Authors: Susmita Ghosh, Abhiroop Chatterjee
The rapid spread of COVID-19 has necessitated efficient and accurate diagnostic methods. Computed Tomography (CT) scan images have emerged as a valuable tool for detecting the disease. In this article, we present a novel deep learning approach for automated COVID-19 CT scan classification where a modified Xception model is proposed which incorporates a newly designed channel attention mechanism and weighted global average pooling to enhance feature extraction thereby improving classification accuracy. The channel attention module selectively focuses on informative regions within each channel, enabling the model to learn discriminative features for COVID-19 detection. Experiments on a widely used COVID-19 CT scan dataset demonstrate a very good accuracy of 96.99% and show its superiority to other state-of-the-art techniques. This research can contribute to the ongoing efforts in using artificial intelligence to combat current and future pandemics and can offer promising and timely solutions for efficient medical image analysis tasks.
Authors: Muhammet Balcilar, Bharath Bhushan Damodaran, Karam Naser, Franck Galpin, Pierre Hellier
End-to-end image/video codecs are getting competitive compared to traditional compression techniques that have been developed through decades of manual engineering efforts. These trainable codecs have many advantages over traditional techniques such as easy adaptation on perceptual distortion metrics and high performance on specific domains thanks to their learning ability. However, state of the art neural codecs does not take advantage of the existence of gradient of entropy in decoding device. In this paper, we theoretically show that gradient of entropy (available at decoder side) is correlated with the gradient of the reconstruction error (which is not available at decoder side). We then demonstrate experimentally that this gradient can be used on various compression methods, leading to a $1-2\%$ rate savings for the same quality. Our method is orthogonal to other improvements and brings independent rate savings.
Authors: Hengchu Lu, Yuanjie Shao, Xiang Wang, Changxin Gao
Cross-domain few-shot classification (CD-FSC) aims to identify novel target classes with a few samples, assuming that there exists a domain shift between source and target domains. Existing state-of-the-art practices typically pre-train on source domain and then finetune on the few-shot target data to yield task-adaptive representations. Despite promising progress, these methods are prone to overfitting the limited target distribution since data-scarcity and ignore the transferable knowledge learned in the source domain. To alleviate this problem, we propose a simple plug-and-play Adaptive Semantic Consistency (ASC) framework, which improves cross-domain robustness by preserving source transfer capability during the finetuning stage. Concretely, we reuse the source images in the pretraining phase and design an adaptive weight assignment strategy to highlight the samples similar to target domain, aiming to aggregate informative target-related knowledge from source domain. Subsequently, a semantic consistency regularization is applied to constrain the consistency between the semantic features of the source images output by the source model and target model. In this way, the proposed ASC enables explicit transfer of source domain knowledge to prevent the model from overfitting the target domain. Extensive experiments on multiple benchmarks demonstrate the effectiveness of the proposed ASC, and ASC provides consistent improvements over the baselines. The source code will be released.
Authors: Jieming Lou, Weide Liu, Zhuo Chen, Fayao Liu, Jun Cheng
Although existing stereo matching models have achieved continuous improvement, they often face issues related to trustworthiness due to the absence of uncertainty estimation. Additionally, effectively leveraging multi-scale and multi-view knowledge of stereo pairs remains unexplored. In this paper, we introduce the \textbf{E}vidential \textbf{L}ocal-global \textbf{F}usion (ELF) framework for stereo matching, which endows both uncertainty estimation and confidence-aware fusion with trustworthy heads. Instead of predicting the disparity map alone, our model estimates an evidential-based disparity considering both aleatoric and epistemic uncertainties. With the normal inverse-Gamma distribution as a bridge, the proposed framework realizes intra evidential fusion of multi-level predictions and inter evidential fusion between cost-volume-based and transformer-based stereo matching. Extensive experimental results show that the proposed framework exploits multi-view information effectively and achieves state-of-the-art overall performance both on accuracy and cross-domain generalization.
The codes are available at https://github.com/jimmy19991222/ELFNet.
Authors: Hongbo Liu, Mingda Wu, Kun Yuan, Ming Sun, Yansong Tang, Chuanchuan Zheng, Xing Wen, Xiu Li
Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods. To surmount the constraint of insufficient training data, in this paper, we first consider the complete range of video distribution diversity (\ie content, distortion, motion) and employ diverse pretrained models (\eg architecture, pretext task, pre-training dataset) to benefit quality representation. An Adaptive Diverse Quality-aware feature Acquisition (Ada-DQA) framework is proposed to capture desired quality-related features generated by these frozen pretrained models. By leveraging the Quality-aware Acquisition Module (QAM), the framework is able to extract more essential and relevant features to represent quality. Finally, the learned quality representation is utilized as supplementary supervisory information, along with the supervision of the labeled quality score, to guide the training of a relatively lightweight VQA model in a knowledge distillation manner, which largely reduces the computational cost during inference. Experimental results on three mainstream no-reference VQA benchmarks clearly show the superior performance of Ada-DQA in comparison with current state-of-the-art approaches without using extra training data of VQA.
Authors: Preethi Seshadri, Sameer Singh, Yanai Elazar
Bias amplification is a phenomenon in which models increase imbalances present in the training data. In this paper, we study bias amplification in the text-to-image domain using Stable Diffusion by comparing gender ratios in training vs. generated images. We find that the model appears to amplify gender-occupation biases found in the training data (LAION). However, we discover that amplification can largely be attributed to discrepancies between training captions and model prompts. For example, an inherent difference is that captions from the training data often contain explicit gender information while the prompts we use do not, which leads to a distribution shift and consequently impacts bias measures. Once we account for various distributional differences between texts used for training and generation, we observe that amplification decreases considerably. Our findings illustrate the challenges of comparing biases in models and the data they are trained on, and highlight confounding factors that contribute to bias amplification.
Authors: Jinghao Zhang, Jie Huang, Man Zhou, Chongyi Li, Feng Zhao
Learning to restore multiple image degradations within a single model is quite beneficial for real-world applications. Nevertheless, existing works typically concentrate on regarding each degradation independently, while their relationship has been less exploited to ensure the synergistic learning. To this end, we revisit the diverse degradations through the lens of singular value decomposition, with the observation that the decomposed singular vectors and singular values naturally undertake the different types of degradation information, dividing various restoration tasks into two groups,\ie, singular vector dominated and singular value dominated. The above analysis renders a more unified perspective to ascribe the diverse degradations, compared to previous task-level independent learning. The dedicated optimization of degraded singular vectors and singular values inherently utilizes the potential relationship among diverse restoration tasks, attributing to the Decomposition Ascribed Synergistic Learning (DASL). Specifically, DASL comprises two effective operators, namely, Singular VEctor Operator (SVEO) and Singular VAlue Operator (SVAO), to favor the decomposed optimization, which can be lightly integrated into existing convolutional image restoration backbone. Moreover, the congruous decomposition loss has been devised for auxiliary. Extensive experiments on blended five image restoration tasks demonstrate the effectiveness of our method, including image deraining, image dehazing, image denoising, image deblurring, and low-light image enhancement.
Authors: Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
Face rendering using neural radiance fields (NeRF) is a rapidly developing research area in computer vision. While recent methods primarily focus on controlling facial attributes such as identity and expression, they often overlook the crucial aspect of modeling eyeball rotation, which holds importance for various downstream tasks. In this paper, we aim to learn a face NeRF model that is sensitive to eye movements from multi-view images. We address two key challenges in eye-aware face NeRF learning: how to effectively capture eyeball rotation for training and how to construct a manifold for representing eyeball rotation. To accomplish this, we first fit FLAME, a well-established parametric face model, to the multi-view images considering multi-view consistency. Subsequently, we introduce a new Dynamic Eye-aware NeRF (DeNeRF). DeNeRF transforms 3D points from different views into a canonical space to learn a unified face NeRF model. We design an eye deformation field for the transformation, including rigid transformation, e.g., eyeball rotation, and non-rigid transformation. Through experiments conducted on the ETH-XGaze dataset, we demonstrate that our model is capable of generating high-fidelity images with accurate eyeball rotation and non-rigid periocular deformation, even under novel viewing angles. Furthermore, we show that utilizing the rendered images can effectively enhance gaze estimation performance.
Authors: Mingzhan Yang, Guangxin Han, Bin Yan, Wenhua Zhang, Jinqing Qi, Huchuan Lu, Dong Wang
Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames. Most methods accomplish the task by explicitly or implicitly leveraging strong cues (i.e., spatial and appearance information), which exhibit powerful instance-level discrimination. However, when object occlusion and clustering occur, both spatial and appearance information will become ambiguous simultaneously due to the high overlap between objects. In this paper, we demonstrate that this long-standing challenge in MOT can be efficiently and effectively resolved by incorporating weak cues to compensate for strong cues. Along with velocity direction, we introduce the confidence state and height state as potential weak cues. With superior performance, our method still maintains Simple, Online and Real-Time (SORT) characteristics. Furthermore, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner. Significant and consistent improvements are observed when applying our method to 5 different representative trackers. Further, by leveraging both strong and weak cues, our method Hybrid-SORT achieves superior performance on diverse benchmarks, including MOT17, MOT20, and especially DanceTrack where interaction and occlusion are frequent and severe. The code and models are available at https://github.com/ymzis69/HybirdSORT.
Authors: Yufei Zhang, Hanjing Wang, Jeffrey O. Kephart, Qiang Ji
While 3D body reconstruction methods have made remarkable progress recently, it remains difficult to acquire the sufficiently accurate and numerous 3D supervisions required for training. In this paper, we propose \textbf{KNOWN}, a framework that effectively utilizes body \textbf{KNOW}ledge and u\textbf{N}certainty modeling to compensate for insufficient 3D supervisions. KNOWN exploits a comprehensive set of generic body constraints derived from well-established body knowledge. These generic constraints precisely and explicitly characterize the reconstruction plausibility and enable 3D reconstruction models to be trained without any 3D data. Moreover, existing methods typically use images from multiple datasets during training, which can result in data noise (\textit{e.g.}, inconsistent joint annotation) and data imbalance (\textit{e.g.}, minority images representing unusual poses or captured from challenging camera views). KNOWN solves these problems through a novel probabilistic framework that models both aleatoric and epistemic uncertainty. Aleatoric uncertainty is encoded in a robust Negative Log-Likelihood (NLL) training loss, while epistemic uncertainty is used to guide model refinement. Experiments demonstrate that KNOWN's body reconstruction outperforms prior weakly-supervised approaches, particularly on the challenging minority images.
Authors: Abhinav Benagi, Dhanyatha Narayan, Charith Rage, A Sushmitha
The main backbone of our Artificial Eye model is the Raspberry pi3 which is connected to the webcam ,ultrasonic proximity sensor, speaker and we also run all our software models i.e object detection, Optical Character recognition, google text to speech conversion and the Mycroft voice assistance model. At first the ultrasonic proximity sensor will be measuring the distance between itself and any obstacle in front of it .When the Proximity sensor detects any obstacle in front within its specified range, the blind person will hear an audio prompt about an obstacle in his way at a certain distance. At this time the Webcam will capture an image in front of it and the Object detection model and the Optical Character Recognition model will begin to run on the Raspberry pi. The imat of the blind person. The text and the object detected are conveyed to the blind pege captured is first sent through the Tesseract OCR module to detect any texts in the image and then through the Object detection model to detect the objects in fronrson by converting the texts to speech by using the gTTS module. Along with the above mentioned process going on there will be an active MYCROFT voice assistant model which can be used to interact with the blind person. The blind person can ask about the weather , daily news , any information on the internet ,etc
Authors: Md Sakib Hossain Shovon, M. F. Mridha, Khan Md Hasib, Sultan Alfarhood, Mejdl Safran, Dunren Che
Breast Cancer (BC) is among women's most lethal health concerns. Early diagnosis can alleviate the mortality rate by helping patients make efficient treatment decisions. Human Epidermal Growth Factor Receptor (HER2) has become one the most lethal subtype of BC. According to the College of American Pathologists/American Society of Clinical Oncology (CAP/ASCO), the severity level of HER2 expression can be classified between 0 and 3+ range. HER2 can be detected effectively from immunohistochemical (IHC) and, hematoxylin \& eosin (HE) images of different classes such as 0, 1+, 2+, and 3+. An ensemble approach integrated with threshold filtered single instance evaluation (SIE) technique has been proposed in this study to diagnose BC from the multi-categorical expression of HER2 subtypes. Initially, DenseNet201 and Xception have been ensembled into a single classifier as feature extractors with an effective combination of global average pooling, dropout layer, dense layer with a swish activation function, and l2 regularizer, batch normalization, etc. After that, extracted features has been processed through single instance evaluation (SIE) to determine different confidence levels and adjust decision boundary among the imbalanced classes. This study has been conducted on the BC immunohistochemical (BCI) dataset, which is classified by pathologists into four stages of HER2 BC. This proposed approach known as DenseNet201-Xception-SIE with a threshold value of 0.7 surpassed all other existing state-of-art models with an accuracy of 97.12\%, precision of 97.15\%, and recall of 97.68\% on H\&E data and, accuracy of 97.56\%, precision of 97.57\%, and recall of 98.00\% on IHC data respectively, maintaining momentous improvement. Finally, Grad-CAM and Guided Grad-CAM have been employed in this study to interpret, how TL-based model works on the histopathology dataset and make decisions from the data.
Authors: Sizhe Guan, Haolan Liu, Hamid R. Pourreza, Hamidreza Mahyar
This paper presents a comprehensive review of recent advancements in image processing and deep learning techniques for pavement distress detection and classification, a critical aspect in modern pavement management systems. The conventional manual inspection process conducted by human experts is gradually being superseded by automated solutions, leveraging machine learning and deep learning algorithms to enhance efficiency and accuracy. The ability of these algorithms to discern patterns and make predictions based on extensive datasets has revolutionized the domain of pavement distress identification. The paper investigates the integration of unmanned aerial vehicles (UAVs) for data collection, offering unique advantages such as aerial perspectives and efficient coverage of large areas. By capturing high-resolution images, UAVs provide valuable data that can be processed using deep learning algorithms to detect and classify various pavement distresses effectively. While the primary focus is on 2D image processing, the paper also acknowledges the challenges associated with 3D images, such as sensor limitations and computational requirements. Understanding these challenges is crucial for further advancements in the field. The findings of this review significantly contribute to the evolution of pavement distress detection, fostering the development of efficient pavement management systems. As automated approaches continue to mature, the implementation of deep learning techniques holds great promise in ensuring safer and more durable road infrastructure for the benefit of society.
Authors: Muhammad A. Shah, Bhiksha Raj
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks -- subtle, perceptually indistinguishable perturbations of inputs that change the response of the model. In the context of vision, we hypothesize that an important contributor to the robustness of human visual perception is constant exposure to low-fidelity visual stimuli in our peripheral vision. To investigate this hypothesis, we develop \RBlur, an image transform that simulates the loss in fidelity of peripheral vision by blurring the image and reducing its color saturation based on the distance from a given fixation point. We show that compared to DNNs trained on the original images, DNNs trained on images transformed by \RBlur are substantially more robust to adversarial attacks, as well as other, non-adversarial, corruptions, achieving up to 25\% higher accuracy on perturbed data.
Authors: Yasheng Sun, Yifan Yang, Houwen Peng, Yifei Shen, Yuqing Yang, Han Hu, Lili Qiu, Hideki Koike
While language-guided image manipulation has made remarkable progress, the challenge of how to instruct the manipulation process faithfully reflecting human intentions persists. An accurate and comprehensive description of a manipulation task using natural language is laborious and sometimes even impossible, primarily due to the inherent uncertainty and ambiguity present in linguistic expressions. Is it feasible to accomplish image manipulation without resorting to external cross-modal language information? If this possibility exists, the inherent modality gap would be effortlessly eliminated. In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing. Our key idea is to employ a pair of transformation images as visual instructions, which not only precisely captures human intention but also facilitates accessibility in real-world scenarios. Capturing visual instructions is particularly challenging because it involves extracting the underlying intentions solely from visual demonstrations and then applying this operation to a new image. To address this challenge, we formulate visual instruction learning as a diffusion-based inpainting problem, where the contextual information is fully exploited through an iterative process of generation. A visual prompting encoder is carefully devised to enhance the model's capacity in uncovering human intent behind the visual instructions. Extensive experiments show that our method generates engaging manipulation results conforming to the transformations entailed in demonstrations. Moreover, our model exhibits robust generalization capabilities on various downstream tasks such as pose transfer, image translation and video inpainting.
Authors: Dongjia Zhao, Lei Qi, Xiao Shi, Yinghuan Shi, Xin Geng
Single domain generalization aims to enhance the ability of the model to generalize to unknown domains when trained on a single source domain. However, the limited diversity in the training data hampers the learning of domain-invariant features, resulting in compromised generalization performance. To address this, data perturbation (augmentation) has emerged as a crucial method to increase data diversity. Nevertheless, existing perturbation methods often focus on either image-level or feature-level perturbations independently, neglecting their synergistic effects. To overcome these limitations, we propose CPerb, a simple yet effective cross-perturbation method. Specifically, CPerb utilizes both horizontal and vertical operations. Horizontally, it applies image-level and feature-level perturbations to enhance the diversity of the training data, mitigating the issue of limited diversity in single-source domains. Vertically, it introduces multi-route perturbation to learn domain-invariant features from different perspectives of samples with the same semantic category, thereby enhancing the generalization capability of the model. Additionally, we propose MixPatch, a novel feature-level perturbation method that exploits local image style information to further diversify the training data. Extensive experiments on various benchmark datasets validate the effectiveness of our method.
Authors: Yuzhu Li, Nir Pillar, Jingxi Li, Tairan Liu, Di Wu, Songyu Sun, Guangdong Ma, Kevin de Haan, Luzhe Huang, Sepehr Hamidi, Anatoly Urisman, Tal Keidar Haran, William Dean Wallace, Jonathan E. Zuckerman, Aydogan Ozcan
Histological examination is a crucial step in an autopsy; however, the traditional histochemical staining of post-mortem samples faces multiple challenges, including the inferior staining quality due to autolysis caused by delayed fixation of cadaver tissue, as well as the resource-intensive nature of chemical staining procedures covering large tissue areas, which demand substantial labor, cost, and time. These challenges can become more pronounced during global health crises when the availability of histopathology services is limited, resulting in further delays in tissue fixation and more severe staining artifacts. Here, we report the first demonstration of virtual staining of autopsy tissue and show that a trained neural network can rapidly transform autofluorescence images of label-free autopsy tissue sections into brightfield equivalent images that match hematoxylin and eosin (H&E) stained versions of the same samples, eliminating autolysis-induced severe staining artifacts inherent in traditional histochemical staining of autopsied tissue. Our virtual H&E model was trained using >0.7 TB of image data and a data-efficient collaboration scheme that integrates the virtual staining network with an image registration network. The trained model effectively accentuated nuclear, cytoplasmic and extracellular features in new autopsy tissue samples that experienced severe autolysis, such as COVID-19 samples never seen before, where the traditional histochemical staining failed to provide consistent staining quality. This virtual autopsy staining technique can also be extended to necrotic tissue, and can rapidly and cost-effectively generate artifact-free H&E stains despite severe autolysis and cell death, also reducing labor, cost and infrastructure requirements associated with the standard histochemical staining.
Authors: Chowdhury Sadman Jahan, Andreas Savakis
Domain adaptation (DA) strives to mitigate the domain gap between the source domain where a model is trained, and the target domain where the model is deployed. When a deep learning model is deployed on an aerial platform, it may face gradually degrading weather conditions during operation, leading to widening domain gaps between the training data and the encountered evaluation data. We synthesize two such gradually worsening weather conditions on real images from two existing aerial imagery datasets, generating a total of four benchmark datasets. Under the continual, or test-time adaptation setting, we evaluate three DA models on our datasets: a baseline standard DA model and two continual DA models. In such setting, the models can access only one small portion, or one batch of the target data at a time, and adaptation takes place continually, and over only one epoch of the data. The combination of the constraints of continual adaptation, and gradually deteriorating weather conditions provide the practical DA scenario for aerial deployment. Among the evaluated models, we consider both convolutional and transformer architectures for comparison. We discover stability issues during adaptation for existing buffer-fed continual DA methods, and offer gradient normalization as a simple solution to curb training instability.
Authors: Samia Sultana, Shyla Afroge
Astronomical images provide information about the great variety of cosmic objects in the Universe. Due to the large volumes of data, the presence of innumerable bright point sources as well as noise within the frame and the spatial gap between objects and satellite cameras, it is a challenging task to classify and detect the celestial objects. We propose an Adaptive Thresholding Method (ATM) based segmentation and Back Propagation Neural Network (BPNN) based cosmic object detection including a well-structured series of pre-processing steps designed to enhance segmentation and detection.
Authors: Suncheng Xiang, Qingzhong Chen, Shilun Cai, Chengfeng Zhou, Crystal Cai, Sijia Du, Dahong Qian
Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras and plays an important role in the prevention and treatment of colorectal cancer in computer-aided diagnosis. However, traditional methods for object ReID directly adopting CNN models trained on the ImageNet dataset usually produce unsatisfactory retrieval performance on colonoscopic datasets due to the large domain gap. Additionally, these methods neglect to explore the potential of self-discrepancy among intra-class relations in the colonoscopic polyp dataset, which remains an open research problem in the medical community. To solve this dilemma, we propose a simple but effective training method named Colo-ReID, which can help our model to learn more general and discriminative knowledge based on the meta-learning strategy in scenarios with fewer samples. Based on this, a dynamic Meta-Learning Regulation mechanism called MLR is introduced to further boost the performance of polyp re-identification. To the best of our knowledge, this is the first attempt to leverage the meta-learning paradigm instead of traditional machine learning to effectively train deep models in the task of colonoscopic polyp re-identification. Empirical results show that our method significantly outperforms current state-of-the-art methods by a clear margin.
Authors: Zengxi Zhang, Zhiying Jiang, Jinyuan Liu, Xin Fan, Risheng Liu
Underwater images suffer from light refraction and absorption, which impairs visibility and interferes the subsequent applications. Existing underwater image enhancement methods mainly focus on image quality improvement, ignoring the effect on practice. To balance the visual quality and application, we propose a heuristic normalizing flow for detection-driven underwater image enhancement, dubbed WaterFlow. Specifically, we first develop an invertible mapping to achieve the translation between the degraded image and its clear counterpart. Considering the differentiability and interpretability, we incorporate the heuristic prior into the data-driven mapping procedure, where the ambient light and medium transmission coefficient benefit credible generation. Furthermore, we introduce a detection perception module to transmit the implicit semantic guidance into the enhancement procedure, where the enhanced images hold more detection-favorable features and are able to promote the detection performance. Extensive experiments prove the superiority of our WaterFlow, against state-of-the-art methods quantitatively and qualitatively.
Authors: Zhenyuan Ning, Yixiao Mao, Qianjin Feng, Shengzhou Zhong, Yu Zhang
Complex scenario of ultrasound image, in which adjacent tissues (i.e., background) share similar intensity with and even contain richer texture patterns than lesion region (i.e., foreground), brings a unique challenge for accurate lesion segmentation. This work presents a decomposition-coupling network, called DC-Net, to deal with this challenge in a (foreground-background) saliency map disentanglement-fusion manner. The DC-Net consists of decomposition and coupling subnets, and the former preliminarily disentangles original image into foreground and background saliency maps, followed by the latter for accurate segmentation under the assistance of saliency prior fusion. The coupling subnet involves three aspects of fusion strategies, including: 1) regional feature aggregation (via differentiable context pooling operator in the encoder) to adaptively preserve local contextual details with the larger receptive field during dimension reduction; 2) relation-aware representation fusion (via cross-correlation fusion module in the decoder) to efficiently fuse low-level visual characteristics and high-level semantic features during resolution restoration; 3) dependency-aware prior incorporation (via coupler) to reinforce foreground-salient representation with the complementary information derived from background representation. Furthermore, a harmonic loss function is introduced to encourage the network to focus more attention on low-confidence and hard samples. The proposed method is evaluated on two ultrasound lesion segmentation tasks, which demonstrates the remarkable performance improvement over existing state-of-the-art methods.
Authors: Yuchen Shen, Dong Zhang, Yuhui Zheng, Zechao Li, Liyong Fu, Qiaolin Ye
In recent years, the development of instance segmentation has garnered significant attention in a wide range of applications. However, the training of a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In contrast, weakly-supervised instance segmentation methods (i.e., with image-level class labels or point labels) struggle to satisfy the accuracy and recall requirements of practical scenarios. In this paper, we propose a novel paradigm for instance segmentation called training-free instance segmentation (TFISeg), which achieves instance segmentation results from image masks predicted using off-the-shelf semantic segmentation models. TFISeg does not require training a semantic or/and instance segmentation model and avoids the need for instance-level image annotations. Therefore, it is highly efficient. Specifically, we first obtain a semantic segmentation mask of the input image via a trained semantic segmentation model. Then, we calculate a displacement field vector for each pixel based on the segmentation mask, which can indicate representations belonging to the same class but different instances, i.e., obtaining the instance-level object information. Finally, instance segmentation results are obtained after being refined by a learnable category-agnostic object boundary branch. Extensive experimental results on two challenging datasets and representative semantic segmentation baselines (including CNNs and Transformers) demonstrate that TFISeg can achieve competitive results compared to the state-of-the-art fully-supervised instance segmentation methods without the need for additional human resources or increased computational costs. The code is available at: TFISeg
Authors: Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Neil Houlsby
Sparse mixture of expert architectures (MoEs) scale model capacity without large increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to scale the number of experts, or ineffective finetuning. In this work, we proposeSoft MoE, a fully-differentiable sparse Transformer that addresses these challenges, while maintaining the benefits of MoEs. Soft MoE performs an implicit soft assignment by passing different weighted combinations of all input tokens to each expert. As in other MoE works, experts in Soft MoE only process a subset of the (combined) tokens, enabling larger model capacity at lower inference cost. In the context of visual recognition, Soft MoE greatly outperforms standard Transformers (ViTs) and popular MoE variants (Tokens Choice and Experts Choice). For example, Soft MoE-Base/16 requires 10.5x lower inference cost (5.7x lower wall-clock time) than ViT-Huge/14 while matching its performance after similar training. Soft MoE also scales well: Soft MoE Huge/14 with 128 experts in 16 MoE layers has over 40x more parameters than ViT Huge/14, while inference time cost grows by only 2%, and it performs substantially better.
Authors: Chowdhury Sadman Jahan, Andreas Savakis
Addressing the rising concerns of privacy and security, domain adaptation in the dark aims to adapt a black-box source trained model to an unlabeled target domain without access to any source data or source model parameters. The need for domain adaptation of black-box predictors becomes even more pronounced to protect intellectual property as deep learning based solutions are becoming increasingly commercialized. Current methods distill noisy predictions on the target data obtained from the source model to the target model, and/or separate clean/noisy target samples before adapting using traditional noisy label learning algorithms. However, these methods do not utilize the easy-to-hard learning nature of the clean/noisy data splits. Also, none of the existing methods are end-to-end, and require a separate fine-tuning stage and an initial warmup stage. In this work, we present Curriculum Adaptation for Black-Box (CABB) which provides a curriculum guided adaptation approach to gradually train the target model, first on target data with high confidence (clean) labels, and later on target data with noisy labels. CABB utilizes Jensen-Shannon divergence as a better criterion for clean-noisy sample separation, compared to the traditional criterion of cross entropy loss. Our method utilizes co-training of a dual-branch network to suppress error accumulation resulting from confirmation bias. The proposed approach is end-to-end trainable and does not require any extra finetuning stage, unlike existing methods. Empirical results on standard domain adaptation datasets show that CABB outperforms existing state-of-the-art black-box DA models and is comparable to white-box domain adaptation models.
Authors: Jiucui Lu, Yuezun Li, Jiaran Zhou, Bin Li, Junyu Dong, Siwei Lyu
The prominent progress in generative models has significantly improved the reality of generated faces, bringing serious concerns to society. Since recent GAN-generated faces are in high realism, the forgery traces have become more imperceptible, increasing the forensics challenge. To combat GAN-generated faces, many countermeasures based on Convolutional Neural Networks (CNNs) have been spawned due to their strong learning ability. In this paper, we rethink this problem and explore a new approach based on forest models instead of CNNs. Specifically, we describe a simple and effective forest-based method set called {\em ForensicsForest Family} to detect GAN-generate faces. The proposed ForensicsForest family is composed of three variants, which are {\em ForensicsForest}, {\em Hybrid ForensicsForest} and {\em Divide-and-Conquer ForensicsForest} respectively. ForenscisForest is a newly proposed Multi-scale Hierarchical Cascade Forest, which takes semantic, frequency and biology features as input, hierarchically cascades different levels of features for authenticity prediction, and then employs a multi-scale ensemble scheme that can comprehensively consider different levels of information to improve the performance further. Based on ForensicsForest, we develop Hybrid ForensicsForest, an extended version that integrates the CNN layers into models, to further refine the effectiveness of augmented features. Moreover, to reduce the memory cost in training, we propose Divide-and-Conquer ForensicsForest, which can construct a forest model using only a portion of training samplings. In the training stage, we train several candidate forest models using the subsets of training samples. Then a ForensicsForest is assembled by picking the suitable components from these candidate forest models...
Authors: Fabian Deuser, Konrad Habel, Martin Werner, Norbert Oswald
Retrieving relevant multimedia content is one of the main problems in a world that is increasingly data-driven. With the proliferation of drones, high quality aerial footage is now available to a wide audience for the first time. Integrating this footage into applications can enable GPS-less geo-localisation or location correction.
In this paper, we present an orientation-guided training framework for UAV-view geo-localisation. Through hierarchical localisation orientations of the UAV images are estimated in relation to the satellite imagery. We propose a lightweight prediction module for these pseudo labels which predicts the orientation between the different views based on the contrastive learned embeddings. We experimentally demonstrate that this prediction supports the training and outperforms previous approaches. The extracted pseudo-labels also enable aligned rotation of the satellite image as augmentation to further strengthen the generalisation. During inference, we no longer need this orientation module, which means that no additional computations are required. We achieve state-of-the-art results on both the University-1652 and University-160k datasets.
Authors: Moon Ye-Bin, Nam Hyeon-Woo, Wonseok Choi, Nayeong Kim, Suha Kwak, Tae-Hyun Oh
We live in a vast ocean of data, and deep neural networks are no exception to this. However, this data exhibits an inherent phenomenon of imbalance. This imbalance poses a risk of deep neural networks producing biased predictions, leading to potentially severe ethical and social consequences. To address these challenges, we believe that the use of generative models is a promising approach for comprehending tasks, given the remarkable advancements demonstrated by recent diffusion models in generating high-quality images. In this work, we propose a simple yet effective baseline, SYNAuG, that utilizes synthetic data as a preliminary step before employing task-specific algorithms to address data imbalance problems. This straightforward approach yields impressive performance on datasets such as CIFAR100-LT, ImageNet100-LT, UTKFace, and Waterbird, surpassing the performance of existing task-specific methods. While we do not claim that our approach serves as a complete solution to the problem of data imbalance, we argue that supplementing the existing data with synthetic data proves to be an effective and crucial preliminary step in addressing data imbalance concerns.
Authors: Louis Soum-Fontez, Jean-Emmanuel Deschaud, François Goulette
Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data from the target domain may not be available for finetuning or for domain adaptation methods. Indeed, 3D object detection models trained on a source dataset with a specific point distribution have shown difficulties in generalizing to unseen datasets. Therefore, we decided to leverage the information available from several annotated source datasets with our Multi-Dataset Training for 3D Object Detection (MDT3D) method to increase the robustness of 3D object detection models when tested in a new environment with a different sensor configuration. To tackle the labelling gap between datasets, we used a new label mapping based on coarse labels. Furthermore, we show how we managed the mix of datasets during training and finally introduce a new cross-dataset augmentation method: cross-dataset object injection. We demonstrate that this training paradigm shows improvements for different types of 3D object detection models. The source code and additional results for this research project will be publicly available on GitHub for interested parties to access and utilize: https://github.com/LouisSF/MDT3D
Authors: Tengju Ye, Wei Jing, Chunyong Hu, Shikun Huang, Lingping Gao, Fangzhen Li, Jingke Wang, Ke Guo, Wencong Xiao, Weibo Mao, Hang Zheng, Kun Li, Junbo Chen, Kaicheng Yu
Building a multi-modality multi-task neural network toward accurate and robust performance is a de-facto standard in perception task of autonomous driving. However, leveraging such data from multiple sensors to jointly optimize the prediction and planning tasks remains largely unexplored. In this paper, we present FusionAD, to the best of our knowledge, the first unified framework that fuse the information from two most critical sensors, camera and LiDAR, goes beyond perception task. Concretely, we first build a transformer based multi-modality fusion network to effectively produce fusion based features. In constrast to camera-based end-to-end method UniAD, we then establish a fusion aided modality-aware prediction and status-aware planning modules, dubbed FMSPnP that take advantages of multi-modality features. We conduct extensive experiments on commonly used benchmark nuScenes dataset, our FusionAD achieves state-of-the-art performance and surpassing baselines on average 15% on perception tasks like detection and tracking, 10% on occupancy prediction accuracy, reducing prediction error from 0.708 to 0.389 in ADE score and reduces the collision rate from 0.31% to only 0.12%.
Authors: Nanami Kotani, Asako Kanezaki
One of the intuitive instruction methods in robot navigation is a pointing gesture. In this study, we propose a method using an omnidirectional camera to eliminate the user/object position constraint and the left/right constraint of the pointing arm. Although the accuracy of skeleton and object detection is low due to the high distortion of equirectangular images, the proposed method enables highly accurate estimation by repeatedly extracting regions of interest from the equirectangular image and projecting them onto perspective images. Furthermore, we found that training the likelihood of the target object in machine learning further improves the estimation accuracy.
Authors: Hyunjun Choi, JaeHo Chung, Hawook Jeong, Jin Young Choi
In the problem of out-of-distribution (OOD) detection, the usage of auxiliary data as outlier data for fine-tuning has demonstrated encouraging performance. However, previous methods have suffered from a trade-off between classification accuracy (ACC) and OOD detection performance (AUROC, FPR, AUPR). To improve this trade-off, we make three contributions: (i) Incorporating a self-knowledge distillation loss can enhance the accuracy of the network; (ii) Sampling semi-hard outlier data for training can improve OOD detection performance with minimal impact on accuracy; (iii) The introduction of our novel supervised contrastive learning can simultaneously improve OOD detection performance and the accuracy of the network. By incorporating all three factors, our approach enhances both accuracy and OOD detection performance by addressing the trade-off between classification and OOD detection. Our method achieves improvements over previous approaches in both performance metrics.
Authors: Leyla Benhamida, Khadidja Delloul, Slimane Larabi
Computer vision was long a tool used for aiding visually impaired people to move around their environment and avoid obstacles and falls. Solutions are limited to either indoor or outdoor scenes, which limits the kind of places and scenes visually disabled people can be in, including entertainment places such as theatres. Furthermore, most of the proposed computer-vision-based methods rely on RGB benchmarks to train their models resulting in a limited performance due to the absence of the depth modality.
In this paper, we propose a novel RGB-D dataset containing theatre scenes with ground truth human actions and dense captions annotations for image captioning and human action recognition: TS-RGBD dataset. It includes three types of data: RGB, depth, and skeleton sequences, captured by Microsoft Kinect.
We test image captioning models on our dataset as well as some skeleton-based human action recognition models in order to extend the range of environment types where a visually disabled person can be, by detecting human actions and textually describing appearances of regions of interest in theatre scenes.
Authors: Xingjian Wang, Li Chai, Jiming Chen, Zhiguo Shi
Multispectral pedestrian detection achieves better visibility in challenging conditions and thus has a broad application in various tasks, for which both the accuracy and computational cost are of paramount importance. Most existing approaches treat RGB and infrared modalities equally, typically adopting two symmetrical CNN backbones for multimodal feature extraction, which ignores the substantial differences between modalities and brings great difficulty for the reduction of the computational cost as well as effective crossmodal fusion. In this work, we propose a novel and efficient framework named WCCNet that is able to differentially extract rich features of different spectra with lower computational complexity and semantically rearranges these features for effective crossmodal fusion. Specifically, the discrete wavelet transform (DWT) allowing fast inference and training speed is embedded to construct a dual-stream backbone for efficient feature extraction. The DWT layers of WCCNet extract frequency components for infrared modality, while the CNN layers extract spatial-domain features for RGB modality. This methodology not only significantly reduces the computational complexity, but also improves the extraction of infrared features to facilitate the subsequent crossmodal fusion. Based on the well extracted features, we elaborately design the crossmodal rearranging fusion module (CMRF), which can mitigate spatial misalignment and merge semantically complementary features of spatially-related local regions to amplify the crossmodal complementary information. We conduct comprehensive evaluations on KAIST and FLIR benchmarks, in which WCCNet outperforms state-of-the-art methods with considerable computational efficiency and competitive accuracy. We also perform the ablation study and analyze thoroughly the impact of different components on the performance of WCCNet.
Authors: Quan Tang, Bowen Zhang, Jiajun Liu, Fagiu Liu, Yifan Liu
Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs and outputs usually imply more tokens involved in computations. Directly removing the less attentive tokens has been discussed for the image classification task but can not be extended to semantic segmentation since a dense prediction is required for every patch. To this end, this work introduces a Dynamic Token Pruning (DToP) method based on the early exit of tokens for semantic segmentation. Motivated by the coarse-to-fine segmentation process by humans, we naturally split the widely adopted auxiliary-loss-based network architecture into several stages, where each auxiliary block grades every token's difficulty level. We can finalize the prediction of easy tokens in advance without completing the entire forward pass. Moreover, we keep $k$ highest confidence tokens for each semantic category to uphold the representative context information. Thus, computational complexity will change with the difficulty of the input, akin to the way humans do segmentation. Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.
Authors: Yijun Yang, Shujun Wang, Lihao Liu, Sarah Hickman, Fiona J Gilbert, Carola-Bibiane Schönlieb, Angelica I. Aviles-Rivero
Breast cancer is a major cause of cancer death among women, emphasising the importance of early detection for improved treatment outcomes and quality of life. Mammography, the primary diagnostic imaging test, poses challenges due to the high variability and patterns in mammograms. Double reading of mammograms is recommended in many screening programs to improve diagnostic accuracy but increases radiologists' workload. Researchers explore Machine Learning models to support expert decision-making. Stand-alone models have shown comparable or superior performance to radiologists, but some studies note decreased sensitivity with multiple datasets, indicating the need for high generalisation and robustness models. This work devises MammoDG, a novel deep-learning framework for generalisable and reliable analysis of cross-domain multi-center mammography data. MammoDG leverages multi-view mammograms and a novel contrastive mechanism to enhance generalisation capabilities. Extensive validation demonstrates MammoDG's superiority, highlighting the critical importance of domain generalisation for trustworthy mammography analysis in imaging protocol variations.
Authors: Ivano Donadi, Emilio Olivastri, Daniel Fusaro, Wanmeng Li, Daniele Evangelista, Alberto Pretto
Autonomous navigation in underwater environments presents challenges due to factors such as light absorption and water turbidity, limiting the effectiveness of optical sensors. Sonar systems are commonly used for perception in underwater operations as they are unaffected by these limitations. Traditional computer vision algorithms are less effective when applied to sonar-generated acoustic images, while convolutional neural networks (CNNs) typically require large amounts of labeled training data that are often unavailable or difficult to acquire. To this end, we propose a novel compact deep sonar descriptor pipeline that can generalize to real scenarios while being trained exclusively on synthetic data. Our architecture is based on a ResNet18 back-end and a properly parameterized random Gaussian projection layer, whereas input sonar data is enhanced with standard ad-hoc normalization/prefiltering techniques. A customized synthetic data generation procedure is also presented. The proposed method has been evaluated extensively using both synthetic and publicly available real data, demonstrating its effectiveness compared to state-of-the-art methods.
Authors: Giacomo D'Amicantonio, Egor Bondarau, Peter H.N. De With
Surveillance videos and images are used for a broad set of applications, ranging from traffic analysis to crime detection. Extrinsic camera calibration data is important for most analysis applications. However, security cameras are susceptible to environmental conditions and small camera movements, resulting in a need for an automated re-calibration method that can account for these varying conditions. In this paper, we present an automated camera-calibration process leveraging a dictionary-based approach that does not require prior knowledge on any camera settings. The method consists of a custom implementation of a Spatial Transformer Network (STN) and a novel topological loss function. Experiments reveal that the proposed method improves the IoU metric by up to 12% w.r.t. a state-of-the-art model across five synthetic datasets and the World Cup 2014 dataset.
Authors: Gianluca Amprimo, Giulia Masi, Giuseppe Pettiti, Gabriella Olmo, Lorenzo Priano, Claudia Ferraris
Accurate 3D tracking of hand and fingers movements poses significant challenges in computer vision. The potential applications span across multiple domains, including human-computer interaction, virtual reality, industry, and medicine. While gesture recognition has achieved remarkable accuracy, quantifying fine movements remains a hurdle, particularly in clinical applications where the assessment of hand dysfunctions and rehabilitation training outcomes necessitate precise measurements. Several novel and lightweight frameworks based on Deep Learning have emerged to address this issue; however, their performance in accurately and reliably measuring fingers movements requires validation against well-established gold standard systems. In this paper, the aim is to validate the handtracking framework implemented by Google MediaPipe Hand (GMH) and an innovative enhanced version, GMH-D, that exploits the depth estimation of an RGB-Depth camera to achieve more accurate tracking of 3D movements. Three dynamic exercises commonly administered by clinicians to assess hand dysfunctions, namely Hand Opening-Closing, Single Finger Tapping and Multiple Finger Tapping are considered. Results demonstrate high temporal and spectral consistency of both frameworks with the gold standard. However, the enhanced GMH-D framework exhibits superior accuracy in spatial measurements compared to the baseline GMH, for both slow and fast movements. Overall, our study contributes to the advancement of hand tracking technology, the establishment of a validation procedure as a good-practice to prove efficacy of deep-learning-based hand-tracking, and proves the effectiveness of GMH-D as a reliable framework for assessing 3D hand movements in clinical applications.
Authors: Jinpeng Lin, Min Zhou, Ye Ma, Yifan Gao, Chenxi Fei, Yangjian Chen, Zhang Yu, Tiezheng Ge
Advertising posters, a form of information presentation, combine visual and linguistic modalities. Creating a poster involves multiple steps and necessitates design experience and creativity. This paper introduces AutoPoster, a highly automatic and content-aware system for generating advertising posters. With only product images and titles as inputs, AutoPoster can automatically produce posters of varying sizes through four key stages: image cleaning and retargeting, layout generation, tagline generation, and style attribute prediction. To ensure visual harmony of posters, two content-aware models are incorporated for layout and tagline generation. Moreover, we propose a novel multi-task Style Attribute Predictor (SAP) to jointly predict visual style attributes. Meanwhile, to our knowledge, we propose the first poster generation dataset that includes visual attribute annotations for over 76k posters. Qualitative and quantitative outcomes from user studies and experiments substantiate the efficacy of our system and the aesthetic superiority of the generated posters compared to other poster generation methods.
Authors: Jiexin Wang, Yujie Zhou, Wenwen Qiang, Ying Ba, Bing Su, Ji-Rong Wen
Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications, but it remains a challenging task due to the stochastic and aperiodic nature of future poses. Traditional methods rely on hand-crafted features and machine learning techniques, which often struggle to model the complex dynamics of human motion. Recent deep learning-based methods have achieved success by learning spatio-temporal representations of motion, but these models often overlook the reliability of motion data. Additionally, the temporal and spatial dependencies of skeleton nodes are distinct. The temporal relationship captures motion information over time, while the spatial relationship describes body structure and the relationships between different nodes. In this paper, we propose a novel spatio-temporal branching network using incremental information for HMP, which decouples the learning of temporal-domain and spatial-domain features, extracts more motion information, and achieves complementary cross-domain knowledge learning through knowledge distillation. Our approach effectively reduces noise interference and provides more expressive information for characterizing motion by separately extracting temporal and spatial features. We evaluate our approach on standard HMP benchmarks and outperform state-of-the-art methods in terms of prediction accuracy.
Authors: Misgina Tsighe Hagos, Kathleen M. Curran, Brian Mac Namee
Medical image classification models are frequently trained using training datasets derived from multiple data sources. While leveraging multiple data sources is crucial for achieving model generalization, it is important to acknowledge that the diverse nature of these sources inherently introduces unintended confounders and other challenges that can impact both model accuracy and transparency. A notable confounding factor in medical image classification, particularly in musculoskeletal image classification, is skeletal maturation-induced bone growth observed during adolescence. We train a deep learning model using a Covid-19 chest X-ray dataset and we showcase how this dataset can lead to spurious correlations due to unintended confounding regions. eXplanation Based Learning (XBL) is a deep learning approach that goes beyond interpretability by utilizing model explanations to interactively unlearn spurious correlations. This is achieved by integrating interactive user feedback, specifically feature annotations. In our study, we employed two non-demanding manual feedback mechanisms to implement an XBL-based approach for effectively eliminating these spurious correlations. Our results underscore the promising potential of XBL in constructing robust models even in the presence of confounding factors.
Authors: Shenbagaraj Kannapiran, Nalin Bendapudi, Ming-Yuan Yu, Devarth Parikh, Spring Berman, Ankit Vora, Gaurav Pandey
Robust feature matching forms the backbone for most Visual Simultaneous Localization and Mapping (vSLAM), visual odometry, 3D reconstruction, and Structure from Motion (SfM) algorithms. However, recovering feature matches from texture-poor scenes is a major challenge and still remains an open area of research. In this paper, we present a Stereo Visual Odometry (StereoVO) technique based on point and line features which uses a novel feature-matching mechanism based on an Attention Graph Neural Network that is designed to perform well even under adverse weather conditions such as fog, haze, rain, and snow, and dynamic lighting conditions such as nighttime illumination and glare scenarios. We perform experiments on multiple real and synthetic datasets to validate the ability of our method to perform StereoVO under low visibility weather and lighting conditions through robust point and line matches. The results demonstrate that our method achieves more line feature matches than state-of-the-art line matching algorithms, which when complemented with point feature matches perform consistently well in adverse weather and dynamic lighting conditions.
Authors: Kanzhi Cheng, Wenpo Song, Zheng Ma, Wenhao Zhu, Zixuan Zhu, Jianbing Zhang
Current captioning approaches tend to generate correct but "generic" descriptions that lack real-world knowledge, e.g., named entities and contextual information. Considering that Vision-Language Pre-Training (VLP) models master massive such knowledge from large-scale web-harvested data, it is promising to utilize the generalizability of VLP models to incorporate knowledge into image descriptions. However, using VLP models faces challenges: zero-shot inference suffers from knowledge hallucination that leads to low-quality descriptions, but the generic bias in downstream task fine-tuning hinders the VLP model from expressing knowledge. To address these concerns, we propose a simple yet effective method called Knowledge-guided Replay (K-Replay), which enables the retention of pre-training knowledge during fine-tuning. Our approach consists of two parts: (1) a knowledge prediction task on automatically collected replay exemplars to continuously awaken the VLP model's memory about knowledge, thus preventing the model from collapsing into the generic pattern; (2) a knowledge distillation constraint to improve the faithfulness of generated descriptions hence alleviating the knowledge hallucination. To evaluate knowledge-enhanced descriptions, we construct a novel captioning benchmark KnowCap, containing knowledge of landmarks, famous brands, special foods and movie characters. Experimental results show that our approach effectively incorporates knowledge into descriptions, outperforming strong VLP baseline by 20.9 points (78.7->99.6) in CIDEr score and 20.5 percentage points (34.0%->54.5%) in knowledge recognition accuracy. Our code and data is available at https://github.com/njucckevin/KnowCap.
Authors: Jingfan Chen, Yuxi Wang, Pengfei Wang, Xiao Chen, Zhaoxiang Zhang, Zhen Lei, Qing Li
The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes. Previous work has introduced generative replay, which involves replaying old class samples generated from a pre-trained GAN, to address the issues of catastrophic forgetting and privacy concerns. However, the generated images lack semantic precision and exhibit out-of-distribution characteristics, resulting in inaccurate masks that further degrade the segmentation performance. To tackle these challenges, we propose DiffusePast, a novel framework featuring a diffusion-based generative replay module that generates semantically accurate images with more reliable masks guided by different instructions (e.g., text prompts or edge maps). Specifically, DiffusePast introduces a dual-generator paradigm, which focuses on generating old class images that align with the distribution of downstream datasets while preserving the structure and layout of the original images, enabling more precise masks. To adapt to the novel visual concepts of newly added classes continuously, we incorporate class-wise token embedding when updating the dual-generator. Moreover, we assign adequate pseudo-labels of old classes to the background pixels in the new step images, further mitigating the forgetting of previously learned knowledge. Through comprehensive experiments, our method demonstrates competitive performance across mainstream benchmarks, striking a better balance between the performance of old and novel classes.
Authors: Dimitrios Tsourounis, Ilias Theodorakopoulos, Elias N. Zois, George Economou
This paper introduces a novel approach to leverage the knowledge of existing expert models for training new Convolutional Neural Networks, on domains where task-specific data are limited or unavailable. The presented scheme is applied in offline handwritten signature verification (OffSV) which, akin to other biometric applications, suffers from inherent data limitations due to regulatory restrictions. The proposed Student-Teacher (S-T) configuration utilizes feature-based knowledge distillation (FKD), combining graph-based similarity for local activations with global similarity measures to supervise student's training, using only handwritten text data. Remarkably, the models trained using this technique exhibit comparable, if not superior, performance to the teacher model across three popular signature datasets. More importantly, these results are attained without employing any signatures during the feature extraction training process. This study demonstrates the efficacy of leveraging existing expert models to overcome data scarcity challenges in OffSV and potentially other related domains.
Authors: Weronika Hryniewska-Guzik, Maria Kędzierska, Przemysław Biecek
Lung cancer and covid-19 have one of the highest morbidity and mortality rates in the world. For physicians, the identification of lesions is difficult in the early stages of the disease and time-consuming. Therefore, multi-task learning is an approach to extracting important features, such as lesions, from small amounts of medical data because it learns to generalize better. We propose a novel multi-task framework for classification, segmentation, reconstruction, and detection. To the best of our knowledge, we are the first ones who added detection to the multi-task solution. Additionally, we checked the possibility of using two different backbones and different loss functions in the segmentation task.
Authors: Siladittya Manna, Soumitri Chattopadhyay, Rakesh Dey, Saumik Bhattacharya, Umapada Pal
In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples from different classes is primarily affected by the presence of hard negative samples. While the InfoNCE loss has been shown to impose penalties based on hardness, the temperature hyper-parameter is the key to regulating the penalties and the trade-off between uniformity and tolerance. In this work, we focus our attention to improve the performance of InfoNCE loss in SSL by studying the effect of temperature hyper-parameter values. We propose a cosine similarity-dependent temperature scaling function to effectively optimize the distribution of the samples in the feature space. We further analyze the uniformity and tolerance metrics to investigate the optimal regions in the cosine similarity space for better optimization. Additionally, we offer a comprehensive examination of the behavior of local and global structures in the feature space throughout the pre-training phase, as the temperature varies. Experimental evidence shows that the proposed framework outperforms or is at par with the contrastive loss-based SSL algorithms. We believe our work (DySTreSS) on temperature scaling in SSL provides a foundation for future research in contrastive learning.
Authors: Kanzhi Cheng, Zheng Ma, Shi Zong, Jianbing Zhang, Xinyu Dai, Jiajun Chen
Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns. In this paper, we propose a novel framework to generate Accurate and Diverse Stylized Captions (ADS-Cap). Our ADS-Cap first uses a contrastive learning module to align the image and text features, which unifies paired factual and unpaired stylistic corpora during the training process. A conditional variational auto-encoder is then used to automatically memorize diverse stylistic patterns in latent space and enhance diversity through sampling. We also design a simple but effective recheck module to boost style accuracy by filtering style-specific captions. Experimental results on two widely used stylized image captioning datasets show that regarding consistency with the image, style accuracy and diversity, ADS-Cap achieves outstanding performances compared to various baselines. We finally conduct extensive analyses to understand the effectiveness of our method. Our code is available at https://github.com/njucckevin/ADS-Cap.
Authors: Qingsong Xu, Yilei Shi, Jianhua Guo, Chaojun Ouyang, Xiao Xiang Zhu
Change detection (CD) by comparing two bi-temporal images is a crucial task in remote sensing. With the advantages of requiring no cumbersome labeled change information, unsupervised CD has attracted extensive attention in the community. However, existing unsupervised CD approaches rarely consider the seasonal and style differences incurred by the illumination and atmospheric conditions in multi-temporal images. To this end, we propose a change detection with domain shift setting for remote sensing images. Furthermore, we present a novel unsupervised CD method using a light-weight transformer, called UCDFormer. Specifically, a transformer-driven image translation composed of a light-weight transformer and a domain-specific affinity weight is first proposed to mitigate domain shift between two images with real-time efficiency. After image translation, we can generate the difference map between the translated before-event image and the original after-event image. Then, a novel reliable pixel extraction module is proposed to select significantly changed/unchanged pixel positions by fusing the pseudo change maps of fuzzy c-means clustering and adaptive threshold. Finally, a binary change map is obtained based on these selected pixel pairs and a binary classifier. Experimental results on different unsupervised CD tasks with seasonal and style changes demonstrate the effectiveness of the proposed UCDFormer. For example, compared with several other related methods, UCDFormer improves performance on the Kappa coefficient by more than 12\%. In addition, UCDFormer achieves excellent performance for earthquake-induced landslide detection when considering large-scale applications. The code is available at \url{https://github.com/zhu-xlab/UCDFormer}
Authors: Guojin Zhong, Jin Yuan, Pan Wang, Kailun Yang, Weili Guan, Zhiyong Li
The recently rising markup-to-image generation poses greater challenges as compared to natural image generation, due to its low tolerance for errors as well as the complex sequence and context correlations between markup and rendered image. This paper proposes a novel model named "Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment" (FSA-CDM), which introduces contrastive positive/negative samples into the diffusion model to boost performance for markup-to-image generation. Technically, we design a fine-grained cross-modal alignment module to well explore the sequence similarity between the two modalities for learning robust feature representations. To improve the generalization ability, we propose a contrast-augmented diffusion model to explicitly explore positive and negative samples by maximizing a novel contrastive variational objective, which is mathematically inferred to provide a tighter bound for the model's optimization. Moreover, the context-aware cross attention module is developed to capture the contextual information within markup language during the denoising process, yielding better noise prediction results. Extensive experiments are conducted on four benchmark datasets from different domains, and the experimental results demonstrate the effectiveness of the proposed components in FSA-CDM, significantly exceeding state-of-the-art performance by about 2%-12% DTW improvements. The code will be released at https://github.com/zgj77/FSACDM.
Authors: Huzheng Yang, James Gee, Jianbo Shi
We explore a new class of brain encoding model by adding memory-related information as input. Memory is an essential brain mechanism that works alongside visual stimuli. During a vision-memory cognitive task, we found the non-visual brain is largely predictable using previously seen images. Our Memory Encoding Model (Mem) won the Algonauts 2023 visual brain competition even without model ensemble (single model score 66.8, ensemble score 70.8). Our ensemble model without memory input (61.4) can also stand a 3rd place. Furthermore, we observe periodic delayed brain response correlated to 6th-7th prior image, and hippocampus also showed correlated activity timed with this periodicity. We conjuncture that the periodic replay could be related to memory mechanism to enhance the working memory.
Authors: Yiyang Sun, Xiaonian Wang, Yangyang Zhang, Jiagui Tang, Xiaqiang Tang, Jing Yao
Driving scene understanding is to obtain comprehensive scene information through the sensor data and provide a basis for downstream tasks, which is indispensable for the safety of self-driving vehicles. Specific perception tasks, such as object detection and scene graph generation, are commonly used. However, the results of these tasks are only equivalent to the characterization of sampling from high-dimensional scene features, which are not sufficient to represent the scenario. In addition, the goal of perception tasks is inconsistent with human driving that just focuses on what may affect the ego-trajectory. Therefore, we propose an end-to-end Interpretable Implicit Driving Scene Understanding (II-DSU) model to extract implicit high-dimensional scene features as scene understanding results guided by a planning module and to validate the plausibility of scene understanding using auxiliary perception tasks for visualization. Experimental results on CARLA benchmarks show that our approach achieves the new state-of-the-art and is able to obtain scene features that embody richer scene information relevant to driving, enabling superior performance of the downstream planning.
Authors: Fengbei Liu, Yuanhong Chen, Chong Wang, Yuyuan Liu, Gustavo Carneiro
The learning with noisy labels has been addressed with both discriminative and generative models. Although discriminative models have dominated the field due to their simpler modeling and more efficient computational training processes, generative models offer a more effective means of disentangling clean and noisy labels and improving the estimation of the label transition matrix. However, generative approaches maximize the joint likelihood of noisy labels and data using a complex formulation that only indirectly optimizes the model of interest associating data and clean labels. Additionally, these approaches rely on generative models that are challenging to train and tend to use uninformative clean label priors. In this paper, we propose a new generative noisy-label learning approach that addresses these three issues. First, we propose a new model optimisation that directly associates data and clean labels. Second, the generative model is implicitly estimated using a discriminative model, eliminating the inefficient training of a generative model. Third, we propose a new informative label prior inspired by partial label learning as supervision signal for noisy label learning. Extensive experiments on several noisy-label benchmarks demonstrate that our generative model provides state-of-the-art results while maintaining a similar computational complexity as discriminative models.
Authors: Yongkang He, Mingjin Chen, Zhijing Yang, Yongyi Lu
This paper seeks to address the dense labeling problems where a significant fraction of the dataset can be pruned without sacrificing much accuracy. We observe that, on standard medical image segmentation benchmarks, the loss gradient norm-based metrics of individual training examples applied in image classification fail to identify the important samples. To address this issue, we propose a data pruning method by taking into consideration the training dynamics on target regions using Dynamic Average Dice (DAD) score. To the best of our knowledge, we are among the first to address the data importance in dense labeling tasks in the field of medical image analysis, making the following contributions: (1) investigating the underlying causes with rigorous empirical analysis, and (2) determining effective data pruning approach in dense labeling problems. Our solution can be used as a strong yet simple baseline to select important examples for medical image segmentation with combined data sources.
Authors: Siao Liu, Zhaoyu Chen, Yang Liu, Yuzheng Wang, Dingkang Yang, Zhile Zhao, Ziqing Zhou, Xie Yi, Wei Li, Wenqiang Zhang, Zhongxue Gan
Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combination in the supervised learning generalization, naively applying it to visual RL algorithms may damage the training efficiency, suffering from serve performance degradation. In this paper, we first conduct qualitative analysis and illuminate the main causes: (i) high-variance gradient magnitudes and (ii) gradient conflicts existed in various augmentation methods. To alleviate these issues, we propose a general policy gradient optimization framework, named Conflict-aware Gradient Agreement Augmentation (CG2A), and better integrate augmentation combination into visual RL algorithms to address the generalization bias. In particular, CG2A develops a Gradient Agreement Solver to adaptively balance the varying gradient magnitudes, and introduces a Soft Gradient Surgery strategy to alleviate the gradient conflicts. Extensive experiments demonstrate that CG2A significantly improves the generalization performance and sample efficiency of visual RL algorithms.
Authors: Jorge Paz-Ruza, Amparo Alonso-Betanzos, Berta Guijarro-Berdiñas, Brais Cancela, Carlos Eiras-Franco
Recommender Systems have become crucial in the modern world, commonly guiding users towards relevant content or products, and having a large influence over the decisions of users and citizens. However, ensuring transparency and user trust in these systems remains a challenge; personalized explanations have emerged as a solution, offering justifications for recommendations. Among the existing approaches for generating personalized explanations, using visual content created by the users is one particularly promising option, showing a potential to maximize transparency and user trust. Existing models for explaining recommendations in this context face limitations: sustainability has been a critical concern, as they often require substantial computational resources, leading to significant carbon emissions comparable to the Recommender Systems where they would be integrated. Moreover, most models employ surrogate learning goals that do not align with the objective of ranking the most effective personalized explanations for a given recommendation, leading to a suboptimal learning process and larger model sizes. To address these limitations, we present BRIE, a novel model designed to tackle the existing challenges by adopting a more adequate learning goal based on Bayesian Pairwise Ranking, enabling it to achieve consistently superior performance than state-of-the-art models in six real-world datasets, while exhibiting remarkable efficiency, emitting up to 75% less CO${_2}$ during training and inference with a model up to 64 times smaller than previous approaches.
Authors: Kaibin Tian, Ruixiang Zhao, Hu Hu, Runquan Xie, Fengzong Lian, Zhanhui Kang, Xirong Li
For text-to-video retrieval (T2VR), which aims to retrieve unlabeled videos by ad-hoc textual queries, CLIP-based methods are dominating. Compared to CLIP4Clip which is efficient and compact, the state-of-the-art models tend to compute video-text similarity by fine-grained cross-modal feature interaction and matching, putting their scalability for large-scale T2VR into doubt. For efficient T2VR, we propose TeachCLIP with multi-grained teaching to let a CLIP4Clip based student network learn from more advanced yet computationally heavy models such as X-CLIP, TS2-Net and X-Pool . To improve the student's learning capability, we add an Attentional frame-Feature Aggregation (AFA) block, which by design adds no extra storage/computation overhead at the retrieval stage. While attentive weights produced by AFA are commonly used for combining frame-level features, we propose a novel use of the weights to let them imitate frame-text relevance estimated by the teacher network. As such, AFA provides a fine-grained learning (teaching) channel for the student (teacher). Extensive experiments on multiple public datasets justify the viability of the proposed method.
Authors: Yu Wu, Yana Wei, Haozhe Wang, Yongfei Liu, Sibei Yang, Xuming He
This paper introduces Grounded Image Text Matching with Mismatched Relation (GITM-MR), a novel visual-linguistic joint task that evaluates the relation understanding capabilities of transformer-based pre-trained models. GITM-MR requires a model to first determine if an expression describes an image, then localize referred objects or ground the mismatched parts of the text. We provide a benchmark for evaluating pre-trained models on this task, with a focus on the challenging settings of limited data and out-of-distribution sentence lengths. Our evaluation demonstrates that pre-trained models lack data efficiency and length generalization ability. To address this, we propose the Relation-sensitive Correspondence Reasoning Network (RCRN), which incorporates relation-aware reasoning via bi-directional message propagation guided by language structure. RCRN can be interpreted as a modular program and delivers strong performance in both length generalization and data efficiency.
Authors: Fenghe Tang, Jianrui Ding, Lingtao Wang, Chunping Ning, S. Kevin Zhou
The U-shaped architecture has emerged as a crucial paradigm in the design of medical image segmentation networks. However, due to the inherent local limitations of convolution, a fully convolutional segmentation network with U-shaped architecture struggles to effectively extract global context information, which is vital for the precise localization of lesions. While hybrid architectures combining CNNs and Transformers can address these issues, their application in real medical scenarios is limited due to the computational resource constraints imposed by the environment and edge devices. In addition, the convolutional inductive bias in lightweight networks adeptly fits the scarce medical data, which is lacking in the Transformer based network. In order to extract global context information while taking advantage of the inductive bias, we propose CMUNeXt, an efficient fully convolutional lightweight medical image segmentation network, which enables fast and accurate auxiliary diagnosis in real scene scenarios. CMUNeXt leverages large kernel and inverted bottleneck design to thoroughly mix distant spatial and location information, efficiently extracting global context information. We also introduce the Skip-Fusion block, designed to enable smooth skip-connections and ensure ample feature fusion. Experimental results on multiple medical image datasets demonstrate that CMUNeXt outperforms existing heavyweight and lightweight medical image segmentation networks in terms of segmentation performance, while offering a faster inference speed, lighter weights, and a reduced computational cost. The code is available at https://github.com/FengheTan9/CMUNeXt.
Authors: Jyotirmaya Shivottam, Subhankar Mishra
Digital preservation of Cultural Heritage (CH) sites is crucial to protect them against damage from natural disasters or human activities. Creating 3D models of CH sites has become a popular method of digital preservation thanks to advancements in computer vision and photogrammetry. However, the process is time-consuming, expensive, and typically requires specialized equipment and expertise, posing challenges in resource-limited developing countries. Additionally, the lack of an open repository for 3D models hinders research and public engagement with their heritage. To address these issues, we propose Tirtha, a web platform for crowdsourcing images of CH sites and creating their 3D models. Tirtha utilizes state-of-the-art Structure from Motion (SfM) and Multi-View Stereo (MVS) techniques. It is modular, extensible and cost-effective, allowing for the incorporation of new techniques as photogrammetry advances. Tirtha is accessible through a web interface at https://tirtha.niser.ac.in and can be deployed on-premise or in a cloud environment. In our case studies, we demonstrate the pipeline's effectiveness by creating 3D models of temples in Odisha, India, using crowdsourced images. These models are available for viewing, interaction, and download on the Tirtha website. Our work aims to provide a dataset of crowdsourced images and 3D reconstructions for research in computer vision, heritage conservation, and related domains. Overall, Tirtha is a step towards democratizing digital preservation, primarily in resource-limited developing countries.
Authors: Vincenzo Mariano Scarrica, Ciro Panariello, Alessio Ferone, Antonino Staiano
Multi-Object Tracking, also known as Multi-Target Tracking, is a significant area of computer vision that has many uses in a variety of settings. The development of deep learning, which has encouraged researchers to propose more and more work in this direction, has significantly impacted the scientific advancement around the study of tracking as well as many other domains related to computer vision. In fact, all of the solutions that are currently state-of-the-art in the literature and in the tracking industry, are built on top of deep learning methodologies that produce exceptionally good results. Deep learning is enabled thanks to the ever more powerful technology researchers can use to handle the significant computational resources demanded by these models. However, when real-time is a main requirement, developing a tracking system without being constrained by expensive hardware support with enormous computational resources is necessary to widen tracking applications in real-world contexts. To this end, a compromise is to combine powerful deep strategies with more traditional approaches to favor considerably lower processing solutions at the cost of less accurate tracking results even though suitable for real-time domains. Indeed, the present work goes in that direction, proposing a hybrid strategy for real-time multi-target tracking that combines effectively a classical optical flow algorithm with a deep learning architecture, targeted to a human-crowd tracking system exhibiting a desirable trade-off between performance in tracking precision and computational costs. The developed architecture was experimented with different settings, and yielded a MOTA of 0.608 out of the compared state-of-the-art 0.549 results, and about half the running time when introducing the optical flow phase, achieving almost the same performance in terms of accuracy.
Authors: Yiming Zhou, Yuexing Peng, Wei Li, Junchuan Yu, Daqing Ge, Wei Xiang
As a harzard disaster, landslide often brings tremendous losses to humanity, so it's necessary to achieve reliable detection of landslide. However, the problems of visual blur and small-sized dataset cause great challenges for old landslide detection task when using remote sensing data. To reliably extract semantic features, a hyper-pixel-wise contrastive learning augmented segmentation network (HPCL-Net) is proposed, which augments the local salient feature extraction from the boundaries of landslides through HPCL and fuses the heterogeneous infromation in the semantic space from High-Resolution Remote Sensing Images and Digital Elevation Model Data data. For full utilization of the precious samples, a global hyper-pixel-wise sample pair queues-based contrastive learning method, which includes the construction of global queues that store hyper-pixel-wise samples and the updating scheme of a momentum encoder, is developed, reliably enhancing the extraction ability of semantic features. The proposed HPCL-Net is evaluated on a Loess Plateau old landslide dataset and experiment results show that the model greatly improves the reliablity of old landslide detection compared to the previous old landslide segmentation model, where mIoU metric is increased from 0.620 to 0.651, Landslide IoU metric is increased from 0.334 to 0.394 and F1-score metric is increased from 0.501 to 0.565.
Authors: Vincenzo Mariano Scarrica, Antonino Staiano
Long-Term tracking is a hot topic in Computer Vision. In this context, competitive models are presented every year, showing a constant growth rate in performances, mainly measured in standardized protocols as Visual Object Tracking (VOT) and Object Tracking Benchmark (OTB). Fusion-trackers strategy has been applied over last few years for overcoming the known re-detection problem, turning out to be an important breakthrough. Following this approach, this work aims to generalize the fusion concept to an arbitrary number of trackers used as baseline trackers in the pipeline, leveraging a learning phase to better understand how outcomes correlate with each other, even when no target is present. A model and data independence conjecture will be evidenced in the manuscript, yielding a recall of 0.738 on LTB-50 dataset when learning from VOT-LT2022, and 0.619 by reversing the two datasets. In both cases, results are strongly competitive with state-of-the-art and recall turns out to be the first on the podium.
Authors: Michael Gableman, Avinash Kak
As a result of Shadow NeRF and Sat-NeRF, it is possible to take the solar angle into account in a NeRF-based framework for rendering a scene from a novel viewpoint using satellite images for training. Our work extends those contributions and shows how one can make the renderings season-specific. Our main challenge was creating a Neural Radiance Field (NeRF) that could render seasonal features independently of viewing angle and solar angle while still being able to render shadows. We teach our network to render seasonal features by introducing one more input variable -- time of the year. However, the small training datasets typical of satellite imagery can introduce ambiguities in cases where shadows are present in the same location for every image of a particular season. We add additional terms to the loss function to discourage the network from using seasonal features for accounting for shadows. We show the performance of our network on eight Areas of Interest containing images captured by the Maxar WorldView-3 satellite. This evaluation includes tests measuring the ability of our framework to accurately render novel views, generate height maps, predict shadows, and specify seasonal features independently from shadows. Our ablation studies justify the choices made for network design parameters.
Authors: Suruchi Kumari, Pravendra Singh
Deep learning has demonstrated remarkable performance across various tasks in medical imaging. However, these approaches primarily focus on supervised learning, assuming that the training and testing data are drawn from the same distribution. Unfortunately, this assumption may not always hold true in practice. To address these issues, unsupervised domain adaptation (UDA) techniques have been developed to transfer knowledge from a labeled domain to a related but unlabeled domain. In recent years, significant advancements have been made in UDA, resulting in a wide range of methodologies, including feature alignment, image translation, self-supervision, and disentangled representation methods, among others. In this paper, we provide a comprehensive literature review of recent deep UDA approaches in medical imaging from a technical perspective. Specifically, we categorize current UDA research in medical imaging into six groups and further divide them into finer subcategories based on the different tasks they perform. We also discuss the respective datasets used in the studies to assess the divergence between the different domains. Finally, we discuss emerging areas and provide insights and discussions on future research directions to conclude this survey.
Authors: Yan Ma, Weicong Liang, Yiduo Hao, Bohan Chen, Xiangyu Yue, Chao Zhang, Yuhui Yuan
Motivated by that DETR-based approaches have established new records on COCO detection and segmentation benchmarks, many recent endeavors show increasing interest in how to further improve DETR-based approaches by pre-training the Transformer in a self-supervised manner while keeping the backbone frozen. Some studies already claimed significant improvements in accuracy. In this paper, we take a closer look at their experimental methodology and check if their approaches are still effective on the very recent state-of-the-art such as $\mathcal{H}$-Deformable-DETR. We conduct thorough experiments on COCO object detection tasks to study the influence of the choice of pre-training datasets, localization, and classification target generation schemes. Unfortunately, we find the previous representative self-supervised approach such as DETReg, fails to boost the performance of the strong DETR-based approaches on full data regimes. We further analyze the reasons and find that simply combining a more accurate box predictor and Objects$365$ benchmark can significantly improve the results in follow-up experiments. We demonstrate the effectiveness of our approach by achieving strong object detection results of AP=$59.3\%$ on COCO val set, which surpasses $\mathcal{H}$-Deformable-DETR + Swin-L by +$1.4\%$. Last, we generate a series of synthetic pre-training datasets by combining the very recent image-to-text captioning models (LLaVA) and text-to-image generative models (SDXL). Notably, pre-training on these synthetic datasets leads to notable improvements in object detection performance. Looking ahead, we anticipate substantial advantages through the future expansion of the synthetic pre-training dataset.
Authors: Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang
CLIP, as a foundational vision language model, is widely used in zero-shot image classification due to its ability to understand various visual concepts and natural language descriptions. However, how to fully leverage CLIP's unprecedented human-like understanding capabilities to achieve better zero-shot classification is still an open question. This paper draws inspiration from the human visual perception process: a modern neuroscience view suggests that in classifying an object, humans first infer its class-independent attributes (e.g., background and orientation) which help separate the foreground object from the background, and then make decisions based on this information. Inspired by this, we observe that providing CLIP with contextual attributes improves zero-shot classification and mitigates reliance on spurious features. We also observe that CLIP itself can reasonably infer the attributes from an image. With these observations, we propose a training-free, two-step zero-shot classification method named PerceptionCLIP. Given an image, it first infers contextual attributes (e.g., background) and then performs object classification conditioning on them. Our experiments show that PerceptionCLIP achieves better generalization, group robustness, and better interpretability. For example, PerceptionCLIP with ViT-L/14 improves the worst group accuracy by 16.5% on the Waterbirds dataset and by 3.5% on CelebA.
Authors: Zheng Ding, Mengqi Zhang, Jiajun Wu, Zhuowen Tu
We propose an effective denoising diffusion model for generating high-resolution images (e.g., 1024$\times$512), trained on small-size image patches (e.g., 64$\times$64). We name our algorithm Patch-DM, in which a new feature collage strategy is designed to avoid the boundary artifact when synthesizing large-size images. Feature collage systematically crops and combines partial features of the neighboring patches to predict the features of a shifted image patch, allowing the seamless generation of the entire image due to the overlap in the patch feature space. Patch-DM produces high-quality image synthesis results on our newly collected dataset of nature images (1024$\times$512), as well as on standard benchmarks of smaller sizes (256$\times$256), including LSUN-Bedroom, LSUN-Church, and FFHQ. We compare our method with previous patch-based generation methods and achieve state-of-the-art FID scores on all four datasets. Further, Patch-DM also reduces memory complexity compared to the classic diffusion models.
Authors: Shawn Xu, Lin Yang, Christopher Kelly, Marcin Sieniek, Timo Kohlberger, Martin Ma, Wei-Hung Weng, Attila Kiraly, Sahar Kazemzadeh, Zakkai Melamed, Jungyeon Park, Patricia Strachan, Yun Liu, Chuck Lau, Preeti Singh, Christina Chen, Mozziyar Etemadi, Sreenivasa Raju Kalidindi, Yossi Matias, Katherine Chou, Greg S. Corrado, Shravya Shetty, Daniel Tse, Shruthi Prabhakara, Daniel Golden, Rory Pilgrim, Krish Eswaran, Andrew Sellergren
Our approach, which we call Embeddings for Language/Image-aligned X-Rays, or ELIXR, leverages a language-aligned image encoder combined or grafted onto a fixed LLM, PaLM 2, to perform a broad range of tasks. We train this lightweight adapter architecture using images paired with corresponding free-text radiology reports from the MIMIC-CXR dataset. ELIXR achieved state-of-the-art performance on zero-shot chest X-ray (CXR) classification (mean AUC of 0.850 across 13 findings), data-efficient CXR classification (mean AUCs of 0.893 and 0.898 across five findings (atelectasis, cardiomegaly, consolidation, pleural effusion, and pulmonary edema) for 1% (~2,200 images) and 10% (~22,000 images) training data), and semantic search (0.76 normalized discounted cumulative gain (NDCG) across nineteen queries, including perfect retrieval on twelve of them). Compared to existing data-efficient methods including supervised contrastive learning (SupCon), ELIXR required two orders of magnitude less data to reach similar performance. ELIXR also showed promise on CXR vision-language tasks, demonstrating overall accuracies of 58.7% and 62.5% on visual question answering and report quality assurance tasks, respectively. These results suggest that ELIXR is a robust and versatile approach to CXR AI.
Authors: Federico Pernici, Matteo Bruni, Claudio Baecchi, Francesco Turchini, Alberto Del Bimbo
In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired knowledge. To address this problem, effective methods exploit past data stored in an episodic memory while expanding the final classifier nodes to accommodate the new classes.
In this work, we substitute the expanding classifier with a novel fixed classifier in which a number of pre-allocated output nodes are subject to the classification loss right from the beginning of the learning phase. Contrarily to the standard expanding classifier, this allows: (a) the output nodes of future unseen classes to firstly see negative samples since the beginning of learning together with the positive samples that incrementally arrive; (b) to learn features that do not change their geometric configuration as novel classes are incorporated in the learning model.
Experiments with public datasets show that the proposed approach is as effective as the expanding classifier while exhibiting novel intriguing properties of the internal feature representation that are otherwise not-existent. Our ablation study on pre-allocating a large number of classes further validates the approach.
Authors: Sangrok Lee, Taekang Woo, Sang Hun Lee
Vehicle re-identification helps in distinguishing between images of the same and other vehicles. It is a challenging process because of significant intra-instance differences between identical vehicles from different views and subtle inter-instance differences between similar vehicles. To solve this issue, researchers have extracted view-aware or part-specific features via spatial attention mechanisms, which usually result in noisy attention maps or otherwise require expensive additional annotation for metadata, such as key points, to improve the quality. Meanwhile, based on the researchers' insights, various handcrafted multi-attention architectures for specific viewpoints or vehicle parts have been proposed. However, this approach does not guarantee that the number and nature of attention branches will be optimal for real-world re-identification tasks. To address these problems, we proposed a new vehicle re-identification network based on a multiple soft attention mechanism for capturing various discriminative regions from different viewpoints more efficiently. Furthermore, this model can significantly reduce the noise in spatial attention maps by devising a new method for creating an attention map for insignificant regions and then excluding it from generating the final result. We also combined a channel-wise attention mechanism with a spatial attention mechanism for the efficient selection of important semantic attributes for vehicle re-identification. Our experiments showed that our proposed model achieved a state-of-the-art performance among the attention-based methods without metadata and was comparable to the approaches using metadata for the VehicleID and VERI-Wild datasets.
Authors: Yuemeng Li, Miguel Romanello Joaquim, Stephen Pickup, Hee Kwon Song, Rong Zhou, Yong Fan
Purpose: To accelerate radially sampled diffusion weighted spin-echo (Rad-DW-SE) acquisition method for generating high quality apparent diffusion coefficient (ADC) maps. Methods: A deep learning method was developed to generate accurate ADC maps from accelerated DWI data acquired with the Rad-DW-SE method. The deep learning method integrates convolutional neural networks (CNNs) with vision transformers to generate high quality ADC maps from accelerated DWI data, regularized by a monoexponential ADC model fitting term. A model was trained on DWI data of 147 mice and evaluated on DWI data of 36 mice, with acceleration factors of 4x and 8x compared to the original acquisition parameters. We have made our code publicly available at GitHub: https://github.com/ymli39/DeepADC-Net-Learning-Apparent-Diffusion-Coefficient-Maps, and our dataset can be downloaded at https://pennpancreaticcancerimagingresource.github.io/data.html. Results: Ablation studies and experimental results have demonstrated that the proposed deep learning model generates higher quality ADC maps from accelerated DWI data than alternative deep learning methods under comparison when their performance is quantified in whole images as well as in regions of interest, including tumors, kidneys, and muscles. Conclusions: The deep learning method with integrated CNNs and transformers provides an effective means to accurately compute ADC maps from accelerated DWI data acquired with the Rad-DW-SE method.
Authors: Yibo Liu, Jinjun Shan, Hunter Schofield
The LiDAR fiducial marker, akin to the well-known AprilTag used in camera applications, serves as a convenient resource to impart artificial features to the LiDAR sensor, facilitating robotics applications. Unfortunately, current LiDAR fiducial marker detection methods are limited to occlusion-free point clouds. In this work, we present a novel approach for occlusion-resistant LiDAR fiducial marker detection. We first extract 3D points potentially corresponding to the markers, leveraging the 3D intensity gradients. Afterward, we analyze the 3D spatial distribution of the extracted points through clustering. Subsequently, we determine the potential marker locations by examining the geometric characteristics of these clusters. We then successively transfer the 3D points that fall within the candidate locations from the raw point cloud onto a designed intermediate plane. Finally, using the intermediate plane, we validate each location for the presence of a fiducial marker and compute the marker's pose if found. We conduct both qualitative and quantitative experiments to demonstrate that our approach is the first LiDAR fiducial marker detection method applicable to point clouds with occlusion while achieving better accuracy.
Authors: Mu-Jung Chen, Yi-Hsin Chen, Wen-Hsiao Peng
Over the past few years, learning-based video compression has become an active research area. However, most works focus on P-frame coding. Learned B-frame coding is under-explored and more challenging. This work introduces a novel B-frame coding framework, termed B-CANF, that exploits conditional augmented normalizing flows for B-frame coding. B-CANF additionally features two novel elements: frame-type adaptive coding and B*-frames. Our frame-type adaptive coding learns better bit allocation for hierarchical B-frame coding by dynamically adapting the feature distributions according to the B-frame type. Our B*-frames allow greater flexibility in specifying the group-of-pictures (GOP) structure by reusing the B-frame codec to mimic P-frame coding, without the need for an additional, separate P-frame codec. On commonly used datasets, B-CANF achieves the state-of-the-art compression performance as compared to the other learned B-frame codecs and shows comparable BD-rate results to HM-16.23 under the random access configuration in terms of PSNR. When evaluated on different GOP structures, our B*-frames achieve similar performance to the additional use of a separate P-frame codec.
Authors: Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Dingkang Yang, Lingyi Hong, Pinxue Guo, Haijing Guo, Wenqiang Zhang
Deep neural networks are vulnerable to adversarial examples, which attach human invisible perturbations to benign inputs. Simultaneously, adversarial examples exhibit transferability under different models, which makes practical black-box attacks feasible. However, existing methods are still incapable of achieving desired transfer attack performance. In this work, from the perspective of gradient optimization and consistency, we analyze and discover the gradient elimination phenomenon as well as the local momentum optimum dilemma. To tackle these issues, we propose Global Momentum Initialization (GI) to suppress gradient elimination and help search for the global optimum. Specifically, we perform gradient pre-convergence before the attack and carry out a global search during the pre-convergence stage. Our method can be easily combined with almost all existing transfer methods, and we improve the success rate of transfer attacks significantly by an average of 6.4% under various advanced defense mechanisms compared to state-of-the-art methods. Eventually, we achieve an attack success rate of 95.4%, fully illustrating the insecurity of existing defense mechanisms. Code is available at $\href{https://github.com/Omenzychen/Global-Momentum-Initialization}{this\ URL}$.
Authors: German Barquero, Sergio Escalera, Cristina Palmero
Stochastic human motion prediction (HMP) has generally been tackled with generative adversarial networks and variational autoencoders. Most prior works aim at predicting highly diverse movements in terms of the skeleton joints' dispersion. This has led to methods predicting fast and motion-divergent movements, which are often unrealistic and incoherent with past motion. Such methods also neglect contexts that need to anticipate diverse low-range behaviors, or actions, with subtle joint displacements. To address these issues, we present BeLFusion, a model that, for the first time, leverages latent diffusion models in HMP to sample from a latent space where behavior is disentangled from pose and motion. As a result, diversity is encouraged from a behavioral perspective. Thanks to our behavior coupler's ability to transfer sampled behavior to ongoing motion, BeLFusion's predictions display a variety of behaviors that are significantly more realistic than the state of the art. To support it, we introduce two metrics, the Area of the Cumulative Motion Distribution, and the Average Pairwise Distance Error, which are correlated to our definition of realism according to a qualitative study with 126 participants. Finally, we prove BeLFusion's generalization power in a new cross-dataset scenario for stochastic HMP.
Authors: Noah Barrett, Zahra Sadeghi, Stan Matwin
Self-supervised Learning (SSL) is a machine learning algorithm for pretraining Deep Neural Networks (DNNs) without requiring manually labeled data. The central idea of this learning technique is based on an auxiliary stage aka pretext task in which labeled data are created automatically through data augmentation and exploited for pretraining the DNN. However, the effect of each pretext task is not well studied or compared in the literature. In this paper, we study the contribution of augmentation operators on the performance of self supervised learning algorithms in a constrained settings. We propose an evolutionary search method for optimization of data augmentation pipeline in pretext tasks and measure the impact of augmentation operators in several SOTA SSL algorithms. By encoding different combination of augmentation operators in chromosomes we seek the optimal augmentation policies through an evolutionary optimization mechanism. We further introduce methods for analyzing and explaining the performance of optimized SSL algorithms. Our results indicate that our proposed method can find solutions that outperform the accuracy of classification of SSL algorithms which confirms the influence of augmentation policy choice on the overall performance of SSL algorithms. We also compare optimal SSL solutions found by our evolutionary search mechanism and show the effect of batch size in the pretext task on two visual datasets.
Authors: Vincent Gaudillière, Leo Pauly, Arunkumar Rathinam, Albert Garcia Sanchez, Mohamed Adel Musallam, Djamila Aouada
To automatically localize a target object in an image is crucial for many computer vision applications. To represent the 2D object, ellipse labels have recently been identified as a promising alternative to axis-aligned bounding boxes. This paper further considers 3D-aware ellipse labels, \textit{i.e.}, ellipses which are projections of a 3D ellipsoidal approximation of the object, for 2D target localization. Indeed, projected ellipses carry more geometric information about the object geometry and pose (3D awareness) than traditional 3D-agnostic bounding box labels. Moreover, such a generic 3D ellipsoidal model allows for approximating known to coarsely known targets. We then propose to have a new look at ellipse regression and replace the discontinuous geometric ellipse parameters with the parameters of an implicit Gaussian distribution encoding object occupancy in the image. The models are trained to regress the values of this bivariate Gaussian distribution over the image pixels using a statistical loss function. We introduce a novel non-trainable differentiable layer, E-DSNT, to extract the distribution parameters. Also, we describe how to readily generate consistent 3D-aware Gaussian occupancy parameters using only coarse dimensions of the target and relative pose labels. We extend three existing spacecraft pose estimation datasets with 3D-aware Gaussian occupancy labels to validate our hypothesis. Labels and source code are publicly accessible here: https://cvi2.uni.lu/3d-aware-obj-loc/.
Authors: Ekta U. Samani, Feng Tao, Harshavardhan R. Dasari, Sihao Ding, Ashis G. Banerjee
Bird's Eye View (BEV) representations are tremendously useful for perception-related automated driving tasks. However, generating BEVs from surround-view fisheye camera images is challenging due to the strong distortions introduced by such wide-angle lenses. We take the first step in addressing this challenge and introduce a baseline, F2BEV, to generate discretized BEV height maps and BEV semantic segmentation maps from fisheye images. F2BEV consists of a distortion-aware spatial cross attention module for querying and consolidating spatial information from fisheye image features in a transformer-style architecture followed by a task-specific head. We evaluate single-task and multi-task variants of F2BEV on our synthetic FB-SSEM dataset, all of which generate better BEV height and segmentation maps (in terms of the IoU) than a state-of-the-art BEV generation method operating on undistorted fisheye images. We also demonstrate discretized height map generation from real-world fisheye images using F2BEV. Our dataset is publicly available at https://github.com/volvo-cars/FB-SSEM-dataset
Authors: Zhen Wang, Jun Xiao, Yueting Zhuang, Fei Gao, Jian Shao, Long Chen
Controllable Image Captioning (CIC) -- generating natural language descriptions about images under the guidance of given control signals -- is one of the most promising directions towards next-generation captioning systems. Till now, various kinds of control signals for CIC have been proposed, ranging from content-related control to structure-related control. However, due to the format and target gaps of different control signals, all existing CIC works (or architectures) only focus on one certain control signal, and overlook the human-like combinatorial ability. By ``combinatorial", we mean that our humans can easily meet multiple needs (or constraints) simultaneously when generating descriptions. To this end, we propose a novel prompt-based framework for CIC by learning Combinatorial Prompts, dubbed as ComPro. Specifically, we directly utilize a pretrained language model GPT-2 as our language model, which can help to bridge the gap between different signal-specific CIC architectures. Then, we reformulate the CIC as a prompt-guide sentence generation problem, and propose a new lightweight prompt generation network to generate the combinatorial prompts for different kinds of control signals. For different control signals, we further design a new mask attention mechanism to realize the prompt-based CIC. Due to its simplicity, our ComPro can be further extended to more kinds of combined control signals by concatenating these prompts. Extensive experiments on two prevalent CIC benchmarks have verified the effectiveness and efficiency of our ComPro on both single and combined control signals.
Authors: Kai Ren, Ke Zou, Xianjie Liu, Yidi Chen, Xuedong Yuan, Xiaojing Shen, Meng Wang, Huazhu Fu
Classification and segmentation are crucial in medical image analysis as they enable accurate diagnosis and disease monitoring. However, current methods often prioritize the mutual learning features and shared model parameters, while neglecting the reliability of features and performances. In this paper, we propose a novel Uncertainty-informed Mutual Learning (UML) framework for reliable and interpretable medical image analysis. Our UML introduces reliability to joint classification and segmentation tasks, leveraging mutual learning with uncertainty to improve performance. To achieve this, we first use evidential deep learning to provide image-level and pixel-wise confidences. Then, an Uncertainty Navigator Decoder is constructed for better using mutual features and generating segmentation results. Besides, an Uncertainty Instructor is proposed to screen reliable masks for classification. Overall, UML could produce confidence estimation in features and performance for each link (classification and segmentation). The experiments on the public datasets demonstrate that our UML outperforms existing methods in terms of both accuracy and robustness. Our UML has the potential to explore the development of more reliable and explainable medical image analysis models. We will release the codes for reproduction after acceptance.
Authors: Ludwig Bothmann, Lisa Wimmer, Omid Charrakh, Tobias Weber, Hendrik Edelhoff, Wibke Peters, Hien Nguyen, Caryl Benjamin, Annette Menzel
Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence systems can take over this task but usually need a large number of already-labeled training images to achieve sufficient performance. This requirement necessitates human expert labor and poses a particular challenge for projects with few cameras or short durations. We propose a label-efficient learning strategy that enables researchers with small or medium-sized image databases to leverage the potential of modern machine learning, thus freeing crucial resources for subsequent analyses.
Our methodological proposal is two-fold: (1) We improve current strategies of combining object detection and image classification by tuning the hyperparameters of both models. (2) We provide an active learning (AL) system that allows training deep learning models very efficiently in terms of required human-labeled training images. We supply a software package that enables researchers to use these methods directly and thereby ensure the broad applicability of the proposed framework in ecological practice.
We show that our tuning strategy improves predictive performance. We demonstrate how the AL pipeline reduces the amount of pre-labeled data needed to achieve a specific predictive performance and that it is especially valuable for improving out-of-sample predictive performance.
We conclude that the combination of tuning and AL increases predictive performance substantially. Furthermore, we argue that our work can broadly impact the community through the ready-to-use software package provided. Finally, the publication of our models tailored to European wildlife data enriches existing model bases mostly trained on data from Africa and North America.
Authors: Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, Min Zhang
Training a Large Visual Language Model (LVLM) from scratch, like GPT-4, is resource-intensive. Our paper presents a play-and-plug module for Large Language Models (LLMs), namely Interactive Perception Network (IPN), aiming to achieve a LVLM by incorporating the image understanding capability into LLMs. Previous methods incorporate visual information into LLMs with a simple visual mapping network, where the image feature is projected into the embedding space of LLMs via a linear layer. Such mapping network projects the image feature once yet does not consider the interaction between the image and the human input query. Hence, the obtained visual information with no connections with human intention may be inadequate for LLMs to make intention-following responses, which we term as static visual information. IPN addresses this issue by allowing the LLM to request the desired visual information aligned with various human instructions, which we term as the dynamic interaction between the LLM and visual information. Specifically, IPN consists of a simple visual mapping network to provide the basic perception of an image for LLMs. It also contains additional modules responsible for acquiring requests from LLMs, performing request-based visual information interaction, and transmitting the resulting interacted visual information to LLMs, respectively. In this way, LLMs act to understand the human query, deliver the corresponding request to the request-based visual information interaction module, and generate the response based on the interleaved multimodal information. We evaluate IPN through extensive experiments on multimodal question answering, reasoning, and so on, demonstrating that it significantly improves the zero-shot performance of LVLMs on various multimodal tasks compared to previous methods.
Authors: Eden Dolev, Alaa Awad, Denisa Roberts, Zahra Ebrahimzadeh, Marcin Mejran, Vaibhav Malpani, Mahir Yavuz
Efficiently learning visual representations of items is vital for large-scale recommendations. In this article we compare several pretrained efficient backbone architectures, both in the convolutional neural network (CNN) and in the vision transformer (ViT) family. We describe challenges in e-commerce vision applications at scale and highlight methods to efficiently train, evaluate, and serve visual representations. We present ablation studies evaluating visual representations in several downstream tasks. To this end, we present a novel multilingual text-to-image generative offline evaluation method for visually similar recommendation systems. Finally, we include online results from deployed machine learning systems in production on a large scale e-commerce platform.
Authors: Numan Saeed, Muhammad Ridzuan, Roba Al Majzoub, Mohammad Yaqub
Medical image segmentation is a vital healthcare endeavor requiring precise and efficient models for appropriate diagnosis and treatment. Vision transformer (ViT)-based segmentation models have shown great performance in accomplishing this task. However, to build a powerful backbone, the self-attention block of ViT requires large-scale pre-training data. The present method of modifying pre-trained models entails updating all or some of the backbone parameters. This paper proposes a novel fine-tuning strategy for adapting a pretrained transformer-based segmentation model on data from a new medical center. This method introduces a small number of learnable parameters, termed prompts, into the input space (less than 1\% of model parameters) while keeping the rest of the model parameters frozen. Extensive studies employing data from new unseen medical centers show that the prompt-based fine-tuning of medical segmentation models provides excellent performance regarding the new-center data with a negligible drop regarding the old centers. Additionally, our strategy delivers great accuracy with minimum re-training on new-center data, significantly decreasing the computational and time costs of fine-tuning pre-trained models.
Authors: Kyle Henke, Elijah Pelofske, Georg Hahn, Garrett T. Kenyon
We consider the problem of computing a sparse binary representation of an image. To be precise, given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an $L_2$ loss on the reconstruction error, and an $L_0$ (or, equivalently, an $L_1$) loss on the binary vector enforcing sparsity. This yields a so-called Quadratic Unconstrained Binary Optimization (QUBO) problem, whose solution is generally NP-hard to find. The contribution of this work is twofold. First, the method of unsupervised and unnormalized dictionary feature learning for a desired sparsity level to best match the data is presented. Second, the binary sparse coding problem is then solved on the Loihi 1 neuromorphic chip by the use of stochastic networks of neurons to traverse the non-convex energy landscape. The solutions are benchmarked against the classical heuristic simulated annealing. We demonstrate neuromorphic computing is suitable for sampling low energy solutions of binary sparse coding QUBO models, and although Loihi 1 is capable of sampling very sparse solutions of the QUBO models, there needs to be improvement in the implementation in order to be competitive with simulated annealing.
Authors: Zhenhui Ye, Ziyue Jiang, Yi Ren, Jinglin Liu, Chen Zhang, Xiang Yin, Zejun Ma, Zhou Zhao
We are interested in a novel task, namely low-resource text-to-talking avatar. Given only a few-minute-long talking person video with the audio track as the training data and arbitrary texts as the driving input, we aim to synthesize high-quality talking portrait videos corresponding to the input text. This task has broad application prospects in the digital human industry but has not been technically achieved yet due to two challenges: (1) It is challenging to mimic the timbre from out-of-domain audio for a traditional multi-speaker Text-to-Speech system. (2) It is hard to render high-fidelity and lip-synchronized talking avatars with limited training data. In this paper, we introduce Adaptive Text-to-Talking Avatar (Ada-TTA), which (1) designs a generic zero-shot multi-speaker TTS model that well disentangles the text content, timbre, and prosody; and (2) embraces recent advances in neural rendering to achieve realistic audio-driven talking face video generation. With these designs, our method overcomes the aforementioned two challenges and achieves to generate identity-preserving speech and realistic talking person video. Experiments demonstrate that our method could synthesize realistic, identity-preserving, and audio-visual synchronized talking avatar videos.
Authors: Ioannis Prapas, Nikolaos Ioannis Bountos, Spyros Kondylatos, Dimitrios Michail, Gustau Camps-Valls, Ioannis Papoutsis
Wildfires are increasingly exacerbated as a result of climate change, necessitating advanced proactive measures for effective mitigation. It is important to forecast wildfires weeks and months in advance to plan forest fuel management, resource procurement and allocation. To achieve such accurate long-term forecasts at a global scale, it is crucial to employ models that account for the Earth system's inherent spatio-temporal interactions, such as memory effects and teleconnections. We propose a teleconnection-driven vision transformer (TeleViT), capable of treating the Earth as one interconnected system, integrating fine-grained local-scale inputs with global-scale inputs, such as climate indices and coarse-grained global variables. Through comprehensive experimentation, we demonstrate the superiority of TeleViT in accurately predicting global burned area patterns for various forecasting windows, up to four months in advance. The gain is especially pronounced in larger forecasting windows, demonstrating the improved ability of deep learning models that exploit teleconnections to capture Earth system dynamics. Code available at https://github.com/Orion-Ai-Lab/TeleViT.
Authors: Yuhang Huang, Zheng Qin, Xinwang Liu, Kai Xu
Recent diffusion probabilistic models (DPMs) have shown remarkable abilities of generated content, however, they often suffer from complex forward processes, resulting in inefficient solutions for the reversed process and prolonged sampling times. In this paper, we aim to address the aforementioned challenges by focusing on the diffusion process itself that we propose to decouple the intricate diffusion process into two comparatively simpler process to improve the generative efficacy and speed. In particular, we present a novel diffusion paradigm named DDM (Decoupled Diffusion Models) based on the Ito diffusion process, in which the image distribution is approximated by an explicit transition probability while the noise path is controlled by the standard Wiener process. We find that decoupling the diffusion process reduces the learning difficulty and the explicit transition probability improves the generative speed significantly. We prove a new training objective for DPM, which enables the model to learn to predict the noise and image components separately. Moreover, given the novel forward diffusion equation, we derive the reverse denoising formula of DDM that naturally supports fewer steps of generation without ordinary differential equation (ODE) based accelerators. Our experiments demonstrate that DDM outperforms previous DPMs by a large margin in fewer function evaluations setting and gets comparable performances in long function evaluations setting. We also show that our framework can be applied to image-conditioned generation and high-resolution image synthesis, and that it can generate high-quality images with only 10 function evaluations.
Authors: Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan
Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. Typical diffusion models and modern large-scale conditional generative models like text-to-image generative models are vulnerable to overfitting when fine-tuned on extremely limited data. Existing works have explored subject-driven generation using a reference set containing a few images. However, few prior works explore DDPM-based domain-driven generation, which aims to learn the common features of target domains while maintaining diversity. This paper proposes a novel DomainStudio approach to adapt DDPMs pre-trained on large-scale source datasets to target domains using limited data. It is designed to keep the diversity of subjects provided by source domains and get high-quality and diverse adapted samples in target domains. We propose to keep the relative distances between adapted samples to achieve considerable generation diversity. In addition, we further enhance the learning of high-frequency details for better generation quality. Our approach is compatible with both unconditional and conditional diffusion models. This work makes the first attempt to realize unconditional few-shot image generation with diffusion models, achieving better quality and greater diversity than current state-of-the-art GAN-based approaches. Moreover, this work also significantly relieves overfitting for conditional generation and realizes high-quality domain-driven generation, further expanding the applicable scenarios of modern large-scale text-to-image models.
Authors: Mohan Zhou, Yalong Bai, Wei Zhang, Ting Yao, Tiejun Zhao, Tao Mei
A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quantitative evaluations often fail to capture the full complexity of human preference, as they only consider limited evaluation dimensions. Qualitative evaluations and user studies offer a solution but are time-consuming and labor-intensive. This limitation hinders the advancement of conversational head generation algorithms and systems. In this paper, we propose a novel learning-based evaluation metric named Preference Score (PS) for fitting human preference according to the quantitative evaluations across different dimensions. PS can serve as a quantitative evaluation without the need for human annotation. Experimental results validate the superiority of Preference Score in aligning with human perception, and also demonstrate robustness and generalizability to unseen data, making it a valuable tool for advancing conversation head generation. We expect this metric could facilitate new advances in conversational head generation. Project Page: https://https://github.com/dc3ea9f/PreferenceScore.
Authors: Jianan Liu, Qiuchi Zhao, Weiyi Xiong, Tao Huang, Qing-Long Han, Bing Zhu
The 4D Millimeter wave (mmWave) radar is a promising technology for vehicle sensing due to its cost-effectiveness and operability in adverse weather conditions. However, the adoption of this technology has been hindered by sparsity and noise issues in radar point cloud data. This paper introduces spatial multi-representation fusion (SMURF), a novel approach to 3D object detection using a single 4D imaging radar. SMURF leverages multiple representations of radar detection points, including pillarization and density features of a multi-dimensional Gaussian mixture distribution through kernel density estimation (KDE). KDE effectively mitigates measurement inaccuracy caused by limited angular resolution and multi-path propagation of radar signals. Additionally, KDE helps alleviate point cloud sparsity by capturing density features. Experimental evaluations on View-of-Delft (VoD) and TJ4DRadSet datasets demonstrate the effectiveness and generalization ability of SMURF, outperforming recently proposed 4D imaging radar-based single-representation models. Moreover, while using 4D imaging radar only, SMURF still achieves comparable performance to the state-of-the-art 4D imaging radar and camera fusion-based method, with an increase of 1.22% in the mean average precision on bird's-eye view of TJ4DRadSet dataset and 1.32% in the 3D mean average precision on the entire annotated area of VoD dataset. Our proposed method demonstrates impressive inference time and addresses the challenges of real-time detection, with the inference time no more than 0.05 seconds for most scans on both datasets. This research highlights the benefits of 4D mmWave radar and is a strong benchmark for subsequent works regarding 3D object detection with 4D imaging radar.
Authors: Xiaofeng Mao, Yuefeng Chen, Yao Zhu, Da Chen, Hang Su, Rong Zhang, Hui Xue
Practical object detection application can lose its effectiveness on image inputs with natural distribution shifts. This problem leads the research community to pay more attention on the robustness of detectors under Out-Of-Distribution (OOD) inputs. Existing works construct datasets to benchmark the detector's OOD robustness for a specific application scenario, e.g., Autonomous Driving. However, these datasets lack universality and are hard to benchmark general detectors built on common tasks such as COCO. To give a more comprehensive robustness assessment, we introduce COCO-O(ut-of-distribution), a test dataset based on COCO with 6 types of natural distribution shifts. COCO-O has a large distribution gap with training data and results in a significant 55.7% relative performance drop on a Faster R-CNN detector. We leverage COCO-O to conduct experiments on more than 100 modern object detectors to investigate if their improvements are credible or just over-fitting to the COCO test set. Unfortunately, most classic detectors in early years do not exhibit strong OOD generalization. We further study the robustness effect on recent breakthroughs of detector's architecture design, augmentation and pre-training techniques. Some empirical findings are revealed: 1) Compared with detection head or neck, backbone is the most important part for robustness; 2) An end-to-end detection transformer design brings no enhancement, and may even reduce robustness; 3) Large-scale foundation models have made a great leap on robust object detection. We hope our COCO-O could provide a rich testbed for robustness study of object detection. The dataset will be available at https://github.com/alibaba/easyrobust/tree/main/benchmarks/coco_o.
Authors: Yu-Hang Chien, Fang Yu
Sports professionals constantly under pressure to perform at the highest level can benefit from sports analysis, which allows coaches and players to reduce manual efforts and systematically evaluate their performance using automated tools. This research aims to advance sports analysis in badminton, systematically detecting hit-frames automatically from match videos using modern deep learning techniques. The data included in hit-frames can subsequently be utilized to synthesize players' strokes and on-court movement, as well as for other downstream applications such as analyzing training tasks and competition strategy. The proposed approach in this study comprises several automated procedures like rally-wise video trimming, player and court keypoints detection, shuttlecock flying direction prediction, and hit-frame detection. In the study, we achieved 99% accuracy on shot angle recognition for video trimming, over 92% accuracy for applying player keypoints sequences on shuttlecock flying direction prediction, and reported the evaluation results of rally-wise video trimming and hit-frame detection.
Authors: Bohao Li, Rui Wang, Guangzhi Wang, Yuying Ge, Yixiao Ge, Ying Shan
Based on powerful Large Language Models (LLMs), recent generative Multimodal Large Language Models (MLLMs) have gained prominence as a pivotal research area, exhibiting remarkable capability for both comprehension and generation. In this work, we address the evaluation of generative comprehension in MLLMs as a preliminary step towards a comprehensive assessment of generative models, by introducing a benchmark named SEED-Bench. SEED-Bench consists of 19K multiple choice questions with accurate human annotations (x 6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality. We develop an advanced pipeline for generating multiple-choice questions that target specific evaluation dimensions, integrating both automatic filtering and manual verification processes. Multiple-choice questions with groundtruth options derived from human annotation enables an objective and efficient assessment of model performance, eliminating the need for human or GPT intervention during evaluation. We further evaluate the performance of 18 models across all 12 dimensions, covering both the spatial and temporal understanding. By revealing the limitations of existing MLLMs through evaluation results, we aim for SEED-Bench to provide insights for motivating future research. We will launch and consistently maintain a leaderboard to provide a platform for the community to assess and investigate model capability.
Authors: Weikang Yu, Yonghao Xu, Pedram Ghamisi
Deep neural networks (DNNs) have achieved tremendous success in many remote sensing (RS) applications, in which DNNs are vulnerable to adversarial perturbations. Unfortunately, current adversarial defense approaches in RS studies usually suffer from performance fluctuation and unnecessary re-training costs due to the need for prior knowledge of the adversarial perturbations among RS data. To circumvent these challenges, we propose a universal adversarial defense approach in RS imagery (UAD-RS) using pre-trained diffusion models to defend the common DNNs against multiple unknown adversarial attacks. Specifically, the generative diffusion models are first pre-trained on different RS datasets to learn generalized representations in various data domains. After that, a universal adversarial purification framework is developed using the forward and reverse process of the pre-trained diffusion models to purify the perturbations from adversarial samples. Furthermore, an adaptive noise level selection (ANLS) mechanism is built to capture the optimal noise level of the diffusion model that can achieve the best purification results closest to the clean samples according to their Frechet Inception Distance (FID) in deep feature space. As a result, only a single pre-trained diffusion model is needed for the universal purification of adversarial samples on each dataset, which significantly alleviates the re-training efforts and maintains high performance without prior knowledge of the adversarial perturbations. Experiments on four heterogeneous RS datasets regarding scene classification and semantic segmentation verify that UAD-RS outperforms state-of-the-art adversarial purification approaches with a universal defense against seven commonly existing adversarial perturbations. Codes and the pre-trained models are available online (https://github.com/EricYu97/UAD-RS).
Authors: Anant Khandelwal
Large text-to-image diffusion models have achieved remarkable success in generating diverse high-quality images in alignment with text prompt used for editing the input image. But, when these models applied to video the main challenge is to ensure temporal consistency and coherence across frames. In this paper, we proposed InFusion, a framework for zero-shot text-based video editing leveraging large pre-trained image diffusion models. Our framework specifically supports editing of multiple concepts with the pixel level control over diverse concepts mentioned in the editing prompt. Specifically, we inject the difference of features obtained with source and edit prompt from U-Net residual blocks in decoder layers, this when combined with injected attention features make it feasible to query the source contents and scale edited concepts along with the injection of unedited parts. The editing is further controlled in fine-grained manner with mask extraction and attention fusion strategy which cuts the edited part from source and paste it into the denoising pipeline for editing prompt. Our framework is a low cost alternative of one-shot tuned models for editing since it does not require training. We demonstrated the complex concept editing with generalised image model (Stable Diffusion v1.5) using LoRA. Adaptation is compatible with all the existing image diffusion techniques. Extensive experimental results demonstrate the effectiveness over existing methods in rendering high-quality and temporally consistent videos.