downstream task.
Authors: Xuan Liu, Yaoqin Xie, Jun Cheng, Songhui Diao, Shan Tan, Xiaokun Liang
Denoising low-dose computed tomography (CT) images is a critical task in medical image computing. Supervised deep learning-based approaches have made significant advancements in this area in recent years. However, these methods typically require pairs of low-dose and normal-dose CT images for training, which are challenging to obtain in clinical settings. Existing unsupervised deep learning-based methods often require training with a large number of low-dose CT images or rely on specially designed data acquisition processes to obtain training data. To address these limitations, we propose a novel unsupervised method that only utilizes normal-dose CT images during training, enabling zero-shot denoising of low-dose CT images. Our method leverages the diffusion model, a powerful generative model. We begin by training a cascaded unconditional diffusion model capable of generating high-quality normal-dose CT images from low-resolution to high-resolution. The cascaded architecture makes the training of high-resolution diffusion models more feasible. Subsequently, we introduce low-dose CT images into the reverse process of the diffusion model as likelihood, combined with the priors provided by the diffusion model and iteratively solve multiple maximum a posteriori (MAP) problems to achieve denoising. Additionally, we propose methods to adaptively adjust the coefficients that balance the likelihood and prior in MAP estimations, allowing for adaptation to different noise levels in low-dose CT images. We test our method on low-dose CT datasets of different regions with varying dose levels. The results demonstrate that our method outperforms the state-of-the-art unsupervised method and surpasses several supervised deep learning-based methods. Codes are available in https://github.com/DeepXuan/Dn-Dp.
Authors: Xingzhe Su, Wenwen Qiang, Zeen Song, Changwen Zheng, Fengge Wu, Fuchun Sun
Generative Adversarial Networks (GANs) and their variants have achieved remarkable success on natural images. However, their performance degrades when applied to remote sensing (RS) images, and the discriminator often suffers from the overfitting problem. In this paper, we examine the differences between natural and RS images and find that the intrinsic dimensions of RS images are much lower than those of natural images. As the discriminator is more susceptible to overfitting on data with lower intrinsic dimension, it focuses excessively on local characteristics of RS training data and disregards the overall structure of the distribution, leading to a faulty generation model. In respond, we propose a novel approach that leverages the real data manifold to constrain the discriminator and enhance the model performance. Specifically, we introduce a learnable information-theoretic measure to capture the real data manifold. Building upon this measure, we propose manifold alignment regularization, which mitigates the discriminator's overfitting and improves the quality of generated samples. Moreover, we establish a unified GAN framework for manifold alignment, applicable to both supervised and unsupervised RS image generation tasks.
Authors: Tao Zhang, Xingye Tian, Yu Wu, Shunping Ji, Xuebo Wang, Yuan Zhang, Pengfei Wan
Video instance segmentation (VIS) is a critical task with diverse applications, including autonomous driving and video editing. Existing methods often underperform on complex and long videos in real world, primarily due to two factors. Firstly, offline methods are limited by the tightly-coupled modeling paradigm, which treats all frames equally and disregards the interdependencies between adjacent frames. Consequently, this leads to the introduction of excessive noise during long-term temporal alignment. Secondly, online methods suffer from inadequate utilization of temporal information. To tackle these challenges, we propose a decoupling strategy for VIS by dividing it into three independent sub-tasks: segmentation, tracking, and refinement. The efficacy of the decoupling strategy relies on two crucial elements: 1) attaining precise long-term alignment outcomes via frame-by-frame association during tracking, and 2) the effective utilization of temporal information predicated on the aforementioned accurate alignment outcomes during refinement. We introduce a novel referring tracker and temporal refiner to construct the \textbf{D}ecoupled \textbf{VIS} framework (\textbf{DVIS}). DVIS achieves new SOTA performance in both VIS and VPS, surpassing the current SOTA methods by 7.3 AP and 9.6 VPQ on the OVIS and VIPSeg datasets, which are the most challenging and realistic benchmarks. Moreover, thanks to the decoupling strategy, the referring tracker and temporal refiner are super light-weight (only 1.69\% of the segmenter FLOPs), allowing for efficient training and inference on a single GPU with 11G memory. The code is available at \href{https://github.com/zhang-tao-whu/DVIS}{https://github.com/zhang-tao-whu/DVIS}.
Authors: Yi-Ching Hung, Yu-Qing Jiang, Fong-Syuan Liou, Yu-Hsuan Tsao, Zi-Cing Chiang, MIn-Te Sun
The rehabilitation treatment helps to heal minor sports and occupational injuries. In a traditional rehabilitation process, a therapist will assign certain actions to a patient to perform in between hospital visits, and it will rely on the patient to remember actions correctly and the schedule to perform them. Unfortunately, many patients forget to perform actions or fail to recall actions in detail. As a consequence, the rehabilitation treatment is hampered or, in the worst case, the patient may suffer from additional injury caused by performing incorrect actions. To resolve these issues, we propose a HRNet-based rehabilitation monitoring system, which can remind a patient when to perform the actions and display the actions for the patient to follow via the patient's smartphone. In addition, it helps the therapist to monitor the progress of the rehabilitation for the patient. Our system consists of an iOS app and several components at the server side. The app is in charge of displaying and collecting action videos. The server computes the similarity score between the therapist's actions and the patient's in the videos to keep track of the number of repetitions of each action. Theses stats will be shown to both of the patient and therapist. The extensive experiments show that the F1-Score of the similarity calculation is as high as 0.9 and the soft accuracy of the number of repetitions is higher than 90%.
Authors: Kshama Kodthalu Shivashankara, Afagh Mehri Shervedani, Reza Sameni
The electrocardiogram (ECG) is an accurate and widely available tool for diagnosing cardiovascular diseases. ECGs have been recorded in printed formats for decades and their digitization holds great potential for training machine learning (ML) models in algorithmic ECG diagnosis. Physical ECG archives are at risk of deterioration and scanning printed ECGs alone is insufficient, as ML models require ECG time-series data. Therefore, the digitization and conversion of paper ECG archives into time-series data is of utmost importance. Deep learning models for image processing show promise in this regard. However, the scarcity of ECG archives with reference time-series is a challenge. Data augmentation techniques utilizing \textit{digital twins} present a potential solution.
We introduce a novel method for generating synthetic ECG images on standard paper-like ECG backgrounds with realistic artifacts. Distortions including handwritten text artifacts, wrinkles, creases and perspective transforms are applied to the generated images, without personally identifiable information. As a use case, we generated an ECG image dataset of 21,801 records from the 12-lead PhysioNet PTB-XL ECG time-series dataset. A deep ECG image digitization model was built and trained on the synthetic dataset, and was employed to convert the synthetic images to time-series data for evaluation. The signal-to-noise ratio (SNR) was calculated to assess the image digitization quality vs the ground truth ECG time-series. The results show an average signal recovery SNR of 27$\pm$2.8\,dB, demonstrating the significance of the proposed synthetic ECG image dataset for training deep learning models. The codebase is available as an open-access toolbox for ECG research.
Authors: José Morano, Guilherme Aresta, Dmitrii Lachinov, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunović
Deep learning has become a valuable tool for the automation of certain medical image segmentation tasks, significantly relieving the workload of medical specialists. Some of these tasks require segmentation to be performed on a subset of the input dimensions, the most common case being 3D-to-2D. However, the performance of existing methods is strongly conditioned by the amount of labeled data available, as there is currently no data efficient method, e.g. transfer learning, that has been validated on these tasks. In this work, we propose a novel convolutional neural network (CNN) and self-supervised learning (SSL) method for label-efficient 3D-to-2D segmentation. The CNN is composed of a 3D encoder and a 2D decoder connected by novel 3D-to-2D blocks. The SSL method consists of reconstructing image pairs of modalities with different dimensionality. The approach has been validated in two tasks with clinical relevance: the en-face segmentation of geographic atrophy and reticular pseudodrusen in optical coherence tomography. Results on different datasets demonstrate that the proposed CNN significantly improves the state of the art in scenarios with limited labeled data by up to 8% in Dice score. Moreover, the proposed SSL method allows further improvement of this performance by up to 23%, and we show that the SSL is beneficial regardless of the network architecture.
Authors: Dhiraj Neupane, Lakpa Dorje Tamang, Ngoc Dung Huynh, Mohamed Reda Bouadjenek, Sunil Aryal
We implemented a simple method for early detection in this research. The implemented methods are plotting the given mat files and analyzing scalogram images generated by performing Continuous Wavelet Transform (CWT) on the samples. Also, finding the mean, standard deviation (STD), and peak-to-peak (P2P) values from each signal also helped detect faulty signs. We have implemented the autoregressive integrated moving average (ARIMA) method to track the progression.
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: Lei Li, Julia Camps, Zhinuo (Jenny) Wang, Abhirup Banerjee, Marcel Beetz, Blanca Rodriguez, Vicente Grau
Myocardial infarction (MI) demands precise and swift diagnosis. Cardiac digital twins (CDTs) have the potential to offer individualized evaluation of cardiac function in a non-invasive manner, making them a promising approach for personalized diagnosis and treatment planning of MI. The inference of accurate myocardial tissue properties is crucial in creating a reliable CDT platform, and particularly in the context of studying MI. In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG), focusing on the development of a comprehensive CDT platform specifically designed for MI. The platform integrates multi-modal data, such as cardiac MRI and ECG, to enhance the accuracy and reliability of the inferred tissue properties. We perform a sensitivity analysis based on computer simulations, systematically exploring the effects of infarct location, size, degree of transmurality, and electrical activity alteration on the simulated QRS complex of ECG, to establish the limits of the approach. We subsequently propose a deep computational model to infer infarct location and distribution from the simulated QRS. The in silico experimental results show that our model can effectively capture the complex relationships between the QRS signals and the corresponding infarct regions, with promising potential for clinical application in the future. The code will be released publicly once the manuscript is accepted for publication.
Authors: Sara Hatami Gazani, Matthew Tucsok, Iraj Mantegh, Homayoun Najjaran
UAV-based intelligent data acquisition for 3D reconstruction and monitoring of infrastructure has been experiencing an increasing surge of interest due to the recent advancements in image processing and deep learning-based techniques. View planning is an essential part of this task that dictates the information capture strategy and heavily impacts the quality of the 3D model generated from the captured data. Recent methods have used prior knowledge or partial reconstruction of the target to accomplish view planning for active reconstruction; the former approach poses a challenge for complex or newly identified targets while the latter is computationally expensive. In this work, we present Bag-of-Views (BoV), a fully appearance-based model used to assign utility to the captured views for both offline dataset refinement and online next-best-view (NBV) planning applications targeting the task of 3D reconstruction. With this contribution, we also developed the View Planning Toolbox (VPT), a lightweight package for training and testing machine learning-based view planning frameworks, custom view dataset generation of arbitrary 3D scenes, and 3D reconstruction. Through experiments which pair a BoV-based reinforcement learning model with VPT, we demonstrate the efficacy of our model in reducing the number of required views for high-quality reconstructions in dataset refinement and NBV planning.
Authors: Julian Moosmann, Hanna Mueller, Nicky Zimmerman, Georg Rutishauser, Luca Benini, Michele Magno
This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network's detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting an in-depth a comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a novel parallel RISC-V processor (GAP9 from Greenwaves) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from STM and Apollo4b from Ambiq), and a multi-core platform with a CNN hardware accelerator (Analog Devices MAX78000). Experimental results show that the GAP9's hardware accelerator achieves the lowest inference latency and energy at 2.12ms and 150uJ respectively, which is around 2x faster and 20% more efficient than the next best platform, the MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with 112x112 pixels and 10 detection classes within 3.2ms, consuming 245uJ. To showcase the competitiveness of a versatile general-purpose system we also deployed and profiled a multi-core implementation on GAP9 at different operating points, achieving 11.3ms with the lowest-latency and 490uJ with the most energy-efficient configuration. With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference.
Authors: Mara Graziani, Laura O' Mahony, An-Phi Nguyen, Henning Müller, Vincent Andrearczyk
Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution estimates such as pixel saliency. However, defining the concepts for the interpretability analysis biases the explanations by the user's expectations on the concepts. To address this, we propose a novel post-hoc unsupervised method that automatically uncovers the concepts learned by deep models during training. By decomposing the latent space of a layer in singular vectors and refining them by unsupervised clustering, we uncover concept vectors aligned with directions of high variance that are relevant to the model prediction, and that point to semantically distinct concepts. Our extensive experiments reveal that the majority of our concepts are readily understandable to humans, exhibit coherency, and bear relevance to the task at hand. Moreover, we showcase the practical utility of our method in dataset exploration, where our concept vectors successfully identify outlier training samples affected by various confounding factors. This novel exploration technique has remarkable versatility to data types and model architectures and it will facilitate the identification of biases and the discovery of sources of error within training data.