Authors: Thinh Phan, Khoa Vo, Duy Le, Gianfranco Doretto, Donald Adjeroh, Ngan Le
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with closed-set setting on large training data, recent zero-shot TAD methods showcase the promising of open-set setting by leveraging large-scale contrastive visual-language (ViL) pretrained models. However, existing zero-shot TAD methods have limitations on how to properly construct the strong relationships between two interdependent tasks of localization and classification and adapt ViL model to video understanding. In this work, we present ZEETAD, featuring two modules: dual-localization and zero-shot proposal classification. The former is a Transformer-based module that detects action events while selectively collecting crucial semantic embeddings for later recognition. The latter one, CLIP-based module, generates semantic embeddings from text and frame inputs for each temporal unit. Additionally, we enhance discriminative capability on unseen classes by minimally updating the frozen CLIP encoder with lightweight adapters. Extensive experiments on THUMOS14 and ActivityNet-1.3 datasets demonstrate our approach's superior performance in zero-shot TAD and effective knowledge transfer from ViL models to unseen action categories.
Authors: Abhishek Kumar, Dong-Gyu Lee
Contemporary deep clustering approaches often rely on either contrastive or non-contrastive techniques to acquire effective representations for clustering tasks. Contrastive methods leverage negative pairs to achieve homogenous representations but can introduce class collision issues, potentially compromising clustering performance. On the contrary, non-contrastive techniques prevent class collisions but may produce non-uniform representations that lead to clustering collapse. In this work, we propose a novel end-to-end deep clustering approach named PIPCDR, designed to harness the strengths of both approaches while mitigating their limitations. PIPCDR incorporates a positive instance proximity loss and a cluster dispersion regularizer. The positive instance proximity loss ensures alignment between augmented views of instances and their sampled neighbors, enhancing within-cluster compactness by selecting genuinely positive pairs within the embedding space. Meanwhile, the cluster dispersion regularizer maximizes inter-cluster distances while minimizing within-cluster compactness, promoting uniformity in the learned representations. PIPCDR excels in producing well-separated clusters, generating uniform representations, avoiding class collision issues, and enhancing within-cluster compactness. We extensively validate the effectiveness of PIPCDR within an end-to-end Majorize-Minimization framework, demonstrating its competitive performance on moderate-scale clustering benchmark datasets and establishing new state-of-the-art results on large-scale datasets.
Authors: Joshua Santoso, Christian Simon, Williem Pao
Diffusion models have gained attention for image editing yielding impressive results in text-to-image tasks. On the downside, one might notice that generated images of stable diffusion models suffer from deteriorated details. This pitfall impacts image editing tasks that require information preservation e.g., scene text editing. As a desired result, the model must show the capability to replace the text on the source image to the target text while preserving the details e.g., color, font size, and background. To leverage the potential of diffusion models, in this work, we introduce Diffusion-BasEd Scene Text manipulation Network so-called DBEST. Specifically, we design two adaptation strategies, namely one-shot style adaptation and text-recognition guidance. In experiments, we thoroughly assess and compare our proposed method against state-of-the-arts on various scene text datasets, then provide extensive ablation studies for each granularity to analyze our performance gain. Also, we demonstrate the effectiveness of our proposed method to synthesize scene text indicated by competitive Optical Character Recognition (OCR) accuracy. Our method achieves 94.15% and 98.12% on COCO-text and ICDAR2013 datasets for character-level evaluation.
Authors: Bohui Shen, Wei Zhang, Xubiao Liu, Pengfei Yu, Shirui Jiang, Xinchong Shi, Xiangsong Zhang, Xiaoyu Zhou, Weirui Zhang, Bingxuan Li, Qiegen Liu
Positron emission tomography (PET), as an imaging technique with high biochemical sensitivity, has been widely used in diagnosis of encephalopathy and brain science research used in brain disease diagnosis and brain science research. Since different tracers present different effects on the same focal area, the choice of tracers is getting more significant for PET imaging. Nowadays, with the wide application of PET imaging in neuropsychiatric treatment, 6-18F-fluoro-3, 4-dihydroxy-L-phenylalanine (DOPA) has been found to be more effective than 18F-labeled fluorine-2-deoxyglucose (FDG) in this field. However, due to the complexity of its preparation and other limitations, DOPA is far less widely used than FDG. To address this issue, a tracer conversion invertible neural network (TC-INN) for image projection is developed to map FDG images to DOPA images through deep learning. More diagnostic information is obtained by generating PET images from FDG to DOPA. Specifically, the proposed TC-INN consists of two separate phases, one for training the traceable data, the other for re-building the new data. The reference DOPA PET image is used as the learning target for the corresponding network during the training process of tracer conversion. Mean-while, the invertible network iteratively estimates the resultant DOPA PET data and compares it to the reference DOPA PET data. Notably, the reversible model employed variable enhancement techniques to achieve better power generation. Moreover, image registration needs to be performed before training due to the angular deviation of the acquired FDG and DOPA data information. Experimental results show generative ability in mapping be-tween FDG images and DOPA images. It demonstrates great potential for PET image conversion in the case of limited tracer applications.
Authors: Klemen Kotar, Stephen Tian, Hong-Xing Yu, Daniel L.K. Yamins, Jiajun Wu
The human visual system can effortlessly recognize an object under different extrinsic factors such as lighting, object poses, and background, yet current computer vision systems often struggle with these variations. An important step to understanding and improving artificial vision systems is to measure image similarity purely based on intrinsic object properties that define object identity. This problem has been studied in the computer vision literature as re-identification, though mostly restricted to specific object categories such as people and cars. We propose to extend it to general object categories, exploring an image similarity metric based on object intrinsics. To benchmark such measurements, we collect the Common paired objects Under differenT Extrinsics (CUTE) dataset of $18,000$ images of $180$ objects under different extrinsic factors such as lighting, poses, and imaging conditions. While existing methods such as LPIPS and CLIP scores do not measure object intrinsics well, we find that combining deep features learned from contrastive self-supervised learning with foreground filtering is a simple yet effective approach to approximating the similarity. We conduct an extensive survey of pre-trained features and foreground extraction methods to arrive at a strong baseline that best measures intrinsic object-centric image similarity among current methods. Finally, we demonstrate that our approach can aid in downstream applications such as acting as an analog for human subjects and improving generalizable re-identification. Please see our project website at https://s-tian.github.io/projects/cute/ for visualizations of the data and demos of our metric.
Authors: Carol Neidle
There have been recent advances in computer-based recognition of isolated, citation-form signs from video. There are many challenges for such a task, not least the naturally occurring inter- and intra- signer synchronic variation in sign production, including sociolinguistic variation in the realization of certain signs. However, there are several significant factors that make recognition of signs from continuous signing an even more difficult problem. This article presents an overview of such challenges, based in part on findings from a large corpus of linguistically annotated video data for American Sign Language (ASL). Some linguistic regularities in the structure of signs that can boost handshape and sign recognition are also discussed.
Authors: Ahmed Zgaren, Wassim Bouachir, Nizar Bouguila
In forest industry, mechanical site preparation by mounding is widely used prior to planting operations. One of the main problems when planning planting operations is the difficulty in estimating the number of mounds present on a planting block, as their number may greatly vary depending on site characteristics. This estimation is often carried out through field surveys by several forestry workers. However, this procedure is prone to error and slowness. Motivated by recent advances in UAV imagery and artificial intelligence, we propose a fully automated framework to estimate the number of mounds on a planting block. Using computer vision and machine learning, we formulate the counting task as a supervised learning problem using two prediction models. A local detection model is firstly used to detect visible mounds based on deep features, while a global prediction function is subsequently applied to provide a final estimation based on block-level features. To evaluate the proposed method, we constructed a challenging UAV dataset representing several plantation blocks with different characteristics. The performed experiments demonstrated the robustness of the proposed method, which outperforms manual methods in precision, while significantly reducing time and cost.
Authors: AmirHosein Fadaei, Mohammad-Reza A. Dehaqani
A defining characteristic of natural vision is its ability to withstand a variety of input alterations, resulting in the creation of an invariant representation of the surroundings. While convolutional neural networks exhibit resilience to certain forms of spatial input variation, modifications in the spatial and temporal aspects can significantly affect the representations of video content in deep neural networks. Inspired by the resilience of natural vision to input variations, we employ a simple multi-stream model to explore its potential to address spatiotemporal changes by including temporal features. Our primary goal is to introduce a video-trained model and evaluate its robustness to diverse image and video inputs, with a particular focus on exploring the role of temporal features in invariant recognition. Results show that including videos and the temporal stream during training mitigates the decline in accuracy and mAP in image and video understanding tasks by 1.36% and 3.14%, respectively.
Authors: Suraj Jyothi Unni, Raha Moraffah, Huan Liu
Visual question answering (VQA) models are designed to demonstrate visual-textual reasoning capabilities. However, their real-world applicability is hindered by a lack of comprehensive benchmark datasets. Existing domain generalization datasets for VQA exhibit a unilateral focus on textual shifts while VQA being a multi-modal task contains shifts across both visual and textual domains. We propose VQA-GEN, the first ever multi-modal benchmark dataset for distribution shift generated through a shift induced pipeline. Experiments demonstrate VQA-GEN dataset exposes the vulnerability of existing methods to joint multi-modal distribution shifts. validating that comprehensive multi-modal shifts are critical for robust VQA generalization. Models trained on VQA-GEN exhibit improved cross-domain and in-domain performance, confirming the value of VQA-GEN. Further, we analyze the importance of each shift technique of our pipeline contributing to the generalization of the model.
Authors: Afia Abedin, Abdul Bais, Cody Buntain, Laura Courchesne, Brian McQuinn, Matthew E. Taylor, Muhib Ullah
The massive proliferation of social media data represents a transformative moment in conflict studies. This data can provide unique insights into the spread and use of weaponry, but the scale and types of data are problematic for traditional open-source intelligence. This paper presents preliminary, transdisciplinary work using computer vision to identify specific weapon systems and the insignias of the armed groups using them. There is potential to not only track how weapons are distributed through networks of armed units but also to track which types of weapons are being used by the different types of state and non-state military actors in Ukraine. Such a system could ultimately be used to understand conflicts in real-time, including where humanitarian and medical aid is most needed. We believe that using AI to help automate such processes should be a high-priority goal for our community, with near-term real-world payoffs.
Authors: Fengyi Wu, Tianfang Zhang, Lei Li, Yian Huang, Zhenming Peng
Deep learning (DL) networks have achieved remarkable performance in infrared small target detection (ISTD). However, these structures exhibit a deficiency in interpretability and are widely regarded as black boxes, as they disregard domain knowledge in ISTD. To alleviate this issue, this work proposes an interpretable deep network for detecting infrared dim targets, dubbed RPCANet. Specifically, our approach formulates the ISTD task as sparse target extraction, low-rank background estimation, and image reconstruction in a relaxed Robust Principle Component Analysis (RPCA) model. By unfolding the iterative optimization updating steps into a deep-learning framework, time-consuming and complex matrix calculations are replaced by theory-guided neural networks. RPCANet detects targets with clear interpretability and preserves the intrinsic image feature, instead of directly transforming the detection task into a matrix decomposition problem. Extensive experiments substantiate the effectiveness of our deep unfolding framework and demonstrate its trustworthy results, surpassing baseline methods in both qualitative and quantitative evaluations.
Authors: Wentao Yuan, Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox
With the advent of large language models and large-scale robotic datasets, there has been tremendous progress in high-level decision-making for object manipulation. These generic models are able to interpret complex tasks using language commands, but they often have difficulties generalizing to out-of-distribution objects due to the inability of low-level action primitives. In contrast, existing task-specific models excel in low-level manipulation of unknown objects, but only work for a single type of action. To bridge this gap, we present M2T2, a single model that supplies different types of low-level actions that work robustly on arbitrary objects in cluttered scenes. M2T2 is a transformer model which reasons about contact points and predicts valid gripper poses for different action modes given a raw point cloud of the scene. Trained on a large-scale synthetic dataset with 128K scenes, M2T2 achieves zero-shot sim2real transfer on the real robot, outperforming the baseline system with state-of-the-art task-specific models by about 19% in overall performance and 37.5% in challenging scenes where the object needs to be re-oriented for collision-free placement. M2T2 also achieves state-of-the-art results on a subset of language conditioned tasks in RLBench. Videos of robot experiments on unseen objects in both real world and simulation are available on our project website https://m2-t2.github.io.
Authors: Qingsen Yan, Tao Hu, Yuan Sun, Hao Tang, Yu Zhu, Wei Dong, Luc Van Gool, Yanning Zhang
High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR images have saturation and large motion, which hinders potential applications in real-world scenarios. To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition, consisting of the feature condition generator and the noise predictor. Feature condition generator employs attention and Domain Feature Alignment (DFA) layer to transform the intermediate features to avoid ghosting artifacts. With the learned features as conditions, the noise predictor leverages a stochastic iterative denoising process for diffusion models to generate an HDR image by steering the sampling process. Furthermore, to mitigate semantic confusion caused by the saturation problem of LDR images, we design a sliding window noise estimator to sample smooth noise in a patch-based manner. In addition, an image space loss is proposed to avoid the color distortion of the estimated HDR results. We empirically evaluate our model on benchmark datasets for HDR imaging. The results demonstrate that our approach achieves state-of-the-art performances and well generalization to real-world images.
Authors: Mélisande Teng, Amna Elmustafa, Benjamin Akera, Yoshua Bengio, Hager Radi Abdelwahed, Hugo Larochelle, David Rolnick
Biodiversity is declining at an unprecedented rate, impacting ecosystem services necessary to ensure food, water, and human health and well-being. Understanding the distribution of species and their habitats is crucial for conservation policy planning. However, traditional methods in ecology for species distribution models (SDMs) generally focus either on narrow sets of species or narrow geographical areas and there remain significant knowledge gaps about the distribution of species. A major reason for this is the limited availability of data traditionally used, due to the prohibitive amount of effort and expertise required for traditional field monitoring. The wide availability of remote sensing data and the growing adoption of citizen science tools to collect species observations data at low cost offer an opportunity for improving biodiversity monitoring and enabling the modelling of complex ecosystems. We introduce a novel task for mapping bird species to their habitats by predicting species encounter rates from satellite images, and present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird, considering summer (breeding) and winter seasons. We also provide a dataset in Kenya representing low-data regimes. We additionally provide environmental data and species range maps for each location. We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks. SatBird opens up possibilities for scalably modelling properties of ecosystems worldwide.
Authors: Niket Patel, Luis Salamanca, Luis Barba
Diffusion models have emerged as a pivotal advancement in generative models, setting new standards to the quality of the generated instances. In the current paper we aim to underscore a discrepancy between conventional training methods and the desired conditional sampling behavior of these models. While the prevalent classifier-free guidance technique works well, it's not without flaws. At higher values for the guidance scale parameter $w$, we often get out of distribution samples and mode collapse, whereas at lower values for $w$ we may not get the desired specificity. To address these challenges, we introduce an updated loss function that better aligns training objectives with sampling behaviors. Experimental validation with FID scores on CIFAR-10 elucidates our method's ability to produce higher quality samples with fewer sampling timesteps, and be more robust to the choice of guidance scale $w$. We also experiment with fine-tuning Stable Diffusion on the proposed loss, to provide early evidence that large diffusion models may also benefit from this refined loss function.
Authors: Hanzhong Guo, Cheng Lu, Fan Bao, Tianyu Pang, Shuicheng Yan, Chao Du, Chongxuan Li
Recently, diffusion models have achieved great success in generative tasks. Sampling from diffusion models is equivalent to solving the reverse diffusion stochastic differential equations (SDEs) or the corresponding probability flow ordinary differential equations (ODEs). In comparison, SDE-based solvers can generate samples of higher quality and are suited for image translation tasks like stroke-based synthesis. During inference, however, existing SDE-based solvers are severely constrained by the efficiency-effectiveness dilemma. Our investigation suggests that this is because the Gaussian assumption in the reverse transition kernel is frequently violated (even in the case of simple mixture data) given a limited number of discretization steps. To overcome this limitation, we introduce a novel class of SDE-based solvers called \emph{Gaussian Mixture Solvers (GMS)} for diffusion models. Our solver estimates the first three-order moments and optimizes the parameters of a Gaussian mixture transition kernel using generalized methods of moments in each step during sampling. Empirically, our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis in various diffusion models, which validates the motivation and effectiveness of GMS. Our code is available at https://github.com/Guohanzhong/GMS.
Authors: Shijie Ma, Huayi Xu, Mengjian Li, Weidong Geng, Meng Wang, Yaxiong Wang
Despite the remarkable progress in text-to-video generation, existing diffusion-based models often exhibit instability in terms of noise during inference. Specifically, when different noises are fed for the given text, these models produce videos that differ significantly in terms of both frame quality and temporal consistency. With this observation, we posit that there exists an optimal noise matched to each textual input; however, the widely adopted strategies of random noise sampling often fail to capture it. In this paper, we argue that the optimal noise can be approached through inverting the groundtruth video using the established noise-video mapping derived from the diffusion model. Nevertheless, the groundtruth video for the text prompt is not available during inference. To address this challenge, we propose to approximate the optimal noise via a search and inversion pipeline. Given a text prompt, we initially search for a video from a predefined candidate pool that closely relates to the text prompt. Subsequently, we invert the searched video into the noise space, which serves as an improved noise prompt for the textual input. In addition to addressing noise, we also observe that the text prompt with richer details often leads to higher-quality videos. Motivated by this, we further design a semantic-preserving rewriter to enrich the text prompt, where a reference-guided rewriting is devised for reasonable details compensation, and a denoising with a hybrid semantics strategy is proposed to preserve the semantic consistency. Extensive experiments on the WebVid-10M benchmark show that our proposed method can improve the text-to-video models with a clear margin, while introducing no optimization burden.
Authors: Zhouqiang Jiang, Bowen Wang, Tong Xiang, Zhaofeng Niu, Hong Tang, Guangshun Li, Liangzhi Li
Learning representations from videos requires understanding continuous motion and visual correspondences between frames. In this paper, we introduce the Concatenated Masked Autoencoders (CatMAE) as a spatial-temporal learner for self-supervised video representation learning. For the input sequence of video frames, CatMAE keeps the initial frame unchanged while applying substantial masking (95%) to subsequent frames. The encoder in CatMAE is responsible for encoding visible patches for each frame individually; subsequently, for each masked frame, the decoder leverages visible patches from both previous and current frames to reconstruct the original image. Our proposed method enables the model to estimate the motion information between visible patches, match the correspondences between preceding and succeeding frames, and ultimately learn the evolution of scenes. Furthermore, we propose a new data augmentation strategy, Video-Reverse (ViRe), which uses reversed video frames as the model's reconstruction targets. This further encourages the model to utilize continuous motion details and correspondences to complete the reconstruction, thereby enhancing the model's capabilities. Compared to the most advanced pre-training methods, CatMAE achieves a leading level in video segmentation tasks and action recognition tasks.
Authors: Xiuli Bi, Bo Liu, Fan Yang, Bin Xiao, Weisheng Li, Gao Huang, Pamela C. Cosman
As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect visual artifacts in generated images or learn discriminative features from both real and generated images by massive training. This learning paradigm will result in efficiency and generalization issues, making detection methods always lag behind generation methods. This paper approaches the generated image detection problem from a new perspective: Start from real images. By finding the commonality of real images and mapping them to a dense subspace in feature space, the goal is that generated images, regardless of their generative model, are then projected outside the subspace. As a result, images from different generative models can be detected, solving some long-existing problems in the field. Experimental results show that although our method was trained only by real images and uses 99.9\% less training data than other deep learning-based methods, it can compete with state-of-the-art methods and shows excellent performance in detecting emerging generative models with high inference efficiency. Moreover, the proposed method shows robustness against various post-processing. These advantages allow the method to be used in real-world scenarios.
Authors: Wei Zhang, Dingquan Li, Ge Li, Wen Gao
This paper presents an approach for compressing point cloud geometry by leveraging a lightweight super-resolution network. The proposed method involves decomposing a point cloud into a base point cloud and the interpolation patterns for reconstructing the original point cloud. While the base point cloud can be efficiently compressed using any lossless codec, such as Geometry-based Point Cloud Compression, a distinct strategy is employed for handling the interpolation patterns. Rather than directly compressing the interpolation patterns, a lightweight super-resolution network is utilized to learn this information through overfitting. Subsequently, the network parameter is transmitted to assist in point cloud reconstruction at the decoder side. Notably, our approach differentiates itself from lookup table-based methods, allowing us to obtain more accurate interpolation patterns by accessing a broader range of neighboring voxels at an acceptable computational cost. Experiments on MPEG Cat1 (Solid) and Cat2 datasets demonstrate the remarkable compression performance achieved by our method.
Authors: Weixi Wang, Xichen Zhong, Xin Li, Sizhe Li, Xun Ma
Overhead line inspection greatly benefits from defect recognition using visible light imagery. Addressing the limitations of existing feature extraction techniques and the heavy data dependency of deep learning approaches, this paper introduces a novel defect recognition framework. This is built on the Faster RCNN network and complemented by unsupervised semantic segmentation. The approach involves identifying the type and location of the target equipment, utilizing semantic segmentation to differentiate between the device and its backdrop, and finally employing similarity measures and logical rules to categorize the type of defect. Experimental results indicate that this methodology focuses more on the equipment rather than the defects when identifying issues in overhead lines. This leads to a notable enhancement in accuracy and exhibits impressive adaptability. Thus, offering a fresh perspective for automating the inspection of distribution network equipment.
Authors: Wei-Hsin Yeh, Pei Hsin Lin, Yu-An Su, Wen Hsiang Cheng, Lun-Wei Ku
Many people engage in self-directed sports training at home but lack the real-time guidance of professional coaches, making them susceptible to injuries or the development of incorrect habits. In this paper, we propose a novel application framework called MAAIG(Motion Analysis And Instruction Generation). It can generate embedding vectors for each frame based on user-provided sports action videos. These embedding vectors are associated with the 3D skeleton of each frame and are further input into a pretrained T5 model. Ultimately, our model utilizes this information to generate specific sports instructions. It has the capability to identify potential issues and provide real-time guidance in a manner akin to professional coaches, helping users improve their sports skills and avoid injuries.
Authors: Hang Zhang
In this research, I proposed a network structure for multi-view 3D object detection using camera-only data and a Bird's-Eye-View map. My work is based on a current key challenge domain adaptation and visual data transfer. Although many excellent camera-only 3D object detection has been continuously proposed, many research work risk dramatic performance drop when the networks are trained on the source domain but tested on a different target domain. Then I found it is very surprising that predictions on bounding boxes and classes are still replied to on 2D networks. Based on the domain gap assumption on various 3D datasets, I found they still shared a similar data extraction on the same BEV map size and camera data transfer. Therefore, to analyze the domain gap influence on the current method and to make good use of 3D space information among the dataset and the real world, I proposed a transfer learning method and Transformer construction to study the 3D object detection on NuScenes-mini and Lyft. Through multi-dataset training and a detection head from the Transformer, the network demonstrated good data migration performance and efficient detection performance by using 3D anchor query and 3D positional information. Relying on only a small amount of source data and the existing large model pre-training weights, the efficient network manages to achieve competitive results on the new target domain. Moreover, my study utilizes 3D information as available semantic information and 2D multi-view image features blending into the visual-language transfer design. In the final 3D anchor box prediction and object classification, my network achieved good results on standard metrics of 3D object detection, which differs from dataset-specific models on each training domain without any fine-tuning.
Authors: Yiming Cui, Cheng Han, Dongfang Liu
The advancement of computer vision has pushed visual analysis tasks from still images to the video domain. In recent years, video instance segmentation, which aims to track and segment multiple objects in video frames, has drawn much attention for its potential applications in various emerging areas such as autonomous driving, intelligent transportation, and smart retail. In this paper, we propose an effective framework for instance-level visual analysis on video frames, which can simultaneously conduct object detection, instance segmentation, and multi-object tracking. The core idea of our method is collaborative multi-task learning which is achieved by a novel structure, named associative connections among detection, segmentation, and tracking task heads in an end-to-end learnable CNN. These additional connections allow information propagation across multiple related tasks, so as to benefit these tasks simultaneously. We evaluate the proposed method extensively on KITTI MOTS and MOTS Challenge datasets and obtain quite encouraging results.
Authors: Hong Chen, Xin Wang, Guanning Zeng, Yipeng Zhang, Yuwei Zhou, Feilin Han, Wenwu Zhu
Customized text-to-video generation aims to generate text-guided videos with customized user-given subjects, which has gained increasing attention recently. However, existing works are primarily limited to generating videos for a single subject, leaving the more challenging problem of customized multi-subject text-to-video generation largely unexplored. In this paper, we fill this gap and propose a novel VideoDreamer framework. VideoDreamer can generate temporally consistent text-guided videos that faithfully preserve the visual features of the given multiple subjects. Specifically, VideoDreamer leverages the pretrained Stable Diffusion with latent-code motion dynamics and temporal cross-frame attention as the base video generator. The video generator is further customized for the given multiple subjects by the proposed Disen-Mix Finetuning and Human-in-the-Loop Re-finetuning strategy, which can tackle the attribute binding problem of multi-subject generation. We also introduce MultiStudioBench, a benchmark for evaluating customized multi-subject text-to-video generation models. Extensive experiments demonstrate the remarkable ability of VideoDreamer to generate videos with new content such as new events and backgrounds, tailored to the customized multiple subjects. Our project page is available at https://videodreamer23.github.io/.
Authors: Jamsheed Manja Ppallan, Ruchi Pandey, Yellappa Damam, Vijay Narayan Tiwari, Karthikeyan Arunachalam, Antariksha Ray
With the widespread adoption of smartphones, ensuring pedestrian safety on roads has become a critical concern due to smartphone distraction. This paper proposes a novel and real-time assistance system called UWB-assisted Safe Walk (UASW) for obstacle detection and warns users about real-time situations. The proposed method leverages Impulse Radio Ultra-Wideband (IR-UWB) radar embedded in the smartphone, which provides excellent range resolution and high noise resilience using short pulses. We implemented UASW specifically for Android smartphones with IR-UWB connectivity. The framework uses complex Channel Impulse Response (CIR) data to integrate rule-based obstacle detection with artificial neural network (ANN) based obstacle classification. The performance of the proposed UASW system is analyzed using real-time collected data. The results show that the proposed system achieves an obstacle detection accuracy of up to 97% and obstacle classification accuracy of up to 95% with an inference delay of 26.8 ms. The results highlight the effectiveness of UASW in assisting smartphone-distracted pedestrians and improving their situational awareness.
Authors: Kim Sung-Bin, Lee Hyun, Da Hye Hong, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
Laughter is a unique expression, essential to affirmative social interactions of humans. Although current 3D talking head generation methods produce convincing verbal articulations, they often fail to capture the vitality and subtleties of laughter and smiles despite their importance in social context. In this paper, we introduce a novel task to generate 3D talking heads capable of both articulate speech and authentic laughter. Our newly curated dataset comprises 2D laughing videos paired with pseudo-annotated and human-validated 3D FLAME parameters and vertices. Given our proposed dataset, we present a strong baseline with a two-stage training scheme: the model first learns to talk and then acquires the ability to express laughter. Extensive experiments demonstrate that our method performs favorably compared to existing approaches in both talking head generation and expressing laughter signals. We further explore potential applications on top of our proposed method for rigging realistic avatars.
Authors: Hrishikesh Sharma
Generative Adversarial Networks (GANs) have been workhorse generative models for last many years, especially in the research field of computer vision. Accordingly, there have been many significant advancements in the theory and application of GAN models, which are notoriously hard to train, but produce good results if trained well. There have been many a surveys on GANs, organizing the vast GAN literature from various focus and perspectives. However, none of the surveys brings out the important chronological aspect: how the multiple challenges of employing GAN models were solved one-by-one over time, across multiple landmark research works. This survey intends to bridge that gap and present some of the landmark research works on the theory and application of GANs, in chronological order.
Authors: Boyang Wang, Bowen Liu, Shiyu Liu, Fengyu Yang
In the blind single image super-resolution (SISR) task, existing works have been successful in restoring image-level unknown degradations. However, when a single video frame becomes the input, these works usually fail to address degradations caused by video compression, such as mosquito noise, ringing, blockiness, and staircase noise. In this work, we for the first time, present a video compression-based degradation model to synthesize low-resolution image data in the blind SISR task. Our proposed image synthesizing method is widely applicable to existing image datasets, so that a single degraded image can contain distortions caused by the lossy video compression algorithms. This overcomes the leak of feature diversity in video data and thus retains the training efficiency. By introducing video coding artifacts to SISR degradation models, neural networks can super-resolve images with the ability to restore video compression degradations, and achieve better results on restoring generic distortions caused by image compression as well. Our proposed approach achieves superior performance in SOTA no-reference Image Quality Assessment, and shows better visual quality on various datasets. In addition, we evaluate the SISR neural network trained with our degradation model on video super-resolution (VSR) datasets. Compared to architectures specifically designed for the VSR purpose, our method exhibits similar or better performance, evidencing that the presented strategy on infusing video-based degradation is generalizable to address more complicated compression artifacts even without temporal cues.
Authors: Haechang Lee, Wongi Jeong, Dongil Ryu, Hyunwoo Je, Albert No, Kijeong Kim, Se Young Chun
Despite significant research on lightweight deep neural networks (DNNs) designed for edge devices, the current face detectors do not fully meet the requirements for "intelligent" CMOS image sensors (iCISs) integrated with embedded DNNs. These sensors are essential in various practical applications, such as energy-efficient mobile phones and surveillance systems with always-on capabilities. One noteworthy limitation is the absence of suitable face detectors for the always-on scenario, a crucial aspect of image sensor-level applications. These detectors must operate directly with sensor RAW data before the image signal processor (ISP) takes over. This gap poses a significant challenge in achieving optimal performance in such scenarios. Further research and development are necessary to bridge this gap and fully leverage the potential of iCIS applications. In this study, we aim to bridge the gap by exploring extremely low-bit lightweight face detectors, focusing on the always-on face detection scenario for mobile image sensor applications. To achieve this, our proposed model utilizes sensor-aware synthetic RAW inputs, simulating always-on face detection processed "before" the ISP chain. Our approach employs ternary (-1, 0, 1) weights for potential implementations in image sensors, resulting in a relatively simple network architecture with shallow layers and extremely low-bitwidth. Our method demonstrates reasonable face detection performance and excellent efficiency in simulation studies, offering promising possibilities for practical always-on face detectors in real-world applications.
Authors: Gaoang Wang, Zhenyu Zhang, Benlu Wang, Weijie Liang, Yizhi Li, Xuechen Guo, Guanhong Wang, Shiyan Li
With the development of multimodality and large language models, the deep learning-based technique for medical image captioning holds the potential to offer valuable diagnostic recommendations. However, current generic text and image pre-trained models do not yield satisfactory results when it comes to describing intricate details within medical images. In this paper, we present a novel medical image captioning method guided by the segment anything model (SAM) to enable enhanced encoding with both general and detailed feature extraction. In addition, our approach employs a distinctive pre-training strategy with mixed semantic learning to simultaneously capture both the overall information and finer details within medical images. We demonstrate the effectiveness of this approach, as it outperforms the pre-trained BLIP2 model on various evaluation metrics for generating descriptions of medical images.
Authors: Deval Mehta, Brigid Betz-Stablein, Toan D Nguyen, Yaniv Gal, Adrian Bowling, Martin Haskett, Maithili Sashindranath, Paul Bonnington, Victoria Mar, H Peter Soyer, Zongyuan Ge
The surge in developing deep learning models for diagnosing skin lesions through image analysis is notable, yet their clinical black faces challenges. Current dermatology AI models have limitations: limited number of possible diagnostic outputs, lack of real-world testing on uncommon skin lesions, inability to detect out-of-distribution images, and over-reliance on dermoscopic images. To address these, we present an All-In-One \textbf{H}ierarchical-\textbf{O}ut of Distribution-\textbf{C}linical Triage (HOT) model. For a clinical image, our model generates three outputs: a hierarchical prediction, an alert for out-of-distribution images, and a recommendation for dermoscopy if clinical image alone is insufficient for diagnosis. When the recommendation is pursued, it integrates both clinical and dermoscopic images to deliver final diagnosis. Extensive experiments on a representative cutaneous lesion dataset demonstrate the effectiveness and synergy of each component within our framework. Our versatile model provides valuable decision support for lesion diagnosis and sets a promising precedent for medical AI applications.
Authors: Borui Zhang, Baotong Tian, Wenzhao Zheng, Jie Zhou, Jiwen Lu
Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values encounters exponential complexity in the number of features. Various approaches, including ApproSemivalue, KernelSHAP, and FastSHAP, have been explored to expedite the computation. We analyze the consistency of existing works and conclude that stochastic estimators can be unified as the linear transformation of importance sampling of feature subsets. Based on this, we investigate the possibility of designing simple amortized estimators and propose a straightforward and efficient one, SimSHAP, by eliminating redundant techniques. Extensive experiments conducted on tabular and image datasets validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
Authors: Peng Jin, Yang Wu, Yanbo Fan, Zhongqian Sun, Yang Wei, Li Yuan
Most text-driven human motion generation methods employ sequential modeling approaches, e.g., transformer, to extract sentence-level text representations automatically and implicitly for human motion synthesis. However, these compact text representations may overemphasize the action names at the expense of other important properties and lack fine-grained details to guide the synthesis of subtly distinct motion. In this paper, we propose hierarchical semantic graphs for fine-grained control over motion generation. Specifically, we disentangle motion descriptions into hierarchical semantic graphs including three levels of motions, actions, and specifics. Such global-to-local structures facilitate a comprehensive understanding of motion description and fine-grained control of motion generation. Correspondingly, to leverage the coarse-to-fine topology of hierarchical semantic graphs, we decompose the text-to-motion diffusion process into three semantic levels, which correspond to capturing the overall motion, local actions, and action specifics. Extensive experiments on two benchmark human motion datasets, including HumanML3D and KIT, with superior performances, justify the efficacy of our method. More encouragingly, by modifying the edge weights of hierarchical semantic graphs, our method can continuously refine the generated motion, which may have a far-reaching impact on the community. Code and pre-training weights are available at https://github.com/jpthu17/GraphMotion.
Authors: Yiran Li, Junpeng Wang, Prince Aboagye, Michael Yeh, Yan Zheng, Liang Wang, Wei Zhang, Kwan-Liu Ma
Recent advancements in pre-trained large-scale language-image models have ushered in a new era of visual comprehension, offering a significant leap forward. These breakthroughs have proven particularly instrumental in addressing long-standing challenges that were previously daunting. Leveraging these innovative techniques, this paper tackles two well-known issues within the realm of visual analytics: (1) the efficient exploration of large-scale image datasets and identification of potential data biases within them; (2) the evaluation of image captions and steering of their generation process. On the one hand, by visually examining the captions automatically generated from language-image models for an image dataset, we gain deeper insights into the semantic underpinnings of the visual contents, unearthing data biases that may be entrenched within the dataset. On the other hand, by depicting the association between visual contents and textual captions, we expose the weaknesses of pre-trained language-image models in their captioning capability and propose an interactive interface to steer caption generation. The two parts have been coalesced into a coordinated visual analytics system, fostering mutual enrichment of visual and textual elements. We validate the effectiveness of the system with domain practitioners through concrete case studies with large-scale image datasets.
Authors: Lunjun Zhang, Yuwen Xiong, Ze Yang, Sergio Casas, Rui Hu, Raquel Urtasun
Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such as autonomous driving has been somewhat less rapid than scaling language models with Generative Pre-trained Transformers (GPT). We identify two reasons as major bottlenecks: dealing with complex and unstructured observation space, and having a scalable generative model. Consequently, we propose a novel world modeling approach that first tokenizes sensor observations with VQVAE, then predicts the future via discrete diffusion. To efficiently decode and denoise tokens in parallel, we recast Masked Generative Image Transformer into the discrete diffusion framework with a few simple changes, resulting in notable improvement. When applied to learning world models on point cloud observations, our model reduces prior SOTA Chamfer distance by more than 65% for 1s prediction, and more than 50% for 3s prediction, across NuScenes, KITTI Odometry, and Argoverse2 datasets. Our results demonstrate that discrete diffusion on tokenized agent experience can unlock the power of GPT-like unsupervised learning for robotic agents.
Authors: Jiwan Hur, Jaehyun Choi, Gyojin Han, Dong-Jae Lee, Junmo Kim
Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain translation and text-guided image manipulation. In this paper, we propose Self-Distillation for Fine-Tuning diffusion models (SDFT), a methodology to address these challenges by leveraging diverse features from diffusion models pretrained on large source datasets. SDFT distills more general features (shape, colors, etc.) and less domain-specific features (texture, fine details, etc) from the source model, allowing successful knowledge transfer without disturbing the training process on target datasets. The proposed method is not constrained by the specific architecture of the model and thus can be generally adopted to existing frameworks. Experimental results demonstrate that SDFT enhances the expressiveness of the diffusion model with limited datasets, resulting in improved generation capabilities across various downstream tasks.
Authors: Kottakota Asish, P. Sarath Teja, R. Kishan Chander, Dr. D. Deva Hema
The rapid evolution of deep neural networks has revolutionized the field of machine learning, enabling remarkable advancements in various domains. In this article, we introduce NeuroWrite, a unique method for predicting the categorization of handwritten digits using deep neural networks. Our model exhibits outstanding accuracy in identifying and categorising handwritten digits by utilising the strength of convolutional neural networks (CNNs) and recurrent neural networks (RNNs).In this article, we give a thorough examination of the data preparation methods, network design, and training methods used in NeuroWrite. By implementing state-of-the-art techniques, we showcase how NeuroWrite can achieve high classification accuracy and robust generalization on handwritten digit datasets, such as MNIST. Furthermore, we explore the model's potential for real-world applications, including digit recognition in digitized documents, signature verification, and automated postal code recognition. NeuroWrite is a useful tool for computer vision and pattern recognition because of its performance and adaptability.The architecture, training procedure, and evaluation metrics of NeuroWrite are covered in detail in this study, illustrating how it can improve a number of applications that call for handwritten digit classification. The outcomes show that NeuroWrite is a promising method for raising the bar for deep neural network-based handwritten digit recognition.
Authors: Yanming Guo
The utilisation of deep learning segmentation algorithms that learn complex organs and tissue patterns and extract essential regions of interest from the noisy background to improve the visual ability for medical image diagnosis has achieved impressive results in Medical Image Computing (MIC). This thesis focuses on retinal blood vessel segmentation tasks, providing an extensive literature review of deep learning-based medical image segmentation approaches while comparing the methodologies and empirical performances. The work also examines the limitations of current state-of-the-art methods by pointing out the two significant existing limitations: data size constraints and the dependency on high computational resources. To address such problems, this work proposes a novel efficient, simple multiview learning framework that contrastively learns invariant vessel feature representation by comparing with multiple augmented views by various transformations to overcome data shortage and improve generalisation ability. Moreover, the hybrid network architecture integrates the attention mechanism into a Convolutional Neural Network to further capture complex continuous curvilinear vessel structures. The result demonstrates the proposed method validated on the CHASE-DB1 dataset, attaining the highest F1 score of 83.46% and the highest Intersection over Union (IOU) score of 71.62% with UNet structure, surpassing existing benchmark UNet-based methods by 1.95% and 2.8%, respectively. The combination of the metrics indicates the model detects the vessel object accurately with a highly coincidental location with the ground truth. Moreover, the proposed approach could be trained within 30 minutes by consuming less than 3 GB GPU RAM, and such characteristics support the efficient implementation for real-world applications and deployments.
Authors: Sungjune Park, Hyunjun Kim, Yong Man Ro
Large language models (LLMs) have shown their capability in understanding contextual and semantic information regarding appearance knowledge of instances. In this paper, we introduce a novel approach to utilize the strength of an LLM in understanding contextual appearance variations and to leverage its knowledge into a vision model (here, pedestrian detection). While pedestrian detection is considered one of crucial tasks directly related with our safety (e.g., intelligent driving system), it is challenging because of varying appearances and poses in diverse scenes. Therefore, we propose to formulate language-driven appearance knowledge units and incorporate them with visual cues in pedestrian detection. To this end, we establish description corpus which includes numerous narratives describing various appearances of pedestrians and others. By feeding them through an LLM, we extract appearance knowledge sets that contain the representations of appearance variations. After that, we perform a task-prompting process to obtain appearance knowledge units which are representative appearance knowledge guided to be relevant to a downstream pedestrian detection task. Finally, we provide plentiful appearance information by integrating the language-driven knowledge units with visual cues. Through comprehensive experiments with various pedestrian detectors, we verify the effectiveness of our method showing noticeable performance gains and achieving state-of-the-art detection performance.
Authors: Hinako Asaoka, Kazue Kudo
Classical computing has borne witness to the development of machine learning. The integration of quantum technology into this mix will lead to unimaginable benefits and be regarded as a giant leap forward in mankind's ability to compute. Demonstrating the benefits of this integration now becomes essential. With the advance of quantum computing, several machine-learning techniques have been proposed that use quantum annealing. In this study, we implement a matrix factorization method using quantum annealing for image classification and compare the performance with traditional machine-learning methods. Nonnegative/binary matrix factorization (NBMF) was originally introduced as a generative model, and we propose a multiclass classification model as an application. We extract the features of handwritten digit images using NBMF and apply them to solve the classification problem. Our findings show that when the amount of data, features, and epochs is small, the accuracy of models trained by NBMF is superior to classical machine-learning methods, such as neural networks. Moreover, we found that training models using a quantum annealing solver significantly reduces computation time. Under certain conditions, there is a benefit to using quantum annealing technology with machine learning.
Authors: Xueting Hu, Ce Zhang, Yi Zhang, Bowen Hai, Ke Yu, Zhihai He
Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results. The coarse estimation of depth is then achieved by weighting and summing the depth values, called depth bins, corresponding to the predefined semantic descriptions. The zero-shot approach circumvents the computational and time-intensive nature of traditional fully-supervised depth estimation methods. However, this method, utilizing fixed depth bins, may not effectively generalize as images from different scenes may exhibit distinct depth distributions. To address this challenge, we propose a few-shot-based method which learns to adapt the VLMs for monocular depth estimation to balance training costs and generalization capabilities. Specifically, it assigns different depth bins for different scenes, which can be selected by the model during inference. Additionally, we incorporate learnable prompts to preprocess the input text to convert the easily human-understood text into easily model-understood vectors and further enhance the performance. With only one image per scene for training, our extensive experiment results on the NYU V2 and KITTI dataset demonstrate that our method outperforms the previous state-of-the-art method by up to 10.6\% in terms of MARE.
Authors: Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, Michele Magno
Smart glasses are rapidly gaining advanced functionality thanks to cutting-edge computing technologies, accelerated hardware architectures, and tiny AI algorithms. Integrating AI into smart glasses featuring a small form factor and limited battery capacity is still challenging when targeting full-day usage for a satisfactory user experience. This paper illustrates the design and implementation of tiny machine-learning algorithms exploiting novel low-power processors to enable prolonged continuous operation in smart glasses. We explore the energy- and latency-efficient of smart glasses in the case of real-time object detection. To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication. The smart glasses integrate power cycling mechanisms, including image and audio sensing interfaces. Furthermore, we developed a family of novel tiny deep-learning models based on YOLO with sub-million parameters customized for microcontroller-based inference dubbed TinyissimoYOLO v1.3, v5, and v8, aiming at benchmarking object detection with smart glasses for energy and latency. Evaluations on the prototype of the smart glasses demonstrate TinyissimoYOLO's 17ms inference latency and 1.59mJ energy consumption per inference while ensuring acceptable detection accuracy. Further evaluation reveals an end-to-end latency from image capturing to the algorithm's prediction of 56ms or equivalently 18 fps, with a total power consumption of 62.9mW, equivalent to a 9.3 hours of continuous run time on a 154mAh battery. These results outperform MCUNet (TinyNAS+TinyEngine), which runs a simpler task (image classification) at just 7.3 fps per second.
Authors: Zalan Fabian, Zhongqi Miao, Chunyuan Li, Yuanhan Zhang, Ziwei Liu, Andrés Hernández, Andrés Montes-Rojas, Rafael Escucha, Laura Siabatto, Andrés Link, Pablo Arbeláez, Rahul Dodhia, Juan Lavista Ferres
Due to deteriorating environmental conditions and increasing human activity, conservation efforts directed towards wildlife is crucial. Motion-activated camera traps constitute an efficient tool for tracking and monitoring wildlife populations across the globe. Supervised learning techniques have been successfully deployed to analyze such imagery, however training such techniques requires annotations from experts. Reducing the reliance on costly labelled data therefore has immense potential in developing large-scale wildlife tracking solutions with markedly less human labor. In this work we propose WildMatch, a novel zero-shot species classification framework that leverages multimodal foundation models. In particular, we instruction tune vision-language models to generate detailed visual descriptions of camera trap images using similar terminology to experts. Then, we match the generated caption to an external knowledge base of descriptions in order to determine the species in a zero-shot manner. We investigate techniques to build instruction tuning datasets for detailed animal description generation and propose a novel knowledge augmentation technique to enhance caption quality. We demonstrate the performance of WildMatch on a new camera trap dataset collected in the Magdalena Medio region of Colombia.
Authors: Congrui Hetang, Yuping Wang
In this paper, we propose an approach for synthesizing novel view images from a single RGBD (Red Green Blue-Depth) input. Novel view synthesis (NVS) is an interesting computer vision task with extensive applications. Methods using multiple images has been well-studied, exemplary ones include training scene-specific Neural Radiance Fields (NeRF), or leveraging multi-view stereo (MVS) and 3D rendering pipelines. However, both are either computationally intensive or non-generalizable across different scenes, limiting their practical value. Conversely, the depth information embedded in RGBD images unlocks 3D potential from a singular view, simplifying NVS. The widespread availability of compact, affordable stereo cameras, and even LiDARs in contemporary devices like smartphones, makes capturing RGBD images more accessible than ever. In our method, we convert an RGBD image into a point cloud and render it from a different viewpoint, then formulate the NVS task into an image translation problem. We leveraged generative adversarial networks to style-transfer the rendered image, achieving a result similar to a photograph taken from the new perspective. We explore both unsupervised learning using CycleGAN and supervised learning with Pix2Pix, and demonstrate the qualitative results. Our method circumvents the limitations of traditional multi-image techniques, holding significant promise for practical, real-time applications in NVS.
Authors: Yingying Fang, Shuang Wu, Sheng Zhang, Chaoyan Huang, Tieyong Zeng, Xiaodan Xing, Simon Walsh, Guang Yang
Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosis tasks. Most existing multi-modal techniques only focus on enhancing their performance by leveraging the differences or shared features from various modalities and fusing feature across different modalities. These approaches are generally not optimal for clinical settings, which pose the additional challenges of limited training data, as well as being rife with redundant data or noisy modality channels, leading to subpar performance. To address this gap, we study the robustness of existing methods to data redundancy and noise and propose a generalized dynamic multimodal information bottleneck framework for attaining a robust fused feature representation. Specifically, our information bottleneck module serves to filter out the task-irrelevant information and noises in the fused feature, and we further introduce a sufficiency loss to prevent dropping of task-relevant information, thus explicitly preserving the sufficiency of prediction information in the distilled feature. We validate our model on an in-house and a public COVID19 dataset for mortality prediction as well as two public biomedical datasets for diagnostic tasks. Extensive experiments show that our method surpasses the state-of-the-art and is significantly more robust, being the only method to remain performance when large-scale noisy channels exist. Our code is publicly available at https://github.com/BII-wushuang/DMIB.
Authors: Nicolas Cherel, Andrés Almansa, Yann Gousseau, Alasdair Newson
Video inpainting is the task of filling a desired region in a video in a visually convincing manner. It is a very challenging task due to the high dimensionality of the signal and the temporal consistency required for obtaining convincing results. Recently, diffusion models have shown impressive results in modeling complex data distributions, including images and videos. Diffusion models remain nonetheless very expensive to train and perform inference with, which strongly restrict their application to video. We show that in the case of video inpainting, thanks to the highly auto-similar nature of videos, the training of a diffusion model can be restricted to the video to inpaint and still produce very satisfying results. This leads us to adopt an internal learning approch, which also allows for a greatly reduced network size. We call our approach "Infusion": an internal learning algorithm for video inpainting through diffusion. Due to our frugal network, we are able to propose the first video inpainting approach based purely on diffusion. Other methods require supporting elements such as optical flow estimation, which limits their performance in the case of dynamic textures for example. We introduce a new method for efficient training and inference of diffusion models in the context of internal learning. We split the diffusion process into different learning intervals which greatly simplifies the learning steps. We show qualititative and quantitative results, demonstrating that our method reaches state-of-the-art performance, in particular in the case of dynamic backgrounds and textures.
Authors: Tianrui Hui, Zihan Ding, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Jiao Dai, Jizhong Han, Si Liu
Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a PhraseObject Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.
Authors: Lijian Xu, Ziyu Ni, Xinglong Liu, Xiaosong Wang, Hongsheng Li, Shaoting Zhang
The emergence of multi-modal deep learning models has made significant impacts on clinical applications in the last decade. However, the majority of models are limited to single-tasking, without considering disease diagnosis is indeed a multi-task procedure. Here, we demonstrate a unified transformer model specifically designed for multi-modal clinical tasks by incorporating customized instruction tuning. We first compose a multi-task training dataset comprising 13.4 million instruction and ground-truth pairs (with approximately one million radiographs) for the customized tuning, involving both image- and pixel-level tasks. Thus, we can unify the various vision-intensive tasks in a single training framework with homogeneous model inputs and outputs to increase clinical interpretability in one reading. Finally, we demonstrate the overall superior performance of our model compared to prior arts on various chest X-ray benchmarks across multi-tasks in both direct inference and finetuning settings. Three radiologists further evaluate the generated reports against the recorded ones, which also exhibit the enhanced explainability of our multi-task model.
Authors: Tomas Karella, Filip Sroubek, Jan Flusser, Jan Blazek, Vasek Kosik
The widespread popularity of equivariant networks underscores the significance of parameter efficient models and effective use of training data. At a time when robustness to unseen deformations is becoming increasingly important, we present H-NeXt, which bridges the gap between equivariance and invariance. H-NeXt is a parameter-efficient roto-translation invariant network that is trained without a single augmented image in the training set. Our network comprises three components: an equivariant backbone for learning roto-translation independent features, an invariant pooling layer for discarding roto-translation information, and a classification layer. H-NeXt outperforms the state of the art in classification on unaugmented training sets and augmented test sets of MNIST and CIFAR-10.
Authors: Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj
RGB-based surface anomaly detection methods have advanced significantly. However, certain surface anomalies remain practically invisible in RGB alone, necessitating the incorporation of 3D information. Existing approaches that employ point-cloud backbones suffer from suboptimal representations and reduced applicability due to slow processing. Re-training RGB backbones, designed for faster dense input processing, on industrial depth datasets is hindered by the limited availability of sufficiently large datasets. We make several contributions to address these challenges. (i) We propose a novel Depth-Aware Discrete Autoencoder (DADA) architecture, that enables learning a general discrete latent space that jointly models RGB and 3D data for 3D surface anomaly detection. (ii) We tackle the lack of diverse industrial depth datasets by introducing a simulation process for learning informative depth features in the depth encoder. (iii) We propose a new surface anomaly detection method 3DSR, which outperforms all existing state-of-the-art on the challenging MVTec3D anomaly detection benchmark, both in terms of accuracy and processing speed. The experimental results validate the effectiveness and efficiency of our approach, highlighting the potential of utilizing depth information for improved surface anomaly detection.
Authors: Michela Perino, Michele Ginolfi, Anna Candida Felici, Michela Rosellini
Palimpsests refer to historical manuscripts where erased writings have been partially covered by the superimposition of a second writing. By employing imaging techniques, e.g., multispectral imaging, it becomes possible to identify features that are imperceptible to the naked eye, including faded and erased inks. When dealing with overlapping inks, Artificial Intelligence techniques can be utilized to disentangle complex nodes of overlapping letters. In this work, we propose deep learning-based semantic segmentation as a method for identifying and segmenting individual letters in overlapping characters. The experiment was conceived as a proof of concept, focusing on the palimpsests of the Ars Grammatica by Prisciano as a case study. Furthermore, caveats and prospects of our approach combined with multispectral imaging are also discussed.
Authors: Karen-Helene Støverud, David Bouget, Andre Pedersen, Håkon Olav Leira, Thomas Langø, Erlend Fagertun Hofstad
To improve the prognosis of patients suffering from pulmonary diseases, such as lung cancer, early diagnosis and treatment are crucial. The analysis of CT images is invaluable for diagnosis, whereas high quality segmentation of the airway tree are required for intervention planning and live guidance during bronchoscopy. Recently, the Multi-domain Airway Tree Modeling (ATM'22) challenge released a large dataset, both enabling training of deep-learning based models and bringing substantial improvement of the state-of-the-art for the airway segmentation task. However, the ATM'22 dataset includes few patients with severe pathologies affecting the airway tree anatomy. In this study, we introduce a new public benchmark dataset (AeroPath), consisting of 27 CT images from patients with pathologies ranging from emphysema to large tumors, with corresponding trachea and bronchi annotations. Second, we present a multiscale fusion design for automatic airway segmentation. Models were trained on the ATM'22 dataset, tested on the AeroPath dataset, and further evaluated against competitive open-source methods. The same performance metrics as used in the ATM'22 challenge were used to benchmark the different considered approaches. Lastly, an open web application is developed, to easily test the proposed model on new data. The results demonstrated that our proposed architecture predicted topologically correct segmentations for all the patients included in the AeroPath dataset. The proposed method is robust and able to handle various anomalies, down to at least the fifth airway generation. In addition, the AeroPath dataset, featuring patients with challenging pathologies, will contribute to development of new state-of-the-art methods. The AeroPath dataset and the web application are made openly available.
Authors: Menglin Wang, Xiaojin Gong
Supervised person re-identification assumes that a person has images captured under multiple cameras. However when cameras are placed in distance, a person rarely appears in more than one camera. This paper thus studies person re-ID under such isolated camera supervised (ISCS) setting. Instead of trying to generate fake cross-camera features like previous methods, we explore a novel perspective by making efficient use of the variation in training data. Under ISCS setting, a person only has limited images from a single camera, so the camera bias becomes a critical issue confounding ID discrimination. Cross-camera images are prone to being recognized as different IDs simply by camera style. To eliminate the confounding effect of camera bias, we propose to learn both intra- and inter-camera invariance under a unified framework. First, we construct style-consistent environments via clustering, and perform prototypical contrastive learning within each environment. Meanwhile, strongly augmented images are contrasted with original prototypes to enforce intra-camera augmentation invariance. For inter-camera invariance, we further design a much improved variant of multi-camera negative loss that optimizes the distance of multi-level negatives. The resulting model learns to be invariant to both subtle and severe style variation within and cross-camera. On multiple benchmarks, we conduct extensive experiments and validate the effectiveness and superiority of the proposed method. Code will be available at https://github.com/Terminator8758/IICI.
Authors: Al Zahraa Elsayed, Khalil Mohamed, Hany Harb
The emergence of pandemics has significantly emphasized the need for effective solutions in healthcare data analysis. One particular challenge in this domain is the manual examination of medical images, such as X-rays and CT scans. This process is time-consuming and involves the logistical complexities of transferring these images to centralized cloud computing servers. Additionally, the speed and accuracy of image analysis are vital for efficient healthcare image management. This research paper introduces an innovative healthcare architecture that tackles the challenges of analysis efficiency and accuracy by harnessing the capabilities of Artificial Intelligence (AI). Specifically, the proposed architecture utilizes fog computing and presents a modified Convolutional Neural Network (CNN) designed specifically for image analysis. Different architectures of CNN layers are thoroughly explored and evaluated to optimize overall performance. To demonstrate the effectiveness of the proposed approach, a dataset of X-ray images is utilized for analysis and evaluation. Comparative assessments are conducted against recent models such as VGG16, VGG19, MobileNet, and related research papers. Notably, the proposed approach achieves an exceptional accuracy rate of 99.88% in classifying normal cases, accompanied by a validation rate of 96.5%, precision and recall rates of 100%, and an F1 score of 100%. These results highlight the immense potential of fog computing and modified CNNs in revolutionizing healthcare image analysis and diagnosis, not only during pandemics but also in the future. By leveraging these technologies, healthcare professionals can enhance the efficiency and accuracy of medical image analysis, leading to improved patient care and outcomes.
Authors: Anuja Vats, David Völgyes, Martijn Vermeer, Marius Pedersen, Kiran Raja, Daniele S.M.Fantin, Jacob Alexander Hay
Estimating building footprint maps from geospatial data is of paramount importance in urban planning, development, disaster management, and various other applications. Deep learning methodologies have gained prominence in building segmentation maps, offering the promise of precise footprint extraction without extensive post-processing. However, these methods face challenges in generalization and label efficiency, particularly in remote sensing, where obtaining accurate labels can be both expensive and time-consuming. To address these challenges, we propose terrain-aware self-supervised learning, tailored to remote sensing, using digital elevation models from LiDAR data. We propose to learn a model to differentiate between bare Earth and superimposed structures enabling the network to implicitly learn domain-relevant features without the need for extensive pixel-level annotations. We test the effectiveness of our approach by evaluating building segmentation performance on test datasets with varying label fractions. Remarkably, with only 1% of the labels (equivalent to 25 labeled examples), our method improves over ImageNet pre-training, showing the advantage of leveraging unlabeled data for feature extraction in the domain of remote sensing. The performance improvement is more pronounced in few-shot scenarios and gradually closes the gap with ImageNet pre-training as the label fraction increases. We test on a dataset characterized by substantial distribution shifts and labeling errors to demonstrate the generalizability of our approach. When compared to other baselines, including ImageNet pretraining and more complex architectures, our approach consistently performs better, demonstrating the efficiency and effectiveness of self-supervised terrain-aware feature learning.
Authors: Hyeongjin Kim, Sangwon Kim, Jong Taek Lee, Byoung Chul Ko
Along with generative AI, interest in scene graph generation (SGG), which comprehensively captures the relationships and interactions between objects in an image and creates a structured graph-based representation, has significantly increased in recent years. However, relying on object-centric and dichotomous relationships, existing SGG methods have a limited ability to accurately predict detailed relationships. To solve these problems, a new approach to the modeling multiobject relationships, called edge dual scene graph generation (EdgeSGG), is proposed herein. EdgeSGG is based on a edge dual scene graph and Dual Message Passing Neural Network (DualMPNN), which can capture rich contextual interactions between unconstrained objects. To facilitate the learning of edge dual scene graphs with a symmetric graph structure, the proposed DualMPNN learns both object- and relation-centric features for more accurately predicting relation-aware contexts and allows fine-grained relational updates between objects. A comparative experiment with state-of-the-art (SoTA) methods was conducted using two public datasets for SGG operations and six metrics for three subtasks. Compared with SoTA approaches, the proposed model exhibited substantial performance improvements across all SGG subtasks. Furthermore, experiment on long-tail distributions revealed that incorporating the relationships between objects effectively mitigates existing long-tail problems.
Authors: Jin Li, Yaoming Wang, Xiaopeng Zhang, Bowen Shi, Dongsheng Jiang, Chenglin Li, Wenrui Dai, Hongkai Xiong, Qi Tian
Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require high-resolution input, the complexity of ViTs increases significantly. Notably, dense prediction tasks, such as semantic segmentation or object detection, emphasize more on the contours or shapes of objects, while the texture inside objects is less informative. Motivated by this observation, we propose to apply adaptive resolution for different regions in the image according to their importance. Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence. Once the representative tokens are determined, we proceed to merge other tokens into their closest representative token. Consequently, semantic similar tokens are merged together to form low-resolution regions, while semantic irrelevant tokens are preserved independently as high-resolution regions. This strategy effectively reduces the number of tokens, allowing subsequent layers to handle a reduced token sequence and achieve acceleration. We evaluate our proposed method on three different datasets and observe promising performance. For example, the "Segmenter ViT-L" model can be accelerated by 48% FPS without fine-tuning, while maintaining the performance. Additionally, our method can be applied to accelerate fine-tuning as well. Experimental results demonstrate that we can save 52% training time while accelerating 2.46 times FPS with only a 0.09% performance drop. The code is available at https://github.com/caddyless/ailurus/tree/main.
Authors: Yifan Xie, Jihua Zhu, Shiqi Li, Pengcheng Shi
The majority of point cloud registration methods currently rely on extracting features from points. However, these methods are limited by their dependence on information obtained from a single modality of points, which can result in deficiencies such as inadequate perception of global features and a lack of texture information. Actually, humans can employ visual information learned from 2D images to comprehend the 3D world. Based on this fact, we present a novel Cross-Modal Information-Guided Network (CMIGNet), which obtains global shape perception through cross-modal information to achieve precise and robust point cloud registration. Specifically, we first incorporate the projected images from the point clouds and fuse the cross-modal features using the attention mechanism. Furthermore, we employ two contrastive learning strategies, namely overlapping contrastive learning and cross-modal contrastive learning. The former focuses on features in overlapping regions, while the latter emphasizes the correspondences between 2D and 3D features. Finally, we propose a mask prediction module to identify keypoints in the point clouds. Extensive experiments on several benchmark datasets demonstrate that our network achieves superior registration performance.
Authors: Chun Liu, Longwei Yang, Zheng Li, Wei Yang, Zhigang Han, Jianzhong Guo, Junyong Yu
Cross-domain few-shot hyperspectral image classification focuses on learning prior knowledge from a large number of labeled samples from source domain and then transferring the knowledge to the tasks which contain only few labeled samples in target domains. Following the metric-based manner, many current methods first extract the features of the query and support samples, and then directly predict the classes of query samples according to their distance to the support samples or prototypes. The relations between samples have not been fully explored and utilized. Different from current works, this paper proposes to learn sample relations from different views and take them into the model learning process, to improve the cross-domain few-shot hyperspectral image classification. Building on current DCFSL method which adopts a domain discriminator to deal with domain-level distribution difference, the proposed method applys contrastive learning to learn the class-level sample relations to obtain more discriminable sample features. In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attentions from query samples to support samples. Our experimental results have demonstrated the contribution of the multi-view relation learning mechanism for few-shot hyperspectral image classification when compared with the state of the art methods.
Authors: Xiongzheng Li, Jinsong Zhang, Yu-Kun Lai, Jingyu Yang, Kun Li
Much progress has been made in reconstructing garments from an image or a video. However, none of existing works meet the expectations of digitizing high-quality animatable dynamic garments that can be adjusted to various unseen poses. In this paper, we propose the first method to recover high-quality animatable dynamic garments from monocular videos without depending on scanned data. To generate reasonable deformations for various unseen poses, we propose a learnable garment deformation network that formulates the garment reconstruction task as a pose-driven deformation problem. To alleviate the ambiguity estimating 3D garments from monocular videos, we design a multi-hypothesis deformation module that learns spatial representations of multiple plausible deformations. Experimental results on several public datasets demonstrate that our method can reconstruct high-quality dynamic garments with coherent surface details, which can be easily animated under unseen poses. The code will be provided for research purposes.
Authors: Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis
In this work, we present new proofs of convergence for Plug-and-Play (PnP) algorithms. PnP methods are efficient iterative algorithms for solving image inverse problems where regularization is performed by plugging a pre-trained denoiser in a proximal algorithm, such as Proximal Gradient Descent (PGD) or Douglas-Rachford Splitting (DRS). Recent research has explored convergence by incorporating a denoiser that writes exactly as a proximal operator. However, the corresponding PnP algorithm has then to be run with stepsize equal to $1$. The stepsize condition for nonconvex convergence of the proximal algorithm in use then translates to restrictive conditions on the regularization parameter of the inverse problem. This can severely degrade the restoration capacity of the algorithm. In this paper, we present two remedies for this limitation. First, we provide a novel convergence proof for PnP-DRS that does not impose any restrictions on the regularization parameter. Second, we examine a relaxed version of the PGD algorithm that converges across a broader range of regularization parameters. Our experimental study, conducted on deblurring and super-resolution experiments, demonstrate that both of these solutions enhance the accuracy of image restoration.
Authors: Xiang Gu, Liwei Yang, Jian Sun, Zongben Xu
Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation. However, it requires the paired data as condition, and there would be insufficient paired data provided in real-world applications. To tackle the applications with partially paired or even unpaired dataset, we propose a novel Optimal Transport-guided Conditional Score-based diffusion model (OTCS) in this paper. We build the coupling relationship for the unpaired or partially paired dataset based on $L_2$-regularized unsupervised or semi-supervised optimal transport, respectively. Based on the coupling relationship, we develop the objective for training the conditional score-based model for unpaired or partially paired settings, which is based on a reformulation and generalization of the conditional SBDM for paired setting. With the estimated coupling relationship, we effectively train the conditional score-based model by designing a ``resampling-by-compatibility'' strategy to choose the sampled data with high compatibility as guidance. Extensive experiments on unpaired super-resolution and semi-paired image-to-image translation demonstrated the effectiveness of the proposed OTCS model. From the viewpoint of optimal transport, OTCS provides an approach to transport data across distributions, which is a challenge for OT on large-scale datasets. We theoretically prove that OTCS realizes the data transport in OT with a theoretical bound. Code is available at \url{https://github.com/XJTU-XGU/OTCS}.
Authors: Jayateja Kalla, Soma Biswas
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data distributions. Addressing the challenge posed by the under-representation of tail classes in long-tail class incremental learning, our approach achieves classifier alignment by leveraging global variance as an informative measure and class prototypes in the second stage. This process effectively captures class properties and eliminates the need for data balancing or additional layer tuning. Alongside traditional class incremental learning losses in the first stage, the proposed approach incorporates mixup classes to learn robust feature representations, ensuring smoother boundaries. The proposed framework can seamlessly integrate as a module with any class incremental learning method to effectively handle long-tail class incremental learning scenarios. Extensive experimentation on the CIFAR-100 and ImageNet-Subset datasets validates the approach's efficacy, showcasing its superiority over state-of-the-art techniques across various long-tail CIL settings.
Authors: Jiwan Chung, Youngjae Yu
Large language models such as GPT-3 have demonstrated an impressive capability to adapt to new tasks without requiring task-specific training data. This capability has been particularly effective in settings such as narrative question answering, where the diversity of tasks is immense, but the available supervision data is small. In this work, we investigate if such language models can extend their zero-shot reasoning abilities to long multimodal narratives in multimedia content such as drama, movies, and animation, where the story plays an essential role. We propose Long Story Short, a framework for narrative video QA that first summarizes the narrative of the video to a short plot and then searches parts of the video relevant to the question. We also propose to enhance visual matching with CLIPCheck. Our model outperforms state-of-the-art supervised models by a large margin, highlighting the potential of zero-shot QA for long videos.
Authors: Fernando Alonso-Fernandez, Kiran B. Raja, Christoph Busch, Josef Bigun
The proliferation of cameras and personal devices results in a wide variability of imaging conditions, producing large intra-class variations and a significant performance drop when images from heterogeneous environments are compared. However, many applications require to deal with data from different sources regularly, thus needing to overcome these interoperability problems. Here, we employ fusion of several comparators to improve periocular performance when images from different smartphones are compared. We use a probabilistic fusion framework based on linear logistic regression, in which fused scores tend to be log-likelihood ratios, obtaining a reduction in cross-sensor EER of up to 40% due to the fusion. Our framework also provides an elegant and simple solution to handle signals from different devices, since same-sensor and cross-sensor score distributions are aligned and mapped to a common probabilistic domain. This allows the use of Bayes thresholds for optimal decision-making, eliminating the need of sensor-specific thresholds, which is essential in operational conditions because the threshold setting critically determines the accuracy of the authentication process in many applications.
Authors: Yiangos Georgiou, Marios Loizou, Tom Kelly, Melinos Averkiou
We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints. Our method employs a conditional GAN, taking a single view of a facade along with the desired viewpoint information and generates an image of the facade from the distinct viewpoint. To precisely modify view-dependent elements like windows and doors while preserving the structure of view-independent components such as walls, we introduce a selective editing module. This module leverages image embeddings extracted from a pre-trained vision transformer. Our experiments demonstrated state-of-the-art performance on building facade generation, surpassing alternative methods.
Authors: Eduardo Ribeiro, Andreas Uhl, Fernando Alonso-Fernandez, Reuben A. Farrugia
In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local information and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms.
Authors: Han Xue, Yutong Li, Wenqiang Xu, Huanyu Li, Dongzhe Zheng, Cewu Lu
This paper explores the development of UniFolding, a sample-efficient, scalable, and generalizable robotic system for unfolding and folding various garments. UniFolding employs the proposed UFONet neural network to integrate unfolding and folding decisions into a single policy model that is adaptable to different garment types and states. The design of UniFolding is based on a garment's partial point cloud, which aids in generalization and reduces sensitivity to variations in texture and shape. The training pipeline prioritizes low-cost, sample-efficient data collection. Training data is collected via a human-centric process with offline and online stages. The offline stage involves human unfolding and folding actions via Virtual Reality, while the online stage utilizes human-in-the-loop learning to fine-tune the model in a real-world setting. The system is tested on two garment types: long-sleeve and short-sleeve shirts. Performance is evaluated on 20 shirts with significant variations in textures, shapes, and materials. More experiments and videos can be found in the supplementary materials and on the website: https://unifolding.robotflow.ai
Authors: Hamid Ahmadabadi, Omid Nejati Manzari, Ahmad Ayatollahi
This paper presents a study on improving human action recognition through the utilization of knowledge distillation, and the combination of CNN and ViT models. The research aims to enhance the performance and efficiency of smaller student models by transferring knowledge from larger teacher models. The proposed method employs a Transformer vision network as the student model, while a convolutional network serves as the teacher model. The teacher model extracts local image features, whereas the student model focuses on global features using an attention mechanism. The Vision Transformer (ViT) architecture is introduced as a robust framework for capturing global dependencies in images. Additionally, advanced variants of ViT, namely PVT, Convit, MVIT, Swin Transformer, and Twins, are discussed, highlighting their contributions to computer vision tasks. The ConvNeXt model is introduced as a teacher model, known for its efficiency and effectiveness in computer vision. The paper presents performance results for human action recognition on the Stanford 40 dataset, comparing the accuracy and mAP of student models trained with and without knowledge distillation. The findings illustrate that the suggested approach significantly improves the accuracy and mAP when compared to training networks under regular settings. These findings emphasize the potential of combining local and global features in action recognition tasks.
Authors: Hermes McGriff, Renato Martins, Nicolas Andreff, Cédric Demonceaux
In this paper, we propose an approach to address the problem of 3D reconstruction of scenes from a single image captured by a light-field camera equipped with a rolling shutter sensor. Our method leverages the 3D information cues present in the light-field and the motion information provided by the rolling shutter effect. We present a generic model for the imaging process of this sensor and a two-stage algorithm that minimizes the re-projection error while considering the position and motion of the camera in a motion-shape bundle adjustment estimation strategy. Thereby, we provide an instantaneous 3D shape-and-pose-and-velocity sensing paradigm. To the best of our knowledge, this is the first study to leverage this type of sensor for this purpose. We also present a new benchmark dataset composed of different light-fields showing rolling shutter effects, which can be used as a common base to improve the evaluation and tracking the progress in the field. We demonstrate the effectiveness and advantages of our approach through several experiments conducted for different scenes and types of motions. The source code and dataset are publicly available at: https://github.com/ICB-Vision-AI/RSLF
Authors: Wenxuan Bao, Francesco Pittaluga, Vijay Kumar B G, Vincent Bindschaedler
Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are fundamentally incompatible with differentially private learning approaches, due to the latter's built-in assumption that each training image's contribution to the learned model is bounded. In this paper, we investigate why naive applications of multi-sample data augmentation techniques, such as mixup, fail to achieve good performance and propose two novel data augmentation techniques specifically designed for the constraints of differentially private learning. Our first technique, DP-Mix_Self, achieves SoTA classification performance across a range of datasets and settings by performing mixup on self-augmented data. Our second technique, DP-Mix_Diff, further improves performance by incorporating synthetic data from a pre-trained diffusion model into the mixup process. We open-source the code at https://github.com/wenxuan-Bao/DP-Mix.
Authors: Jihoon Cho, Jinah Park
Medical segmentation has grown exponentially through the advent of a fully convolutional network (FCN), and we have now reached a turning point through the success of Transformer. However, the different characteristics of the modality have not been fully integrated into Transformer for medical segmentation. In this work, we propose the novel hybrid fusion Transformer (HFTrans) for multisequence MRI image segmentation. We take advantage of the differences among multimodal MRI sequences and utilize the Transformer layers to integrate the features extracted from each modality as well as the features of the early fused modalities. We validate the effectiveness of our hybrid-fusion method in three-dimensional (3D) medical segmentation. Experiments on two public datasets, BraTS2020 and MRBrainS18, show that the proposed method outperforms previous state-of-the-art methods on the task of brain tumor segmentation and brain structure segmentation.
Authors: Badri N. Patro, Vijay Srinivas Agneeswaran
Vision transformers have gained significant attention and achieved state-of-the-art performance in various computer vision tasks, including image classification, instance segmentation, and object detection. However, challenges remain in addressing attention complexity and effectively capturing fine-grained information within images. Existing solutions often resort to down-sampling operations, such as pooling, to reduce computational cost. Unfortunately, such operations are non-invertible and can result in information loss. In this paper, we present a novel approach called Scattering Vision Transformer (SVT) to tackle these challenges. SVT incorporates a spectrally scattering network that enables the capture of intricate image details. SVT overcomes the invertibility issue associated with down-sampling operations by separating low-frequency and high-frequency components. Furthermore, SVT introduces a unique spectral gating network utilizing Einstein multiplication for token and channel mixing, effectively reducing complexity. We show that SVT achieves state-of-the-art performance on the ImageNet dataset with a significant reduction in a number of parameters and FLOPS. SVT shows 2\% improvement over LiTv2 and iFormer. SVT-H-S reaches 84.2\% top-1 accuracy, while SVT-H-B reaches 85.2\% (state-of-art for base versions) and SVT-H-L reaches 85.7\% (again state-of-art for large versions). SVT also shows comparable results in other vision tasks such as instance segmentation. SVT also outperforms other transformers in transfer learning on standard datasets such as CIFAR10, CIFAR100, Oxford Flower, and Stanford Car datasets. The project page is available on this webpage.\url{https://badripatro.github.io/svt/}.
Authors: Qizhang Li, Yiwen Guo, Wangmeng Zuo, Hao Chen
The adversarial vulnerability of deep neural networks (DNNs) has drawn great attention due to the security risk of applying these models in real-world applications. Based on transferability of adversarial examples, an increasing number of transfer-based methods have been developed to fool black-box DNN models whose architecture and parameters are inaccessible. Although tremendous effort has been exerted, there still lacks a standardized benchmark that could be taken advantage of to compare these methods systematically, fairly, and practically. Our investigation shows that the evaluation of some methods needs to be more reasonable and more thorough to verify their effectiveness, to avoid, for example, unfair comparison and insufficient consideration of possible substitute/victim models. Therefore, we establish a transfer-based attack benchmark (TA-Bench) which implements 30+ methods. In this paper, we evaluate and compare them comprehensively on 25 popular substitute/victim models on ImageNet. New insights about the effectiveness of these methods are gained and guidelines for future evaluations are provided. Code at: https://github.com/qizhangli/TA-Bench.
Authors: Yu Zhou, Jan Sollman, Jianxu Chen
With the fast development of modern microscopes and bioimaging techniques, an unprecedentedly large amount of imaging data are being generated, stored, analyzed, and even shared through networks. The size of the data poses great challenges for current data infrastructure. One common way to reduce the data size is by image compression. This present study analyzes classic and deep learning based image compression methods, and their impact on deep learning based image processing models. Deep learning based label-free prediction models (i.e., predicting fluorescent images from bright field images) are used as an example application for comparison and analysis. Effective image compression methods could help reduce the data size significantly without losing necessary information, and therefore reduce the burden on data management infrastructure and permit fast transmission through the network for data sharing or cloud computing. To compress images in such a wanted way, multiple classical lossy image compression techniques are compared to several AI-based compression models provided by and trained with the CompressAI toolbox using python. These different compression techniques are compared in compression ratio, multiple image similarity measures and, most importantly, the prediction accuracy from label-free models on compressed images. We found that AI-based compression techniques largely outperform the classic ones and will minimally affect the downstream label-free task in 2D cases. In the end, we hope the present study could shed light on the potential of deep learning based image compression and the impact of image compression on downstream deep learning based image analysis models.
Authors: Tianyi Wang, Mengxiao Huang, Harry Cheng, Bin Ma, Yinglong Wang
Notwithstanding offering convenience and entertainment to society, Deepfake face swapping has caused critical privacy issues with the rapid development of deep generative models. Due to imperceptible artifacts in high-quality synthetic images, passive detection models against face swapping in recent years usually suffer performance damping regarding the generalizability issue. Therefore, several studies have been attempted to proactively protect the original images against malicious manipulations by inserting invisible signals in advance. However, the existing proactive defense approaches demonstrate unsatisfactory results with respect to visual quality, detection accuracy, and source tracing ability. In this study, we propose the first robust identity perceptual watermarking framework that concurrently performs detection and source tracing against Deepfake face swapping proactively. We assign identity semantics regarding the image contents to the watermarks and devise an unpredictable and unreversible chaotic encryption system to ensure watermark confidentiality. The watermarks are encoded and recovered by jointly training an encoder-decoder framework along with adversarial image manipulations. Extensive experiments demonstrate state-of-the-art performance against Deepfake face swapping under both cross-dataset and cross-manipulation settings.
Authors: Xinlu Zhang, Yujie Lu, Weizhi Wang, An Yan, Jun Yan, Lianke Qin, Heng Wang, Xifeng Yan, William Yang Wang, Linda Ruth Petzold
Automatically evaluating vision-language tasks is challenging, especially when it comes to reflecting human judgments due to limitations in accounting for fine-grained details. Although GPT-4V has shown promising results in various multi-modal tasks, leveraging GPT-4V as a generalist evaluator for these tasks has not yet been systematically explored. We comprehensively validate GPT-4V's capabilities for evaluation purposes, addressing tasks ranging from foundational image-to-text and text-to-image synthesis to high-level image-to-image translations and multi-images to text alignment. We employ two evaluation methods, single-answer grading and pairwise comparison, using GPT-4V. Notably, GPT-4V shows promising agreement with humans across various tasks and evaluation methods, demonstrating immense potential for multi-modal LLMs as evaluators. Despite limitations like restricted visual clarity grading and real-world complex reasoning, its ability to provide human-aligned scores enriched with detailed explanations is promising for universal automatic evaluator.
Authors: Haosen Yang, Chuofan Ma, Bin Wen, Yi Jiang, Zehuan Yuan, Xiatian Zhu
Understanding the semantics of individual regions or patches within unconstrained images, such as in open-world object detection, represents a critical yet challenging task in computer vision. Building on the success of powerful image-level vision-language (ViL) foundation models like CLIP, recent efforts have sought to harness their capabilities by either training a contrastive model from scratch with an extensive collection of region-label pairs or aligning the outputs of a detection model with image-level representations of region proposals. Despite notable progress, these approaches are plagued by computationally intensive training requirements, susceptibility to data noise, and deficiency in contextual information. To address these limitations, we explore the synergistic potential of off-the-shelf foundation models, leveraging their respective strengths in localization and semantics. We introduce a novel, generic, and efficient region recognition architecture, named RegionSpot, designed to integrate position-aware localization knowledge from a localization foundation model (e.g., SAM) with semantic information extracted from a ViL model (e.g., CLIP). To fully exploit pretrained knowledge while minimizing training overhead, we keep both foundation models frozen, focusing optimization efforts solely on a lightweight attention-based knowledge integration module. Through extensive experiments in the context of open-world object recognition, our RegionSpot demonstrates significant performance improvements over prior alternatives, while also providing substantial computational savings. For instance, training our model with 3 million data in a single day using 8 V100 GPUs. Our model outperforms GLIP by 6.5 % in mean average precision (mAP), with an even larger margin by 14.8 % for more challenging and rare categories.
Authors: Gabriele M. Caddeo, Andrea Maracani, Paolo D. Alfano, Nicola A. Piga, Lorenzo Rosasco, Lorenzo Natale
In this paper, we address the Sim2Real gap in the field of vision-based tactile sensors for classifying object surfaces. We train a Diffusion Model to bridge this gap using a relatively small dataset of real-world images randomly collected from unlabeled everyday objects via the DIGIT sensor. Subsequently, we employ a simulator to generate images by uniformly sampling the surface of objects from the YCB Model Set. These simulated images are then translated into the real domain using the Diffusion Model and automatically labeled to train a classifier. During this training, we further align features of the two domains using an adversarial procedure. Our evaluation is conducted on a dataset of tactile images obtained from a set of ten 3D printed YCB objects. The results reveal a total accuracy of 81.9%, a significant improvement compared to the 34.7% achieved by the classifier trained solely on simulated images. This demonstrates the effectiveness of our approach. We further validate our approach using the classifier on a 6D object pose estimation task from tactile data.
Authors: Chris Zhang, James Tu, Lunjun Zhang, Kelvin Wong, Simon Suo, Raquel Urtasun
Realistic traffic simulation is crucial for developing self-driving software in a safe and scalable manner prior to real-world deployment. Typically, imitation learning (IL) is used to learn human-like traffic agents directly from real-world observations collected offline, but without explicit specification of traffic rules, agents trained from IL alone frequently display unrealistic infractions like collisions and driving off the road. This problem is exacerbated in out-of-distribution and long-tail scenarios. On the other hand, reinforcement learning (RL) can train traffic agents to avoid infractions, but using RL alone results in unhuman-like driving behaviors. We propose Reinforcing Traffic Rules (RTR), a holistic closed-loop learning objective to match expert demonstrations under a traffic compliance constraint, which naturally gives rise to a joint IL + RL approach, obtaining the best of both worlds. Our method learns in closed-loop simulations of both nominal scenarios from real-world datasets as well as procedurally generated long-tail scenarios. Our experiments show that RTR learns more realistic and generalizable traffic simulation policies, achieving significantly better tradeoffs between human-like driving and traffic compliance in both nominal and long-tail scenarios. Moreover, when used as a data generation tool for training prediction models, our learned traffic policy leads to considerably improved downstream prediction metrics compared to baseline traffic agents. For more information, visit the project website: https://waabi.ai/rtr
Authors: Gabriel B. Margolis, Xiang Fu, Yandong Ji, Pulkit Agrawal
Knowledge of terrain's physical properties inferred from color images can aid in making efficient robotic locomotion plans. However, unlike image classification, it is unintuitive for humans to label image patches with physical properties. Without labeled data, building a vision system that takes as input the observed terrain and predicts physical properties remains challenging. We present a method that overcomes this challenge by self-supervised labeling of images captured by robots during real-world traversal with physical property estimators trained in simulation. To ensure accurate labeling, we introduce Active Sensing Motor Policies (ASMP), which are trained to explore locomotion behaviors that increase the accuracy of estimating physical parameters. For instance, the quadruped robot learns to swipe its foot against the ground to estimate the friction coefficient accurately. We show that the visual system trained with a small amount of real-world traversal data accurately predicts physical parameters. The trained system is robust and works even with overhead images captured by a drone despite being trained on data collected by cameras attached to a quadruped robot walking on the ground.
Authors: Shen Nie, Hanzhong Allan Guo, Cheng Lu, Yuhao Zhou, Chenyu Zheng, Chongxuan Li
We present a unified probabilistic formulation for diffusion-based image editing, where a latent variable is edited in a task-specific manner and generally deviates from the corresponding marginal distribution induced by the original stochastic or ordinary differential equation (SDE or ODE). Instead, it defines a corresponding SDE or ODE for editing. In the formulation, we prove that the Kullback-Leibler divergence between the marginal distributions of the two SDEs gradually decreases while that for the ODEs remains as the time approaches zero, which shows the promise of SDE in image editing. Inspired by it, we provide the SDE counterparts for widely used ODE baselines in various tasks including inpainting and image-to-image translation, where SDE shows a consistent and substantial improvement. Moreover, we propose SDE-Drag -- a simple yet effective method built upon the SDE formulation for point-based content dragging. We build a challenging benchmark (termed DragBench) with open-set natural, art, and AI-generated images for evaluation. A user study on DragBench indicates that SDE-Drag significantly outperforms our ODE baseline, existing diffusion-based methods, and the renowned DragGAN. Our results demonstrate the superiority and versatility of SDE in image editing and push the boundary of diffusion-based editing methods.
Authors: Jen-Hao Cheng, Sheng-Yao Kuan, Hugo Latapie, Gaowen Liu, Jenq-Neng Hwang
Robust perception is a vital component for ensuring safe autonomous and assisted driving. Automotive radar (77 to 81 GHz), which offers weather-resilient sensing, provides a complementary capability to the vision- or LiDAR-based autonomous driving systems. Raw radio-frequency (RF) radar tensors contain rich spatiotemporal semantics besides 3D location information. The majority of previous methods take in 3D (Doppler-range-azimuth) RF radar tensors, allowing prediction of an object's location, heading angle, and size in bird's-eye-view (BEV). However, they lack the ability to at the same time infer objects' size, orientation, and identity in the 3D space. To overcome this limitation, we propose an efficient joint architecture called CenterRadarNet, designed to facilitate high-resolution representation learning from 4D (Doppler-range-azimuth-elevation) radar data for 3D object detection and re-identification (re-ID) tasks. As a single-stage 3D object detector, CenterRadarNet directly infers the BEV object distribution confidence maps, corresponding 3D bounding box attributes, and appearance embedding for each pixel. Moreover, we build an online tracker utilizing the learned appearance embedding for re-ID. CenterRadarNet achieves the state-of-the-art result on the K-Radar 3D object detection benchmark. In addition, we present the first 3D object-tracking result using radar on the K-Radar dataset V2. In diverse driving scenarios, CenterRadarNet shows consistent, robust performance, emphasizing its wide applicability.
Authors: Aized Amin Soofi, Fazal-e-Amin
Glaucoma is one of the primary causes of vision loss around the world, necessitating accurate and efficient detection methods. Traditional manual detection approaches have limitations in terms of cost, time, and subjectivity. Recent developments in deep learning approaches demonstrate potential in automating glaucoma detection by detecting relevant features from retinal fundus images. This article provides a comprehensive overview of cutting-edge deep learning methods used for the segmentation, classification, and detection of glaucoma. By analyzing recent studies, the effectiveness and limitations of these techniques are evaluated, key findings are highlighted, and potential areas for further research are identified. The use of deep learning algorithms may significantly improve the efficacy, usefulness, and accuracy of glaucoma detection. The findings from this research contribute to the ongoing advancements in automated glaucoma detection and have implications for improving patient outcomes and reducing the global burden of glaucoma.
Authors: Javad Mirzapour Kaleybar, Hooman Khaloo, Avaz Naghipour
This research paper addresses the challenges associated with traffic sign detection in self-driving vehicles and driver assistance systems. The development of reliable and highly accurate algorithms is crucial for the widespread adoption of traffic sign recognition and detection (TSRD) in diverse real-life scenarios. However, this task is complicated by suboptimal traffic images affected by factors such as camera movement, adverse weather conditions, and inadequate lighting. This study specifically focuses on traffic sign detection methods and introduces the application of the Transformer model, particularly the Vision Transformer variants, to tackle this task. The Transformer's attention mechanism, originally designed for natural language processing, offers improved parallel efficiency. Vision Transformers have demonstrated success in various domains, including autonomous driving, object detection, healthcare, and defense-related applications. To enhance the efficiency of the Transformer model, the research proposes a novel strategy that integrates a locality inductive bias and a transformer module. This includes the introduction of the Efficient Convolution Block and the Local Transformer Block, which effectively capture short-term and long-term dependency information, thereby improving both detection speed and accuracy. Experimental evaluations demonstrate the significant advancements achieved by this approach, particularly when applied to the GTSDB dataset.
Authors: Xinyi Li, Zijian Ma, Yinlong Liu, Walter Zimmer, Hu Cao, Feihu Zhang, Alois Knoll
Point cloud registration is challenging in the presence of heavy outlier correspondences. This paper focuses on addressing the robust correspondence-based registration problem with gravity prior that often arises in practice. The gravity directions are typically obtained by inertial measurement units (IMUs) and can reduce the degree of freedom (DOF) of rotation from 3 to 1. We propose a novel transformation decoupling strategy by leveraging screw theory. This strategy decomposes the original 4-DOF problem into three sub-problems with 1-DOF, 2-DOF, and 1-DOF, respectively, thereby enhancing the computation efficiency. Specifically, the first 1-DOF represents the translation along the rotation axis and we propose an interval stabbing-based method to solve it. The second 2-DOF represents the pole which is an auxiliary variable in screw theory and we utilize a branch-and-bound method to solve it. The last 1-DOF represents the rotation angle and we propose a global voting method for its estimation. The proposed method sequentially solves three consensus maximization sub-problems, leading to efficient and deterministic registration. In particular, it can even handle the correspondence-free registration problem due to its significant robustness. Extensive experiments on both synthetic and real-world datasets demonstrate that our method is more efficient and robust than state-of-the-art methods, even when dealing with outlier rates exceeding 99%.
Authors: Andy Zhou, Jindong Wang, Yu-Xiong Wang, Haohan Wang
We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for better teachers by showing strong gains in out-of-distribution robustness when distilling from pretrained foundation models. Following this finding, we propose Discrete Adversarial Distillation (DAD), which leverages a robust teacher to generate adversarial examples and a VQGAN to discretize them, creating more informative samples than standard data augmentation techniques. We provide a theoretical framework for the use of a robust teacher in the knowledge distillation with data augmentation setting and demonstrate strong gains in out-of-distribution robustness and clean accuracy across different student architectures. Notably, our method adds minor computational overhead compared to similar techniques and can be easily combined with other data augmentations for further improvements.
Authors: Anqi Joyce Yang, Sergio Casas, Nikita Dvornik, Sean Segal, Yuwen Xiong, Jordan Sir Kwang Hu, Carter Fang, Raquel Urtasun
A major bottleneck to scaling-up training of self-driving perception systems are the human annotations required for supervision. A promising alternative is to leverage "auto-labelling" offboard perception models that are trained to automatically generate annotations from raw LiDAR point clouds at a fraction of the cost. Auto-labels are most commonly generated via a two-stage approach -- first objects are detected and tracked over time, and then each object trajectory is passed to a learned refinement model to improve accuracy. Since existing refinement models are overly complex and lack advanced temporal reasoning capabilities, in this work we propose LabelFormer, a simple, efficient, and effective trajectory-level refinement approach. Our approach first encodes each frame's observations separately, then exploits self-attention to reason about the trajectory with full temporal context, and finally decodes the refined object size and per-frame poses. Evaluation on both urban and highway datasets demonstrates that LabelFormer outperforms existing works by a large margin. Finally, we show that training on a dataset augmented with auto-labels generated by our method leads to improved downstream detection performance compared to existing methods. Please visit the project website for details https://waabi.ai/labelformer
Authors: Jay Sarva, Jingkang Wang, James Tu, Yuwen Xiong, Sivabalan Manivasagam, Raquel Urtasun
Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate how the SDV interacts on a corpus of synthetic and real scenarios and verify it performs properly. However, they primarily only test the system's motion planning module, and only consider behavior variations. It is key to evaluate the full autonomy system in closed-loop, and to understand how variations in sensor data based on scene appearance, such as the shape of actors, affect system performance. In this paper, we propose a framework, Adv3D, that takes real world scenarios and performs closed-loop sensor simulation to evaluate autonomy performance, and finds vehicle shapes that make the scenario more challenging, resulting in autonomy failures and uncomfortable SDV maneuvers. Unlike prior works that add contrived adversarial shapes to vehicle roof-tops or roadside to harm perception only, we optimize a low-dimensional shape representation to modify the vehicle shape itself in a realistic manner to degrade autonomy performance (e.g., perception, prediction, and motion planning). Moreover, we find that the shape variations found with Adv3D optimized in closed-loop are much more effective than those in open-loop, demonstrating the importance of finding scene appearance variations that affect autonomy in the interactive setting.
Authors: Jingkang Wang, Sivabalan Manivasagam, Yun Chen, Ze Yang, Ioan Andrei Bârsan, Anqi Joyce Yang, Wei-Chiu Ma, Raquel Urtasun
Realistic simulation is key to enabling safe and scalable development of % self-driving vehicles. A core component is simulating the sensors so that the entire autonomy system can be tested in simulation. Sensor simulation involves modeling traffic participants, such as vehicles, with high quality appearance and articulated geometry, and rendering them in real time. The self-driving industry has typically employed artists to build these assets. However, this is expensive, slow, and may not reflect reality. Instead, reconstructing assets automatically from sensor data collected in the wild would provide a better path to generating a diverse and large set with good real-world coverage. Nevertheless, current reconstruction approaches struggle on in-the-wild sensor data, due to its sparsity and noise. To tackle these issues, we present CADSim, which combines part-aware object-class priors via a small set of CAD models with differentiable rendering to automatically reconstruct vehicle geometry, including articulated wheels, with high-quality appearance. Our experiments show our method recovers more accurate shapes from sparse data compared to existing approaches. Importantly, it also trains and renders efficiently. We demonstrate our reconstructed vehicles in several applications, including accurate testing of autonomy perception systems.
Authors: Łukasz Struski, Szymon Knop, Jacek Tabor, Wiktor Daniec, Przemysław Spurek
In the paper we construct a fully convolutional GAN model: LocoGAN, which latent space is given by noise-like images of possibly different resolutions. The learning is local, i.e. we process not the whole noise-like image, but the sub-images of a fixed size. As a consequence LocoGAN can produce images of arbitrary dimensions e.g. LSUN bedroom data set. Another advantage of our approach comes from the fact that we use the position channels, which allows the generation of fully periodic (e.g. cylindrical panoramic images) or almost periodic ,,infinitely long" images (e.g. wall-papers).
Authors: Jiangpeng Yan, Shuo Chen, Yongbing Zhang, Xiu Li
Recent works have demonstrated that deep learning (DL) based compressed sensing (CS) implementation can accelerate Magnetic Resonance (MR) Imaging by reconstructing MR images from sub-sampled k-space data. However, network architectures adopted in previous methods are all designed by handcraft. Neural Architecture Search (NAS) algorithms can automatically build neural network architectures which have outperformed human designed ones in several vision tasks. Inspired by this, here we proposed a novel and efficient network for the MR image reconstruction problem via NAS instead of manual attempts. Particularly, a specific cell structure, which was integrated into the model-driven MR reconstruction pipeline, was automatically searched from a flexible pre-defined operation search space in a differentiable manner. Experimental results show that our searched network can produce better reconstruction results compared to previous state-of-the-art methods in terms of PSNR and SSIM with 4-6 times fewer computation resources. Extensive experiments were conducted to analyze how hyper-parameters affect reconstruction performance and the searched structures. The generalizability of the searched architecture was also evaluated on different organ MR datasets. Our proposed method can reach a better trade-off between computation cost and reconstruction performance for MR reconstruction problem with good generalizability and offer insights to design neural networks for other medical image applications. The evaluation code will be available at https://github.com/yjump/NAS-for-CSMRI.
Authors: Dipti Mishra, Satish Kumar Singh, Rajat Kumar Singh
We propose a learning-based compression scheme that envelopes a standard codec between pre and post-processing deep CNNs. Specifically, we demonstrate improvements over prior approaches utilizing a compression-decompression network by introducing: (a) an edge-aware loss function to prevent blurring that is commonly occurred in prior works & (b) a super-resolution convolutional neural network (CNN) for post-processing along with a corresponding pre-processing network for improved rate-distortion performance in the low rate regime. The algorithm is assessed on a variety of datasets varying from low to high resolution namely Set 5, Set 7, Classic 5, Set 14, Live 1, Kodak, General 100, CLIC 2019. When compared to JPEG, JPEG2000, BPG, and recent CNN approach, the proposed algorithm contributes significant improvement in PSNR with an approximate gain of 20.75%, 8.47%, 3.22%, 3.23% and 24.59%, 14.46%, 10.14%, 8.57% at low and high bit-rates respectively. Similarly, this improvement in MS-SSIM is approximately 71.43%, 50%, 36.36%, 23.08%, 64.70% and 64.47%, 61.29%, 47.06%, 51.52%, 16.28% at low and high bit-rates respectively. With CLIC 2019 dataset, PSNR is found to be superior with approximately 16.67%, 10.53%, 6.78%, and 24.62%, 17.39%, 14.08% at low and high bit-rates respectively, over JPEG2000, BPG, and recent CNN approach. Similarly, the MS-SSIM is found to be superior with approximately 72%, 45.45%, 39.13%, 18.52%, and 71.43%, 50%, 41.18%, 17.07% at low and high bit-rates respectively, compared to the same approaches. A similar type of improvement is achieved with other datasets also.
Authors: Joonhyun Jeong, Beomyoung Kim, Joonsang Yu, Youngjoon Yoo
This paper analyzes the design choices of face detection architecture that improve efficiency of computation cost and accuracy. Specifically, we re-examine the effectiveness of the standard convolutional block as a lightweight backbone architecture for face detection. Unlike the current tendency of lightweight architecture design, which heavily utilizes depthwise separable convolution layers, we show that heavily channel-pruned standard convolution layers can achieve better accuracy and inference speed when using a similar parameter size. This observation is supported by the analyses concerning the characteristics of the target data domain, faces. Based on our observation, we propose to employ ResNet with a highly reduced channel, which surprisingly allows high efficiency compared to other mobile-friendly networks (e.g., MobileNetV1, V2, V3). From the extensive experiments, we show that the proposed backbone can replace that of the state-of-the-art face detector with a faster inference speed. Also, we further propose a new feature aggregation method to maximize the detection performance. Our proposed detector EResFD obtained 80.4% mAP on WIDER FACE Hard subset which only takes 37.7 ms for VGA image inference on CPU. Code is available at https://github.com/clovaai/EResFD.
Authors: Ruihan Yang, Stephan Mandt
This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional "content" latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image. The remaining "texture" variables characterizing the diffusion process are synthesized at decoding time. We show that the model's performance can be tuned toward perceptual metrics of interest. Our extensive experiments involving multiple datasets and image quality assessment metrics show that our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics. Furthermore, training the diffusion with X-parameterization enables high-quality reconstructions in only a handful of decoding steps, greatly affecting the model's practicality.
Authors: Patrick Perrine, Trevor Kirkby
Digitally synthesizing human motion is an inherently complex process, which can create obstacles in application areas such as virtual reality. We offer a new approach for predicting human motion, KP-RNN, a neural network which can integrate easily with existing image processing and generation pipelines. We utilize a new human motion dataset of performance art, Take The Lead, as well as the motion generation pipeline, the Everybody Dance Now system, to demonstrate the effectiveness of KP-RNN's motion predictions. We have found that our neural network can predict human dance movements effectively, which serves as a baseline result for future works using the Take The Lead dataset. Since KP-RNN can work alongside a system such as Everybody Dance Now, we argue that our approach could inspire new methods for rendering human avatar animation. This work also serves to benefit the visualization of performance art in digital platforms by utilizing accessible neural networks.
Authors: Sergio Romero-Tapiador, Ruben Tolosana, Aythami Morales, Julian Fierrez, Ruben Vera-Rodriguez, Isabel Espinosa-Salinas, Gala Freixer, Enrique Carrillo de Santa Pau, Ana Ramírez de Molina, Javier Ortega-Garcia
Maintaining a healthy lifestyle has become increasingly challenging in today's sedentary society marked by poor eating habits. To address this issue, both national and international organisations have made numerous efforts to promote healthier diets and increased physical activity. However, implementing these recommendations in daily life can be difficult, as they are often generic and not tailored to individuals. This study presents the AI4Food-NutritionDB database, the first nutrition database that incorporates food images and a nutrition taxonomy based on recommendations by national and international health authorities. The database offers a multi-level categorisation, comprising 6 nutritional levels, 19 main categories (e.g., "Meat"), 73 subcategories (e.g., "White Meat"), and 893 specific food products (e.g., "Chicken"). The AI4Food-NutritionDB opens the doors to new food computing approaches in terms of food intake frequency, quality, and categorisation. Also, we present a standardised experimental protocol and benchmark including three tasks based on the nutrition taxonomy (i.e., category, subcategory, and final product recognition). These resources are available to the research community, including our deep learning models trained on AI4Food-NutritionDB, which can serve as pre-trained models, achieving accurate recognition results for challenging food image databases.
Authors: Chiara Di Vece, Maela Le Lous, Brian Dromey, Francisco Vasconcelos, Anna L David, Donald Peebles, Danail Stoyanov
In obstetric ultrasound (US) scanning, the learner's ability to mentally build a three-dimensional (3D) map of the fetus from a two-dimensional (2D) US image represents a significant challenge in skill acquisition. We aim to build a US plane localization system for 3D visualization, training, and guidance without integrating additional sensors. This work builds on top of our previous work, which predicts the six-dimensional (6D) pose of arbitrarily oriented US planes slicing the fetal brain with respect to a normalized reference frame using a convolutional neural network (CNN) regression network. Here, we analyze in detail the assumptions of the normalized fetal brain reference frame and quantify its accuracy with respect to the acquisition of transventricular (TV) standard plane (SP) for fetal biometry. We investigate the impact of registration quality in the training and testing data and its subsequent effect on trained models. Finally, we introduce data augmentations and larger training sets that improve the results of our previous work, achieving median errors of 2.97 mm and 6.63 degrees for translation and rotation, respectively.
Authors: Tomáš Dlask, Bogdan Savchynskyy
We study the set of optimal solutions of the dual linear programming formulation of the linear assignment problem (LAP) to propose a method for computing a solution from the relative interior of this set. Assuming that an arbitrary dual-optimal solution and an optimal assignment are available (for which many efficient algorithms already exist), our method computes a relative-interior solution in linear time. Since LAP occurs as a subproblem in the linear programming relaxation of quadratic assignment problem (QAP), we employ our method as a new component in the family of dual-ascent algorithms that provide bounds on the optimal value of QAP. To make our results applicable to incomplete QAP, which is of interest in practical use-cases, we also provide a linear-time reduction from incomplete LAP to complete LAP along with a mapping that preserves optimality and membership in the relative interior. Our experiments on publicly available benchmarks indicate that our approach with relative-interior solution is frequently capable of providing superior bounds and otherwise is at least comparable.
Authors: Can Qin, Ning Yu, Chen Xing, Shu Zhang, Zeyuan Chen, Stefano Ermon, Yun Fu, Caiming Xiong, Ran Xu
Text-to-image (T2I) models based on diffusion processes have achieved remarkable success in controllable image generation using user-provided captions. However, the tight coupling between the current text encoder and image decoder in T2I models makes it challenging to replace or upgrade. Such changes often require massive fine-tuning or even training from scratch with the prohibitive expense. To address this problem, we propose GlueGen, which applies a newly proposed GlueNet model to align features from single-modal or multi-modal encoders with the latent space of an existing T2I model. The approach introduces a new training objective that leverages parallel corpora to align the representation spaces of different encoders. Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation. By the alignment of various feature representations, the GlueNet allows for flexible and efficient integration of new functionality into existing T2I models and sheds light on X-to-image (X2I) generation.
Authors: Md Yousuf Harun, Jhair Gallardo, Tyler L. Hayes, Ronald Kemker, Christopher Kanan
In supervised continual learning, a deep neural network (DNN) is updated with an ever-growing data stream. Unlike the offline setting where data is shuffled, we cannot make any distributional assumptions about the data stream. Ideally, only one pass through the dataset is needed for computational efficiency. However, existing methods are inadequate and make many assumptions that cannot be made for real-world applications, while simultaneously failing to improve computational efficiency. In this paper, we propose a novel continual learning method, SIESTA based on wake/sleep framework for training, which is well aligned to the needs of on-device learning. The major goal of SIESTA is to advance compute efficient continual learning so that DNNs can be updated efficiently using far less time and energy. The principal innovations of SIESTA are: 1) rapid online updates using a rehearsal-free, backpropagation-free, and data-driven network update rule during its wake phase, and 2) expedited memory consolidation using a compute-restricted rehearsal policy during its sleep phase. For memory efficiency, SIESTA adapts latent rehearsal using memory indexing from REMIND. Compared to REMIND and prior arts, SIESTA is far more computationally efficient, enabling continual learning on ImageNet-1K in under 2 hours on a single GPU; moreover, in the augmentation-free setting it matches the performance of the offline learner, a milestone critical to driving adoption of continual learning in real-world applications.
Authors: Zhuoming Liu, Xuefeng Hu, Ram Nevatia
We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD). It expands the zero-shot object detection setting by allowing the novel objects to exist in the training images and restricts the additional information the detector uses to novel category names. Recently, to detect unseen objects, large-scale vision-language models (e.g., CLIP) are leveraged by different methods. The distillation-based methods have good overall performance but suffer from a long training schedule caused by two factors. First, existing work creates distillation regions biased to the base categories, which limits the distillation of novel category information. Second, directly using the raw feature from CLIP for distillation neglects the domain gap between the training data of CLIP and the detection datasets, which makes it difficult to learn the mapping from the image region to the vision-language feature space. To solve these problems, we propose Efficient feature distillation for Zero-shot Annotation object Detection (EZAD). Firstly, EZAD adapts the CLIP's feature space to the target detection domain by re-normalizing CLIP; Secondly, EZAD uses CLIP to generate distillation proposals with potential novel category names to avoid the distillation being overly biased toward the base categories. Finally, EZAD takes advantage of semantic meaning for regression to further improve the model performance. As a result, EZAD outperforms the previous distillation-based methods in COCO by 4% with a much shorter training schedule and achieves a 3% improvement on the LVIS dataset. Our code is available at https://github.com/dragonlzm/EZAD
Authors: Janne Alatalo, Tuomo Sipola, Mika Rantonen
Satellite-based Synthetic Aperture Radar (SAR) images can be used as a source of remote sensed imagery regardless of cloud cover and day-night cycle. However, the speckle noise and varying image acquisition conditions pose a challenge for change detection classifiers. This paper proposes a new method of improving SAR image processing to produce higher quality difference images for the classification algorithms. The method is built on a neural network-based mapping transformation function that produces artificial SAR images from a location in the requested acquisition conditions. The inputs for the model are: previous SAR images from the location, imaging angle information from the SAR images, digital elevation model, and weather conditions. The method was tested with data from a location in North-East Finland by using Sentinel-1 SAR images from European Space Agency, weather data from Finnish Meteorological Institute, and a digital elevation model from National Land Survey of Finland. In order to verify the method, changes to the SAR images were simulated, and the performance of the proposed method was measured using experimentation where it gave substantial improvements to performance when compared to a more conventional method of creating difference images.
Authors: Yue Gao, Yuan Zhou, Jinglu Wang, Xiao Li, Xiang Ming, Yan Lu
Talking head generation is to generate video based on a given source identity and target motion. However, current methods face several challenges that limit the quality and controllability of the generated videos. First, the generated face often has unexpected deformation and severe distortions. Second, the driving image does not explicitly disentangle movement-relevant information, such as poses and expressions, which restricts the manipulation of different attributes during generation. Third, the generated videos tend to have flickering artifacts due to the inconsistency of the extracted landmarks between adjacent frames. In this paper, we propose a novel model that produces high-fidelity talking head videos with free control over head pose and expression. Our method leverages both self-supervised learned landmarks and 3D face model-based landmarks to model the motion. We also introduce a novel motion-aware multi-scale feature alignment module to effectively transfer the motion without face distortion. Furthermore, we enhance the smoothness of the synthesized talking head videos with a feature context adaptation and propagation module. We evaluate our model on challenging datasets and demonstrate its state-of-the-art performance.
Authors: Qizhang Li, Yiwen Guo, Wangmeng Zuo, Hao Chen
Intermediate-level attacks that attempt to perturb feature representations following an adversarial direction drastically have shown favorable performance in crafting transferable adversarial examples. Existing methods in this category are normally formulated with two separate stages, where a directional guide is required to be determined at first and the scalar projection of the intermediate-level perturbation onto the directional guide is enlarged thereafter. The obtained perturbation deviates from the guide inevitably in the feature space, and it is revealed in this paper that such a deviation may lead to sub-optimal attack. To address this issue, we develop a novel intermediate-level method that crafts adversarial examples within a single stage of optimization. In particular, the proposed method, named intermediate-level perturbation decay (ILPD), encourages the intermediate-level perturbation to be in an effective adversarial direction and to possess a great magnitude simultaneously. In-depth discussion verifies the effectiveness of our method. Experimental results show that it outperforms state-of-the-arts by large margins in attacking various victim models on ImageNet (+10.07% on average) and CIFAR-10 (+3.88% on average). Our code is at https://github.com/qizhangli/ILPD-attack.
Authors: Yan Wang, Jian Cheng, Yixin Chen, Shuai Shao, Lanyun Zhu, Zhenzhou Wu, Tao Liu, Haogang Zhu
Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data from the source domain and unlabeled data from the target domain. Source-Free UDA (SFUDA) was recently proposed for UDA without requiring the source data during the adaptation, due to data privacy or data transmission issues, which normally adapts the pre-trained deep model in the testing stage. However, in real clinical scenarios of medical image segmentation, the trained model is normally frozen in the testing stage. In this paper, we propose Fourier Visual Prompting (FVP) for SFUDA of medical image segmentation. Inspired by prompting learning in natural language processing, FVP steers the frozen pre-trained model to perform well in the target domain by adding a visual prompt to the input target data. In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model. To our knowledge, FVP is the first work to apply visual prompts to SFUDA for medical image segmentation. The proposed FVP is validated using three public datasets, and experiments demonstrate that FVP yields better segmentation results, compared with various existing methods.
Authors: Han Liu, Zhoubing Xu, Riqiang Gao, Hao Li, Jianing Wang, Guillaume Chabin, Ipek Oguz, Sasa Grbic
Deep learning models have demonstrated remarkable success in multi-organ segmentation but typically require large-scale datasets with all organs of interest annotated. However, medical image datasets are often low in sample size and only partially labeled, i.e., only a subset of organs are annotated. Therefore, it is crucial to investigate how to learn a unified model on the available partially labeled datasets to leverage their synergistic potential. In this paper, we systematically investigate the partial-label segmentation problem with theoretical and empirical analyses on the prior techniques. We revisit the problem from a perspective of partial label supervision signals and identify two signals derived from ground truth and one from pseudo labels. We propose a novel two-stage framework termed COSST, which effectively and efficiently integrates comprehensive supervision signals with self-training. Concretely, we first train an initial unified model using two ground truth-based signals and then iteratively incorporate the pseudo label signal to the initial model using self-training. To mitigate performance degradation caused by unreliable pseudo labels, we assess the reliability of pseudo labels via outlier detection in latent space and exclude the most unreliable pseudo labels from each self-training iteration. Extensive experiments are conducted on one public and three private partial-label segmentation tasks over 12 CT datasets. Experimental results show that our proposed COSST achieves significant improvement over the baseline method, i.e., individual networks trained on each partially labeled dataset. Compared to the state-of-the-art partial-label segmentation methods, COSST demonstrates consistent superior performance on various segmentation tasks and with different training data sizes.
Authors: Jiaxin Shi, Ke Alexander Wang, Emily B. Fox
Efficiently capturing the long-range patterns in sequential data sources salient to a given task -- such as classification and generative modeling -- poses a fundamental challenge. Popular approaches in the space tradeoff between the memory burden of brute-force enumeration and comparison, as in transformers, the computational burden of complicated sequential dependencies, as in recurrent neural networks, or the parameter burden of convolutional networks with many or large filters. We instead take inspiration from wavelet-based multiresolution analysis to define a new building block for sequence modeling, which we call a MultiresLayer. The key component of our model is the multiresolution convolution, capturing multiscale trends in the input sequence. Our MultiresConv can be implemented with shared filters across a dilated causal convolution tree. Thus it garners the computational advantages of convolutional networks and the principled theoretical motivation of wavelet decompositions. Our MultiresLayer is straightforward to implement, requires significantly fewer parameters, and maintains at most a $\mathcal{O}(N\log N)$ memory footprint for a length $N$ sequence. Yet, by stacking such layers, our model yields state-of-the-art performance on a number of sequence classification and autoregressive density estimation tasks using CIFAR-10, ListOps, and PTB-XL datasets.
Authors: Fangwen Wu, Jingxuan He, Yufei Yin, Yanbin Hao, Gang Huang, Lechao Cheng
This study introduces an efficacious approach, Masked Collaborative Contrast (MCC), to highlight semantic regions in weakly supervised semantic segmentation. MCC adroitly draws inspiration from masked image modeling and contrastive learning to devise a novel framework that induces keys to contract toward semantic regions. Unlike prevalent techniques that directly eradicate patch regions in the input image when generating masks, we scrutinize the neighborhood relations of patch tokens by exploring masks considering keys on the affinity matrix. Moreover, we generate positive and negative samples in contrastive learning by utilizing the masked local output and contrasting it with the global output. Elaborate experiments on commonly employed datasets evidences that the proposed MCC mechanism effectively aligns global and local perspectives within the image, attaining impressive performance. The source code is available at \url{https://github.com/fwu11/MCC}.
Authors: Zhimin Chen, Longlong Jing, Yingwei Li, Bing Li
Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely untapped due to the existence of the domain gap. In this work, we propose an innovative methodology called Bridge3D to address this gap by pre-training 3D models using features, semantic masks, and captions sourced from foundation models. Specifically, our method employs semantic masks from foundation models to guide the masking and reconstruction process for the masked autoencoder, enabling more focused attention on foreground representations. Moreover, we bridge the 3D-text gap at the scene level using image captioning foundation models, thereby facilitating scene-level knowledge distillation. We further extend this bridging effort by introducing an innovative object-level knowledge distillation method that harnesses highly accurate object-level masks and semantic text data from foundation models. Our methodology significantly surpasses the performance of existing state-of-the-art methods in 3D object detection and semantic segmentation tasks. For instance, on the ScanNet dataset, Bridge3D improves the baseline by a notable margin of 6.3%. Code will be available at: https://github.com/Zhimin-C/Bridge3D
Authors: Ameya Prabhu, Zhipeng Cai, Puneet Dokania, Philip Torr, Vladlen Koltun, Ozan Sener
Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lifetime. However, a broad range of real-world applications are primarily constrained by computational costs rather than storage limitations. In this paper, we target such applications, investigating the online continual learning problem under relaxed storage constraints and limited computational budgets. We contribute a simple algorithm, which updates a kNN classifier continually along with a fixed, pretrained feature extractor. We selected this algorithm due to its exceptional suitability for online continual learning. It can adapt to rapidly changing streams, has zero stability gap, operates within tiny computational budgets, has low storage requirements by only storing features, and has a consistency property: It never forgets previously seen data. These attributes yield significant improvements, allowing our proposed algorithm to outperform existing methods by over 20% in accuracy on two large-scale OCL datasets: Continual LOCalization (CLOC) with 39M images and 712 classes and Continual Google Landmarks V2 (CGLM) with 580K images and 10,788 classes, even when existing methods retain all previously seen images. Furthermore, we achieve this superior performance with considerably reduced computational and storage expenses. We provide code to reproduce our results at github.com/drimpossible/ACM.
Authors: Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, Stefano Ermon, Yun Fu, Ran Xu
Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages. However, they often fall short in generating images with spatial, structural, or geometric controls. The integration of such controls, which can accommodate various visual conditions in a single unified model, remains an unaddressed challenge. In response, we introduce UniControl, a new generative foundation model that consolidates a wide array of controllable condition-to-image (C2I) tasks within a singular framework, while still allowing for arbitrary language prompts. UniControl enables pixel-level-precise image generation, where visual conditions primarily influence the generated structures and language prompts guide the style and context. To equip UniControl with the capacity to handle diverse visual conditions, we augment pretrained text-to-image diffusion models and introduce a task-aware HyperNet to modulate the diffusion models, enabling the adaptation to different C2I tasks simultaneously. Trained on nine unique C2I tasks, UniControl demonstrates impressive zero-shot generation abilities with unseen visual conditions. Experimental results show that UniControl often surpasses the performance of single-task-controlled methods of comparable model sizes. This control versatility positions UniControl as a significant advancement in the realm of controllable visual generation.
Authors: Naoya Mamada, Masaichiro Mizumaki, Ichiro Akai, Toru Aonishi
We estimate the spatial distribution of heterogeneous physical parameters involved in the formation of magnetic domain patterns of polycrystalline thin films by using convolutional neural networks. We propose a method to obtain a spatial map of physical parameters by estimating the parameters from patterns within a small subregion window of the full magnetic domain and subsequently shifting this window. To enhance the accuracy of parameter estimation in such subregions, we employ large-scale models utilized for natural image classification and exploit the benefits of pretraining. Using a model with high estimation accuracy on these subregions, we conduct inference on simulation data featuring spatially varying parameters and demonstrate the capability to detect such parameter variations.
Authors: Yixun Liang, Hao He, Ying-cong Chen
Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified volume rendering process employed. In this paper, we present Reconstruction TRansformer (ReTR), a novel framework that leverages the transformer architecture to redesign the rendering process, enabling complex render interaction modeling. It introduces a learnable $\textit{meta-ray token}$ and utilizes the cross-attention mechanism to simulate the interaction of rendering process with sampled points and render the observed color. Meanwhile, by operating within a high-dimensional feature space rather than the color space, ReTR mitigates sensitivity to projected colors in source views. Such improvements result in accurate surface assessment with high confidence. We demonstrate the effectiveness of our approach on various datasets, showcasing how our method outperforms the current state-of-the-art approaches in terms of reconstruction quality and generalization ability. $\textit{Our code is available at }$ https://github.com/YixunLiang/ReTR.
Authors: Aditya Vora, Akshay Gadi Patil, Hao Zhang
We present a volume rendering-based neural surface reconstruction method that takes as few as three disparate RGB images as input. Our key idea is to regularize the reconstruction, which is severely ill-posed and leaving significant gaps between the sparse views, by learning a set of neural templates to act as surface priors. Our method, coined DiViNet, operates in two stages. It first learns the templates, in the form of 3D Gaussian functions, across different scenes, without 3D supervision. In the reconstruction stage, our predicted templates serve as anchors to help "stitch'' the surfaces over sparse regions. We demonstrate that our approach is not only able to complete the surface geometry but also reconstructs surface details to a reasonable extent from a few disparate input views. On the DTU and BlendedMVS datasets, our approach achieves the best reconstruction quality among existing methods in the presence of such sparse views and performs on par, if not better, with competing methods when dense views are employed as inputs.
Authors: Zhijin Ge, Hongying Liu, Xiaosen Wang, Fanhua Shang, Yuanyuan Liu
Transfer-based attack adopts the adversarial examples generated on the surrogate model to attack various models, making it applicable in the physical world and attracting increasing interest. Recently, various adversarial attacks have emerged to boost adversarial transferability from different perspectives. In this work, inspired by the observation that flat local minima are correlated with good generalization, we assume and empirically validate that adversarial examples at a flat local region tend to have good transferability by introducing a penalized gradient norm to the original loss function. Since directly optimizing the gradient regularization norm is computationally expensive and intractable for generating adversarial examples, we propose an approximation optimization method to simplify the gradient update of the objective function. Specifically, we randomly sample an example and adopt a first-order procedure to approximate the curvature of Hessian/vector product, which makes computing more efficient by interpolating two neighboring gradients. Meanwhile, in order to obtain a more stable gradient direction, we randomly sample multiple examples and average the gradients of these examples to reduce the variance due to random sampling during the iterative process. Extensive experimental results on the ImageNet-compatible dataset show that the proposed method can generate adversarial examples at flat local regions, and significantly improve the adversarial transferability on either normally trained models or adversarially trained models than the state-of-the-art attacks. Our codes are available at: https://github.com/Trustworthy-AI-Group/PGN.
Authors: Jiangtao Zhang, Shunyu Liu, Jie Song, Tongtian Zhu, Zhengqi Xu, Mingli Song
Weight Average (WA) is an active research topic due to its simplicity in ensembling deep networks and the effectiveness in promoting generalization. Existing weight average approaches, however, are often carried out along only one training trajectory in a post-hoc manner (i.e., the weights are averaged after the entire training process is finished), which significantly degrades the diversity between networks and thus impairs the effectiveness. In this paper, inspired by weight average, we propose Lookaround, a straightforward yet effective SGD-based optimizer leading to flatter minima with better generalization. Specifically, Lookaround iterates two steps during the whole training period: the around step and the average step. In each iteration, 1) the around step starts from a common point and trains multiple networks simultaneously, each on transformed data by a different data augmentation, and 2) the average step averages these trained networks to get the averaged network, which serves as the starting point for the next iteration. The around step improves the functionality diversity while the average step guarantees the weight locality of these networks during the whole training, which is essential for WA to work. We theoretically explain the superiority of Lookaround by convergence analysis, and make extensive experiments to evaluate Lookaround on popular benchmarks including CIFAR and ImageNet with both CNNs and ViTs, demonstrating clear superiority over state-of-the-arts. Our code is available at https://github.com/Ardcy/Lookaround.
Authors: Daniel Dauner, Marcel Hallgarten, Andreas Geiger, Kashyap Chitta
The release of nuPlan marks a new era in vehicle motion planning research, offering the first large-scale real-world dataset and evaluation schemes requiring both precise short-term planning and long-horizon ego-forecasting. Existing systems struggle to simultaneously meet both requirements. Indeed, we find that these tasks are fundamentally misaligned and should be addressed independently. We further assess the current state of closed-loop planning in the field, revealing the limitations of learning-based methods in complex real-world scenarios and the value of simple rule-based priors such as centerline selection through lane graph search algorithms. More surprisingly, for the open-loop sub-task, we observe that the best results are achieved when using only this centerline as scene context (i.e., ignoring all information regarding the map and other agents). Combining these insights, we propose an extremely simple and efficient planner which outperforms an extensive set of competitors, winning the nuPlan planning challenge 2023.
Authors: Ziniu Hu, Ahmet Iscen, Chen Sun, Kai-Wei Chang, Yizhou Sun, David A Ross, Cordelia Schmid, Alireza Fathi
In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their outputs, thereby acquiring the indispensable knowledge needed to provide answers to the posed questions. Responding to visual questions that necessitate external knowledge, such as "What event is commemorated by the building depicted in this image?", is a complex task. This task presents a combinatorial search space that demands a sequence of actions, including invoking APIs, analyzing their responses, and making informed decisions. We conduct a user study to collect a variety of instances of human decision-making when faced with this task. This data is then used to design a system comprised of three components: an LLM-powered planner that dynamically determines which tool to use next, an LLM-powered reasoner that analyzes and extracts key information from the tool outputs, and a working memory component that retains the acquired information throughout the process. The collected user behavior serves as a guide for our system in two key ways. First, we create a transition graph by analyzing the sequence of decisions made by users. This graph delineates distinct states and confines the set of actions available at each state. Second, we use examples of user decision-making to provide our LLM-powered planner and reasoner with relevant contextual instances, enhancing their capacity to make informed decisions. We show that AVIS achieves state-of-the-art results on knowledge-intensive visual question answering benchmarks such as Infoseek and OK-VQA.
Authors: Xihua Sheng, Li Li, Dong Liu, Houqiang Li
Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by machine vision algorithms. Intuitively, it is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. Therefore, we propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis, thereby being versatile for both human and machine vision. Our VNVC framework has a feature-based compression loop. In the loop, one frame is encoded into compact representations and decoded to an intermediate feature that is obtained before performing reconstruction. The intermediate feature can be used as reference in motion compensation and motion estimation through feature-based temporal context mining and cross-domain motion encoder-decoder to compress the following frames. The intermediate feature is directly fed into video reconstruction, video enhancement, and video analysis networks to evaluate its effectiveness. The evaluation shows that our framework with the intermediate feature achieves high compression efficiency for video reconstruction and satisfactory task performances with lower complexities.
Authors: Chuanyang Jin
Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which can be hard to obtain for many domains. To address this, we introduce a self-supervised image captioning method. After learning an initial signal from a small labeled dataset, our method transitions to self-supervised learning on unlabeled data, leveraging the auxiliary task of enhancing the CLIP relevance between images and generated captions. Remarkably, despite utilizing less than 2% of the labeled COCO dataset, our method delivers a performance comparable to state-of-the-art models trained on the complete dataset. Human evaluations further reveal that our method produces captions with greater distinctiveness and informativeness, two attributes inherently challenging to achieve through supervised learning.
Authors: Hsiao-Yu Tung, Mingyu Ding, Zhenfang Chen, Daniel Bear, Chuang Gan, Joshua B. Tenenbaum, Daniel LK Yamins, Judith E Fan, Kevin A. Smith
General physical scene understanding requires more than simply localizing and recognizing objects -- it requires knowledge that objects can have different latent properties (e.g., mass or elasticity), and that those properties affect the outcome of physical events. While there has been great progress in physical and video prediction models in recent years, benchmarks to test their performance typically do not require an understanding that objects have individual physical properties, or at best test only those properties that are directly observable (e.g., size or color). This work proposes a novel dataset and benchmark, termed Physion++, that rigorously evaluates visual physical prediction in artificial systems under circumstances where those predictions rely on accurate estimates of the latent physical properties of objects in the scene. Specifically, we test scenarios where accurate prediction relies on estimates of properties such as mass, friction, elasticity, and deformability, and where the values of those properties can only be inferred by observing how objects move and interact with other objects or fluids. We evaluate the performance of a number of state-of-the-art prediction models that span a variety of levels of learning vs. built-in knowledge, and compare that performance to a set of human predictions. We find that models that have been trained using standard regimes and datasets do not spontaneously learn to make inferences about latent properties, but also that models that encode objectness and physical states tend to make better predictions. However, there is still a huge gap between all models and human performance, and all models' predictions correlate poorly with those made by humans, suggesting that no state-of-the-art model is learning to make physical predictions in a human-like way. Project page: https://dingmyu.github.io/physion_v2/
Authors: Pei Liu, Luping Ji, Xinyu Zhang, Feng Ye
Given the special situation of modeling gigapixel images, multiple instance learning (MIL) has become one of the most important frameworks for Whole Slide Image (WSI) classification. In current practice, most MIL networks often face two unavoidable problems in training: i) insufficient WSI data and ii) the sample memorization inclination inherent in neural networks. These problems may hinder MIL models from adequate and efficient training, suppressing the continuous performance promotion of classification models on WSIs. Inspired by the basic idea of Mixup, this paper proposes a new Pseudo-bag Mixup (PseMix) data augmentation scheme to improve the training of MIL models. This scheme generalizes the Mixup strategy for general images to special WSIs via pseudo-bags so as to be applied in MIL-based WSI classification. Cooperated by pseudo-bags, our PseMix fulfills the critical size alignment and semantic alignment in Mixup strategy. Moreover, it is designed as an efficient and decoupled method, neither involving time-consuming operations nor relying on MIL model predictions. Comparative experiments and ablation studies are specially designed to evaluate the effectiveness and advantages of our PseMix. Experimental results show that PseMix could often assist state-of-the-art MIL networks to refresh their classification performance on WSIs. Besides, it could also boost the generalization performance of MIL models in special test scenarios, and promote their robustness to patch occlusion and label noise. Our source code is available at https://github.com/liupei101/PseMix.
Authors: Wenlong Huang, Chen Wang, Ruohan Zhang, Yunzhu Li, Jiajun Wu, Li Fei-Fei
Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation in the form of reasoning and planning. Despite the progress, most still rely on pre-defined motion primitives to carry out the physical interactions with the environment, which remains a major bottleneck. In this work, we aim to synthesize robot trajectories, i.e., a dense sequence of 6-DoF end-effector waypoints, for a large variety of manipulation tasks given an open-set of instructions and an open-set of objects. We achieve this by first observing that LLMs excel at inferring affordances and constraints given a free-form language instruction. More importantly, by leveraging their code-writing capabilities, they can interact with a vision-language model (VLM) to compose 3D value maps to ground the knowledge into the observation space of the agent. The composed value maps are then used in a model-based planning framework to zero-shot synthesize closed-loop robot trajectories with robustness to dynamic perturbations. We further demonstrate how the proposed framework can benefit from online experiences by efficiently learning a dynamics model for scenes that involve contact-rich interactions. We present a large-scale study of the proposed method in both simulated and real-robot environments, showcasing the ability to perform a large variety of everyday manipulation tasks specified in free-form natural language. Videos and code at https://voxposer.github.io
Authors: Sophie Starck, Yadunandan Vivekanand Kini, Jessica Johanna Maria Ritter, Rickmer Braren, Daniel Rueckert, Tamara Mueller
Age prediction is an important part of medical assessments and research. It can aid in detecting diseases as well as abnormal ageing by highlighting the discrepancy between chronological and biological age. To gain a comprehensive understanding of age-related changes observed in various body parts, we investigate them on a larger scale by using whole-body 3D images. We utilise the Grad-CAM interpretability method to determine the body areas most predictive of a person's age. We expand our analysis beyond individual subjects by employing registration techniques to generate population-wide interpretability maps. Our findings reveal three primary areas of interest: the spine, the autochthonous back muscles, and the cardiac region, which exhibits the highest importance.
Authors: Guoqiang Zhang, J. P. Lewis, W. Bastiaan Kleijn
Recently, various methods have been proposed to address the inconsistency issue of DDIM inversion to enable image editing, such as EDICT [36] and Null-text inversion [22]. However, the above methods introduce considerable computational overhead. In this paper, we propose a new technique, named \emph{bi-directional integration approximation} (BDIA), to perform exact diffusion inversion with neglible computational overhead. Suppose we would like to estimate the next diffusion state $\boldsymbol{z}_{i-1}$ at timestep $t_i$ with the historical information $(i,\boldsymbol{z}_i)$ and $(i+1,\boldsymbol{z}_{i+1})$. We first obtain the estimated Gaussian noise $\hat{\boldsymbol{\epsilon}}(\boldsymbol{z}_i,i)$, and then apply the DDIM update procedure twice for approximating the ODE integration over the next time-slot $[t_i, t_{i-1}]$ in the forward manner and the previous time-slot $[t_i, t_{t+1}]$ in the backward manner. The DDIM step for the previous time-slot is used to refine the integration approximation made earlier when computing $\boldsymbol{z}_i$. A nice property of BDIA-DDIM is that the update expression for $\boldsymbol{z}_{i-1}$ is a linear combination of $(\boldsymbol{z}_{i+1}, \boldsymbol{z}_i, \hat{\boldsymbol{\epsilon}}(\boldsymbol{z}_i,i))$. This allows for exact backward computation of $\boldsymbol{z}_{i+1}$ given $(\boldsymbol{z}_i, \boldsymbol{z}_{i-1})$, thus leading to exact diffusion inversion. It is demonstrated with experiments that (round-trip) BDIA-DDIM is particularly effective for image editing. Our experiments further show that BDIA-DDIM produces markedly better image sampling qualities than DDIM for text-to-image generation.
BDIA can also be applied to improve the performance of other ODE solvers in addition to DDIM. In our work, it is found that applying BDIA to the EDM sampling procedure produces consistently better performance over four pre-trained models.
Authors: Hyungmin Kim, Sungho Suh, Daehwan Kim, Daun Jeong, Hansang Cho, Junmo Kim
Recent advances in deep learning have significantly improved the performance of various computer vision applications. However, discovering novel categories in an incremental learning scenario remains a challenging problem due to the lack of prior knowledge about the number and nature of new categories. Existing methods for novel category discovery are limited by their reliance on labeled datasets and prior knowledge about the number of novel categories and the proportion of novel samples in the batch. To address the limitations and more accurately reflect real-world scenarios, in this paper, we propose a novel unsupervised class incremental learning approach for discovering novel categories on unlabeled sets without prior knowledge. The proposed method fine-tunes the feature extractor and proxy anchors on labeled sets, then splits samples into old and novel categories and clusters on the unlabeled dataset. Furthermore, the proxy anchors-based exemplar generates representative category vectors to mitigate catastrophic forgetting. Experimental results demonstrate that our proposed approach outperforms the state-of-the-art methods on fine-grained datasets under real-world scenarios.
Authors: Pratheba Selvaraju
Developability refers to the process of creating a surface without any tearing or shearing from a two-dimensional plane. It finds practical applications in the fabrication industry. An essential characteristic of a developable 3D surface is its zero Gaussian curvature, which means that either one or both of the principal curvatures are zero. This paper introduces a method for reconstructing an approximate developable surface from a neural implicit surface. The central idea of our method involves incorporating a regularization term that operates on the second-order derivatives of the neural implicits, effectively promoting zero Gaussian curvature. Implicit surfaces offer the advantage of smoother deformation with infinite resolution, overcoming the high polygonal constraints of state-of-the-art methods using discrete representations. We draw inspiration from the properties of surface curvature and employ rank minimization techniques derived from compressed sensing. Experimental results on both developable and non-developable surfaces, including those affected by noise, validate the generalizability of our method.
Authors: Daniel Wolf, Tristan Payer, Catharina Silvia Lisson, Christoph Gerhard Lisson, Meinrad Beer, Michael Götz, Timo Ropinski
Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations for all training samples. However, in the medical imaging domain, annotated datasets for specific tasks are often small due to the high complexity of annotations, limited access, or the rarity of diseases. To address this challenge, deep learning models can be pre-trained on large image datasets without annotations using methods from the field of self-supervised learning. After pre-training, small annotated datasets are sufficient to fine-tune the models for a specific task. The most popular self-supervised pre-training approaches in medical imaging are based on contrastive learning. However, recent studies in natural image processing indicate a strong potential for masked autoencoder approaches. Our work compares state-of-the-art contrastive learning methods with the recently introduced masked autoencoder approach "SparK" for convolutional neural networks (CNNs) on medical images. Therefore we pre-train on a large unannotated CT image dataset and fine-tune on several CT classification tasks. Due to the challenge of obtaining sufficient annotated training data in medical imaging, it is of particular interest to evaluate how the self-supervised pre-training methods perform when fine-tuning on small datasets. By experimenting with gradually reducing the training dataset size for fine-tuning, we find that the reduction has different effects depending on the type of pre-training chosen. The SparK pre-training method is more robust to the training dataset size than the contrastive methods. Based on our results, we propose the SparK pre-training for medical imaging tasks with only small annotated datasets.
Authors: Katherine Deng, Arijit Ray, Reuben Tan, Saadia Gabriel, Bryan A. Plummer, Kate Saenko
Existing emotion prediction benchmarks contain coarse emotion labels which do not consider the diversity of emotions that an image and text can elicit in humans due to various reasons. Learning diverse reactions to multimodal content is important as intelligent machines take a central role in generating and delivering content to society. To address this gap, we propose Socratis, a societal reactions benchmark, where each image-caption (IC) pair is annotated with multiple emotions and the reasons for feeling them. Socratis contains 18K free-form reactions for 980 emotions on 2075 image-caption pairs from 5 widely-read news and image-caption (IC) datasets. We benchmark the capability of state-of-the-art multimodal large language models to generate the reasons for feeling an emotion given an IC pair. Based on a preliminary human study, we observe that humans prefer human-written reasons over 2 times more often than machine-generated ones. This shows our task is harder than standard generation tasks because it starkly contrasts recent findings where humans cannot tell apart machine vs human-written news articles, for instance. We further see that current captioning metrics based on large vision-language models also fail to correlate with human preferences. We hope that these findings and our benchmark will inspire further research on training emotionally aware models.
Frustrating text entry interface has been a major obstacle in participating in social activities in augmented reality (AR). Popular options, such as mid-air keyboard interface, wireless keyboards or voice input, either suffer from poor ergonomic design, limited accuracy, or are simply embarrassing to use in public. This paper proposes and validates a deep-learning based approach, that enables AR applications to accurately predict keystrokes from the user perspective RGB video stream that can be captured by any AR headset. This enables a user to perform typing activities on any flat surface and eliminates the need of a physical or virtual keyboard. A two-stage model, combing an off-the-shelf hand landmark extractor and a novel adaptive Convolutional Recurrent Neural Network (C-RNN), was trained using our newly built dataset. The final model was capable of adaptive processing user-perspective video streams at ~32 FPS. This base model achieved an overall accuracy of $91.05\%$ when typing 40 Words per Minute (wpm), which is how fast an average person types with two hands on a physical keyboard. The Normalised Levenshtein Distance also further confirmed the real-world applicability of that our approach. The promising results highlight the viability of our approach and the potential for our method to be integrated into various applications. We also discussed the limitations and future research required to bring such technique into a production system.
Authors: Saeid Asgari Taghanaki, Aliasghar Khani, Amir Khasahmadi, Aditya Sanghi, Karl D.D. Willis, Ali Mahdavi-Amiri
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of large language models (LLMs) to interpret the learned features of pre-trained image classifiers. Our method, called TExplain, tackles this task by training a neural network to establish a connection between the feature space of image classifiers and LLMs. Then, during inference, our approach generates a vast number of sentences to explain the features learned by the classifier for a given image. These sentences are then used to extract the most frequent words, providing a comprehensive understanding of the learned features and patterns within the classifier. Our method, for the first time, utilizes these frequent words corresponding to a visual representation to provide insights into the decision-making process of the independently trained classifier, enabling the detection of spurious correlations, biases, and a deeper comprehension of its behavior. To validate the effectiveness of our approach, we conduct experiments on diverse datasets, including ImageNet-9L and Waterbirds. The results demonstrate the potential of our method to enhance the interpretability and robustness of image classifiers.
Authors: Alexander Visheratin
Today, the exponential rise of large models developed by academic and industrial institutions with the help of massive computing resources raises the question of whether someone without access to such resources can make a valuable scientific contribution. To explore this, we tried to solve the challenging task of multilingual image retrieval having a limited budget of $1,000. As a result, we present NLLB-CLIP - CLIP model with a text encoder from the NLLB model. To train the model, we used an automatically created dataset of 106,246 good-quality images with captions in 201 languages derived from the LAION COCO dataset. We trained multiple models using image and text encoders of various sizes and kept different parts of the model frozen during the training. We thoroughly analyzed the trained models using existing evaluation datasets and newly created XTD200 and Flickr30k-200 datasets. We show that NLLB-CLIP is comparable in quality to state-of-the-art models and significantly outperforms them on low-resource languages.
Authors: Sudarshan Sreeram, Bernhard Kainz
Leveraging ML advancements to augment healthcare systems can improve patient outcomes. Yet, uninformed engineering decisions in early-stage research inadvertently hinder the feasibility of such solutions for high-throughput, on-device inference, particularly in settings involving legacy hardware and multi-modal gigapixel images. Through a preliminary case study concerning segmentation in cardiology, we highlight the excess operational complexity in a suboptimally configured ML model from prior work and demonstrate that it can be sculpted away using pruning to meet deployment criteria. Our results show a compression rate of 1148x with minimal loss in quality (~4%) and, at higher rates, achieve faster inference on a CPU than the GPU baseline, stressing the need to consider task complexity and architectural details when using off-the-shelf models. With this, we consider avenues for future research in streamlining workflows for clinical researchers to develop models quicker and better suited for real-world use.
Authors: Hao Wang, Omkar Salunkhe, Walter Quadrini, Björn Johansson, Dan Lämkull, Fredrik Ore, Mélanie Despeisse, Luca Fumagalli, Johan Stahre
This article presents a systematic literature review on computer vision applications that have been proposed for robotized wire harness assembly, derives challenges from existing studies, and identifies opportunities for future research to promote a more practical robotized assembly of wire harnesses.
Authors: Hao Wang, Omkar Salunkhe, Walter Quadrini, Dan Lämkull, Fredrik Ore, Björn Johansson, Johan Stahre
Wire harnesses are essential hardware for electronic systems in modern automotive vehicles. With a shift in the automotive industry towards electrification and autonomous driving, more and more automotive electronics are responsible for energy transmission and safety-critical functions such as maneuvering, driver assistance, and safety system. This paradigm shift places more demand on automotive wiring harnesses from the safety perspective and stresses the greater importance of high-quality wire harness assembly in vehicles. However, most of the current operations of wire harness assembly are still performed manually by skilled workers, and some of the manual processes are problematic from different perspectives, such as quality control and ergonomics. There is also a persistent demand in the industry to increase competitiveness and gain market share. Hence, assuring assembly quality while improving ergonomics and optimizing labor costs is desired. Robotized assembly, accomplished by robots or in human-robot collaboration, is a key enabler for fulfilling the increasingly demanding quality and safety as it enables more replicable, transparent, and comprehensible processes than completely manual operations. However, robotized assembly of wire harnesses is challenging in real environments due to the flexibility of the deformable objects, though many preliminary automation solutions have been proposed under simplified industrial configurations. Previous research efforts have proposed the use of computer vision technology to facilitate robotized automation of wire harness assembly, enabling the robots to better perceive and manipulate the flexible wire harness. This article presents an overview on computer vision technology proposed for robotized wire harness assembly and derives research gaps that require further study to facilitate a more practical robotized assembly of wire harness.
Authors: Jiayuan Wang, Q. M. Jonathan Wu, Ning Zhang
High precision, lightweight, and real-time responsiveness are three essential requirements for implementing autonomous driving. In this study, we present an adaptive, real-time, and lightweight multi-task model designed to concurrently address object detection, drivable area segmentation, and lane line segmentation tasks. Specifically, we developed an end-to-end multi-task model with a unified and streamlined segmentation structure. We introduced a learnable parameter that adaptively concatenate features in segmentation necks, using the same loss function for all segmentation tasks. This eliminates the need for customizations and enhances the model's generalization capabilities. We also introduced a segmentation head composed only of a series of convolutional layers, which reduces the inference time. We achieved competitive results on the BDD100k dataset, particularly in visualization outcomes. The performance results show a mAP50 of 81.1% for object detection, a mIoU of 91.0% for drivable area segmentation, and an IoU of 28.8% for lane line segmentation. Additionally, we introduced real-world scenarios to evaluate our model's performance in a real scene, which significantly outperforms competitors. This demonstrates that our model not only exhibits competitive performance but is also more flexible and faster than existing multi-task models. The source codes and pre-trained models are released at https://github.com/JiayuanWang-JW/YOLOv8-multi-task
Authors: Luca Scimeca, Alexander Rubinstein, Armand Mihai Nicolicioiu, Damien Teney, Yoshua Bengio
Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to shortcut learning phenomena, where a model may rely on erroneous, easy-to-learn, cues while ignoring reliable ones. In this work, we propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs). We discover that DPMs have the inherent capability to represent multiple visual cues independently, even when they are largely correlated in the training data. We leverage this characteristic to encourage model diversity and empirically show the efficacy of the approach with respect to several diversification objectives. We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
Authors: Zhenying Fang
Temporal action detection aims to recognize the action category and determine the starting and ending time of each action instance in untrimmed videos. The mixed methods have achieved remarkable performance by simply merging anchor-based and anchor-free approaches. However, there are still two crucial issues in the mixed framework: (1) Brute-force merging and handcrafted anchors design affect the performance and practical application of the mixed methods. (2) A large number of false positives in action category predictions further impact the detection performance. In this paper, we propose a novel Boundary Discretization and Reliable Classification Network (BDRC-Net) that addresses the above issues by introducing boundary discretization and reliable classification modules. Specifically, the boundary discretization module (BDM) elegantly merges anchor-based and anchor-free approaches in the form of boundary discretization, avoiding the handcrafted anchors design required by traditional mixed methods. Furthermore, the reliable classification module (RCM) predicts reliable action categories to reduce false positives in action category predictions. Extensive experiments conducted on different benchmarks demonstrate that our proposed method achieves favorable performance compared with the state-of-the-art. For example, BDRC-Net hits an average mAP of 68.6% on THUMOS'14, outperforming the previous best by 1.5%. The code will be released at https://github.com/zhenyingfang/BDRC-Net.
Authors: Erik Scheurer, Jenny Schmalfuss, Alexander Lis, Andrés Bruhn
Adversarial patches undermine the reliability of optical flow predictions when placed in arbitrary scene locations. Therefore, they pose a realistic threat to real-world motion detection and its downstream applications. Potential remedies are defense strategies that detect and remove adversarial patches, but their influence on the underlying motion prediction has not been investigated. In this paper, we thoroughly examine the currently available detect-and-remove defenses ILP and LGS for a wide selection of state-of-the-art optical flow methods, and illuminate their side effects on the quality and robustness of the final flow predictions. In particular, we implement defense-aware attacks to investigate whether current defenses are able to withstand attacks that take the defense mechanism into account. Our experiments yield two surprising results: Detect-and-remove defenses do not only lower the optical flow quality on benign scenes, in doing so, they also harm the robustness under patch attacks for all tested optical flow methods except FlowNetC. As currently employed detect-and-remove defenses fail to deliver the promised adversarial robustness for optical flow, they evoke a false sense of security. The code is available at https://github.com/cv-stuttgart/DetectionDefenses.
Authors: Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto
We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. Moreover, unlike vector-based representations, distribution-based representations can also model asymmetric relations (e.g., direction of logical entailment, hypernym/hyponym relations) by using algebraic operations between likelihood functions. These ideas are grounded in distributional perspectives on semantics and are connected to standard constructions in automata theory, but to our knowledge they have not been applied to modern language models. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle. Finally, we extend our method to represent data from different modalities (e.g., image and text) using multimodal autoregressive models.
Authors: Changsheng Lv, Shuai Zhang, Yapeng Tian, Mengshi Qi, Huadong Ma
In this paper, we propose a Disentangled Counterfactual Learning~(DCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects' physics commonsense based on both video and audio input, with the main challenge is how to imitate the reasoning ability of humans. Most of the current methods fail to take full advantage of different characteristics in multi-modal data, and lacking causal reasoning ability in models impedes the progress of implicit physical knowledge inferring. To address these issues, our proposed DCL method decouples videos into static (time-invariant) and dynamic (time-varying) factors in the latent space by the disentangled sequential encoder, which adopts a variational autoencoder (VAE) to maximize the mutual information with a contrastive loss function. Furthermore, we introduce a counterfactual learning module to augment the model's reasoning ability by modeling physical knowledge relationships among different objects under counterfactual intervention. Our proposed method is a plug-and-play module that can be incorporated into any baseline. In experiments, we show that our proposed method improves baseline methods and achieves state-of-the-art performance. Our source code is available at https://github.com/Andy20178/DCL.
Authors: Arthur Ouaknine, Teja Kattenborn, Etienne Laliberté, David Rolnick
Forests play a crucial role in Earth's system processes and provide a suite of social and economic ecosystem services, but are significantly impacted by human activities, leading to a pronounced disruption of the equilibrium within ecosystems. Advancing forest monitoring worldwide offers advantages in mitigating human impacts and enhancing our comprehension of forest composition, alongside the effects of climate change. While statistical modeling has traditionally found applications in forest biology, recent strides in machine learning and computer vision have reached important milestones using remote sensing data, such as tree species identification, tree crown segmentation and forest biomass assessments. For this, the significance of open access data remains essential in enhancing such data-driven algorithms and methodologies. Here, we provide a comprehensive and extensive overview of 86 open access forest datasets across spatial scales, encompassing inventories, ground-based, aerial-based, satellite-based recordings, and country or world maps. These datasets are grouped in OpenForest, a dynamic catalogue open to contributions that strives to reference all available open access forest datasets. Moreover, in the context of these datasets, we aim to inspire research in machine learning applied to forest biology by establishing connections between contemporary topics, perspectives and challenges inherent in both domains. We hope to encourage collaborations among scientists, fostering the sharing and exploration of diverse datasets through the application of machine learning methods for large-scale forest monitoring. OpenForest is available at https://github.com/RolnickLab/OpenForest .
Authors: Daniel Neururer, Volker Dellwo, Thilo Stadelmann
While deep neural networks have shown impressive results in automatic speaker recognition and related tasks, it is dissatisfactory how little is understood about what exactly is responsible for these results. Part of the success has been attributed in prior work to their capability to model supra-segmental temporal information (SST), i.e., learn rhythmic-prosodic characteristics of speech in addition to spectral features. In this paper, we (i) present and apply a novel test to quantify to what extent the performance of state-of-the-art neural networks for speaker recognition can be explained by modeling SST; and (ii) present several means to force respective nets to focus more on SST and evaluate their merits. We find that a variety of CNN- and RNN-based neural network architectures for speaker recognition do not model SST to any sufficient degree, even when forced. The results provide a highly relevant basis for impactful future research into better exploitation of the full speech signal and give insights into the inner workings of such networks, enhancing explainability of deep learning for speech technologies.
Authors: Amin Ranem, Camila González, Daniel Pinto dos Santos, Andreas Michael Bucher, Ahmed Ezzat Othman, Anirban Mukhopadhyay
Continual learning (CL) methods designed for natural image classification often fail to reach basic quality standards for medical image segmentation. Atlas-based segmentation, a well-established approach in medical imaging, incorporates domain knowledge on the region of interest, leading to semantically coherent predictions. This is especially promising for CL, as it allows us to leverage structural information and strike an optimal balance between model rigidity and plasticity over time. When combined with privacy-preserving prototypes, this process offers the advantages of rehearsal-based CL without compromising patient privacy. We propose Atlas Replay, an atlas-based segmentation approach that uses prototypes to generate high-quality segmentation masks through image registration that maintain consistency even as the training distribution changes. We explore how our proposed method performs compared to state-of-the-art CL methods in terms of knowledge transferability across seven publicly available prostate segmentation datasets. Prostate segmentation plays a vital role in diagnosing prostate cancer, however, it poses challenges due to substantial anatomical variations, benign structural differences in older age groups, and fluctuating acquisition parameters. Our results show that Atlas Replay is both robust and generalizes well to yet-unseen domains while being able to maintain knowledge, unlike end-to-end segmentation methods. Our code base is available under https://github.com/MECLabTUDA/Atlas-Replay.