Authors: Ngaire Underhill, Evan Maki, Bilal Gill, Andrew Weinert
Separation provision and collision avoidance to avoid other air traffic are fundamental components of the layered conflict management system to ensure safe and efficient operations. Pilots have visual-based separation responsibilities to see and be seen to maintain separation between aircraft. To safely integrate into the airspace, drones should be required to have a minimum level of performance based on the safety achieved as baselined by crewed aircraft seen and be seen interactions. Drone interactions with crewed aircraft should not be more hazardous than interactions between traditional aviation aircraft. Accordingly, there is need for a methodology to design and evaluate detect and avoid systems, to be equipped by drones to mitigate the risk of a midair collision, where the methodology explicitly addresses, both semantically and mathematically, the appropriate operating rules associated with see and be seen. In response, we simulated how onboard pilots safely operate through see and be seen interactions using an updated visual acquisition model that was originally developed by J.W. Andrews decades ago. Monte Carlo simulations were representative two aircraft flying under visual flight rules and results were analyzed with respect to drone detect and avoid performance standards.
Authors: Jože M. Rožanec, Elias Montini, Vincenzo Cutrona, Dimitrios Papamartzivanos, Timotej Klemenčič, Blaž Fortuna, Dunja Mladenić, Entso Veliou, Thanassis Giannetsos, Christos Emmanouilidis
Industrial revolutions have historically disrupted manufacturing by introducing automation into production. Increasing automation reshapes the role of the human worker. Advances in robotics and artificial intelligence open new frontiers of human-machine collaboration. In this chapter, we first describe Industry 5.0, human-machine collaboration, and state-of-the-art regarding quality inspection, emphasizing visual inspection. We then provide our perspective on how human-machine collaboration could be realized and enhanced in visual inspection. Finally, we share some of the results obtained in the EU H2020 STAR project regarding visual inspection, considering artificial intelligence, human digital twins, and cybersecurity.
Authors: Xiaoyi Ji, Richard Salmon, Nita Mulliqi, Umair Khan, Yinxi Wang, Anders Blilie, Henrik Olsson, Bodil Ginnerup Pedersen, Karina Dalsgaard Sørensen, Benedicte Parm Ulhøi, Svein R Kjosavik, Emilius AM Janssen, Mattias Rantalainen, Lars Egevad, Pekka Ruusuvuori, Martin Eklund, Kimmo Kartasalo
The potential of artificial intelligence (AI) in digital pathology is limited by technical inconsistencies in the production of whole slide images (WSIs), leading to degraded AI performance and posing a challenge for widespread clinical application as fine-tuning algorithms for each new site is impractical. Changes in the imaging workflow can also lead to compromised diagnoses and patient safety risks. We evaluated whether physical color calibration of scanners can standardize WSI appearance and enable robust AI performance. We employed a color calibration slide in four different laboratories and evaluated its impact on the performance of an AI system for prostate cancer diagnosis on 1,161 WSIs. Color standardization resulted in consistently improved AI model calibration and significant improvements in Gleason grading performance. The study demonstrates that physical color calibration provides a potential solution to the variation introduced by different scanners, making AI-based cancer diagnostics more reliable and applicable in clinical settings.
Authors: Iqbal Nouyed, Na Zhang
Unconstrained face recognition is an active research area among computer vision and biometric researchers for many years now. Still the problem of face recognition in low quality photos has not been well-studied so far. In this paper, we explore the face recognition performance on low quality photos, and we try to improve the accuracy in dealing with low quality face images. We assemble a large database with low quality photos, and examine the performance of face recognition algorithms for three different quality sets. Using state-of-the-art facial image enhancement approaches, we explore the face recognition performance for the enhanced face images. To perform this without experimental bias, we have developed a new protocol for recognition with low quality face photos and validate the performance experimentally. Our designed protocol for face recognition with low quality face images can be useful to other researchers. Moreover, experiment results show some of the challenging aspects of this problem.
Authors: Tianyu Luan, Yuanhao Zhai, Jingjing Meng, Zhong Li, Zhang Chen, Yi Xu, Junsong Yuan
Despite the impressive performance obtained by recent single-image hand modeling techniques, they lack the capability to capture sufficient details of the 3D hand mesh. This deficiency greatly limits their applications when high-fidelity hand modeling is required, e.g., personalized hand modeling. To address this problem, we design a frequency split network to generate 3D hand mesh using different frequency bands in a coarse-to-fine manner. To capture high-frequency personalized details, we transform the 3D mesh into the frequency domain, and propose a novel frequency decomposition loss to supervise each frequency component. By leveraging such a coarse-to-fine scheme, hand details that correspond to the higher frequency domain can be preserved. In addition, the proposed network is scalable, and can stop the inference at any resolution level to accommodate different hardware with varying computational powers. To quantitatively evaluate the performance of our method in terms of recovering personalized shape details, we introduce a new evaluation metric named Mean Signal-to-Noise Ratio (MSNR) to measure the signal-to-noise ratio of each mesh frequency component. Extensive experiments demonstrate that our approach generates fine-grained details for high-fidelity 3D hand reconstruction, and our evaluation metric is more effective for measuring mesh details compared with traditional metrics.
Authors: Mahmoud Abdulsalam, Nabil Aouf
As demand for robotics manipulation application increases, accurate vision-based 6D pose estimation becomes essential for autonomous operations. Convolutional Neural Networks (CNNs) based approaches for pose estimation have been previously introduced. However, the quest for better performance still persists especially for accurate robotics manipulation. This quest extends to the Agri-robotics domain. In this paper, we propose TransPose, an improved Transformer-based 6D pose estimation with a depth refinement module. The architecture takes in only an RGB image as input with no additional supplementing modalities such as depth or thermal images. The architecture encompasses an innovative lighter depth estimation network that estimates depth from an RGB image using feature pyramid with an up-sampling method. A transformer-based detection network with additional prediction heads is proposed to directly regress the object's centre and predict the 6D pose of the target. A novel depth refinement module is then used alongside the predicted centers, 6D poses and depth patches to refine the accuracy of the estimated 6D pose. We extensively compared our results with other state-of-the-art methods and analysed our results for fruit-picking applications. The results we achieved show that our proposed technique outperforms the other methods available in the literature.
Authors: Bhavin Jawade, Deen Dayal Mohan, Srirangaraj Setlur, Nalini Ratha, Venu Govindaraju
Contactless fingerprint matching using smartphone cameras can alleviate major challenges of traditional fingerprint systems including hygienic acquisition, portability and presentation attacks. However, development of practical and robust contactless fingerprint matching techniques is constrained by the limited availability of large scale real-world datasets. To motivate further advances in contactless fingerprint matching across sensors, we introduce the RidgeBase benchmark dataset. RidgeBase consists of more than 15,000 contactless and contact-based fingerprint image pairs acquired from 88 individuals under different background and lighting conditions using two smartphone cameras and one flatbed contact sensor. Unlike existing datasets, RidgeBase is designed to promote research under different matching scenarios that include Single Finger Matching and Multi-Finger Matching for both contactless- to-contactless (CL2CL) and contact-to-contactless (C2CL) verification and identification. Furthermore, due to the high intra-sample variance in contactless fingerprints belonging to the same finger, we propose a set-based matching protocol inspired by the advances in facial recognition datasets. This protocol is specifically designed for pragmatic contactless fingerprint matching that can account for variances in focus, polarity and finger-angles. We report qualitative and quantitative baseline results for different protocols using a COTS fingerprint matcher (Verifinger) and a Deep CNN based approach on the RidgeBase dataset. The dataset can be downloaded here: https://www.buffalo.edu/cubs/research/datasets/ridgebase-benchmark-dataset.html
Authors: Debanjan Goswami, Shayok Chakraborty
Deep learning algorithms have pushed the boundaries of computer vision research and have depicted commendable performance in a variety of applications. However, training a robust deep neural network necessitates a large amount of labeled training data, acquiring which involves significant time and human effort. This problem is even more serious for an application like video classification, where a human annotator has to watch an entire video end-to-end to furnish a label. Active learning algorithms automatically identify the most informative samples from large amounts of unlabeled data; this tremendously reduces the human annotation effort in inducing a machine learning model, as only the few samples that are identified by the algorithm, need to be labeled manually. In this paper, we propose a novel active learning framework for video classification, with the goal of further reducing the labeling onus on the human annotators. Our framework identifies a batch of exemplar videos, together with a set of informative frames for each video; the human annotator needs to merely review the frames and provide a label for each video. This involves much less manual work than watching the complete video to come up with a label. We formulate a criterion based on uncertainty and diversity to identify the informative videos and exploit representative sampling techniques to extract a set of exemplar frames from each video. To the best of our knowledge, this is the first research effort to develop an active learning framework for video classification, where the annotators need to inspect only a few frames to produce a label, rather than watching the end-to-end video.
Authors: Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
Textual and semantic comprehension of images is essential for generating proper captions. The comprehension requires detection of objects, modeling of relations between them, an assessment of the semantics of the scene and, finally, representing the extracted knowledge in a language space. To achieve rich language capabilities while ensuring good image-language mappings, pretrained language models (LMs) were conditioned on pretrained multi-modal (image-text) models that allow for image inputs. This requires an alignment of the image representation of the multi-modal model with the language representations of a generative LM. However, it is not clear how to best transfer semantics detected by the vision encoder of the multi-modal model to the LM. We introduce two novel ways of constructing a linear mapping that successfully transfers semantics between the embedding spaces of the two pretrained models. The first aligns the embedding space of the multi-modal language encoder with the embedding space of the pretrained LM via token correspondences. The latter leverages additional data that consists of image-text pairs to construct the mapping directly from vision to language space. Using our semantic mappings, we unlock image captioning for LMs without access to gradient information. By using different sources of data we achieve strong captioning performance on MS-COCO and Flickr30k datasets. Even in the face of limited data, our method partly exceeds the performance of other zero-shot and even finetuned competitors. Our ablation studies show that even LMs at a scale of merely 250M parameters can generate decent captions employing our semantic mappings. Our approach makes image captioning more accessible for institutions with restricted computational resources.
Authors: Artem Bituitskii
This report contributes to the field of unsupervised domain adaptation by providing an analysis of existing methods, introducing a new approach, and demonstrating the potential for improving visual recognition tasks across different domains. The results of this study open up opportunities for further study and development of advanced methods in the field of domain adaptation.
Authors: Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng, Ayan Chakrabarti, Dilip Krishnan, Deqing Sun, Da-Cheng Juan, Andrew Tomkins
Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddings. While analysis through the use of probes has become standard in NLP, there has been much less exploration in vision. Image foundation models have primarily been evaluated for semantic content. Better understanding the non-semantic information in popular embeddings (e.g., MAE, SimCLR, or CLIP) will shed new light both on the training algorithms and on the uses for these foundation models. We design a systematic transformation prediction task and measure the visual content of embeddings along many axes, including image style, quality, and a range of natural and artificial transformations. Surprisingly, six embeddings (including SimCLR) encode enough non-semantic information to identify dozens of transformations. We also consider a generalization task, where we group similar transformations and hold out several for testing. We find that image-text models (CLIP and ALIGN) are better at recognizing new examples of style transfer than masking-based models (CAN and MAE). Overall, our results suggest that the choice of pre-training algorithm impacts the types of information in the embedding, and certain models are better than others for non-semantic downstream tasks.
Authors: Nikhil Verma, Deepkamal Kaur, Lydia Chau
Removing noise from images is a challenging and fundamental problem in the field of computer vision. Images captured by modern cameras are inevitably degraded by noise which limits the accuracy of any quantitative measurements on those images. In this project, we propose a novel image reconstruction framework which can be used for tasks such as image denoising, deblurring or inpainting. The model proposed in this project is based on Vision Transformer (ViT) that takes 2D images as input and outputs embeddings which can be used for reconstructing denoised images. We incorporate four additional optimization techniques in the framework to improve the model reconstruction capability, namely Locality Sensitive Attention (LSA), Shifted Patch Tokenization (SPT), Rotary Position Embeddings (RoPE) and adversarial loss function inspired from Generative Adversarial Networks (GANs). LSA, SPT and RoPE enable the transformer to learn from the dataset more efficiently, while the adversarial loss function enhances the resolution of the reconstructed images. Based on our experiments, the proposed architecture outperforms the benchmark U-Net model by more than 3.5\% structural similarity (SSIM) for the reconstruction tasks of image denoising and inpainting. The proposed enhancements further show an improvement of \textasciitilde5\% SSIM over the benchmark for both tasks.
Authors: Chenglong Wang, Dexuan Li, Sucheng Wang, Chengxiu Zhang, Yida Wang, Yun Liu, Guang Yang
Recently, large vision model, Segment Anything Model (SAM), has revolutionized the computer vision field, especially for image segmentation. SAM presented a new promptable segmentation paradigm that exhibit its remarkable zero-shot generalization ability. An extensive researches have explore the potential and limits of SAM in various downstream tasks. In this study, we presents $\mathrm{SAM^{Med}}$, an enhanced framework for medical image annotation that leverages the capabilities of SAM. $\mathrm{SAM^{Med}}$ framework consisted of two submodules, namely $\mathrm{SAM^{assist}}$ and $\mathrm{SAM^{auto}}$. The $\mathrm{SAM^{assist}}$ demonstrates the generalization ability of SAM to the downstream medical segmentation task using the prompt-learning approach. Results show a significant improvement in segmentation accuracy with only approximately 5 input points. The $\mathrm{SAM^{auto}}$ model aims to accelerate the annotation process by automatically generating input prompts. The proposed SAP-Net model achieves superior segmentation performance with only five annotated slices, achieving an average Dice coefficient of 0.80 and 0.82 for kidney and liver segmentation, respectively. Overall, $\mathrm{SAM^{Med}}$ demonstrates promising results in medical image annotation. These findings highlight the potential of leveraging large-scale vision models in medical image annotation tasks.
Authors: Junming Zhang, Haomeng Zhang, Ram Vasudevan, Matthew Johnson-Roberson
Most real-world 3D measurements from depth sensors are incomplete, and to address this issue the point cloud completion task aims to predict the complete shapes of objects from partial observations. Previous works often adapt an encoder-decoder architecture, where the encoder is trained to extract embeddings that are used as inputs to generate predictions from the decoder. However, the learned embeddings have sparse distribution in the feature space, which leads to worse generalization results during testing. To address these problems, this paper proposes a hyperspherical module, which transforms and normalizes embeddings from the encoder to be on a unit hypersphere. With the proposed module, the magnitude and direction of the output hyperspherical embedding are decoupled and only the directional information is optimized. We theoretically analyze the hyperspherical embedding and show that it enables more stable training with a wider range of learning rates and more compact embedding distributions. Experiment results show consistent improvement of point cloud completion in both single-task and multi-task learning, which demonstrates the effectiveness of the proposed method.
Authors: Száva Bánsághi, Viola Sári, Péter Szerémy, Ákos Lehotsky, Bence Takács, Brigitta K. Tóth, Tamás Haidegger
Healthcare-Associated Infections present a major threat to patient safety globally. According to studies, more than 50% of HAI could be prevented by proper hand hygiene. Effectiveness of hand hygiene is regularly evaluated with the fluorescent method: performing hand hygiene with a handrub containing an ultra violet (UV) fluorescent marker. Typically, human experts evaluate the hands under UV-A light, and decide whether the applied handrub covered the whole hand surface. The aim of this study was to investigate how different experts judge the same UV-pattern, and compare that to microbiology for objective validation. Hands of volunteer participants were contaminated with high concentration of a Staphylococcus epidermidis suspension. Hands were incompletely disinfected with UV-labeled handrub. Four different UV-box type devices were used to take CCD pictures of the hands under UV light. Size of inadequately disinfected areas on the hands were determined in two different ways. First, based on microbiology; the areas where colonies were grown were measured. Second, four independent senior infection control specialists were asked to mark the missed areas on printed image, captured under UV light. 8 hands of healthy volunteers were examined. Expert evaluations were highly uncorrelated (regarding interrater reliability) and inconsistent. Microbiology results weakly correlated with the expert evaluations. In half of the cases, there were more than 10% difference in the size of properly disinfected area, as measured by microbiology versus human experts. Considering the result of the expert evaluations, variability was disconcertingly high. Evaluating the fluorescent method is challenging, even for highly experienced professionals. A patient safety quality assurance system cannot be built on these data quality.
Authors: Matt Deitke, Ruoshi Liu, Matthew Wallingford, Huong Ngo, Oscar Michel, Aditya Kusupati, Alan Fan, Christian Laforte, Vikram Voleti, Samir Yitzhak Gadre, Eli VanderBilt, Aniruddha Kembhavi, Carl Vondrick, Georgia Gkioxari, Kiana Ehsani, Ludwig Schmidt, Ali Farhadi
Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same progress, in part due to the challenges of acquiring high-quality 3D data. In this work, we present Objaverse-XL, a dataset of over 10 million 3D objects. Our dataset comprises deduplicated 3D objects from a diverse set of sources, including manually designed objects, photogrammetry scans of landmarks and everyday items, and professional scans of historic and antique artifacts. Representing the largest scale and diversity in the realm of 3D datasets, Objaverse-XL enables significant new possibilities for 3D vision. Our experiments demonstrate the improvements enabled with the scale provided by Objaverse-XL. We show that by training Zero123 on novel view synthesis, utilizing over 100 million multi-view rendered images, we achieve strong zero-shot generalization abilities. We hope that releasing Objaverse-XL will enable further innovations in the field of 3D vision at scale.
Authors: Anurag Dhote, Mohammed Javed, David S Doermann
Figures visually represent an essential piece of information and provide an effective means to communicate scientific facts. Recently there have been many efforts toward extracting data directly from figures, specifically from tables, diagrams, and plots, using different Artificial Intelligence and Machine Learning techniques. This is because removing information from figures could lead to deeper insights into the concepts highlighted in the scientific documents. In this survey paper, we systematically categorize figures into five classes - tables, photos, diagrams, maps, and plots, and subsequently present a critical review of the existing methodologies and data sets that address the problem of figure classification. Finally, we identify the current research gaps and provide possible directions for further research on figure classification.
Authors: Priyanka Goyal, Sohan Patnaik, Adway Mitra, Manjira Sinha
The accurate mapping of crop production is crucial for ensuring food security, effective resource management, and sustainable agricultural practices. One way to achieve this is by analyzing high-resolution satellite imagery. Deep Learning has been successful in analyzing images, including remote sensing imagery. However, capturing intricate crop patterns is challenging due to their complexity and variability. In this paper, we propose a novel Deep learning approach that integrates HRNet with Separable Convolutional layers to capture spatial patterns and Self-attention to capture temporal patterns of the data. The HRNet model acts as a backbone and extracts high-resolution features from crop images. Spatially separable convolution in the shallow layers of the HRNet model captures intricate crop patterns more effectively while reducing the computational cost. The multi-head attention mechanism captures long-term temporal dependencies from the encoded vector representation of the images. Finally, a CNN decoder generates a crop map from the aggregated representation. Adaboost is used on top of this to further improve accuracy. The proposed algorithm achieves a high classification accuracy of 97.5\% and IoU of 55.2\% in generating crop maps. We evaluate the performance of our pipeline on the Zuericrop dataset and demonstrate that our results outperform state-of-the-art models such as U-Net++, ResNet50, VGG19, InceptionV3, DenseNet, and EfficientNet. This research showcases the potential of Deep Learning for Earth Observation Systems.
Authors: Avinash Kori, Pedro Sanchez, Konstantinos Vilouras, Ben Glocker, Sotirios A. Tsaftaris
Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, argues that factors of variation in a dataset are, in fact, causally related. Allowing latent variables to be correlated, as a consequence of causal relationships, is more realistic and generalisable. So far, provably identifiable methods rely on: auxiliary information, weak labels, and interventional or even counterfactual data. Inspired by causal discovery with functional causal models, we propose a fully unsupervised representation learning method that considers a data generation process with a latent additive noise model (ANM). We encourage the latent space to follow a causal ordering via loss function based on the Hessian of the latent distribution.
Authors: Julien Nicolas, Florent Chiaroni, Imtiaz Ziko, Ola Ahmad, Christian Desrosiers, Jose Dolz
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform satisfactorily within known domains, their performance largely degrades in the presence of novel domains. This limitation hampers their generalizability, and restricts their scalability to more realistic settings where train and test data are drawn from different distributions. To address these limitations, we present a novel DIL approach based on a mixture of prompt-tuned CLIP models (MoP-CLIP), which generalizes the paradigm of S-Prompting to handle both in-distribution and out-of-distribution data at inference. In particular, at the training stage we model the features distribution of every class in each domain, learning individual text and visual prompts to adapt to a given domain. At inference, the learned distributions allow us to identify whether a given test sample belongs to a known domain, selecting the correct prompt for the classification task, or from an unseen domain, leveraging a mixture of the prompt-tuned CLIP models. Our empirical evaluation reveals the poor performance of existing DIL methods under domain shift, and suggests that the proposed MoP-CLIP performs competitively in the standard DIL settings while outperforming state-of-the-art methods in OOD scenarios. These results demonstrate the superiority of MoP-CLIP, offering a robust and general solution to the problem of domain incremental learning.
Authors: Hao Zheng, Regina Lee, Yuqian Lu
Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD - the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view, multi-modality videos (each video contains one assembly task), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.
Authors: Ren Jie Tee, Mengmi Zhang
Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning agents. The goal is to emulate the human learning process, thereby improving knowledge retention and facilitating learning transfer. Existing replay methods in continual learning agents involve the random selection and ordering of data from previous tasks, which has shown to be effective. However, limited research has explored the integration of different curricula with replay methods to enhance continual learning. Our study takes initial steps in examining the impact of integrating curricula with replay methods on continual learning in three specific aspects: the interleaved frequency of replayed exemplars with training data, the sequence in which exemplars are replayed, and the strategy for selecting exemplars into the replay buffer. These aspects of curricula design align with cognitive psychology principles and leverage the benefits of interleaved practice during replays, easy-to-hard rehearsal, and exemplar selection strategy involving exemplars from a uniform distribution of difficulties. Based on our results, these three curricula effectively mitigated catastrophic forgetting and enhanced positive knowledge transfer, demonstrating the potential of curricula in advancing continual learning methodologies.
Authors: Erick Oliveira Rodrigues, Esteban Clua, Giovani Bernardes Vitor
This work proposes a complete methodology to colorize images of Fakemon, anime-style monster-like creatures. In addition, we propose algorithms to extract the line art from colorized images as well as to extract color hints. Our work is the first in the literature to use automatic color hint extraction, to train the networks specifically with anime-styled creatures and to combine the Pix2Pix and CycleGAN approaches, two different generative adversarial networks that create a single final result. Visual results of the colorizations are feasible but there is still room for improvement.
Authors: Chantal Pellegrini, Matthias Keicher, Ege Özsoy, Nassir Navab
Radiology reporting is a crucial part of the communication between radiologists and other medical professionals, but it can be time-consuming and error-prone. One approach to alleviate this is structured reporting, which saves time and enables a more accurate evaluation than free-text reports. However, there is limited research on automating structured reporting, and no public benchmark is available for evaluating and comparing different methods. To close this gap, we introduce Rad-ReStruct, a new benchmark dataset that provides fine-grained, hierarchically ordered annotations in the form of structured reports for X-Ray images. We model the structured reporting task as hierarchical visual question answering (VQA) and propose hi-VQA, a novel method that considers prior context in the form of previously asked questions and answers for populating a structured radiology report. Our experiments show that hi-VQA achieves competitive performance to the state-of-the-art on the medical VQA benchmark VQARad while performing best among methods without domain-specific vision-language pretraining and provides a strong baseline on Rad-ReStruct. Our work represents a significant step towards the automated population of structured radiology reports and provides a valuable first benchmark for future research in this area. We will make all annotations and our code for annotation generation, model evaluation, and training publicly available upon acceptance. Our dataset and code is available at https://github.com/ChantalMP/Rad-ReStruct.
Authors: Anqi Feng, Dimitri Johnson, Grace R. Reilly, Loka Thangamathesvaran, Ann Nampomba, Mathias Unberath, Adrienne W. Scott, Craig Jones
Importance: Ultra-widefield fundus photography (UWF-FP) has shown utility in sickle cell retinopathy screening; however, image artifact may diminish quality and gradeability of images. Objective: To create an automated algorithm for UWF-FP artifact classification. Design: A neural network based automated artifact detection algorithm was designed to identify commonly encountered UWF-FP artifacts in a cross section of patient UWF-FP. A pre-trained ResNet-50 neural network was trained on a subset of the images and the classification accuracy, sensitivity, and specificity were quantified on the hold out test set. Setting: The study is based on patients from a tertiary care hospital site. Participants: There were 243 UWF-FP acquired from patients with sickle cell disease (SCD), and artifact labelling in the following categories was performed: Eyelash Present, Lower Eyelid Obstructing, Upper Eyelid Obstructing, Image Too Dark, Dark Artifact, and Image Not Centered. Results: Overall, the accuracy for each class was Eyelash Present at 83.7%, Lower Eyelid Obstructing at 83.7%, Upper Eyelid Obstructing at 98.0%, Image Too Dark at 77.6%, Dark Artifact at 93.9%, and Image Not Centered at 91.8%. Conclusions and Relevance: This automated algorithm shows promise in identifying common imaging artifacts on a subset of Optos UWF-FP in SCD patients. Further refinement is ongoing with the goal of improving efficiency of tele-retinal screening in sickle cell retinopathy (SCR) by providing a photographer real-time feedback as to the types of artifacts present, and the need for image re-acquisition. This algorithm also may have potential future applicability in other retinal diseases by improving quality and efficiency of image acquisition of UWF-FP.
Authors: Matthias De Lange, Hamid Eghbalzadeh, Reuben Tan, Michael Iuzzolino, Franziska Meier, Karl Ridgeway
In egocentric action recognition a single population model is typically trained and subsequently embodied on a head-mounted device, such as an augmented reality headset. While this model remains static for new users and environments, we introduce an adaptive paradigm of two phases, where after pretraining a population model, the model adapts on-device and online to the user's experience. This setting is highly challenging due to the change from population to user domain and the distribution shifts in the user's data stream. Coping with the latter in-stream distribution shifts is the focus of continual learning, where progress has been rooted in controlled benchmarks but challenges faced in real-world applications often remain unaddressed. We introduce EgoAdapt, a benchmark for real-world egocentric action recognition that facilitates our two-phased adaptive paradigm, and real-world challenges naturally occur in the egocentric video streams from Ego4d, such as long-tailed action distributions and large-scale classification over 2740 actions. We introduce an evaluation framework that directly exploits the user's data stream with new metrics to measure the adaptation gain over the population model, online generalization, and hindsight performance. In contrast to single-stream evaluation in existing works, our framework proposes a meta-evaluation that aggregates the results from 50 independent user streams. We provide an extensive empirical study for finetuning and experience replay.
Authors: Daniel Jörgens, Pierre-Marc Jodoin, Maxime Descoteaux, Rodrigo Moreno
One of the main issues of the current tractography methods is their high false-positive rate. Tractogram filtering is an option to remove false-positive streamlines from tractography data in a post-processing step. In this paper, we train a deep neural network for filtering tractography data in which every streamline of a tractogram is classified as {\em plausible, implausible}, or {\em inconclusive}. For this, we use four different tractogram filtering strategies as supervisors: TractQuerier, RecobundlesX, TractSeg, and an anatomy-inspired filter. Their outputs are combined to obtain the classification labels for the streamlines. We assessed the importance of different types of information along the streamlines for performing this classification task, including the coordinates of the streamlines, diffusion data, landmarks, T1-weighted information, and a brain parcellation. We found that the streamline coordinates are the most relevant followed by the diffusion data in this particular classification task.
The high cure rate of cancer is inextricably linked to physicians' accuracy in diagnosis and treatment, therefore a model that can accomplish high-precision tumor segmentation has become a necessity in many applications of the medical industry. It can effectively lower the rate of misdiagnosis while considerably lessening the burden on clinicians. However, fully automated target organ segmentation is problematic due to the irregular stereo structure of 3D volume organs. As a basic model for this class of real applications, U-Net excels. It can learn certain global and local features, but still lacks the capacity to grasp spatial long-range relationships and contextual information at multiple scales. This paper proposes a tumor segmentation model MPU-Net for patient volume CT images, which is inspired by Transformer with a global attention mechanism. By combining image serialization with the Position Attention Module, the model attempts to comprehend deeper contextual dependencies and accomplish precise positioning. Each layer of the decoder is also equipped with a multi-scale module and a cross-attention mechanism. The capability of feature extraction and integration at different levels has been enhanced, and the hybrid loss function developed in this study can better exploit high-resolution characteristic information. Moreover, the suggested architecture is tested and evaluated on the Liver Tumor Segmentation Challenge 2017 (LiTS 2017) dataset. Compared with the benchmark model U-Net, MPU-Net shows excellent segmentation results. The dice, accuracy, precision, specificity, IOU, and MCC metrics for the best model segmentation results are 92.17%, 99.08%, 91.91%, 99.52%, 85.91%, and 91.74%, respectively. Outstanding indicators in various aspects illustrate the exceptional performance of this framework in automatic medical image segmentation.
Authors: Zhuxian Guo, Qitong Wang, Henning Müller, Themis Palpanas, Nicolas Loménie, Camille Kurtz
In digital histopathology, entire neoplasm segmentation on Whole Slide Image (WSI) of Hepatocellular Carcinoma (HCC) plays an important role, especially as a preprocessing filter to automatically exclude healthy tissue, in histological molecular correlations mining and other downstream histopathological tasks. The segmentation task remains challenging due to HCC's inherent high-heterogeneity and the lack of dependency learning in large field of view. In this article, we propose a novel deep learning architecture with a hierarchical Transformer encoder, HiTrans, to learn the global dependencies within expanded 4096$\times$4096 WSI patches. HiTrans is designed to encode and decode the patches with larger reception fields and the learned global dependencies, compared to the state-of-the-art Fully Convolutional Neural networks (FCNN). Empirical evaluations verified that HiTrans leads to better segmentation performance by taking into account regional and global dependency information.
Authors: Hyojin Kim, Kyle Champley
Data-driven deep learning has been successfully applied to various computed tomographic reconstruction problems. The deep inference models may outperform existing analytical and iterative algorithms, especially in ill-posed CT reconstruction. However, those methods often predict images that do not agree with the measured projection data. This paper presents an accurate differentiable forward and back projection software library to ensure the consistency between the predicted images and the original measurements. The software library efficiently supports various projection geometry types while minimizing the GPU memory footprint requirement, which facilitates seamless integration with existing deep learning training and inference pipelines. The proposed software is available as open source: https://github.com/LLNL/LEAP.
Authors: Seung Yeon Shin, Thomas C. Shen, Ronald M. Summers
We propose a method to incorporate the intensity information of a target lesion on CT scans in training segmentation and detection networks. We first build an intensity-based lesion probability (ILP) function from an intensity histogram of the target lesion. It is used to compute the probability of being the lesion for each voxel based on its intensity. Finally, the computed ILP map of each input CT scan is provided as additional supervision for network training, which aims to inform the network about possible lesion locations in terms of intensity values at no additional labeling cost. The method was applied to improve the segmentation of three different lesion types, namely, small bowel carcinoid tumor, kidney tumor, and lung nodule. The effectiveness of the proposed method on a detection task was also investigated. We observed improvements of 41.3% -> 47.8%, 74.2% -> 76.0%, and 26.4% -> 32.7% in segmenting small bowel carcinoid tumor, kidney tumor, and lung nodule, respectively, in terms of per case Dice scores. An improvement of 64.6% -> 75.5% was achieved in detecting kidney tumors in terms of average precision. The results of different usages of the ILP map and the effect of varied amount of training data are also presented.
Authors: Sara Hatami Gazani, Matthew Tucsok, Iraj Mantegh, Homayoun Najjaran
UAV-based intelligent data acquisition for 3D reconstruction and monitoring of infrastructure has been experiencing an increasing surge of interest due to the recent advancements in image processing and deep learning-based techniques. View planning is an essential part of this task that dictates the information capture strategy and heavily impacts the quality of the 3D model generated from the captured data. Recent methods have used prior knowledge or partial reconstruction of the target to accomplish view planning for active reconstruction; the former approach poses a challenge for complex or newly identified targets while the latter is computationally expensive. In this work, we present Bag-of-Views (BoV), a fully appearance-based model used to assign utility to the captured views for both offline dataset refinement and online next-best-view (NBV) planning applications targeting the task of 3D reconstruction. With this contribution, we also developed the View Planning Toolbox (VPT), a lightweight package for training and testing machine learning-based view planning frameworks, custom view dataset generation of arbitrary 3D scenes, and 3D reconstruction. Through experiments which pair a BoV-based reinforcement learning model with VPT, we demonstrate the efficacy of our model in reducing the number of required views for high-quality reconstructions in dataset refinement and NBV planning.
Authors: Lukas Haas, Silas Alberti, Michal Skreta
We introduce PIGEON, a multi-task end-to-end system for planet-scale image geolocalization that achieves state-of-the-art performance on both external benchmarks and in human evaluation. Our work incorporates semantic geocell creation with label smoothing, conducts pretraining of a vision transformer on images with geographic information, and refines location predictions with ProtoNets across a candidate set of geocells. The contributions of PIGEON are three-fold: first, we design a semantic geocells creation and splitting algorithm based on open-source data which can be adapted to any geospatial dataset. Second, we show the effectiveness of intra-geocell refinement and the applicability of unsupervised clustering and ProtNets to the task. Finally, we make our pre-trained CLIP transformer model, StreetCLIP, publicly available for use in adjacent domains with applications to fighting climate change and urban and rural scene understanding.
Authors: Bruce X.B. Yu, Zhi Zhang, Yongxu Liu, Sheng-hua Zhong, Yan Liu, Chang Wen Chen
3D human pose estimation has been researched for decades with promising fruits. 3D human pose lifting is one of the promising research directions toward the task where both estimated pose and ground truth pose data are used for training. Existing pose lifting works mainly focus on improving the performance of estimated pose, but they usually underperform when testing on the ground truth pose data. We observe that the performance of the estimated pose can be easily improved by preparing good quality 2D pose, such as fine-tuning the 2D pose or using advanced 2D pose detectors. As such, we concentrate on improving the 3D human pose lifting via ground truth data for the future improvement of more quality estimated pose data. Towards this goal, a simple yet effective model called Global-local Adaptive Graph Convolutional Network (GLA-GCN) is proposed in this work. Our GLA-GCN globally models the spatiotemporal structure via a graph representation and backtraces local joint features for 3D human pose estimation via individually connected layers. To validate our model design, we conduct extensive experiments on three benchmark datasets: Human3.6M, HumanEva-I, and MPI-INF-3DHP. Experimental results show that our GLA-GCN implemented with ground truth 2D poses significantly outperforms state-of-the-art methods (e.g., up to around 3%, 17%, and 13% error reductions on Human3.6M, HumanEva-I, and MPI-INF-3DHP, respectively).
Authors: Zichao Dong, Hang Ji, Weikun Zhang, Xufeng Huang, Junbo Chen
Occupancy prediction tasks focus on the inference of both geometry and semantic labels for each voxel, which is an important perception mission. However, it is still a semantic segmentation task without distinguishing various instances. Further, although some existing works, such as Open-Vocabulary Occupancy (OVO), have already solved the problem of open vocabulary detection, visual grounding in occupancy has not been solved to the best of our knowledge. To tackle the above two limitations, this paper proposes Occupancy Grounding (OG), a novel method that equips vanilla occupancy instance segmentation ability and could operate visual grounding in a voxel manner with the help of grounded-SAM. Keys to our approach are (1) affinity field prediction for instance clustering and (2) association strategy for aligning 2D instance masks and 3D occupancy instances. Extensive experiments have been conducted whose visualization results and analysis are shown below. Our code will be publicly released soon.
Authors: Hiroshi Fukui, Taiki Miyagawa, Yusuke Morishita
We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transformer blocks, or graph networks. Conventional MOT models are built upon the multi-step modules listed above, and thus the computational cost is high. Our proposed end-to-end MOT model, \textit{TicrossNet}, is composed of a base detector and a cross-attention module only. As a result, the overhead of tracking does not increase significantly even when the number of instances ($N_t$) increases. We show that TicrossNet runs \textit{in real-time}; specifically, it achieves 32.6 FPS on MOT17 and 31.0 FPS on MOT20 (Tesla V100), which includes as many as $>$100 instances per frame. We also demonstrate that TicrossNet is robust to $N_t$; thus, it does not have to change the size of the base detector, depending on $N_t$, as is often done by other models for real-time processing.
Authors: Hao Wang, Jiatai Lin, Danyi Li, Jing Wang, Bingchao Zhao, Zhenwei Shi, Xipeng Pan, Huadeng Wang, Bingbing Li, Changhong Liang, Guoqiang Han, Li Liang, Chu Han, Zaiyi Liu
Mitosis detection is one of the fundamental tasks in computational pathology, which is extremely challenging due to the heterogeneity of mitotic cell. Most of the current studies solve the heterogeneity in the technical aspect by increasing the model complexity. However, lacking consideration of the biological knowledge and the complex model design may lead to the overfitting problem while limited the generalizability of the detection model. In this paper, we systematically study the morphological appearances in different mitotic phases as well as the ambiguous non-mitotic cells and identify that balancing the data and feature diversity can achieve better generalizability. Based on this observation, we propose a novel generalizable framework (MitDet) for mitosis detection. The data diversity is considered by the proposed diversity-guided sample balancing (DGSB). And the feature diversity is preserved by inter- and intra- class feature diversity-preserved module (InCDP). Stain enhancement (SE) module is introduced to enhance the domain-relevant diversity of both data and features simultaneously. Extensive experiments have demonstrated that our proposed model outperforms all the SOTA approaches in several popular mitosis detection datasets in both internal and external test sets using minimal annotation efforts with point annotations only. Comprehensive ablation studies have also proven the effectiveness of the rethinking of data and feature diversity balancing. By analyzing the results quantitatively and qualitatively, we believe that our proposed model not only achieves SOTA performance but also might inspire the future studies in new perspectives. Source code is at https://github.com/Onehour0108/MitDet.
Authors: Chenglong Ma, Zilong Li, Junping Zhang, Yi Zhang, Hongming Shan
Sparse-view computed tomography (CT) is a promising solution for expediting the scanning process and mitigating radiation exposure to patients, the reconstructed images, however, contain severe streak artifacts, compromising subsequent screening and diagnosis. Recently, deep learning-based image post-processing methods along with their dual-domain counterparts have shown promising results. However, existing methods usually produce over-smoothed images with loss of details due to (1) the difficulty in accurately modeling the artifact patterns in the image domain, and (2) the equal treatment of each pixel in the loss function. To address these issues, we concentrate on the image post-processing and propose a simple yet effective FREquency-band-awarE and SElf-guidED network, termed FreeSeed, which can effectively remove artifact and recover missing detail from the contaminated sparse-view CT images. Specifically, we first propose a frequency-band-aware artifact modeling network (FreeNet), which learns artifact-related frequency-band attention in Fourier domain for better modeling the globally distributed streak artifact on the sparse-view CT images. We then introduce a self-guided artifact refinement network (SeedNet), which leverages the predicted artifact to assist FreeNet in continuing to refine the severely corrupted details. Extensive experiments demonstrate the superior performance of FreeSeed and its dual-domain counterpart over the state-of-the-art sparse-view CT reconstruction methods. Source code is made available at https://github.com/Masaaki-75/freeseed.
Authors: Shi-Sheng Huang, Zi-Xin Zou, Yi-Chi Zhang, Hua Huang
The recent neural surface reconstruction by volume rendering approaches have made much progress by achieving impressive surface reconstruction quality, but are still limited to dense and highly accurate posed views. To overcome such drawbacks, this paper pays special attention on the consistent surface reconstruction from sparse views with noisy camera poses. Unlike previous approaches, the key difference of this paper is to exploit the multi-view constraints directly from the explicit geometry of the neural surface, which can be used as effective regularization to jointly learn the neural surface and refine the camera poses. To build effective multi-view constraints, we introduce a fast differentiable on-surface intersection to generate on-surface points, and propose view-consistent losses based on such differentiable points to regularize the neural surface learning. Based on this point, we propose a jointly learning strategy for neural surface and camera poses, named SC-NeuS, to perform geometry-consistent surface reconstruction in an end-to-end manner. With extensive evaluation on public datasets, our SC-NeuS can achieve consistently better surface reconstruction results with fine-grained details than previous state-of-the-art neural surface reconstruction approaches, especially from sparse and noisy camera views.
Authors: Kien X. Nguyen, Liying Zheng, Ashley L. Hawke, Robert E. Carey, Scott P. Breloff, Kang Li, Xi Peng
It is necessary to analyze the whole-body kinematics (including joint locations and joint angles) to assess risks of fatal and musculoskeletal injuries in occupational tasks. Human pose estimation has gotten more attention in recent years as a method to minimize the errors in determining joint locations. However, the joint angles are not often estimated, nor is the quality of joint angle estimation assessed. In this paper, we presented an end-to-end approach on direct joint angle estimation from multi-view images. Our method leveraged the volumetric pose representation and mapped the rotation representation to a continuous space where each rotation was uniquely represented. We also presented a new kinematic dataset in the domain of residential roofing with a data processing pipeline to generate necessary annotations for the supervised training procedure on direct joint angle estimation. We achieved a mean angle error of $7.19^\circ$ on the new Roofing dataset and $8.41^\circ$ on the Human3.6M dataset, paving the way for employment of on-site kinematic analysis using multi-view images.
Authors: Beilei Cui, Minqing Zhang, Mengya Xu, An Wang, Wu Yuan, Hongliang Ren
Noisy label problems are inevitably in existence within medical image segmentation causing severe performance degradation. Previous segmentation methods for noisy label problems only utilize a single image while the potential of leveraging the correlation between images has been overlooked. Especially for video segmentation, adjacent frames contain rich contextual information beneficial in cognizing noisy labels. Based on two insights, we propose a Multi-Scale Temporal Feature Affinity Learning (MS-TFAL) framework to resolve noisy-labeled medical video segmentation issues. First, we argue the sequential prior of videos is an effective reference, i.e., pixel-level features from adjacent frames are close in distance for the same class and far in distance otherwise. Therefore, Temporal Feature Affinity Learning (TFAL) is devised to indicate possible noisy labels by evaluating the affinity between pixels in two adjacent frames. We also notice that the noise distribution exhibits considerable variations across video, image, and pixel levels. In this way, we introduce Multi-Scale Supervision (MSS) to supervise the network from three different perspectives by re-weighting and refining the samples. This design enables the network to concentrate on clean samples in a coarse-to-fine manner. Experiments with both synthetic and real-world label noise demonstrate that our method outperforms recent state-of-the-art robust segmentation approaches. Code is available at https://github.com/BeileiCui/MS-TFAL.
Authors: Yipeng Leng, Qiangjuan Huang, Zhiyuan Wang, Yangyang Liu, Haoyu Zhang
Diffusion probabilistic models (DPMs) have shown remarkable results on various image synthesis tasks such as text-to-image generation and image inpainting. However, compared to other generative methods like VAEs and GANs, DPMs lack a low-dimensional, interpretable, and well-decoupled latent code. Recently, diffusion autoencoders (Diff-AE) were proposed to explore the potential of DPMs for representation learning via autoencoding. Diff-AE provides an accessible latent space that exhibits remarkable interpretability, allowing us to manipulate image attributes based on latent codes from the space. However, previous works are not generic as they only operated on a few limited attributes. To further explore the latent space of Diff-AE and achieve a generic editing pipeline, we proposed a module called Group-supervised AutoEncoder(dubbed GAE) for Diff-AE to achieve better disentanglement on the latent code. Our proposed GAE has trained via an attribute-swap strategy to acquire the latent codes for multi-attribute image manipulation based on examples. We empirically demonstrate that our method enables multiple-attributes manipulation and achieves convincing sample quality and attribute alignments, while significantly reducing computational requirements compared to pixel-based approaches for representational decoupling. Code will be released soon.
Authors: WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad, David Suter, Alireza Bab-Hadiashar
Deep learning techniques often perform poorly in the presence of domain shift, where the test data follows a different distribution than the training data. The most practically desirable approach to address this issue is Single Domain Generalization (S-DG), which aims to train robust models using data from a single source. Prior work on S-DG has primarily focused on using data augmentation techniques to generate diverse training data. In this paper, we explore an alternative approach by investigating the robustness of linear operators, such as convolution and dense layers commonly used in deep learning. We propose a novel operator called XCNorm that computes the normalized cross-correlation between weights and an input feature patch. This approach is invariant to both affine shifts and changes in energy within a local feature patch and eliminates the need for commonly used non-linear activation functions. We show that deep neural networks composed of this operator are robust to common semantic distribution shifts. Furthermore, our empirical results on single-domain generalization benchmarks demonstrate that our proposed technique performs comparably to the state-of-the-art methods.
Authors: Xinyi Bai, Ze Wang, Lu Yang, Hong Cheng
The virtual viewpoint is perceived as a new technique in virtual navigation, as yet not supported due to the lack of depth information and obscure camera parameters. In this paper, a method for achieving close-up virtual view is proposed and it only uses optical flow to build parallax effects to realize pseudo 3D projection without using depth sensor. We develop a bidirectional optical flow method to obtain any virtual viewpoint by proportional interpolation of optical flow. Moreover, with the ingenious application of the optical-flow-value, we achieve clear and visual-fidelity magnified results through lens stretching in any corner, which overcomes the visual distortion and image blur through viewpoint magnification and transition in Google Street View system.
Authors: Peter Yongho Kim, Junbeom Kwon, Sunghwan Joo, Sangyoon Bae, Donggyu Lee, Yoonho Jung, Shinjae Yoo, Jiook Cha, Taesup Moon
The modeling of spatiotemporal brain dynamics from high-dimensional data, such as 4D functional MRI, is a formidable task in neuroscience. To address this challenge, we present SwiFT (Swin 4D fMRI Transformer), a Swin Transformer architecture that can learn brain dynamics directly from 4D functional brain MRI data in a memory and computation-efficient manner. SwiFT achieves this by implementing a 4D window multi-head self-attention mechanism and absolute positional embeddings. We evaluate SwiFT using multiple largest-scale human functional brain imaging datasets in tasks such as predicting sex, age, and cognitive intelligence. Our experimental outcomes reveal that SwiFT consistently outperforms recent state-of-the-art models. To the best of our knowledge, SwiFT is the first Swin Transformer architecture that can process dimensional spatiotemporal brain functional data in an end-to-end fashion. Furthermore, due to the end-to-end learning capability, we also show that contrastive loss-based self-supervised pre-training of SwiFT is also feasible for achieving improved performance on a downstream task. We believe that our work holds substantial potential in facilitating scalable learning of functional brain imaging in neuroscience research by reducing the hurdles associated with applying Transformer models to high-dimensional fMRI.
Authors: Yuhao Wang
Contrastive language-image Pre-training (CLIP) [13] can leverage large datasets of unlabeled Image-Text pairs, which have demonstrated impressive performance in various downstream tasks. Given that annotating medical data is time-consuming and laborious, Image-Text Pre-training has promising applications in exploiting large-scale medical image and radiology report datasets. However, medical Image-Text Pre-training faces several challenges, as follows: (1) Due to privacy concerns, the amount of available medical data is relatively small compared to natural data, leading to weaker generalization ability of the model. (2) Medical images are highly similar with only fine-grained differences in subtleties, resulting in a large number of false-negative sample pairs in comparison learning. (3) The hand-crafted Prompt usually differs from the natural medical image report, Subtle changes in wording can lead to significant differences in performance. In this paper, we propose a unified Image-Text-Label contrastive learning framework based on continuous prompts, with three main contributions. First, We unified the data of images, text, and labels, which greatly expanded the training data that the model could utilize. Second, we address the issue of data diversity and the impact of hand-crafted prompts on model performance by introducing continuous implicit prompts. Lastly, we propose a ImageText-Label contrastive Training to mitigate the problem of too many false-negative samples. We demonstrate through sufficient experiments that the Unified Medical Contrastive Learning (UMCL) framework exhibits excellent performance on several downstream tasks.
Authors: Yuhao Wang
Automated radiology report generation aims to generate radiology reports that contain rich, fine-grained descriptions of radiology imaging. Compared with image captioning in the natural image domain, medical images are very similar to each other, with only minor differences in the occurrence of diseases. Given the importance of these minor differences in the radiology report, it is crucial to encourage the model to focus more on the subtle regions of disease occurrence. Secondly, the problem of visual and textual data biases is serious. Not only do normal cases make up the majority of the dataset, but sentences describing areas with pathological changes also constitute only a small part of the paragraph. Lastly, generating medical image reports involves the challenge of long text generation, which requires more expertise and empirical training in medical knowledge. As a result, the difficulty of generating such reports is increased. To address these challenges, we propose a disease-oriented retrieval framework that utilizes similar reports as prior knowledge references. We design a factual consistency captioning generator to generate more accurate and factually consistent disease descriptions. Our framework can find most similar reports for a given disease from the CXR database by retrieving a disease-oriented mask consisting of the position and morphological characteristics. By referencing the disease-oriented similar report and the visual features, the factual consistency model can generate a more accurate radiology report.
Authors: Tianxiao Zhang, Kaidong Li, Xiangyu Chen, Cuncong Zhong, Bo Luo, Ivan Grijalva Teran, Brian McCornack, Daniel Flippo, Ajay Sharda, Guanghui Wang
Aphids are one of the main threats to crops, rural families, and global food security. Chemical pest control is a necessary component of crop production for maximizing yields, however, it is unnecessary to apply the chemical approaches to the entire fields in consideration of the environmental pollution and the cost. Thus, accurately localizing the aphid and estimating the infestation level is crucial to the precise local application of pesticides. Aphid detection is very challenging as each individual aphid is really small and all aphids are crowded together as clusters. In this paper, we propose to estimate the infection level by detecting aphid clusters. We have taken millions of images in the sorghum fields, manually selected 5,447 images that contain aphids, and annotated each aphid cluster in the image. To use these images for machine learning models, we crop the images into patches and created a labeled dataset with over 151,000 image patches. Then, we implement and compare the performance of four state-of-the-art object detection models.
Authors: Chanda Grover Kamra, Indra Deep Mastan, Debayan Gupta
CLIPStyler demonstrated image style transfer with realistic textures using only a style text description (instead of requiring a reference style image). However, the ground semantics of objects in the style transfer output is lost due to style spill-over on salient and background objects (content mismatch) or over-stylization. To solve this, we propose Semantic CLIPStyler (Sem-CS), that performs semantic style transfer. Sem-CS first segments the content image into salient and non-salient objects and then transfers artistic style based on a given style text description. The semantic style transfer is achieved using global foreground loss (for salient objects) and global background loss (for non-salient objects). Our empirical results, including DISTS, NIMA and user study scores, show that our proposed framework yields superior qualitative and quantitative performance. Our code is available at github.com/chandagrover/sem-cs.
Authors: Seitaro Otsuki, Shintaro Ishikawa, Komei Sugiura
Although domestic service robots are expected to assist individuals who require support, they cannot currently interact smoothly with people through natural language. For example, given the instruction "Bring me a bottle from the kitchen," it is difficult for such robots to specify the bottle in an indoor environment. Most conventional models have been trained on real-world datasets that are labor-intensive to collect, and they have not fully leveraged simulation data through a transfer learning framework. In this study, we propose a novel transfer learning approach for multimodal language understanding called Prototypical Contrastive Transfer Learning (PCTL), which uses a new contrastive loss called Dual ProtoNCE. We introduce PCTL to the task of identifying target objects in domestic environments according to free-form natural language instructions. To validate PCTL, we built new real-world and simulation datasets. Our experiment demonstrated that PCTL outperformed existing methods. Specifically, PCTL achieved an accuracy of 78.1%, whereas simple fine-tuning achieved an accuracy of 73.4%.
Authors: Raja Sunkara, Tie Luo
We introduce YOGA, a deep learning based yet lightweight object detection model that can operate on low-end edge devices while still achieving competitive accuracy. The YOGA architecture consists of a two-phase feature learning pipeline with a cheap linear transformation, which learns feature maps using only half of the convolution filters required by conventional convolutional neural networks. In addition, it performs multi-scale feature fusion in its neck using an attention mechanism instead of the naive concatenation used by conventional detectors. YOGA is a flexible model that can be easily scaled up or down by several orders of magnitude to fit a broad range of hardware constraints. We evaluate YOGA on COCO-val and COCO-testdev datasets with other over 10 state-of-the-art object detectors. The results show that YOGA strikes the best trade-off between model size and accuracy (up to 22% increase of AP and 23-34% reduction of parameters and FLOPs), making it an ideal choice for deployment in the wild on low-end edge devices. This is further affirmed by our hardware implementation and evaluation on NVIDIA Jetson Nano.
Authors: Junghyun Kim, Gi-Cheon Kang, Jaein Kim, Suyeon Shin, Byoung-Tak Zhang
Language-Guided Robotic Manipulation (LGRM) is a challenging task as it requires a robot to understand human instructions to manipulate everyday objects. Recent approaches in LGRM rely on pre-trained Visual Grounding (VG) models to detect objects without adapting to manipulation environments. This results in a performance drop due to a substantial domain gap between the pre-training and real-world data. A straightforward solution is to collect additional training data, but the cost of human-annotation is extortionate. In this paper, we propose Grounding Vision to Ceaselessly Created Instructions (GVCCI), a lifelong learning framework for LGRM, which continuously learns VG without human supervision. GVCCI iteratively generates synthetic instruction via object detection and trains the VG model with the generated data. We validate our framework in offline and online settings across diverse environments on different VG models. Experimental results show that accumulating synthetic data from GVCCI leads to a steady improvement in VG by up to 56.7% and improves resultant LGRM by up to 29.4%. Furthermore, the qualitative analysis shows that the unadapted VG model often fails to find correct objects due to a strong bias learned from the pre-training data. Finally, we introduce a novel VG dataset for LGRM, consisting of nearly 252k triplets of image-object-instruction from diverse manipulation environments.
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 visual-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. Project website: https://voxposer.github.io
Authors: Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
Large-scale image generation models, with impressive quality made possible by the vast amount of data available on the Internet, raise social concerns that these models may generate harmful or copyrighted content. The biases and harmfulness arise throughout the entire training process and are hard to completely remove, which have become significant hurdles to the safe deployment of these models. In this paper, we propose a method called SDD to prevent problematic content generation in text-to-image diffusion models. We self-distill the diffusion model to guide the noise estimate conditioned on the target removal concept to match the unconditional one. Compared to the previous methods, our method eliminates a much greater proportion of harmful content from the generated images without degrading the overall image quality. Furthermore, our method allows the removal of multiple concepts at once, whereas previous works are limited to removing a single concept at a time.
Authors: Pranav Agarwal, Aamer Abdul Rahman, Pierre-Luc St-Charles, Simon J.D. Prince, Samira Ebrahimi Kahou
Transformers have significantly impacted domains like natural language processing, computer vision, and robotics, where they improve performance compared to other neural networks. This survey explores how transformers are used in reinforcement learning (RL), where they are seen as a promising solution for addressing challenges such as unstable training, credit assignment, lack of interpretability, and partial observability. We begin by providing a brief domain overview of RL, followed by a discussion on the challenges of classical RL algorithms. Next, we delve into the properties of the transformer and its variants and discuss the characteristics that make them well-suited to address the challenges inherent in RL. We examine the application of transformers to various aspects of RL, including representation learning, transition and reward function modeling, and policy optimization. We also discuss recent research that aims to enhance the interpretability and efficiency of transformers in RL, using visualization techniques and efficient training strategies. Often, the transformer architecture must be tailored to the specific needs of a given application. We present a broad overview of how transformers have been adapted for several applications, including robotics, medicine, language modeling, cloud computing, and combinatorial optimization. We conclude by discussing the limitations of using transformers in RL and assess their potential for catalyzing future breakthroughs in this field.
Authors: Julian Moosmann, Hanna Mueller, Nicky Zimmerman, Georg Rutishauser, Luca Benini, Michele Magno
This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network's detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting an in-depth a comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a novel parallel RISC-V processor (GAP9 from Greenwaves) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from STM and Apollo4b from Ambiq), and a multi-core platform with a CNN hardware accelerator (Analog Devices MAX78000). Experimental results show that the GAP9's hardware accelerator achieves the lowest inference latency and energy at 2.12ms and 150uJ respectively, which is around 2x faster and 20% more efficient than the next best platform, the MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with 112x112 pixels and 10 detection classes within 3.2ms, consuming 245uJ. To showcase the competitiveness of a versatile general-purpose system we also deployed and profiled a multi-core implementation on GAP9 at different operating points, achieving 11.3ms with the lowest-latency and 490uJ with the most energy-efficient configuration. With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference.
Authors: Lujie Xia, Ziluo Ding, Rui Zhao, Jiyuan Zhang, Lei Ma, Zhaofei Yu, Tiejun Huang, Ruiqin Xiong
Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers architecture, it applies dilated convolutions on temporal dimension to extract features on multi-temporal scales with few parameters. And we design layer attention to dynamically fuse these features. Moreover, we propose an unsupervised learning method for optical flow estimation in a spike-based manner to break the dependence on labeled data. In addition, to verify the robustness, we also build a spike-based synthetic validation dataset for extreme scenarios in autonomous driving, denoted as SSES dataset. It consists of various corner cases. Experiments show that our method can predict optical flow from spike streams in different high-speed scenes, including real scenes. For instance, our method gets $15\%$ and $19\%$ error reduction from the best spike-based work, SCFlow, in $\Delta t=10$ and $\Delta t=20$ respectively which are the same settings as the previous works.
Authors: Gabriele Merlin, Vedant Nanda, Ruchit Rawal, Mariya Toneva
The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically observed to be beneficial for a range of tasks, there is not a clear understanding yet of the reasons for this effect. In this work, we examine the relationship between pretrained vision transformers and the corresponding finetuned versions on several benchmark datasets and tasks. We present new metrics that specifically investigate the degree to which invariances learned by a pretrained model are retained or forgotten during finetuning. Using these metrics, we present a suite of empirical findings, including that pretraining induces transferable invariances in shallow layers and that invariances from deeper pretrained layers are compressed towards shallower layers during finetuning. Together, these findings contribute to understanding some of the reasons for the successes of pretrained models and the changes that a pretrained model undergoes when finetuned on a downstream task.
Authors: Misgina Tsighe Hagos, Kathleen M. Curran, Brian Mac Namee
eXplanation Based Learning (XBL) is a form of Interactive Machine Learning (IML) that provides a model refining approach via user feedback collected on model explanations. Although the interactivity of XBL promotes model transparency, XBL requires a huge amount of user interaction and can become expensive as feedback is in the form of detailed annotation rather than simple category labelling which is more common in IML. This expense is exacerbated in high stakes domains such as medical image classification. To reduce the effort and expense of XBL we introduce a new approach that uses two input instances and their corresponding Gradient Weighted Class Activation Mapping (GradCAM) model explanations as exemplary explanations to implement XBL. Using a medical image classification task, we demonstrate that, using minimal human input, our approach produces improved explanations (+0.02, +3%) and achieves reduced classification performance (-0.04, -4%) when compared against a model trained without interactions.
Authors: Jinwei Ren, Jianke Zhu
Accurately recovering the dense 3D mesh of both hands from monocular images poses considerable challenges due to occlusions and projection ambiguity. Most of the existing methods extract features from color images to estimate the root-aligned hand meshes, which neglect the crucial depth and scale information in the real world. Given the noisy sensor measurements with limited resolution, depth-based methods predict 3D keypoints rather than a dense mesh. These limitations motivate us to take advantage of these two complementary inputs to acquire dense hand meshes on a real-world scale. In this work, we propose an end-to-end framework for recovering dense meshes for both hands, which employ single-view RGB-D image pairs as input. The primary challenge lies in effectively utilizing two different input modalities to mitigate the blurring effects in RGB images and noises in depth images. Instead of directly treating depth maps as additional channels for RGB images, we encode the depth information into the unordered point cloud to preserve more geometric details. Specifically, our framework employs ResNet50 and PointNet++ to derive features from RGB and point cloud, respectively. Additionally, we introduce a novel pyramid deep fusion network (PDFNet) to aggregate features at different scales, which demonstrates superior efficacy compared to previous fusion strategies. Furthermore, we employ a GCN-based decoder to process the fused features and recover the corresponding 3D pose and dense mesh. Through comprehensive ablation experiments, we have not only demonstrated the effectiveness of our proposed fusion algorithm but also outperformed the state-of-the-art approaches on publicly available datasets. To reproduce the results, we will make our source code and models publicly available at {\url{https://github.com/zijinxuxu/PDFNet}}.
Authors: Joao P C Bertoldo, David Arrustico
This paper introduces a simplified variation of the PaDiM (Pixel-Wise Anomaly Detection through Instance Modeling) method for anomaly detection in images, fitting a single multivariate Gaussian (MVG) distribution to the feature vectors extracted from a backbone convolutional neural network (CNN) and using their Mahalanobis distance as the anomaly score. We introduce an intermediate step in this framework by applying a whitening transformation to the feature vectors, which enables the generation of heatmaps capable of visually explaining the features learned by the MVG. The proposed technique is evaluated on the MVTec-AD dataset, and the results show the importance of visual model validation, providing insights into issues in this framework that were otherwise invisible. The visualizations generated for this paper are publicly available at https://doi.org/10.5281/zenodo.7937978.
Authors: Mete Ahishali, Mehmet Yamac, Serkan Kiranyaz, Moncef Gabbouj
In this work, we propose a novel approach called Operational Support Estimator Networks (OSENs) for the support estimation task. Support Estimation (SE) is defined as finding the locations of non-zero elements in a sparse signal. By its very nature, the mapping between the measurement and sparse signal is a non-linear operation. Traditional support estimators rely on computationally expensive iterative signal recovery techniques to achieve such non-linearity. Contrary to the convolution layers, the proposed OSEN approach consists of operational layers that can learn such complex non-linearities without the need for deep networks. In this way, the performance of the non-iterative support estimation is greatly improved. Moreover, the operational layers comprise so-called generative \textit{super neurons} with non-local kernels. The kernel location for each neuron/feature map is optimized jointly for the SE task during the training. We evaluate the OSENs in three different applications: i. support estimation from Compressive Sensing (CS) measurements, ii. representation-based classification, and iii. learning-aided CS reconstruction where the output of OSENs is used as prior knowledge to the CS algorithm for an enhanced reconstruction. Experimental results show that the proposed approach achieves computational efficiency and outperforms competing methods, especially at low measurement rates by a significant margin. The software implementation is publicly shared at https://github.com/meteahishali/OSEN.
Authors: Raphael Schumann, Wanrong Zhu, Weixi Feng, Tsu-Jui Fu, Stefan Riezler, William Yang Wang
Incremental decision making in real-world environments is one of the most challenging tasks in embodied artificial intelligence. One particularly demanding scenario is Vision and Language Navigation~(VLN) which requires visual and natural language understanding as well as spatial and temporal reasoning capabilities. The embodied agent needs to ground its understanding of navigation instructions in observations of a real-world environment like Street View. Despite the impressive results of LLMs in other research areas, it is an ongoing problem of how to best connect them with an interactive visual environment. In this work, we propose VELMA, an embodied LLM agent that uses a verbalization of the trajectory and of visual environment observations as contextual prompt for the next action. Visual information is verbalized by a pipeline that extracts landmarks from the human written navigation instructions and uses CLIP to determine their visibility in the current panorama view. We show that VELMA is able to successfully follow navigation instructions in Street View with only two in-context examples. We further finetune the LLM agent on a few thousand examples and achieve 25%-30% relative improvement in task completion over the previous state-of-the-art for two datasets.
Authors: Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT). Current methods that still rely on ConvNet-based entropy coding are limited in long-range modeling dependencies due to their local connectivity and an increasing number of architectural biases and priors. On the contrary, the proposed ICT can capture both global and local contexts from the latent representations and better parameterize the distribution of the quantized latents. Further, we leverage a learnable scaling module with a sandwich ConvNeXt-based pre/post-processor to accurately extract more compact latent representation while reconstructing higher-quality images. Extensive experimental results on benchmark datasets showed that the proposed adaptive image compression transformer (AICT) framework significantly improves the trade-off between coding efficiency and decoder complexity over the versatile video coding (VVC) reference encoder (VTM-18.0) and the neural codec SwinT-ChARM.
Authors: Ke Fan, Changan Wang, Yabiao Wang, Chengjie Wang, Ran Yi, Lizhuang Ma
Glass-like objects are widespread in daily life but remain intractable to be segmented for most existing methods. The transparent property makes it difficult to be distinguished from background, while the tiny separation boundary further impedes the acquisition of their exact contour. In this paper, by revealing the key co-evolution demand of semantic and boundary learning, we propose a Selective Mutual Evolution (SME) module to enable the reciprocal feature learning between them. Then to exploit the global shape context, we propose a Structurally Attentive Refinement (SAR) module to conduct a fine-grained feature refinement for those ambiguous points around the boundary. Finally, to further utilize the multi-scale representation, we integrate the above two modules into a cascaded structure and then introduce a Reciprocal Feature Evolution Network (RFENet) for effective glass-like object segmentation. Extensive experiments demonstrate that our RFENet achieves state-of-the-art performance on three popular public datasets.
Authors: Hamed Amini Amirkolaee, Miaojing Shi, Mark Mulligan
Automatic tree density estimation and counting using single aerial and satellite images is a challenging task in photogrammetry and remote sensing, yet has an important role in forest management. In this paper, we propose the first semisupervised transformer-based framework for tree counting which reduces the expensive tree annotations for remote sensing images. Our method, termed as TreeFormer, first develops a pyramid tree representation module based on transformer blocks to extract multi-scale features during the encoding stage. Contextual attention-based feature fusion and tree density regressor modules are further designed to utilize the robust features from the encoder to estimate tree density maps in the decoder. Moreover, we propose a pyramid learning strategy that includes local tree density consistency and local tree count ranking losses to utilize unlabeled images into the training process. Finally, the tree counter token is introduced to regulate the network by computing the global tree counts for both labeled and unlabeled images. Our model was evaluated on two benchmark tree counting datasets, Jiangsu, and Yosemite, as well as a new dataset, KCL-London, created by ourselves. Our TreeFormer outperforms the state of the art semi-supervised methods under the same setting and exceeds the fully-supervised methods using the same number of labeled images. The codes and datasets are available at https://github.com/HAAClassic/TreeFormer.
Authors: Filip Pavičić
This paper presents an innovative approach to student identification during exams and knowledge tests, which overcomes the limitations of the traditional personal information entry method. The proposed method employs a matrix template on the designated section of the exam, where squares containing numbers are selectively blackened. The methodology involves the development of a neural network specifically designed for recognizing students' personal identification numbers. The neural network utilizes a specially adapted U-Net architecture, trained on an extensive dataset comprising images of blackened tables. The network demonstrates proficiency in recognizing the patterns and arrangement of blackened squares, accurately interpreting the information inscribed within them. Additionally, the model exhibits high accuracy in correctly identifying entered student personal numbers and effectively detecting erroneous entries within the table. This approach offers multiple advantages. Firstly, it significantly accelerates the exam marking process by automatically extracting identifying information from the blackened tables, eliminating the need for manual entry and minimizing the potential for errors. Secondly, the method automates the identification process, thereby reducing administrative effort and expediting data processing. The introduction of this innovative identification system represents a notable advancement in the field of exams and knowledge tests, replacing the conventional manual entry of personal data with a streamlined, efficient, and accurate identification process.
Authors: Jinglei Shi, Yihong Xu, Christine Guillemot
Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations. It offers a more immersive perception than classic 2D images but at the cost of huge data volume. In this paper, we draw inspiration from the visual characteristics of Sub-Aperture Images (SAIs) of light field and design a compact neural network representation for the light field compression task. The network backbone takes randomly initialized noise as input and is supervised on the SAIs of the target light field. It is composed of two types of complementary kernels: descriptive kernels (descriptors) that store scene description information learned during training, and modulatory kernels (modulators) that control the rendering of different SAIs from the queried perspectives. To further enhance compactness of the network meanwhile retain high quality of the decoded light field, we accordingly introduce modulator allocation and kernel tensor decomposition mechanisms, followed by non-uniform quantization and lossless entropy coding techniques, to finally form an efficient compression pipeline. Extensive experiments demonstrate that our method outperforms other state-of-the-art (SOTA) methods by a significant margin in the light field compression task. Moreover, after aligning descriptors, the modulators learned from one light field can be transferred to new light fields for rendering dense views, indicating a potential solution for view synthesis task.
Authors: Manuel Hetzel, Hannes Reichert, Günther Reitberger, Erich Fuchs, Konrad Doll, Bernhard Sick
Inner-city intersections are among the most critical traffic areas for injury and fatal accidents. Automated vehicles struggle with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can cooperate with vehicles, can benefit automated traffic by extending the perception capabilities of drivers and vehicle perception systems. Additionally, they offer the opportunity to gather reproducible and precise data of a holistic scene understanding, including context information as a basis for training algorithms for various applications in automated traffic. Therefore, we introduce the Infrastructural Multi-Person Trajectory and Context Dataset (IMPTC). We use an intelligent public inner-city intersection in Germany with visual sensor technology. A multi-view camera and LiDAR system perceives traffic situations and road users' behavior. Additional sensors monitor contextual information like weather, lighting, and traffic light signal status. The data acquisition system focuses on Vulnerable Road Users (VRUs) and multi-agent interaction. The resulting dataset consists of eight hours of measurement data. It contains over 2,500 VRU trajectories, including pedestrians, cyclists, e-scooter riders, strollers, and wheelchair users, and over 20,000 vehicle trajectories at different day times, weather conditions, and seasons. In addition, to enable the entire stack of research capabilities, the dataset includes all data, starting from the sensor-, calibration- and detection data until trajectory and context data. The dataset is continuously expanded and is available online for non-commercial research at https://github.com/kav-institute/imptc-dataset.
Authors: Gengyuan Zhang, Yurui Zhang, Kerui Zhang, Volker Tresp
Vision-Language Models (VLMs) are expected to be capable of reasoning with commonsense knowledge as human beings. One example is that humans can reason where and when an image is taken based on their knowledge. This makes us wonder if, based on visual cues, Vision-Language Models that are pre-trained with large-scale image-text resources can achieve and even outperform human's capability in reasoning times and location. To address this question, we propose a two-stage \recognition\space and \reasoning\space probing task, applied to discriminative and generative VLMs to uncover whether VLMs can recognize times and location-relevant features and further reason about it. To facilitate the investigation, we introduce WikiTiLo, a well-curated image dataset compromising images with rich socio-cultural cues. In the extensive experimental studies, we find that although VLMs can effectively retain relevant features in visual encoders, they still fail to make perfect reasoning. We will release our dataset and codes to facilitate future studies.
Authors: Manuel Hetzel, Hannes Reichert, Konrad Doll, Bernhard Sick
Complex inner-city junctions are among the most critical traffic areas for injury and fatal accidents. The development of highly automated driving (HAD) systems struggles with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can communicate and cooperate with vehicles, are essential to enable a holistic scene understanding to resolve occlusions drivers and vehicle perception systems for themselves can not cover. We introduce an intelligent research infrastructure equipped with visual sensor technology, located at a public inner-city junction in Aschaffenburg, Germany. A multiple-view camera system monitors the traffic situation to perceive road users' behavior. Both motorized and non-motorized traffic is considered. The system is used for research in data generation, evaluating new HAD sensors systems, algorithms, and Artificial Intelligence (AI) training strategies using real-, synthetic- and augmented data. In addition, the junction features a highly accurate digital twin. Real-world data can be taken into the digital twin for simulation purposes and synthetic data generation.
Authors: Lorenzo Li Lu, Giulia D'Ascenzi, Francesco Cappio Borlino, Tatiana Tommasi
Standard recognition approaches are unable to deal with novel categories at test time. Their overconfidence on the known classes makes the predictions unreliable for safety-critical applications such as healthcare or autonomous driving. Out-Of-Distribution (OOD) detection methods provide a solution by identifying semantic novelty. Most of these methods leverage a learning stage on the known data, which means training (or fine-tuning) a model to capture the concept of normality. This process is clearly sensitive to the amount of available samples and might be computationally expensive for on-board systems. A viable alternative is that of evaluating similarities in the embedding space produced by large pre-trained models without any further learning effort. We focus exactly on such a fine-tuning-free OOD detection setting. This works presents an in-depth analysis of the recently introduced relational reasoning pre-training and investigates the properties of the learned embedding, highlighting the existence of a correlation between the inter-class feature distance and the OOD detection accuracy. As the class separation depends on the chosen pre-training objective, we propose an alternative loss function to control the inter-class margin, and we show its advantage with thorough experiments.
Authors: Zhenrong Shen, Maosong Cao, Sheng Wang, Lichi Zhang, Qian Wang
Automatic examination of thin-prep cytologic test (TCT) slides can assist pathologists in finding cervical abnormality for accurate and efficient cancer screening. Current solutions mostly need to localize suspicious cells and classify abnormality based on local patches, concerning the fact that whole slide images of TCT are extremely large. It thus requires many annotations of normal and abnormal cervical cells, to supervise the training of the patch-level classifier for promising performance. In this paper, we propose CellGAN to synthesize cytopathological images of various cervical cell types for augmenting patch-level cell classification. Built upon a lightweight backbone, CellGAN is equipped with a non-linear class mapping network to effectively incorporate cell type information into image generation. We also propose the Skip-layer Global Context module to model the complex spatial relationship of the cells, and attain high fidelity of the synthesized images through adversarial learning. Our experiments demonstrate that CellGAN can produce visually plausible TCT cytopathological images for different cell types. We also validate the effectiveness of using CellGAN to greatly augment patch-level cell classification performance.
Authors: Robin Louiset, Edouard Duchesnay, Antoine Grigis, Benoit Dufumier, Pietro Gori
Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encoders (VAEs) that aims at separating the common factors of variation between a background dataset (BG) (i.e., healthy subjects) and a target dataset (TG) (i.e., patients) from the ones that only exist in the target dataset. To do so, these methods separate the latent space into a set of salient features (i.e., proper to the target dataset) and a set of common features (i.e., exist in both datasets). Currently, all models fail to prevent the sharing of information between latent spaces effectively and to capture all salient factors of variation. To this end, we introduce two crucial regularization losses: a disentangling term between common and salient representations and a classification term between background and target samples in the salient space. We show a better performance than previous CA-VAEs methods on three medical applications and a natural images dataset (CelebA). Code and datasets are available on GitHub https://github.com/neurospin-projects/2023_rlouiset_sepvae.
Authors: Benoit Brummer, Christophe De Vleeschouwer
Image noise is ubiquitous in photography. However, image noise is not compressible nor desirable, thus attempting to convey the noise in compressed image bitstreams yields sub-par results in both rate and distortion. We propose to explicitly learn the image denoising task when training a codec. Therefore, we leverage the Natural Image Noise Dataset, which offers a wide variety of scenes captured with various ISO numbers, leading to different noise levels, including insignificant ones. Given this training set, we supervise the codec with noisy-clean image pairs, and show that a single model trained based on a mixture of images with variable noise levels appears to yield best-in-class results with both noisy and clean images, achieving better rate-distortion than a compression-only model or even than a pair of denoising-then-compression models with almost one order of magnitude fewer GMac operations.
Authors: Pham Vu Hung, Nguyen Duy Manh, Nguyen Thi Oanh, Nguyen Thi Thuy, Dinh Viet Sang
Gastrointestinal endoscopy is a medical procedure that utilizes a flexible tube equipped with a camera and other instruments to examine the digestive tract. This minimally invasive technique allows for diagnosing and managing various gastrointestinal conditions, including inflammatory bowel disease, gastrointestinal bleeding, and colon cancer. The early detection and identification of lesions in the upper gastrointestinal tract and the identification of malignant polyps that may pose a risk of cancer development are critical components of gastrointestinal endoscopy's diagnostic and therapeutic applications. Therefore, enhancing the detection rates of gastrointestinal disorders can significantly improve a patient's prognosis by increasing the likelihood of timely medical intervention, which may prolong the patient's lifespan and improve overall health outcomes. This paper presents a novel Transformer-based deep neural network designed to perform multiple tasks simultaneously, thereby enabling accurate identification of both upper gastrointestinal tract lesions and colon polyps. Our approach proposes a unique global context-aware module and leverages the powerful MiT backbone, along with a feature alignment block, to enhance the network's representation capability. This novel design leads to a significant improvement in performance across various endoscopic diagnosis tasks. Extensive experiments demonstrate the superior performance of our method compared to other state-of-the-art approaches.
Authors: Ruipeng Ma, Jinhao Duan, Fei Kong, Xiaoshuang Shi, Kaidi Xu
Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, there is a dearth of research dedicated to detecting diffusion-generated images, which could pose potential security and privacy risks. This paper addresses this gap by proposing a novel detection method called Stepwise Error for Diffusion-generated Image Detection (SeDID). Comprising statistical-based $\text{SeDID}_{\text{Stat}}$ and neural network-based $\text{SeDID}_{\text{NNs}}$, SeDID exploits the unique attributes of diffusion models, namely deterministic reverse and deterministic denoising computation errors. Our evaluations demonstrate SeDID's superior performance over existing methods when applied to diffusion models. Thus, our work makes a pivotal contribution to distinguishing diffusion model-generated images, marking a significant step in the domain of artificial intelligence security.
Authors: Florian Schiffers, Praneeth Chakravarthula, Nathan Matsuda, Grace Kuo, Ethan Tseng, Douglas Lanman, Felix Heide, Oliver Cossairt
The Visual Turing Test is the ultimate goal to evaluate the realism of holographic displays. Previous studies have focused on addressing challenges such as limited \'etendue and image quality over a large focal volume, but they have not investigated the effect of pupil sampling on the viewing experience in full 3D holograms. In this work, we tackle this problem with a novel hologram generation algorithm motivated by matching the projection operators of incoherent Light Field and coherent Wigner Function light transport. To this end, we supervise hologram computation using synthesized photographs, which are rendered on-the-fly using Light Field refocusing from stochastically sampled pupil states during optimization. The proposed method produces holograms with correct parallax and focus cues, which are important for passing the Visual Turing Test. We validate that our approach compares favorably to state-of-the-art CGH algorithms that use Light Field and Focal Stack supervision. Our experiments demonstrate that our algorithm significantly improves the realism of the viewing experience for a variety of different pupil states.
Authors: Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, Kai Chen, Dahua Lin
Large vision-language models have recently achieved remarkable progress, exhibiting great perception and reasoning abilities concerning visual information. However, how to effectively evaluate these large vision-language models remains a major obstacle, hindering future model development. Traditional benchmarks like VQAv2 or COCO Caption provide quantitative performance measurements but suffer from a lack of fine-grained ability assessment and non-robust evaluation metrics. Recent subjective benchmarks, such as OwlEval, offer comprehensive evaluations of a model's abilities by incorporating human labor, but they are not scalable and display significant bias. In response to these challenges, we propose MMBench, a novel multi-modality benchmark. MMBench methodically develops a comprehensive evaluation pipeline, primarily comprised of two elements. The first element is a meticulously curated dataset that surpasses existing similar benchmarks in terms of the number and variety of evaluation questions and abilities. The second element introduces a novel CircularEval strategy and incorporates the use of ChatGPT. This implementation is designed to convert free-form predictions into pre-defined choices, thereby facilitating a more robust evaluation of the model's predictions. MMBench is a systematically-designed objective benchmark for robustly evaluating the various abilities of vision-language models. We hope MMBench will assist the research community in better evaluating their models and encourage future advancements in this domain. Project page: https://opencompass.org.cn/mmbench.
Authors: Shengchun Wang, Wencheng Wang, Fei Hou
Image smoothing is by reducing pixel-wise gradients to smooth out details. As existing methods always rely on gradients to determine smoothing manners, it is difficult to distinguish structures and details to handle distinctively due to the overlapped ranges of gradients for structures and details. Thus, it is still challenging to achieve high-quality results, especially on preserving weak structures and removing high-contrast details. In this paper, we address this challenge by improving the real-time optimization-based method via iterative least squares (called ILS). We observe that 1) ILS uses gradients as the independent variable in its penalty function for determining smoothing manners, and 2) the framework of ILS can still work for image smoothing when we use some values instead of gradients in the penalty function. Thus, corresponding to the properties of pixels on structures or not, we compute some values to use in the penalty function to determine smoothing manners, and so we can handle structures and details distinctively, no matter whether their gradients are high or low. As a result, we can conveniently remove high-contrast details while preserving weak structures. Moreover, such values can be adjusted to accelerate optimization computation, so that we can use fewer iterations than the original ILS method for efficiency. This also reduces the changes onto structures to help structure preservation. Experimental results show our advantages over existing methods on efficiency and quality.
Authors: Mostafa Dehghani, Basil Mustafa, Josip Djolonga, Jonathan Heek, Matthias Minderer, Mathilde Caron, Andreas Steiner, Joan Puigcerver, Robert Geirhos, Ibrahim Alabdulmohsin, Avital Oliver, Piotr Padlewski, Alexey Gritsenko, Mario Lučić, Neil Houlsby
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT) offer flexible sequence-based modeling, and hence varying input sequence lengths. We take advantage of this with NaViT (Native Resolution ViT) which uses sequence packing during training to process inputs of arbitrary resolutions and aspect ratios. Alongside flexible model usage, we demonstrate improved training efficiency for large-scale supervised and contrastive image-text pretraining. NaViT can be efficiently transferred to standard tasks such as image and video classification, object detection, and semantic segmentation and leads to improved results on robustness and fairness benchmarks. At inference time, the input resolution flexibility can be used to smoothly navigate the test-time cost-performance trade-off. We believe that NaViT marks a departure from the standard, CNN-designed, input and modelling pipeline used by most computer vision models, and represents a promising direction for ViTs.
Authors: Ariel Elazary, Yotam Nitzan, Daniel Cohen-Or
In recent years, the role of image generative models in facial reenactment has been steadily increasing. Such models are usually subject-agnostic and trained on domain-wide datasets. The appearance of the reenacted individual is learned from a single image, and hence, the entire breadth of the individual's appearance is not entirely captured, leading these methods to resort to unfaithful hallucination. Thanks to recent advancements, it is now possible to train a personalized generative model tailored specifically to a given individual. In this paper, we propose a novel method for facial reenactment using a personalized generator. We train the generator using frames from a short, yet varied, self-scan video captured using a simple commodity camera. Images synthesized by the personalized generator are guaranteed to preserve identity. The premise of our work is that the task of reenactment is thus reduced to accurately mimicking head poses and expressions. To this end, we locate the desired frames in the latent space of the personalized generator using carefully designed latent optimization. Through extensive evaluation, we demonstrate state-of-the-art performance for facial reenactment. Furthermore, we show that since our reenactment takes place in a semantic latent space, it can be semantically edited and stylized in post-processing.
Authors: Shengbo Gao, Ziji Zhang, Jiechao Ma, Zihao Li, Shu Zhang
Semi-supervised learning has become increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation methods only focus on extracting information from unlabeled data, disregarding the potential of labeled data to further improve the performance of the model. In this paper, we propose a novel Correlation Aware Mutual Learning (CAML) framework that leverages labeled data to guide the extraction of information from unlabeled data. Our approach is based on a mutual learning strategy that incorporates two modules: the Cross-sample Mutual Attention Module (CMA) and the Omni-Correlation Consistency Module (OCC). The CMA module establishes dense cross-sample correlations among a group of samples, enabling the transfer of label prior knowledge to unlabeled data. The OCC module constructs omni-correlations between the unlabeled and labeled datasets and regularizes dual models by constraining the omni-correlation matrix of each sub-model to be consistent. Experiments on the Atrial Segmentation Challenge dataset demonstrate that our proposed approach outperforms state-of-the-art methods, highlighting the effectiveness of our framework in medical image segmentation tasks. The codes, pre-trained weights, and data are publicly available.
Authors: Kishan Govind, Daniela Oliveros, Antonin Dlouhy, Marc Legros, Stefan Sandfeld
Crystalline defects, such as line-like dislocations, play an important role for the performance and reliability of many metallic devices. Their interaction and evolution still poses a multitude of open questions to materials science and materials physics. In-situ TEM experiments can provide important insights into how dislocations behave and move. During such experiments, the dislocation microstructure is captured in form of videos. The analysis of individual video frames can provide useful insights but is limited by the capabilities of automated identification, digitization, and quantitative extraction of the dislocations as curved objects. The vast amount of data also makes manual annotation very time consuming, thereby limiting the use of Deep Learning-based, automated image analysis and segmentation of the dislocation microstructure. In this work, a parametric model for generating synthetic training data for segmentation of dislocations is developed. Even though domain scientists might dismiss synthetic training images sometimes as too artificial, our findings show that they can result in superior performance, particularly regarding the generalizing of the Deep Learning models with respect to different microstructures and imaging conditions. Additionally, we propose an enhanced deep learning method optimized for segmenting overlapping or intersecting dislocation lines. Upon testing this framework on four distinct real datasets, we find that our synthetic training data are able to yield high-quality results also on real images-even more so if fine-tune on a few real images was done.
Authors: Tony Bonnaire, Aurélien Decelle, Nabila Aghanim
A regularized version of Mixture Models is proposed to learn a principal graph from a distribution of $D$-dimensional data points. In the particular case of manifold learning for ridge detection, we assume that the underlying manifold can be modeled as a graph structure acting like a topological prior for the Gaussian clusters turning the problem into a maximum a posteriori estimation. Parameters of the model are iteratively estimated through an Expectation-Maximization procedure making the learning of the structure computationally efficient with guaranteed convergence for any graph prior in a polynomial time. We also embed in the formalism a natural way to make the algorithm robust to outliers of the pattern and heteroscedasticity of the manifold sampling coherently with the graph structure. The method uses a graph prior given by the minimum spanning tree that we extend using random sub-samplings of the dataset to take into account cycles that can be observed in the spatial distribution.
Authors: Gregory Plumb, Nari Johnson, Ángel Alexander Cabrera, Ameet Talwalkar
A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable concept) subsets of the data where an image classifier performs significantly worse. Motivated by observed gaps in prior work, we introduce a new framework for evaluating BDMs, SpotCheck, that uses synthetic image datasets to train models with known blindspots and a new BDM, PlaneSpot, that uses a 2D image representation. We use SpotCheck to run controlled experiments that identify factors that influence BDM performance (e.g., the number of blindspots in a model, or features used to define the blindspot) and show that PlaneSpot is competitive with and in many cases outperforms existing BDMs. Importantly, we validate these findings by designing additional experiments that use real image data from MS-COCO, a large image benchmark dataset. Our findings suggest several promising directions for future work on BDM design and evaluation. Overall, we hope that the methodology and analyses presented in this work will help facilitate a more rigorous science of blindspot discovery.
Authors: Anjun Chen, Xiangyu Wang, Kun Shi, Shaohao Zhu, Bin Fang, Yingfeng Chen, Jiming Chen, Yuchi Huo, Qi Ye
3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementary, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough weather. However, combining RGB and mmWave signals for robust all-weather 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images. In this paper, we present ImmFusion, the first mmWave-RGB fusion solution to reconstruct 3D human bodies in all weather conditions robustly. Specifically, our ImmFusion consists of image and point backbones for token feature extraction and a Transformer module for token fusion. The image and point backbones refine global and local features from original data, and the Fusion Transformer Module aims for effective information fusion of two modalities by dynamically selecting informative tokens. Extensive experiments on a large-scale dataset, mmBody, captured in various environments demonstrate that ImmFusion can efficiently utilize the information of two modalities to achieve a robust 3D human body reconstruction in all weather conditions. In addition, our method's accuracy is significantly superior to that of state-of-the-art Transformer-based LiDAR-camera fusion methods.
Authors: Keita Mason, Joshua Knights, Milad Ramezani, Peyman Moghadam, Dimity Miller
State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments. To address this issue, we investigate the task of uncertainty-aware lidar place recognition, where each predicted place must have an associated uncertainty that can be used to identify and reject incorrect predictions. We introduce a novel evaluation protocol and present the first comprehensive benchmark for this task, testing across five uncertainty estimation techniques and three large-scale datasets. Our results show that an Ensembles approach is the highest performing technique, consistently improving the performance of lidar place recognition and uncertainty estimation in novel environments, though it incurs a computational cost. Code is publicly available at https://github.com/csiro-robotics/Uncertainty-LPR.
Authors: Kangning Liu, Weicheng Zhu, Yiqiu Shen, Sheng Liu, Narges Razavian, Krzysztof J. Geras, Carlos Fernandez-Granda
Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning (CSSL), which learns to push apart representations corresponding to two different randomly-selected instances. Unfortunately, in real-world applications such as medical image classification, there is often class imbalance, so randomly-selected instances mostly belong to the same majority class, which precludes CSSL from learning inter-class differences. To address this issue, we propose a novel framework, Iterative Self-paced Supervised Contrastive Learning for MIL Representations (ItS2CLR), which improves the learned representation by exploiting instance-level pseudo labels derived from the bag-level labels. The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels. We evaluate ItS2CLR on three medical datasets, showing that it improves the quality of instance-level pseudo labels and representations, and outperforms existing MIL methods in terms of both bag and instance level accuracy. Code is available at https://github.com/Kangningthu/ItS2CLR
Authors: David Rapado Rincon, Eldert J. van Henten, Gert Kootstra
The ability to accurately represent and localise relevant objects is essential for robots to carry out tasks effectively. Traditional approaches, where robots simply capture an image, process that image to take an action, and then forget the information, have proven to struggle in the presence of occlusions. Methods using multi-view perception, which have the potential to address some of these problems, require a world model that guides the collection, integration and extraction of information from multiple viewpoints. Furthermore, constructing a generic representation that can be applied in various environments and tasks is a difficult challenge. In this paper, a novel approach for building generic representations in occluded agro-food environments using multi-view perception and 3D multi-object tracking is introduced. The method is based on a detection algorithm that generates partial point clouds for each detected object, followed by a 3D multi-object tracking algorithm that updates the representation over time. The accuracy of the representation was evaluated in a real-world environment, where successful representation and localisation of tomatoes in tomato plants were achieved, despite high levels of occlusion, with the total count of tomatoes estimated with a maximum error of 5.08% and the tomatoes tracked with an accuracy up to 71.47%. Novel tracking metrics were introduced, demonstrating that valuable insight into the errors in localising and representing the fruits can be provided by their use. This approach presents a novel solution for building representations in occluded agro-food environments, demonstrating potential to enable robots to perform tasks effectively in these challenging environments.
Authors: Junlin Han, Huangying Zhan, Jie Hong, Pengfei Fang, Hongdong Li, Lars Petersson, Ian Reid
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence. Firstly, we propose a self-supervised machine memory quantification pipeline, dubbed ``MachineMem measurer'', to collect machine memorability scores of images. Similar to humans, machines also tend to memorize certain kinds of images, whereas the types of images that machines and humans memorize are different. Through in-depth analysis and comprehensive visualizations, we gradually unveil that``complex" images are usually more memorable to machines. We further conduct extensive experiments across 11 different machines (from linear classifiers to modern ViTs) and 9 pre-training methods to analyze and understand machine memory. This work proposes the concept of machine memorability and opens a new research direction at the interface between machine memory and visual data.
Authors: Rongqin Liang, Yuanman Li, Jiantao Zhou, Xia Li
The pedestrian trajectory prediction task is an essential component of intelligent systems. Its applications include but are not limited to autonomous driving, robot navigation, and anomaly detection of monitoring systems. Due to the diversity of motion behaviors and the complex social interactions among pedestrians, accurately forecasting their future trajectory is challenging. Existing approaches commonly adopt GANs or CVAEs to generate diverse trajectories. However, GAN-based methods do not directly model data in a latent space, which may make them fail to have full support over the underlying data distribution; CVAE-based methods optimize a lower bound on the log-likelihood of observations, which may cause the learned distribution to deviate from the underlying distribution. The above limitations make existing approaches often generate highly biased or inaccurate trajectories. In this paper, we propose a novel generative flow based framework with dual graphormer for pedestrian trajectory prediction (STGlow). Different from previous approaches, our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors. Besides, our method has clear physical meanings for simulating the evolution of human motion behaviors. The forward process of the flow gradually degrades complex motion behavior into simple behavior, while its reverse process represents the evolution of simple behavior into complex motion behavior. Further, we introduce a dual graphormer combining with the graph structure to more adequately model the temporal dependencies and the mutual spatial interactions. Experimental results on several benchmarks demonstrate that our method achieves much better performance compared to previous state-of-the-art approaches.
Authors: Jiahang Zhang, Lilang Lin, Jiaying Liu
Contrastive learning has been proven beneficial for self-supervised skeleton-based action recognition. Most contrastive learning methods utilize carefully designed augmentations to generate different movement patterns of skeletons for the same semantics. However, it is still a pending issue to apply strong augmentations, which distort the images/skeletons' structures and cause semantic loss, due to their resulting unstable training. In this paper, we investigate the potential of adopting strong augmentations and propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition. Specifically, we first design a gradual growing augmentation policy to generate multiple ordered positive pairs, which guide to achieve the consistency of the learned representation from different views. Then, an asymmetric loss is proposed to enforce the hierarchical consistency via a directional clustering operation in the feature space, pulling the representations from strongly augmented views closer to those from weakly augmented views for better generalizability. Meanwhile, we propose and evaluate three kinds of strong augmentations for 3D skeletons to demonstrate the effectiveness of our method. Extensive experiments show that HiCLR outperforms the state-of-the-art methods notably on three large-scale datasets, i.e., NTU60, NTU120, and PKUMMD.
Authors: Tuomo Valkonen
Point source localisation is generally modelled as a Lasso-type problem on measures. However, optimisation methods in non-Hilbert spaces, such as the space of Radon measures, are much less developed than in Hilbert spaces. Most numerical algorithms for point source localisation are based on the Frank-Wolfe conditional gradient method, for which ad hoc convergence theory is developed. We develop extensions of proximal-type methods to spaces of measures. This includes forward-backward splitting, its inertial version, and primal-dual proximal splitting. Their convergence proofs follow standard patterns. We demonstrate their numerical efficacy.
Authors: A. T. Gifford, B. Lahner, S. Saba-Sadiya, M. G. Vilas, A. Lascelles, A. Oliva, K. Kay, G. Roig, R. M. Cichy
The sciences of biological and artificial intelligence are ever more intertwined. Neural computational principles inspire new intelligent machines, which are in turn used to advance theoretical understanding of the brain. To promote further exchange of ideas and collaboration between biological and artificial intelligence researchers, we introduce the 2023 installment of the Algonauts Project challenge: How the Human Brain Makes Sense of Natural Scenes (this http URL). This installment prompts the fields of artificial and biological intelligence to come together towards building computational models of the visual brain using the largest and richest dataset of fMRI responses to visual scenes, the Natural Scenes Dataset (NSD). NSD provides high-quality fMRI responses to ~73,000 different naturalistic colored scenes, making it the ideal candidate for data-driven model building approaches promoted by the 2023 challenge. The challenge is open to all and makes results directly comparable and transparent through a public leaderboard automatically updated after each submission, thus allowing for rapid model development. We believe that the 2023 installment will spark symbiotic collaborations between biological and artificial intelligence scientists, leading to a deeper understanding of the brain through cutting-edge computational models and to novel ways of engineering artificial intelligent agents through inductive biases from biological systems.
Authors: Pasquale Lafiosca, Ip-Shing Fan, Nicolas P. Avdelidis
Aircraft maintenance, repair and overhaul industry is gradually switching to 3D scanning for dent inspection. High-accuracy devices allow quick and repeatable measurements, which translate into efficient reporting and more objective damage evaluations. However, the potential of 3D scanners is far from being exploited. This is due to the traditional way in which the structural repair manual deals with dents, that is, considering length, width and depth as the only relevant measures. Being equivalent to describing a dent similarly to a box, the current approach discards any information about the actual shape. This causes high degrees of ambiguity, with very different shapes (and corresponding fatigue life) being classified as the same, and nullifies the effort of acquiring such great amount of information from high-accuracy 3D scanners. In this paper a 7-parameter model is proposed to describe the actual dent shape, thus enabling the exploitation of the high fidelity data produced by 3D scanners. The compact set of values can then be compared against historical data and structural evaluations based on the same model. The proposed approach has been evaluated in both simulations and point cloud data generated by 8tree's dentCHECK tool, suggesting increased capability to evaluate damage, enabling more targeted interventions and, ultimately, saving costs.
Authors: Pei Xu, Jean-Bernard Hayet, Ioannis Karamouzas
Real-time, accurate prediction of human steering behaviors has wide applications, from developing intelligent traffic systems to deploying autonomous driving systems in both real and simulated worlds. In this paper, we present ContextVAE, a context-aware approach for multi-modal vehicle trajectory prediction. Built upon the backbone architecture of a timewise variational autoencoder, ContextVAE observation encoding employs a dual attention mechanism that accounts for the environmental context and the dynamic agents' states, in a unified way. By utilizing features extracted from semantic maps during agent state encoding, our approach takes into account both the social features exhibited by agents on the scene and the physical environment constraints to generate map-compliant and socially-aware trajectories. We perform extensive testing on the nuScenes prediction challenge, Lyft Level 5 dataset and Waymo Open Motion Dataset to show the effectiveness of our approach and its state-of-the-art performance. In all tested datasets, ContextVAE models are fast to train and provide high-quality multi-modal predictions in real-time. Our code is available at: https://github.com/xupei0610/ContextVAE.
Authors: Srikar Yellapragada, Zhenghong Li, Kevin Bhadresh Doshi, Purva Makarand Mhasakar, Heng Fan, Jie Wei, Erik Blasch, Bin Zhang, Haibin Ling
Gun violence is a critical security problem, and it is imperative for the computer vision community to develop effective gun detection algorithms for real-world scenarios, particularly in Closed Circuit Television (CCTV) surveillance data. Despite significant progress in visual object detection, detecting guns in real-world CCTV images remains a challenging and under-explored task. Firearms, especially handguns, are typically very small in size, non-salient in appearance, and often severely occluded or indistinguishable from other small objects. Additionally, the lack of principled benchmarks and difficulty collecting relevant datasets further hinder algorithmic development. In this paper, we present a meticulously crafted and annotated benchmark, called \textbf{CCTV-Gun}, which addresses the challenges of detecting handguns in real-world CCTV images. Our contribution is three-fold. Firstly, we carefully select and analyze real-world CCTV images from three datasets, manually annotate handguns and their holders, and assign each image with relevant challenge factors such as blur and occlusion. Secondly, we propose a new cross-dataset evaluation protocol in addition to the standard intra-dataset protocol, which is vital for gun detection in practical settings. Finally, we comprehensively evaluate both classical and state-of-the-art object detection algorithms, providing an in-depth analysis of their generalizing abilities. The benchmark will facilitate further research and development on this topic and ultimately enhance security. Code, annotations, and trained models are available at https://github.com/srikarym/CCTV-Gun.
Authors: Jiawei Wang, Weihong Lin, Chixiang Ma, Mingze Li, Zheng Sun, Lei Sun, Qiang Huo
We present a new table structure recognition (TSR) approach, called TSRFormer, to robustly recognizing the structures of complex tables with geometrical distortions from various table images. Unlike previous methods, we formulate table separation line prediction as a line regression problem instead of an image segmentation problem and propose a new two-stage dynamic queries enhanced DETR based separation line regression approach, named DQ-DETR, to predict separation lines from table images directly. Compared to Vallina DETR, we propose three improvements in DQ-DETR to make the two-stage DETR framework work efficiently and effectively for the separation line prediction task: 1) A new query design, named Dynamic Query, to decouple single line query into separable point queries which could intuitively improve the localization accuracy for regression tasks; 2) A dynamic queries based progressive line regression approach to progressively regressing points on the line which further enhances localization accuracy for distorted tables; 3) A prior-enhanced matching strategy to solve the slow convergence issue of DETR. After separation line prediction, a simple relation network based cell merging module is used to recover spanning cells. With these new techniques, our TSRFormer achieves state-of-the-art performance on several benchmark datasets, including SciTSR, PubTabNet, WTW and FinTabNet. Furthermore, we have validated the robustness and high localization accuracy of our approach to tables with complex structures, borderless cells, large blank spaces, empty or spanning cells as well as distorted or even curved shapes on a more challenging real-world in-house dataset.
Authors: Minghan Li, Lei Zhang
It is expensive and labour-extensive to label the pixel-wise object masks in a video. As a result, the amount of pixel-wise annotations in existing video instance segmentation (VIS) datasets is small, limiting the generalization capability of trained VIS models. An alternative but much cheaper solution is to use bounding boxes to label instances in videos. Inspired by the recent success of box-supervised image instance segmentation, we adapt the state-of-the-art pixel-supervised VIS models to a box-supervised VIS (BoxVIS) baseline, and observe slight performance degradation. We consequently propose to improve the BoxVIS performance from two aspects. First, we propose a box-center guided spatial-temporal pairwise affinity (STPA) loss to predict instance masks for better spatial and temporal consistency. Second, we collect a larger scale box-annotated VIS dataset (BVISD) by consolidating the videos from current VIS benchmarks and converting images from the COCO dataset to short pseudo video clips. With the proposed BVISD and the STPA loss, our trained BoxVIS model achieves 43.2\% and 29.0\% mask AP on the YouTube-VIS 2021 and OVIS valid sets, respectively. It exhibits comparable instance mask prediction performance and better generalization ability than state-of-the-art pixel-supervised VIS models by using only 16\% of their annotation time and cost. Codes and data can be found at \url{https://github.com/MinghanLi/BoxVIS}.
Authors: Hoel Kervadec, Marleen de Bruijne
In the past few years, in the context of fully-supervised semantic segmentation, several losses -- such as cross-entropy and dice -- have emerged as de facto standards to supervise neural networks. The Dice loss is an interesting case, as it comes from the relaxation of the popular Dice coefficient; one of the main evaluation metric in medical imaging applications. In this paper, we first study theoretically the gradient of the dice loss, showing that concretely it is a weighted negative of the ground truth, with a very small dynamic range. This enables us, in the second part of this paper, to mimic the supervision of the dice loss, through a simple element-wise multiplication of the network output with a negative of the ground truth. This rather surprising result sheds light on the practical supervision performed by the dice loss during gradient descent. This can help the practitioner to understand and interpret results while guiding researchers when designing new losses.
Authors: Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, Yong Jae Lee
In this work, we present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image, as shown in Fig.1. In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs). More specifically, SEEM is designed with four desiderata: i) Versatility. We introduce a new visual prompt to unify different spatial queries including points, boxes, scribbles and masks, which can further generalize to a different referring image; ii) Compositionality. We learn a joint visual-semantic space between text and visual prompts, which facilitates the dynamic composition of two prompt types required for various segmentation tasks; iii) Interactivity. We further incorporate learnable memory prompts into the decoder to retain segmentation history through mask-guided cross-attention from decoder to image features; and iv) Semantic-awareness. We use a text encoder to encode text queries and mask labels into the same semantic space for open-vocabulary segmentation. We conduct a comprehensive empirical study to validate the effectiveness of SEEM across diverse segmentation tasks. Notably, our single SEEM model achieves competitive performance across interactive segmentation, generic segmentation, referring segmentation, and video object segmentation on 9 datasets with minimum 1/100 supervision. Furthermore, SEEM showcases a remarkable capacity for generalization to novel prompts or their combinations, rendering it a readily universal image segmentation interface.
Authors: Yannick Schnider, Stanislaw Wozniak, Mathias Gehrig, Jules Lecomte, Axel von Arnim, Luca Benini, Davide Scaramuzza, Angeliki Pantazi
Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their complexity is often prohibitive for application at the edge or in robots, where efficiency and latency play crucial role. To address this challenge, we build on the latest developments in event-based vision and spiking neural networks. We propose a new network architecture, inspired by Timelens, that improves the state-of-the-art self-supervised optical flow accuracy when operated both in spiking and non-spiking mode. To implement a real-time pipeline with a physical event camera, we propose a methodology for principled model simplification based on activity and latency analysis. We demonstrate high speed optical flow prediction with almost two orders of magnitude reduced complexity while maintaining the accuracy, opening the path for real-time deployments.
Authors: Jiaxi Yang, Wenglong Deng, Benlin Liu, Yangsibo Huang, Xiaoxiao Li
Data valuation is critical in machine learning, as it helps enhance model transparency and protect data properties. Existing data valuation methods have primarily focused on discriminative models, neglecting deep generative models that have recently gained considerable attention. Similar to discriminative models, there is an urgent need to assess data contributions in deep generative models as well. However, previous data valuation approaches mainly relied on discriminative model performance metrics and required model retraining. Consequently, they cannot be applied directly and efficiently to recent deep generative models, such as generative adversarial networks and diffusion models, in practice. To bridge this gap, we formulate the data valuation problem in generative models from a similarity-matching perspective. Specifically, we introduce Generative Model Valuator (GMValuator), the first model-agnostic approach for any generative models, designed to provide data valuation for generation tasks. We have conducted extensive experiments to demonstrate the effectiveness of the proposed method. To the best of their knowledge, GMValuator is the first work that offers a training-free, post-hoc data valuation strategy for deep generative models.
Authors: Grigory Solomatov, Derya Akkaynak
A number of problems in computer vision and related fields would be mitigated if camera spectral sensitivities were known. As consumer cameras are not designed for high-precision visual tasks, manufacturers do not disclose spectral sensitivities. Their estimation requires a costly optical setup, which triggered researchers to come up with numerous indirect methods that aim to lower cost and complexity by using color targets. However, the use of color targets gives rise to new complications that make the estimation more difficult, and consequently, there currently exists no simple, low-cost, robust go-to method for spectral sensitivity estimation. Furthermore, even if not limited by hardware or cost, researchers frequently work with imagery from multiple cameras that they do not have in their possession. To provide a practical solution to this problem, we propose a framework for spectral sensitivity estimation that not only does not require any hardware, but also does not require physical access to the camera itself. Similar to other work, we formulate an optimization problem that minimizes a two-term objective function: a camera-specific term from a system of equations, and a universal term that bounds the solution space. Different than other work, we use publicly available high-quality calibration data to construct both terms. We use the colorimetric mapping matrices provided by the Adobe DNG Converter to formulate the camera-specific system of equations, and constrain the solutions using an autoencoder trained on a database of ground-truth curves. On average, we achieve reconstruction errors as low as those that can arise due to manufacturing imperfections between two copies of the same camera. We provide our code and predicted sensitivities for 1,000+ cameras, and discuss which tasks can become trivial when camera responses are available.
Authors: Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the ML ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing the resulting model on 38 downstream test sets. Our benchmark consists of multiple compute scales spanning four orders of magnitude, which enables the study of scaling trends and makes the benchmark accessible to researchers with varying resources. Our baseline experiments show that the DataComp workflow leads to better training sets. In particular, our best baseline, DataComp-1B, enables training a CLIP ViT-L/14 from scratch to 79.2% zero-shot accuracy on ImageNet, outperforming OpenAI's CLIP ViT-L/14 by 3.7 percentage points while using the same training procedure and compute. We release DataComp and all accompanying code at www.datacomp.ai.
Authors: Haram Choi, Cheolwoong Na, Jihyeon Oh, Seungjae Lee, Jinseop Kim, Subeen Choe, Jeongmin Lee, Taehoon Kim, Jihoon Yang
Although many recent works have made advancements in the image restoration (IR) field, they often suffer from an excessive number of parameters. Another issue is that most Transformer-based IR methods focus only on either local or global features, leading to limited receptive fields or deficient parameter issues. To address these problems, we propose a lightweight IR network, Reciprocal Attention Mixing Transformer (RAMiT). It employs our proposed dimensional reciprocal attention mixing Transformer (D-RAMiT) blocks, which compute bi-dimensional (spatial and channel) self-attentions in parallel with different numbers of multi-heads. The bi-dimensional attentions help each other to complement their counterpart's drawbacks and are then mixed. Additionally, we introduce a hierarchical reciprocal attention mixing (H-RAMi) layer that compensates for pixel-level information losses and utilizes semantic information while maintaining an efficient hierarchical structure. Furthermore, we revisit and modify MobileNet V1 and V2 to attach efficient convolutions to our proposed components. The experimental results demonstrate that RAMiT achieves state-of-the-art performance on multiple lightweight IR tasks, including super-resolution, color denoising, grayscale denoising, low-light enhancement, and deraining. Codes are available at https://github.com/rami0205/RAMiT.
Authors: Rohit Khorana
It is increasingly common for satellites to lose connection with the ground stations on Earth with which they communicate, due to signal interruptions from the Earth's ionosphere and magnetosphere. Given the important roles that satellites play in national defense, public safety, and worldwide communications, finding ways to determine satellite trajectories in such situations is a crucially important task. In this paper, we demonstrate the efficacy of a novel computer vision based approach, which relies on earth imagery taken by the satellite itself, to determine the orbit of a satellite that has lost contact with its ground stations. We empirically observe significant improvements by more than an order of magnitude, over the present state of the art approach, namely, the Gibbs method for an initial orbit estimate with the Kalman filter for differential error correction. We further investigate the performance of the approach by comparing various neural networks, namely, ResNet50, ResNet101, VGG19, VGG16, AlexNet, and CoAtNet4.
Authors: Yukun Huang, Jianan Wang, Ailing Zeng, He Cao, Xianbiao Qi, Yukai Shi, Zheng-Jun Zha, Lei Zhang
We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. While recent methods have shown encouraging results for text-to-3D generation of common objects, creating high-quality and animatable 3D avatars remains challenging. To create high-quality 3D avatars, DreamWaltz proposes 3D-consistent occlusion-aware Score Distillation Sampling (SDS) to optimize implicit neural representations with canonical poses. It provides view-aligned supervision via 3D-aware skeleton conditioning which enables complex avatar generation without artifacts and multiple faces. For animation, our method learns an animatable and generalizable avatar representation which could map arbitrary poses to the canonical pose representation. Extensive evaluations demonstrate that DreamWaltz is an effective and robust approach for creating 3D avatars that can take on complex shapes and appearances as well as novel poses for animation. The proposed framework further enables the creation of complex scenes with diverse compositions, including avatar-avatar, avatar-object and avatar-scene interactions. See https://dreamwaltz3d.github.io/ for more vivid 3D avatar and animation results.
Authors: Zhisheng Wang, Yue Liu, Shunli Wang, Xingyuan Bian, Zongfeng Li, Junning Cui
This paper is to investigate the high-quality analytical reconstructions of multiple source-translation computed tomography (mSTCT) under an extended field of view (FOV). Under the larger FOVs, the previously proposed backprojection filtration (BPF) algorithms for mSTCT, including D-BPF and S-BPF (their differences are different derivate directions along the detector and source, respectively), make some errors and artifacts in the reconstructed images due to a backprojection weighting factor and the half-scan mode, which deviates from the intention of mSTCT imaging. In this paper, to achieve reconstruction with as little error as possible under the extremely extended FOV, we combine the full-scan mSTCT (F-mSTCT) geometry with the previous BPF algorithms to study the performance and derive a suitable redundancy-weighted function for F-mSTCT. The experimental results indicate FS-BPF can get high-quality, stable images under the extremely extended FOV of imaging a large object, though it requires more projections than FD-BPF. Finally, for different practical requirements in extending FOV imaging, we give suggestions on algorithm selection.
Authors: Julian Moosmann, Marco Giordano, Christian Vogt, Michele Magno
This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180fps and an ultra-low energy consumption of only 196{\mu}J per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper.
Authors: Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
The astounding performance of transformers in natural language processing (NLP) has motivated researchers to explore their applications in computer vision tasks. DEtection TRansformer (DETR) introduces transformers to object detection tasks by reframing detection as a set prediction problem. Consequently, eliminating the need for proposal generation and post-processing steps. Initially, despite competitive performance, DETR suffered from slow training convergence and ineffective detection of smaller objects. However, numerous improvements are proposed to address these issues, leading to substantial improvements in DETR and enabling it to exhibit state-of-the-art performance. To our knowledge, this is the first paper to provide a comprehensive review of 21 recently proposed advancements in the original DETR model. We dive into both the foundational modules of DETR and its recent enhancements, such as modifications to the backbone structure, query design strategies, and refinements to attention mechanisms. Moreover, we conduct a comparative analysis across various detection transformers, evaluating their performance and network architectures. We hope that this study will ignite further interest among researchers in addressing the existing challenges and exploring the application of transformers in the object detection domain. Readers interested in the ongoing developments in detection transformers can refer to our website at: https://github.com/mindgarage-shan/trans_object_detection_survey
Authors: Jianhong Bai, Zuozhu Liu, Hualiang Wang, Jin Hao, Yang Feng, Huanpeng Chu, Haoji Hu
Though Self-supervised learning (SSL) has been widely studied as a promising technique for representation learning, it doesn't generalize well on long-tailed datasets due to the majority classes dominating the feature space. Recent work shows that the long-tailed learning performance could be boosted by sampling extra in-domain (ID) data for self-supervised training, however, large-scale ID data which can rebalance the minority classes are expensive to collect. In this paper, we propose an alternative but easy-to-use and effective solution, Contrastive with Out-of-distribution (OOD) data for Long-Tail learning (COLT), which can effectively exploit OOD data to dynamically re-balance the feature space. We empirically identify the counter-intuitive usefulness of OOD samples in SSL long-tailed learning and principally design a novel SSL method. Concretely, we first localize the `head' and `tail' samples by assigning a tailness score to each OOD sample based on its neighborhoods in the feature space. Then, we propose an online OOD sampling strategy to dynamically re-balance the feature space. Finally, we enforce the model to be capable of distinguishing ID and OOD samples by a distribution-level supervised contrastive loss. Extensive experiments are conducted on various datasets and several state-of-the-art SSL frameworks to verify the effectiveness of the proposed method. The results show that our method significantly improves the performance of SSL on long-tailed datasets by a large margin, and even outperforms previous work which uses external ID data. Our code is available at https://github.com/JianhongBai/COLT.
Authors: Raz Lapid, Moshe Sipper
Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions. Taking inspiration from the analysis of neural networks' robustness against adversarial perturbations, we propose a novel gray-box algorithm for creating adversarial examples in image-to-text models. Unlike image classification tasks that have a finite set of class labels, finding visually similar adversarial examples in an image-to-text task poses greater challenges because the captioning system allows for a virtually infinite space of possible captions. In this paper, we present a gray-box adversarial attack on image-to-text, both untargeted and targeted. We formulate the process of discovering adversarial perturbations as an optimization problem that uses only the image-encoder component, meaning the proposed attack is language-model agnostic. Through experiments conducted on the ViT-GPT2 model, which is the most-used image-to-text model in Hugging Face, and the Flickr30k dataset, we demonstrate that our proposed attack successfully generates visually similar adversarial examples, both with untargeted and targeted captions. Notably, our attack operates in a gray-box manner, requiring no knowledge about the decoder module. We also show that our attacks fool the popular open-source platform Hugging Face.
Authors: Heqin Zhu, Quan Quan, Qingsong Yao, Zaiyi Liu, S. kevin Zhou
One-shot medical landmark detection gains much attention and achieves great success for its label-efficient training process. However, existing one-shot learning methods are highly specialized in a single domain and suffer domain preference heavily in the situation of multi-domain unlabeled data. Moreover, one-shot learning is not robust that it faces performance drop when annotating a sub-optimal image. To tackle these issues, we resort to developing a domain-adaptive one-shot landmark detection framework for handling multi-domain medical images, named Universal One-shot Detection (UOD). UOD consists of two stages and two corresponding universal models which are designed as combinations of domain-specific modules and domain-shared modules. In the first stage, a domain-adaptive convolution model is self-supervised learned to generate pseudo landmark labels. In the second stage, we design a domain-adaptive transformer to eliminate domain preference and build the global context for multi-domain data. Even though only one annotated sample from each domain is available for training, the domain-shared modules help UOD aggregate all one-shot samples to detect more robust and accurate landmarks. We investigated both qualitatively and quantitatively the proposed UOD on three widely-used public X-ray datasets in different anatomical domains (i.e., head, hand, chest) and obtained state-of-the-art performances in each domain. The code is available at https://github.com/heqin-zhu/UOD_universal_oneshot_detection.
Authors: Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Recently, the performance of neural image compression (NIC) has steadily improved thanks to the last line of study, reaching or outperforming state-of-the-art conventional codecs. Despite significant progress, current NIC methods still rely on ConvNet-based entropy coding, limited in modeling long-range dependencies due to their local connectivity and the increasing number of architectural biases and priors, resulting in complex underperforming models with high decoding latency. Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT). Through the proposed ICT, we can capture both global and local contexts from the latent representations and better parameterize the distribution of the quantized latents. Further, we leverage a learnable scaling module with a sandwich ConvNeXt-based pre-/post-processor to accurately extract more compact latent codes while reconstructing higher-quality images. Extensive experimental results on benchmark datasets showed that the proposed framework significantly improves the trade-off between coding efficiency and decoder complexity over the versatile video coding (VVC) reference encoder (VTM-18.0) and the neural codec SwinT-ChARM. Moreover, we provide model scaling studies to verify the computational efficiency of our approach and conduct several objective and subjective analyses to bring to the fore the performance gap between the adaptive image compression transformer (AICT) and the neural codec SwinT-ChARM.
Authors: Yongrae Jo, Seongyun Lee, Aiden SJ Lee, Hyunji Lee, Hanseok Oh, Minjoon Seo
Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation cost, we propose ZeroTA, a novel method for dense video captioning in a zero-shot manner. Our method does not require any videos or annotations for training; instead, it localizes and describes events within each input video at test time by optimizing solely on the input. This is accomplished by introducing a soft moment mask that represents a temporal segment in the video and jointly optimizing it with the prefix parameters of a language model. This joint optimization aligns a frozen language generation model (i.e., GPT-2) with a frozen vision-language contrastive model (i.e., CLIP) by maximizing the matching score between the generated text and a moment within the video. We also introduce a pairwise temporal IoU loss to let a set of soft moment masks capture multiple distinct events within the video. Our method effectively discovers diverse significant events within the video, with the resulting captions appropriately describing these events. The empirical results demonstrate that ZeroTA surpasses zero-shot baselines and even outperforms the state-of-the-art few-shot method on the widely-used benchmark ActivityNet Captions. Moreover, our method shows greater robustness compared to supervised methods when evaluated in out-of-domain scenarios. This research provides insight into the potential of aligning widely-used models, such as language generation models and vision-language models, to unlock a new capability: understanding temporal aspects of videos.
Authors: José Morano, Guilherme Aresta, Dmitrii Lachinov, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunović
Deep learning has become a valuable tool for the automation of certain medical image segmentation tasks, significantly relieving the workload of medical specialists. Some of these tasks require segmentation to be performed on a subset of the input dimensions, the most common case being 3D-to-2D. However, the performance of existing methods is strongly conditioned by the amount of labeled data available, as there is currently no data efficient method, e.g. transfer learning, that has been validated on these tasks. In this work, we propose a novel convolutional neural network (CNN) and self-supervised learning (SSL) method for label-efficient 3D-to-2D segmentation. The CNN is composed of a 3D encoder and a 2D decoder connected by novel 3D-to-2D blocks. The SSL method consists of reconstructing image pairs of modalities with different dimensionality. The approach has been validated in two tasks with clinical relevance: the en-face segmentation of geographic atrophy and reticular pseudodrusen in optical coherence tomography. Results on different datasets demonstrate that the proposed CNN significantly improves the state of the art in scenarios with limited labeled data by up to 8% in Dice score. Moreover, the proposed SSL method allows further improvement of this performance by up to 23%, and we show that the SSL is beneficial regardless of the network architecture.
Authors: Aniruddha Mahapatra, Aliaksandr Siarohin, Hsin-Ying Lee, Sergey Tulyakov, Jun-Yan Zhu
We introduce Text2Cinemagraph, a fully automated method for creating cinemagraphs from text descriptions - an especially challenging task when prompts feature imaginary elements and artistic styles, given the complexity of interpreting the semantics and motions of these images. Existing single-image animation methods fall short on artistic inputs, and recent text-based video methods frequently introduce temporal inconsistencies, struggling to keep certain regions static. To address these challenges, we propose an idea of synthesizing image twins from a single text prompt - a pair of an artistic image and its pixel-aligned corresponding natural-looking twin. While the artistic image depicts the style and appearance detailed in our text prompt, the realistic counterpart greatly simplifies layout and motion analysis. Leveraging existing natural image and video datasets, we can accurately segment the realistic image and predict plausible motion given the semantic information. The predicted motion can then be transferred to the artistic image to create the final cinemagraph. Our method outperforms existing approaches in creating cinemagraphs for natural landscapes as well as artistic and other-worldly scenes, as validated by automated metrics and user studies. Finally, we demonstrate two extensions: animating existing paintings and controlling motion directions using text.
Authors: Jiayu Yang, Enze Xie, Miaomiao Liu, Jose M. Alvarez
Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the main bottleneck of these methods is transforming image features into the BEV coordinate frame. This paper focuses on leveraging geometry information, such as depth, to model such feature transformation. Existing works rely on non-parametric depth distribution modeling leading to significant memory consumption, or ignore the geometry information to address this problem. In contrast, we propose to use parametric depth distribution modeling for feature transformation. We first lift the 2D image features to the 3D space defined for the ego vehicle via a predicted parametric depth distribution for each pixel in each view. Then, we aggregate the 3D feature volume based on the 3D space occupancy derived from depth to the BEV frame. Finally, we use the transformed features for downstream tasks such as object detection and semantic segmentation. Existing semantic segmentation methods do also suffer from an hallucination problem as they do not take visibility information into account. This hallucination can be particularly problematic for subsequent modules such as control and planning. To mitigate the issue, our method provides depth uncertainty and reliable visibility-aware estimations. We further leverage our parametric depth modeling to present a novel visibility-aware evaluation metric that, when taken into account, can mitigate the hallucination problem. Extensive experiments on object detection and semantic segmentation on the nuScenes datasets demonstrate that our method outperforms existing methods on both tasks.
Authors: Amrit Diggavi Seshadri, Alessandra Russo
In this work, following the intuition that adverbs describing scene-sequences are best identified by reasoning over high-level concepts of object-behavior, we propose the design of a new framework that reasons over object-behaviours extracted from raw-video-clips to recognize the clip's corresponding adverb-types. Importantly, while previous works for general scene adverb-recognition assume knowledge of the clips underlying action-types, our method is directly applicable in the more general problem setting where the action-type of a video-clip is unknown. Specifically, we propose a novel pipeline that extracts human-interpretable object-behaviour-facts from raw video clips and propose novel symbolic and transformer based reasoning methods that operate over these extracted facts to identify adverb-types. Experiment results demonstrate that our proposed methods perform favourably against the previous state-of-the-art. Additionally, to support efforts in symbolic video-processing, we release two new datasets of object-behaviour-facts extracted from raw video clips - the MSR-VTT-ASP and ActivityNet-ASP datasets.
Authors: Ayush Singh, Yash Bhambhu, Himanshu Buckchash, Deepak K. Gupta, Dilip K. Prasad
Global contexts in images are quite valuable in image-to-image translation problems. Conventional attention-based and graph-based models capture the global context to a large extent, however, these are computationally expensive. Moreover, the existing approaches are limited to only learning the pairwise semantic relation between any two points on the image. In this paper, we present Latent Graph Attention (LGA) a computationally inexpensive (linear to the number of nodes) and stable, modular framework for incorporating the global context in the existing architectures, especially empowering small-scale architectures to give performance closer to large size architectures, thus making the light-weight architectures more useful for edge devices with lower compute power and lower energy needs. LGA propagates information spatially using a network of locally connected graphs, thereby facilitating to construct a semantically coherent relation between any two spatially distant points that also takes into account the influence of the intermediate pixels. Moreover, the depth of the graph network can be used to adapt the extent of contextual spread to the target dataset, thereby being able to explicitly control the added computational cost. To enhance the learning mechanism of LGA, we also introduce a novel contrastive loss term that helps our LGA module to couple well with the original architecture at the expense of minimal additional computational load. We show that incorporating LGA improves the performance on three challenging applications, namely transparent object segmentation, image restoration for dehazing and optical flow estimation.
Authors: Emma Sarfati, Alexandre Bône, Marc-Michel Rohé, Pietro Gori, Isabelle Bloch
Large medical imaging datasets can be cheaply and quickly annotated with low-confidence, weak labels (e.g., radiological scores). Access to high-confidence labels, such as histology-based diagnoses, is rare and costly. Pretraining strategies, like contrastive learning (CL) methods, can leverage unlabeled or weakly-annotated datasets. These methods typically require large batch sizes, which poses a difficulty in the case of large 3D images at full resolution, due to limited GPU memory. Nevertheless, volumetric positional information about the spatial context of each 2D slice can be very important for some medical applications. In this work, we propose an efficient weakly-supervised positional (WSP) contrastive learning strategy where we integrate both the spatial context of each 2D slice and a weak label via a generic kernel-based loss function. We illustrate our method on cirrhosis prediction using a large volume of weakly-labeled images, namely radiological low-confidence annotations, and small strongly-labeled (i.e., high-confidence) datasets. The proposed model improves the classification AUC by 5% with respect to a baseline model on our internal dataset, and by 26% on the public LIHC dataset from the Cancer Genome Atlas. The code is available at: https://github.com/Guerbet-AI/wsp-contrastive.
Authors: Renhao Wang, Yu Sun, Yossi Gandelsman, Xinlei Chen, Alexei A. Efros, Xiaolong Wang
Prior work has established test-time training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is trained on the same instance using a self-supervised task, such as image reconstruction with masked autoencoders. We extend TTT to the streaming setting, where multiple test instances - video frames in our case - arrive in temporal order. Our extension is online TTT: The current model is initialized from the previous model, then trained on the current frame and a small window of frames immediately before. Online TTT significantly outperforms the fixed-model baseline for four tasks, on three real-world datasets. The relative improvement is 45% and 66% for instance and panoptic segmentation. Surprisingly, online TTT also outperforms its offline variant that accesses more information, training on all frames from the entire test video regardless of temporal order. This differs from previous findings using synthetic videos. We conceptualize locality as the advantage of online over offline TTT. We analyze the role of locality with ablations and a theory based on bias-variance trade-off.
Authors: Adel Oulefki, Yassine Himeur, Thaweesak Trongtiraku, Kahina Amara, Sos Agaian, Samir Benbelkacem, Mohamed Amine Guerroudji, Mohamed Zemmouri, Sahla Ferhat, Nadia Zenati, Shadi Atalla, Wathiq Mansoor
Solar Photovoltaic (PV) is increasingly being used to address the global concern of energy security. However, hot spot and snail trails in PV modules caused mostly by crakes reduce their efficiency and power capacity. This article presents a groundbreaking methodology for automatically identifying and analyzing anomalies like hot spots and snail trails in Solar Photovoltaic (PV) modules, leveraging unsupervised sensing algorithms and 3D Augmented Reality (AR) visualization. By transforming the traditional methods of diagnosis and repair, our approach not only enhances efficiency but also substantially cuts down the cost of PV system maintenance. Validated through computer simulations and real-world image datasets, the proposed framework accurately identifies dirty regions, emphasizing the critical role of regular maintenance in optimizing the power capacity of solar PV modules. Our immediate objective is to leverage drone technology for real-time, automatic solar panel detection, significantly boosting the efficacy of PV maintenance. The proposed methodology could revolutionize solar PV maintenance, enabling swift, precise anomaly detection without human intervention. This could result in significant cost savings, heightened energy production, and improved overall performance of solar PV systems. Moreover, the novel combination of unsupervised sensing algorithms with 3D AR visualization heralds new opportunities for further research and development in solar PV maintenance.
Authors: Sushil Sharma, Ganesh Sistu, Lucie Yahiaoui, Arindam Das, Mark Halton, Ciarán Eising
Autonomous vehicles require accurate and reliable short-term trajectory predictions for safe and efficient driving. While most commercial automated vehicles currently use state machine-based algorithms for trajectory forecasting, recent efforts have focused on end-to-end data-driven systems. Often, the design of these models is limited by the availability of datasets, which are typically restricted to generic scenarios. To address this limitation, we have developed a synthetic dataset for short-term trajectory prediction tasks using the CARLA simulator. This dataset is extensive and incorporates what is considered complex scenarios - pedestrians crossing the road, vehicles overtaking - and comprises 6000 perspective view images with corresponding IMU and odometry information for each frame. Furthermore, an end-to-end short-term trajectory prediction model using convolutional neural networks (CNN) and long short-term memory (LSTM) networks has also been developed. This model can handle corner cases, such as slowing down near zebra crossings and stopping when pedestrians cross the road, without the need for explicit encoding of the surrounding environment. In an effort to accelerate this research and assist others, we are releasing our dataset and model to the research community. Our datasets are publicly available on https://github.com/sharmasushil/Navigating-Uncertainty-Trajectory-Prediction .
Authors: Shantanu Ghosh, Ke Yu, Forough Arabshahi, Kayhan Batmanghelich
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models are inherently explainable. Yet, interpretable models require extensive ML knowledge and tend to be less flexible and underperforming than their Blackbox variants. This paper aims to blur the distinction between a post hoc explanation of a Blackbox and constructing interpretable models. Beginning with a Blackbox, we iteratively carve out a mixture of interpretable experts (MoIE) and a residual network. Each interpretable model specializes in a subset of samples and explains them using First Order Logic (FOL), providing basic reasoning on concepts from the Blackbox. We route the remaining samples through a flexible residual. We repeat the method on the residual network until all the interpretable models explain the desired proportion of data. Our extensive experiments show that our route, interpret, and repeat approach (1) identifies a diverse set of instance-specific concepts with high concept completeness via MoIE without compromising in performance, (2) identifies the relatively ``harder'' samples to explain via residuals, (3) outperforms the interpretable by-design models by significant margins during test-time interventions, and (4) fixes the shortcut learned by the original Blackbox. The code for MoIE is publicly available at: \url{https://github.com/batmanlab/ICML-2023-Route-interpret-repeat}
Authors: Luchao Qi, Jiaye Wu, Shengze Wang, Soumyadip Sengupta
Our paper presents My3DGen, a practical system for creating a personalized and lightweight 3D generative prior using as few as 10 images. My3DGen can reconstruct multi-view consistent images from an input test image, and generate novel appearances by interpolating between any two images of the same individual. While recent studies have demonstrated the effectiveness of personalized generative priors in producing high-quality 2D portrait reconstructions and syntheses, to the best of our knowledge, we are the first to develop a personalized 3D generative prior. Instead of fine-tuning a large pre-trained generative model with millions of parameters to achieve personalization, we propose a parameter-efficient approach. Our method involves utilizing a pre-trained model with fixed weights as a generic prior, while training a separate personalized prior through low-rank decomposition of the weights in each convolution and fully connected layer. However, parameter-efficient few-shot fine-tuning on its own often leads to overfitting. To address this, we introduce a regularization technique based on symmetry of human faces. This regularization enforces that novel view renderings of a training sample, rendered from symmetric poses, exhibit the same identity. By incorporating this symmetry prior, we enhance the quality of reconstruction and synthesis, particularly for non-frontal (profile) faces. Our final system combines low-rank fine-tuning with symmetry regularization and significantly surpasses the performance of pre-trained models, e.g. EG3D. It introduces only approximately 0.6 million additional parameters per identity compared to 31 million for full finetuning of the original model. As a result, our system achieves a 50-fold reduction in model size without sacrificing the quality of the generated 3D faces. Code will be available at our project page: https://luchaoqi.github.io/my3dgen.