Authors: Girik Malik, Dakarai Crowder, Ennio Mingolla
Adversarial attacks can affect the object recognition capabilities of machines in wild. These can often result from spurious correlations between input and class labels, and are prone to memorization in large networks. While networks are expected to do automated feature selection, it is not effective at the scale of the object. Humans, however, are able to select the minimum set of features required to form a robust representation of an object. In this work, we show that finetuning any pretrained off-the-shelf network with Extreme Image Transformations (EIT) not only helps in learning a robust latent representation, it also improves the performance of these networks against common adversarial attacks of various intensities. Our EIT trained networks show strong activations in the object regions even when tested with more intense noise, showing promising generalizations across different kinds of adversarial attacks.
Authors: Guanlin Li, Yifei Chen, Jie Zhang, Jiwei Li, Shangwei Guo, Tianwei Zhang
Artificial Intelligence Generated Content (AIGC) is gaining great popularity in social media, with many commercial services available. These services leverage advanced generative models, such as latent diffusion models and large language models, to generate creative content (e.g., realistic images, fluent sentences) for users. The usage of such generated content needs to be highly regulated, as the service providers need to ensure the users do not violate the usage policies (e.g., abuse for commercialization, generating and distributing unsafe content).
Numerous watermarking approaches have been proposed recently. However, in this paper, we show that an adversary can easily break these watermarking mechanisms. Specifically, we consider two possible attacks. (1) Watermark removal: the adversary can easily erase the embedded watermark from the generated content and then use it freely without the regulation of the service provider. (2) Watermark forge: the adversary can create illegal content with forged watermarks from another user, causing the service provider to make wrong attributions. We propose WMaGi, a unified framework to achieve both attacks in a holistic way. The key idea is to leverage a pre-trained diffusion model for content processing, and a generative adversarial network for watermark removing or forging. We evaluate WMaGi on different datasets and embedding setups. The results prove that it can achieve high success rates while maintaining the quality of the generated content. Compared with existing diffusion model-based attacks, WMaGi is 5,050$\sim$11,000$\times$ faster.
Authors: Atal Tewari, K Prateek, Amrita Singh, Nitin Khanna
Craters are one of the most prominent features on planetary surfaces, used in applications such as age estimation, hazard detection, and spacecraft navigation. Crater detection is a challenging problem due to various aspects, including complex crater characteristics such as varying sizes and shapes, data resolution, and planetary data types. Similar to other computer vision tasks, deep learning-based approaches have significantly impacted research on crater detection in recent years. This survey aims to assist researchers in this field by examining the development of deep learning-based crater detection algorithms (CDAs). The review includes over 140 research works covering diverse crater detection approaches, including planetary data, craters database, and evaluation metrics. To be specific, we discuss the challenges in crater detection due to the complex properties of the craters and survey the DL-based CDAs by categorizing them into three parts: (a) semantic segmentation-based, (b) object detection-based, and (c) classification-based. Additionally, we have conducted training and testing of all the semantic segmentation-based CDAs on a common dataset to evaluate the effectiveness of each architecture for crater detection and its potential applications. Finally, we have provided recommendations for potential future works.
Authors: Qinglong Cao, Zhengqin Xu, Yuantian Chen, Chao Ma, Xiaokang Yang
Large pre-trained vision-language models, such as CLIP, have shown remarkable generalization capabilities across various tasks when appropriate text prompts are provided. However, adapting these models to specialized domains, like remote sensing images (RSIs), medical images, etc, remains unexplored and challenging. Existing prompt learning methods often lack domain-awareness or domain-transfer mechanisms, leading to suboptimal performance due to the misinterpretation of specialized images in natural image patterns. To tackle this dilemma, we proposed a Domain-Controlled Prompt Learning for the specialized domains. Specifically, the large-scale specialized domain foundation model (LSDM) is first introduced to provide essential specialized domain knowledge. Using lightweight neural networks, we transfer this knowledge into domain biases, which control both the visual and language branches to obtain domain-adaptive prompts in a directly incorporating manner. Simultaneously, to overcome the existing overfitting challenge, we propose a novel noisy-adding strategy, without extra trainable parameters, to help the model escape the suboptimal solution in a global domain oscillation manner. Experimental results show our method achieves state-of-the-art performance in specialized domain image recognition datasets. Our code is available at https://anonymous.4open.science/r/DCPL-8588.
Authors: Haibo Qiu, Baosheng Yu, Yixin Chen, Dacheng Tao
Significant progress has been made recently in point cloud segmentation utilizing an encoder-decoder framework, which initially encodes point clouds into low-resolution representations and subsequently decodes high-resolution predictions. Inspired by the success of high-resolution architectures in image dense prediction, which always maintains a high-resolution representation throughout the entire learning process, we consider it also highly important for 3D dense point cloud analysis. Therefore, in this paper, we explore high-resolution architectures for 3D point cloud segmentation. Specifically, we generalize high-resolution architectures using a unified pipeline named PointHR, which includes a knn-based sequence operator for feature extraction and a differential resampling operator to efficiently communicate different resolutions. Additionally, we propose to avoid numerous on-the-fly computations of high-resolution architectures by pre-computing the indices for both sequence and resampling operators. By doing so, we deliver highly competitive high-resolution architectures while capitalizing on the benefits of well-designed point cloud blocks without additional effort. To evaluate these architectures for dense point cloud analysis, we conduct thorough experiments using S3DIS and ScanNetV2 datasets, where the proposed PointHR outperforms recent state-of-the-art methods without any bells and whistles. The source code is available at \url{https://github.com/haibo-qiu/PointHR}.
Authors: Jie An, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Lijuan Wang, Jiebo Luo
This work investigates a challenging task named open-domain interleaved image-text generation, which generates interleaved texts and images following an input query. We propose a new interleaved generation framework based on prompting large-language models (LLMs) and pre-trained text-to-image (T2I) models, namely OpenLEAF. In OpenLEAF, the LLM generates textual descriptions, coordinates T2I models, creates visual prompts for generating images, and incorporates global contexts into the T2I models. This global context improves the entity and style consistencies of images in the interleaved generation. For model assessment, we first propose to use large multi-modal models (LMMs) to evaluate the entity and style consistencies of open-domain interleaved image-text sequences. According to the LMM evaluation on our constructed evaluation set, the proposed interleaved generation framework can generate high-quality image-text content for various domains and applications, such as how-to question answering, storytelling, graphical story rewriting, and webpage/poster generation tasks. Moreover, we validate the effectiveness of the proposed LMM evaluation technique with human assessment. We hope our proposed framework, benchmark, and LMM evaluation could help establish the intriguing interleaved image-text generation task.
Authors: Xiaofan Li, Yifu Zhang, Xiaoqing Ye
With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required. However, such large-scale multi-view data is hard to obtain due to expensive collection and annotation costs. To alleviate the problem, we propose a spatial-temporal consistent diffusion framework DrivingDiffusion, to generate realistic multi-view videos controlled by 3D layout. There are three challenges when synthesizing multi-view videos given a 3D layout: How to keep 1) cross-view consistency and 2) cross-frame consistency? 3) How to guarantee the quality of the generated instances? Our DrivingDiffusion solves the problem by cascading the multi-view single-frame image generation step, the single-view video generation step shared by multiple cameras, and post-processing that can handle long video generation. In the multi-view model, the consistency of multi-view images is ensured by information exchange between adjacent cameras. In the temporal model, we mainly query the information that needs attention in subsequent frame generation from the multi-view images of the first frame. We also introduce the local prompt to effectively improve the quality of generated instances. In post-processing, we further enhance the cross-view consistency of subsequent frames and extend the video length by employing temporal sliding window algorithm. Without any extra cost, our model can generate large-scale realistic multi-camera driving videos in complex urban scenes, fueling the downstream driving tasks. The code will be made publicly available.
Authors: Jieneng Chen, Jieru Mei, Xianhang Li, Yongyi Lu, Qihang Yu, Qingyue Wei, Xiangde Luo, Yutong Xie, Ehsan Adeli, Yan Wang, Matthew Lungren, Lei Xing, Le Lu, Alan Yuille, Yuyin Zhou
Medical image segmentation plays a crucial role in advancing healthcare systems for disease diagnosis and treatment planning. The u-shaped architecture, popularly known as U-Net, has proven highly successful for various medical image segmentation tasks. However, U-Net's convolution-based operations inherently limit its ability to model long-range dependencies effectively. To address these limitations, researchers have turned to Transformers, renowned for their global self-attention mechanisms, as alternative architectures. One popular network is our previous TransUNet, which leverages Transformers' self-attention to complement U-Net's localized information with the global context. In this paper, we extend the 2D TransUNet architecture to a 3D network by building upon the state-of-the-art nnU-Net architecture, and fully exploring Transformers' potential in both the encoder and decoder design. We introduce two key components: 1) A Transformer encoder that tokenizes image patches from a convolution neural network (CNN) feature map, enabling the extraction of global contexts, and 2) A Transformer decoder that adaptively refines candidate regions by utilizing cross-attention between candidate proposals and U-Net features. Our investigations reveal that different medical tasks benefit from distinct architectural designs. The Transformer encoder excels in multi-organ segmentation, where the relationship among organs is crucial. On the other hand, the Transformer decoder proves more beneficial for dealing with small and challenging segmented targets such as tumor segmentation. Extensive experiments showcase the significant potential of integrating a Transformer-based encoder and decoder into the u-shaped medical image segmentation architecture. TransUNet outperforms competitors in various medical applications.
Authors: Caleb Tung, Nicholas Eliopoulos, Purvish Jajal, Gowri Ramshankar, Chen-Yun Yang, Nicholas Synovic, Xuecen Zhang, Vipin Chaudhary, George K. Thiruvathukal, Yung-Hsiang Lu
Computer vision often uses highly accurate Convolutional Neural Networks (CNNs), but these deep learning models are associated with ever-increasing energy and computation requirements. Producing more energy-efficient CNNs often requires model training which can be cost-prohibitive. We propose a novel, automated method to make a pretrained CNN more energy-efficient without re-training. Given a pretrained CNN, we insert a threshold layer that filters activations from the preceding layers to identify regions of the image that are irrelevant, i.e. can be ignored by the following layers while maintaining accuracy. Our modified focused convolution operation saves inference latency (by up to 25%) and energy costs (by up to 22%) on various popular pretrained CNNs, with little to no loss in accuracy.
Authors: Changhe Chen, Mozhgan Pourkeshavarz, Amir Rasouli
Benchmarking is a common method for evaluating trajectory prediction models for autonomous driving. Existing benchmarks rely on datasets, which are biased towards more common scenarios, such as cruising, and distance-based metrics that are computed by averaging over all scenarios. Following such a regiment provides a little insight into the properties of the models both in terms of how well they can handle different scenarios and how admissible and diverse their outputs are. There exist a number of complementary metrics designed to measure the admissibility and diversity of trajectories, however, they suffer from biases, such as length of trajectories.
In this paper, we propose a new benChmarking paRadIgm for evaluaTing trajEctoRy predIction Approaches (CRITERIA). Particularly, we propose 1) a method for extracting driving scenarios at varying levels of specificity according to the structure of the roads, models' performance, and data properties for fine-grained ranking of prediction models; 2) A set of new bias-free metrics for measuring diversity, by incorporating the characteristics of a given scenario, and admissibility, by considering the structure of roads and kinematic compliancy, motivated by real-world driving constraints. 3) Using the proposed benchmark, we conduct extensive experimentation on a representative set of the prediction models using the large scale Argoverse dataset. We show that the proposed benchmark can produce a more accurate ranking of the models and serve as a means of characterizing their behavior. We further present ablation studies to highlight contributions of different elements that are used to compute the proposed metrics.
Authors: Elvis Han Cui, Bingbin Li, Yanan Li, Weng Kee Wong, Donghui Wang
Data augmentation for deep learning benefits model training, image transformation, medical imaging analysis and many other fields. Many existing methods generate new samples from a parametric distribution, like the Gaussian, with little attention to generate samples along the data manifold in either the input or feature space. In this paper, we verify that there are theoretical and practical advantages of using the principal manifold hidden in the feature space than the Gaussian distribution. We then propose a novel trajectory-aware principal manifold framework to restore the manifold backbone and generate samples along a specific trajectory. On top of the autoencoder architecture, we further introduce an intrinsic dimension regularization term to make the manifold more compact and enable few-shot image generation. Experimental results show that the novel framework is able to extract more compact manifold representation, improve classification accuracy and generate smooth transformation among few samples.
Authors: Théo Ardoin, Cédric Sueur (IPHC, ANTHROPO LAB, IUF)
The latest advancements in artificial intelligence technology have opened doors to the analysis of intricate behaviours. In light of this, ethologists are actively exploring the potential of these innovations to streamline the time-intensive process of behavioural analysis using video data. In the realm of primatology, several tools have been developed for this purpose. Nonetheless, each of these tools grapples with technical constraints that we aim to surmount. To address these limitations, we have established a comprehensive protocol designed to harness the capabilities of a cutting-edge tool, LabGym. Our primary objective was to evaluate LabGym's suitability for the analysis of primate behaviour, with a focus on Japanese macaques as our model subjects. We have successfully developed a model that demonstrates a high degree of accuracy in detecting Japanese macaques stone-handling behaviour. Our behavioural analysis model was completed as per our initial expectations and LabGym succeed to recognise stone-handling behaviour on videos. However, it is important to note that our study's ability to draw definitive conclusions regarding the quality of the behavioural analysis is hampered by the absence of quantitative data within the specified timeframe. Nevertheless, our model represents the pioneering endeavour, as far as our knowledge extends, in leveraging LabGym for the analysis of primate behaviours. It lays the groundwork for potential future research in this promising field.
Authors: Arman Maesumi, Paul Guerrero, Vladimir G. Kim, Matthew Fisher, Siddhartha Chaudhuri, Noam Aigerman, Daniel Ritchie
Exploring variations of 3D shapes is a time-consuming process in traditional 3D modeling tools. Deep generative models of 3D shapes often feature continuous latent spaces that can, in principle, be used to explore potential variations starting from a set of input shapes. In practice, doing so can be problematic: latent spaces are high dimensional and hard to visualize, contain shapes that are not relevant to the input shapes, and linear paths through them often lead to sub-optimal shape transitions. Furthermore, one would ideally be able to explore variations in the original high-quality meshes used to train the generative model, not its lower-quality output geometry. In this paper, we present a method to explore variations among a given set of landmark shapes by constructing a mapping from an easily-navigable 2D exploration space to a subspace of a pre-trained generative model. We first describe how to find a mapping that spans the set of input landmark shapes and exhibits smooth variations between them. We then show how to turn the variations in this subspace into deformation fields, to transfer those variations to high-quality meshes for the landmark shapes. Our results show that our method can produce visually-pleasing and easily-navigable 2D exploration spaces for several different shape categories, especially as compared to prior work on learning deformation spaces for 3D shapes.
Authors: Tim Lebailly, Thomas Stegmüller, Behzad Bozorgtabar, Jean-Philippe Thiran, Tinne Tuytelaars
Leveraging nearest neighbor retrieval for self-supervised representation learning has proven beneficial with object-centric images. However, this approach faces limitations when applied to scene-centric datasets, where multiple objects within an image are only implicitly captured in the global representation. Such global bootstrapping can lead to undesirable entanglement of object representations. Furthermore, even object-centric datasets stand to benefit from a finer-grained bootstrapping approach. In response to these challenges, we introduce a novel Cross-Image Object-Level Bootstrapping method tailored to enhance dense visual representation learning. By employing object-level nearest neighbor bootstrapping throughout the training, CrIBo emerges as a notably strong and adequate candidate for in-context learning, leveraging nearest neighbor retrieval at test time. CrIBo shows state-of-the-art performance on the latter task while being highly competitive in more standard downstream segmentation tasks. Our code and pretrained models will be publicly available upon acceptance.
Authors: Pranav Mantini, Shishir K. Shah
Camera tamper detection is the ability to detect unauthorized and unintentional alterations in surveillance cameras by analyzing the video. Camera tampering can occur due to natural events or it can be caused intentionally to disrupt surveillance. We cast tampering detection as a change detection problem, and perform a review of the existing literature with emphasis on feature types. We formulate tampering detection as a time series analysis problem, and design experiments to study the robustness and capability of various feature types. We compute ten features on real-world surveillance video and apply time series analysis to ascertain their predictability, and their capability to detect tampering. Finally, we quantify the performance of various time series models using each feature type to detect tampering.
Authors: Benjamin Salmon, Alexander Krull
Most unsupervised denoising methods are based on the assumption that imaging noise is either pixel-independent, i.e., spatially uncorrelated, or signal-independent, i.e., purely additive. However, in practice many imaging setups, especially in microscopy, suffer from a combination of signal-dependent noise (e.g. Poisson shot noise) and axis-aligned correlated noise (e.g. stripe shaped scanning or readout artifacts). In this paper, we present the first unsupervised deep learning-based denoiser that can remove this type of noise without access to any clean images or a noise model. Unlike self-supervised techniques, our method does not rely on removing pixels by masking or subsampling so can utilize all available information. We implement a Variational Autoencoder (VAE) with a specially designed autoregressive decoder capable of modelling the noise component of an image but incapable of independently modelling the underlying clean signal component. As a consequence, our VAE's encoder learns to encode only underlying clean signal content and to discard imaging noise. We also propose an additional decoder for mapping the encoder's latent variables back into image space, thereby sampling denoised images. Experimental results demonstrate that our approach surpasses existing methods for self- and unsupervised image denoising while being robust with respect to the size of the autoregressive receptive field. Code for this project can be found at https://github.com/krulllab/DVLAE.
Authors: Bowen Pan, Rameswar Panda, SouYoung Jin, Rogerio Feris, Aude Oliva, Phillip Isola, Yoon Kim
We explore the use of language as a perceptual representation for vision-and-language navigation. Our approach uses off-the-shelf vision systems (for image captioning and object detection) to convert an agent's egocentric panoramic view at each time step into natural language descriptions. We then finetune a pretrained language model to select an action, based on the current view and the trajectory history, that would best fulfill the navigation instructions. In contrast to the standard setup which adapts a pretrained language model to work directly with continuous visual features from pretrained vision models, our approach instead uses (discrete) language as the perceptual representation. We explore two use cases of our language-based navigation (LangNav) approach on the R2R vision-and-language navigation benchmark: generating synthetic trajectories from a prompted large language model (GPT-4) with which to finetune a smaller language model; and sim-to-real transfer where we transfer a policy learned on a simulated environment (ALFRED) to a real-world environment (R2R). Our approach is found to improve upon strong baselines that rely on visual features in settings where only a few gold trajectories (10-100) are available, demonstrating the potential of using language as a perceptual representation for navigation tasks.
Authors: Kushagra Pandey, Maja Rudolph, Stephan Mandt
Diffusion models suffer from slow sample generation at inference time. Therefore, developing a principled framework for fast deterministic/stochastic sampling for a broader class of diffusion models is a promising direction. We propose two complementary frameworks for accelerating sample generation in pre-trained models: Conjugate Integrators and Splitting Integrators. Conjugate integrators generalize DDIM, mapping the reverse diffusion dynamics to a more amenable space for sampling. In contrast, splitting-based integrators, commonly used in molecular dynamics, reduce the numerical simulation error by cleverly alternating between numerical updates involving the data and auxiliary variables. After extensively studying these methods empirically and theoretically, we present a hybrid method that leads to the best-reported performance for diffusion models in augmented spaces. Applied to Phase Space Langevin Diffusion [Pandey & Mandt, 2023] on CIFAR-10, our deterministic and stochastic samplers achieve FID scores of 2.11 and 2.36 in only 100 network function evaluations (NFE) as compared to 2.57 and 2.63 for the best-performing baselines, respectively. Our code and model checkpoints will be made publicly available at \url{https://github.com/mandt-lab/PSLD}.
Authors: Ajay Sridhar, Dhruv Shah, Catherine Glossop, Sergey Levine
Robotic learning for navigation in unfamiliar environments needs to provide policies for both task-oriented navigation (i.e., reaching a goal that the robot has located), and task-agnostic exploration (i.e., searching for a goal in a novel setting). Typically, these roles are handled by separate models, for example by using subgoal proposals, planning, or separate navigation strategies. In this paper, we describe how we can train a single unified diffusion policy to handle both goal-directed navigation and goal-agnostic exploration, with the latter providing the ability to search novel environments, and the former providing the ability to reach a user-specified goal once it has been located. We show that this unified policy results in better overall performance when navigating to visually indicated goals in novel environments, as compared to approaches that use subgoal proposals from generative models, or prior methods based on latent variable models. We instantiate our method by using a large-scale Transformer-based policy trained on data from multiple ground robots, with a diffusion model decoder to flexibly handle both goal-conditioned and goal-agnostic navigation. Our experiments, conducted on a real-world mobile robot platform, show effective navigation in unseen environments in comparison with five alternative methods, and demonstrate significant improvements in performance and lower collision rates, despite utilizing smaller models than state-of-the-art approaches. For more videos, code, and pre-trained model checkpoints, see https://general-navigation-models.github.io/nomad/
Authors: Ancheng Lin, Jun Li
Neural Radiance Fields (NeRFs) have shown great potential in modelling 3D scenes. Dynamic NeRFs extend this model by capturing time-varying elements, typically using deformation fields. The existing dynamic NeRFs employ a similar Eulerian representation for both light radiance and deformation fields. This leads to a close coupling of appearance and motion and lacks a physical interpretation. In this work, we propose Dynamic Appearance Particle Neural Radiance Field (DAP-NeRF), which introduces particle-based representation to model the motions of visual elements in a dynamic 3D scene. DAP-NeRF consists of superposition of a static field and a dynamic field. The dynamic field is quantised as a collection of {\em appearance particles}, which carries the visual information of a small dynamic element in the scene and is equipped with a motion model. All components, including the static field, the visual features and motion models of the particles, are learned from monocular videos without any prior geometric knowledge of the scene. We develop an efficient computational framework for the particle-based model. We also construct a new dataset to evaluate motion modelling. Experimental results show that DAP-NeRF is an effective technique to capture not only the appearance but also the physically meaningful motions in a 3D dynamic scene.
Authors: Adyasha Maharana, Prateek Yadav, Mohit Bansal
Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute budget without compromising performance if a dataset can be stripped of its redundancies. Coreset selection (or data pruning) seeks to select a subset of the training data so as to maximize the performance of models trained on this subset, also referred to as coreset. There are two dominant approaches: (1) geometry-based data selection for maximizing data diversity in the coreset, and (2) functions that assign difficulty scores to samples based on training dynamics. Optimizing for data diversity leads to a coreset that is biased towards easier samples, whereas, selection by difficulty ranking omits easy samples that are necessary for the training of deep learning models. This demonstrates that data diversity and importance scores are two complementary factors that need to be jointly considered during coreset selection. We represent a dataset as an undirected graph and propose a novel pruning algorithm, D2 Pruning, that uses forward and reverse message passing over this dataset graph for coreset selection. D2 Pruning updates the difficulty scores of each example by incorporating the difficulty of its neighboring examples in the dataset graph. Then, these updated difficulty scores direct a graph-based sampling method to select a coreset that encapsulates both diverse and difficult regions of the dataset space. We evaluate supervised and self-supervised versions of our method on various vision and language datasets. Results show that D2 Pruning improves coreset selection over previous state-of-the-art methods for up to 70% pruning rates. Additionally, we find that using D2 Pruning for filtering large multimodal datasets leads to increased diversity in the dataset and improved generalization of pretrained models.
Authors: Ran Tian, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik, Andrea Bajcsy
When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representations. Recently there has been excitement in using representations from pre-trained visual models, but key to making these work in robotics is fine-tuning, which is typically done via proxy tasks like dynamics prediction or enforcing temporal cycle-consistency. However, all these proxy tasks bypass the human's input on what matters to them, exacerbating spurious correlations and ultimately leading to robot behaviors that are misaligned with user preferences. In this work, we propose that robots should leverage human feedback to align their visual representations with the end-user and disentangle what matters for the task. We propose Representation-Aligned Preference-based Learning (RAPL), a method for solving the visual representation alignment problem and visual reward learning problem through the lens of preference-based learning and optimal transport. Across experiments in X-MAGICAL and in robotic manipulation, we find that RAPL's reward consistently generates preferred robot behaviors with high sample efficiency, and shows strong zero-shot generalization when the visual representation is learned from a different embodiment than the robot's.
Authors: Abdullah Hayajneh, Erchin Serpedin, Mohammad Shaqfeh, Graeme Glass, Mitchell A. Stotland
A major obstacle when attempting to train a machine learning system to evaluate facial clefts is the scarcity of large datasets of high-quality, ethics board-approved patient images. In response, we have built a deep learning-based cleft lip generator designed to produce an almost unlimited number of artificial images exhibiting high-fidelity facsimiles of cleft lip with wide variation. We undertook a transfer learning protocol testing different versions of StyleGAN-ADA (a generative adversarial network image generator incorporating adaptive data augmentation (ADA)) as the base model. Training images depicting a variety of cleft deformities were pre-processed to adjust for rotation, scaling, color adjustment and background blurring. The ADA modification of the primary algorithm permitted construction of our new generative model while requiring input of a relatively small number of training images. Adversarial training was carried out using 514 unique frontal photographs of cleft-affected faces to adapt a pre-trained model based on 70,000 normal faces. The Frechet Inception Distance (FID) was used to measure the similarity of the newly generated facial images to the cleft training dataset, while Perceptual Path Length (PPL) and the novel Divergence Index of Severity Histograms (DISH) measures were also used to assess the performance of the image generator that we dub CleftGAN. We found that StyleGAN3 with translation invariance (StyleGAN3-t) performed optimally as a base model. Generated images achieved a low FID reflecting a close similarity to our training input dataset of genuine cleft images. Low PPL and DISH measures reflected a smooth and semantically valid interpolation of images through the transfer learning process and a similar distribution of severity in the training and generated images, respectively.
Authors: Sotirios Konstantakos, Despina Ioanna Chalkiadaki, Ioannis Mademlis, Adamantia Anna Rebolledo Chrysochoou, Georgios Th. Papadopoulos
Automated visual firearms classification from RGB images is an important real-world task with applications in public space security, intelligence gathering and law enforcement investigations. When applied to images massively crawled from the World Wide Web (including social media and dark Web sites), it can serve as an important component of systems that attempt to identify criminal firearms trafficking networks, by analyzing Big Data from open-source intelligence. Deep Neural Networks (DNN) are the state-of-the-art methodology for achieving this, with Convolutional Neural Networks (CNN) being typically employed. The common transfer learning approach consists of pretraining on a large-scale, generic annotated dataset for whole-image classification, such as ImageNet-1k, and then finetuning the DNN on a smaller, annotated, task-specific, downstream dataset for visual firearms classification. Neither Visual Transformer (ViT) neural architectures nor Self-Supervised Learning (SSL) approaches have been so far evaluated on this critical task. SSL essentially consists of replacing the traditional supervised pretraining objective with an unsupervised pretext task that does not require ground-truth labels..
Authors: Zhan Chen, Yidan Zhang, Xiyu Qi, Yongqiang Mao, Xin Zhou, Lulu Niu, Hui Wu, Lei Wang, Yunping Ge
Height estimation has long been a pivotal topic within measurement and remote sensing disciplines, proving critical for endeavours such as 3D urban modelling, MR and autonomous driving. Traditional methods utilise stereo matching or multisensor fusion, both well-established techniques that typically necessitate multiple images from varying perspectives and adjunct sensors like SAR, leading to substantial deployment costs. Single image height estimation has emerged as an attractive alternative, boasting a larger data source variety and simpler deployment. However, current methods suffer from limitations such as fixed receptive fields, a lack of global information interaction, leading to noticeable instance-level height deviations. The inherent complexity of height prediction can result in a blurry estimation of object edge depth when using mainstream regression methods based on fixed height division. This paper presents a comprehensive solution for monocular height estimation in remote sensing, termed HeightFormer, combining multilevel interactions and image-adaptive classification-regression. It features the Multilevel Interaction Backbone (MIB) and Image-adaptive Classification-regression Height Generator (ICG). MIB supplements the fixed sample grid in CNN of the conventional backbone network with tokens of different interaction ranges. It is complemented by a pixel-, patch-, and feature map-level hierarchical interaction mechanism, designed to relay spatial geometry information across different scales and introducing a global receptive field to enhance the quality of instance-level height estimation. The ICG dynamically generates height partition for each image and reframes the traditional regression task, using a refinement from coarse to fine classification-regression that significantly mitigates the innate ill-posedness issue and drastically improves edge sharpness.
Authors: Lapo Frati, Neil Traft, Jeff Clune, Nick Cheney
This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism -- the repeated resetting of weights in the last layer, which we nickname "zapping" -- was originally designed for a meta-continual-learning procedure, yet we show it is surprisingly applicable in many settings beyond both meta-learning and continual learning. In our experiments, we wish to transfer a pre-trained image classifier to a new set of classes, in a few shots. We show that our zapping procedure results in improved transfer accuracy and/or more rapid adaptation in both standard fine-tuning and continual learning settings, while being simple to implement and computationally efficient. In many cases, we achieve performance on par with state of the art meta-learning without needing the expensive higher-order gradients, by using a combination of zapping and sequential learning. An intuitive explanation for the effectiveness of this zapping procedure is that representations trained with repeated zapping learn features that are capable of rapidly adapting to newly initialized classifiers. Such an approach may be considered a computationally cheaper type of, or alternative to, meta-learning rapidly adaptable features with higher-order gradients. This adds to recent work on the usefulness of resetting neural network parameters during training, and invites further investigation of this mechanism.
Authors: Chen Zhang, Wanjuan Su, Wenbing Tao
Recently, learning neural implicit surface by volume rendering has been a promising way for multi-view reconstruction. However, limited accuracy and excessive time complexity remain bottlenecks that current methods urgently need to overcome. To address these challenges, we propose a new method called Point-NeuS, utilizing point-guided mechanisms to achieve accurate and efficient reconstruction. Point modeling is organically embedded into the volume rendering to enhance and regularize the representation of implicit surface. Specifically, to achieve precise point guidance and noise robustness, aleatoric uncertainty of the point cloud is modeled to capture the distribution of noise and estimate the reliability of points. Additionally, a Neural Projection module connecting points and images is introduced to add geometric constraints to the Signed Distance Function (SDF). To better compensate for geometric bias between volume rendering and point modeling, high-fidelity points are filtered into an Implicit Displacement Network to improve the representation of SDF. Benefiting from our effective point guidance, lightweight networks are employed to achieve an impressive 11x speedup compared to NeuS. Extensive experiments show that our method yields high-quality surfaces, especially for fine-grained details and smooth regions. Moreover, it exhibits strong robustness to both noisy and sparse data.
Authors: Zeyu Cai, Can Zhang, Xunhao Chen, Shanghuan Liu, Chengqian Jin, Feipeng Da
Coded Aperture Snapshot Spectral Imaging (CASSI) system has great advantages over traditional methods in dynamically acquiring Hyper-Spectral Image (HSI), but there are the following problems. 1) Traditional mask relies on random patterns or analytical design, both of which limit the performance improvement of CASSI. 2) Existing high-quality reconstruction algorithms are slow in reconstruction and can only reconstruct scene information offline. To address the above two problems, this paper designs the AMDC-CASSI system, introducing RGB camera with CASSI based on Adaptive-Mask as multimodal input to improve the reconstruction quality. The existing SOTA reconstruction schemes are based on transformer, but the operation of self-attention pulls down the operation efficiency of the network. In order to improve the inference speed of the reconstruction network, this paper proposes An MLP Architecture for Adaptive-Mask-based Dual-Camera (MLP-AMDC) to replace the transformer structure of the network. Numerous experiments have shown that MLP performs no less well than transformer-based structures for HSI reconstruction, while MLP greatly improves the network inference speed and has less number of parameters and operations, our method has a 8 db improvement over SOTA and at least a 5-fold improvement in reconstruction speed. (https://github.com/caizeyu1992/MLP-AMDC.)
Authors: Pandeng Li, Hongtao Xie, Jiannan Ge, Lei Zhang, Shaobo Min, Yongdong Zhang
Unsupervised video hashing usually optimizes binary codes by learning to reconstruct input videos. Such reconstruction constraint spends much effort on frame-level temporal context changes without focusing on video-level global semantics that are more useful for retrieval. Hence, we address this problem by decomposing video information into reconstruction-dependent and semantic-dependent information, which disentangles the semantic extraction from reconstruction constraint. Specifically, we first design a simple dual-stream structure, including a temporal layer and a hash layer. Then, with the help of semantic similarity knowledge obtained from self-supervision, the hash layer learns to capture information for semantic retrieval, while the temporal layer learns to capture the information for reconstruction. In this way, the model naturally preserves the disentangled semantics into binary codes. Validated by comprehensive experiments, our method consistently outperforms the state-of-the-arts on three video benchmarks.
Authors: Xingyue Liu, Jiahao Qi, Chen Chen, Kangcheng Bin, Ping Zhong
Owing to the capacity of performing full-time target search, cross-modality vehicle re-identification (Re-ID) based on unmanned aerial vehicle (UAV) is gaining more attention in both video surveillance and public security. However, this promising and innovative research has not been studied sufficiently due to the data inadequacy issue. Meanwhile, the cross-modality discrepancy and orientation discrepancy challenges further aggravate the difficulty of this task. To this end, we pioneer a cross-modality vehicle Re-ID benchmark named UAV Cross-Modality Vehicle Re-ID (UCM-VeID), containing 753 identities with 16015 RGB and 13913 infrared images. Moreover, to meet cross-modality discrepancy and orientation discrepancy challenges, we present a hybrid weights decoupling network (HWDNet) to learn the shared discriminative orientation-invariant features. For the first challenge, we proposed a hybrid weights siamese network with a well-designed weight restrainer and its corresponding objective function to learn both modality-specific and modality shared information. In terms of the second challenge, three effective decoupling structures with two pretext tasks are investigated to learn orientation-invariant feature. Comprehensive experiments are carried out to validate the effectiveness of the proposed method. The dataset and codes will be released at https://github.com/moonstarL/UAV-CM-VeID.
Authors: Yi Dai, Hao Lang, Kaisheng Zeng, Fei Huang, Yongbin Li
Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently neglects the rich contextual information of ID classes. Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class. Indiscriminately using such knowledge causes catastrophic damage to OOD detection due to LLMs' hallucinations, as is observed by our analysis. In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs. Specifically, we introduce a consistency-based uncertainty calibration method to estimate the confidence score of each generation. We further extract visual objects from each image to fully capitalize on the aforementioned world knowledge. Extensive experiments demonstrate that our method consistently outperforms the state-of-the-art.
Authors: Jiarong Wei, Yancong Lin, Holger Caesar
Active learning strives to reduce the need for costly data annotation, by repeatedly querying an annotator to label the most informative samples from a pool of unlabeled data and retraining a model from these samples. We identify two problems with existing active learning methods for LiDAR semantic segmentation. First, they ignore the severe class imbalance inherent in LiDAR semantic segmentation datasets. Second, to bootstrap the active learning loop, they train their initial model from randomly selected data samples, which leads to low performance and is referred to as the cold start problem. To address these problems we propose BaSAL, a size-balanced warm start active learning model, based on the observation that each object class has a characteristic size. By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced. Furthermore, in contrast to existing information measures like entropy or CoreSet, size-based sampling does not require an already trained model and thus can be used to address the cold start problem. Results show that we are able to improve the performance of the initial model by a large margin. Combining size-balanced sampling and warm start with established information measures, our approach achieves a comparable performance to training on the entire SemanticKITTI dataset, despite using only 5% of the annotations, which outperforms existing active learning methods. We also match the existing state-of-the-art in active learning on nuScenes. Our code will be made available upon paper acceptance.
Authors: Zihao Xu, Xuan Tang, Yufei Shi, Jianfeng Zhang, Jian Yang, Mingsong Chen, Xian Wei
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based methods use episodic memory to replay samples of previous tasks. However, in the process of knowledge integration when learning a new task, this strategy also suffers from catastrophic forgetting due to an imbalance between old and new knowledge. To address this problem, we propose a novel replay strategy called Manifold Expansion Replay (MaER). We argue that expanding the implicit manifold of the knowledge representation in the episodic memory helps to improve the robustness and expressiveness of the model. To this end, we propose a greedy strategy to keep increasing the diameter of the implicit manifold represented by the knowledge in the buffer during memory management. In addition, we introduce Wasserstein distance instead of cross entropy as distillation loss to preserve previous knowledge. With extensive experimental validation on MNIST, CIFAR10, CIFAR100, and TinyImageNet, we show that the proposed method significantly improves the accuracy in continual learning setup, outperforming the state of the arts.
Authors: Yixuan Zhou, Xuanhan Wang, Xing Xu, Lei Zhao, Jingkuan Song
High-resolution representation is necessary for human pose estimation to achieve high performance, and the ensuing problem is high computational complexity. In particular, predominant pose estimation methods estimate human joints by 2D single-peak heatmaps. Each 2D heatmap can be horizontally and vertically projected to and reconstructed by a pair of 1D heat vectors. Inspired by this observation, we introduce a lightweight and powerful alternative, Spatially Unidimensional Self-Attention (SUSA), to the pointwise (1x1) convolution that is the main computational bottleneck in the depthwise separable 3c3 convolution. Our SUSA reduces the computational complexity of the pointwise (1x1) convolution by 96% without sacrificing accuracy. Furthermore, we use the SUSA as the main module to build our lightweight pose estimation backbone X-HRNet, where `X' represents the estimated cross-shape attention vectors. Extensive experiments on the COCO benchmark demonstrate the superiority of our X-HRNet, and comprehensive ablation studies show the effectiveness of the SUSA modules. The code is publicly available at https://github.com/cool-xuan/x-hrnet.
Authors: Ruijie Zhu, Ziyang Song, Chuxin Wang, Jianfeng He, Tianzhu Zhang
Self-supervised monocular depth estimation holds significant importance in the fields of autonomous driving and robotics. However, existing methods are typically designed to train and test on clear and pristine datasets, overlooking the impact of various adverse conditions prevalent in real-world scenarios. As a result, it is commonly observed that most self-supervised monocular depth estimation methods struggle to perform adequately under challenging conditions. To address this issue, we present EC-Depth, a novel self-supervised two-stage training framework to achieve a robust depth estimation, starting from the foundation of depth prediction consistency under different perturbations. Leveraging the proposed perturbation-invariant depth consistency constraint module and the consistency-based pseudo-label selection module, our model attains accurate and consistent depth predictions in both standard and challenging scenarios. Extensive experiments substantiate the effectiveness of the proposed method. Moreover, our method surpasses existing state-of-the-art methods on KITTI, KITTI-C and DrivingStereo benchmarks, demonstrating its potential for enhancing the reliability of self-supervised monocular depth estimation models in real-world applications.
Authors: Miaomiao Yang, Changwei Yao, Shijin Yan
Age estimation technology is a part of facial recognition and has been applied to identity authentication. This technology achieves the development and application of a juvenile anti-addiction system by authenticating users in the game. Convolutional Neural Network (CNN) and Transformer algorithms are widely used in this application scenario. However, these two models cannot flexibly extract and model features of faces with irregular shapes, and they are ineffective in capturing key information. Furthermore, the above methods will contain a lot of background information while extracting features, which will interfere with the model. In consequence, it is easy to extract redundant information from images. In this paper, a new modeling idea is proposed to solve this problem, which can flexibly model irregular objects. The Graph Convolutional Network (GCN) is used to extract features from irregular face images effectively, and multi-head attention mechanisms are added to avoid redundant features and capture key region information in the image. This model can effectively improve the accuracy of age estimation and reduce the MAE error value to about 3.64, which is better than the effect of today's age estimation model, to improve the accuracy of face recognition and identity authentication.
Authors: Yun Ye, Yanjie Pan, Qually Jiang, Ming Lu, Xiaoran Fang, Beryl Xu
Over-fitting-based image compression requires weights compactness for compression and fast convergence for practical use, posing challenges for deep convolutional neural networks (CNNs) based methods. This paper presents a simple re-parameterization method to train CNNs with reduced weights storage and accelerated convergence. The convolution kernels are re-parameterized as a weighted sum of discrete cosine transform (DCT) kernels enabling direct optimization in the frequency domain. Combined with L1 regularization, the proposed method surpasses vanilla convolutions by achieving a significantly improved rate-distortion with low computational cost. The proposed method is verified with extensive experiments of over-fitting-based image restoration on various datasets, achieving up to -46.12% BD-rate on top of HEIF with only 200 iterations.
Authors: Junyu Gao, Xinhong Ma, Changsheng Xu
Despite the great progress of unsupervised domain adaptation (UDA) with the deep neural networks, current UDA models are opaque and cannot provide promising explanations, limiting their applications in the scenarios that require safe and controllable model decisions. At present, a surge of work focuses on designing deep interpretable methods with adequate data annotations and only a few methods consider the distributional shift problem. Most existing interpretable UDA methods are post-hoc ones, which cannot facilitate the model learning process for performance enhancement. In this paper, we propose an inherently interpretable method, named Transferable Conceptual Prototype Learning (TCPL), which could simultaneously interpret and improve the processes of knowledge transfer and decision-making in UDA. To achieve this goal, we design a hierarchically prototypical module that transfers categorical basic concepts from the source domain to the target domain and learns domain-shared prototypes for explaining the underlying reasoning process. With the learned transferable prototypes, a self-predictive consistent pseudo-label strategy that fuses confidence, predictions, and prototype information, is designed for selecting suitable target samples for pseudo annotations and gradually narrowing down the domain gap. Comprehensive experiments show that the proposed method can not only provide effective and intuitive explanations but also outperform previous state-of-the-arts.
Authors: Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio
Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has claimed that adversarial pruning methods can produce sparse networks while also preserving robustness to adversarial examples. In this work, we first re-evaluate three state-of-the-art adversarial pruning methods, showing that their robustness was indeed overestimated. We then compare pruned and dense versions of the same models, discovering that samples on thin ice, i.e., closer to the unpruned model's decision boundary, are typically misclassified after pruning. We conclude by discussing how this intuition may lead to designing more effective adversarial pruning methods in future work.
Authors: Miao Zhu, Qiming Fu, Bo Liu, Mengxi Zhang, Bojian Li, Xiaoyan Luo, Fugen Zhou
Radiotherapy is one of the primary treatment methods for tumors, but the organ movement caused by respiratory motion limits its accuracy. Recently, 3D imaging from single X-ray projection receives extensive attentions as a promising way to address this issue. However, current methods can only reconstruct 3D image without direct location of the tumor and are only validated for fixed-angle imaging, which fails to fully meet the requirement of motion control in radiotherapy. In this study, we propose a novel imaging method RT-SRTS which integrates 3D imaging and tumor segmentation into one network based on the multi-task learning (MTL) and achieves real-time simultaneous 3D reconstruction and tumor segmentation from single X-ray projection at any angle. Futhermore, we propose the attention enhanced calibrator (AEC) and uncertain-region elaboration (URE) modules to aid feature extraction and improve segmentation accuracy. We evaluated the proposed method on ten patient cases and compared it with two state-of-the-art methods. Our approach not only delivered superior 3D reconstruction but also demonstrated commendable tumor segmentation results. The simultaneous reconstruction and segmentation could be completed in approximately 70 ms, significantly faster than the required time threshold for real-time tumor tracking. The efficacy of both AEC and URE was also validated through ablation studies.
Authors: Haoling Li, Jiuniu Wang, Zhiwei Wei, Wenjia Xu
Navigation and localization of UAVs present a challenge when global navigation satellite systems (GNSS) are disrupted and unreliable. Traditional techniques, such as simultaneous localization and mapping (SLAM) and visual odometry (VO), exhibit certain limitations in furnishing absolute coordinates and mitigating error accumulation. Existing visual localization methods achieve autonomous visual localization without error accumulation by matching with ortho satellite images. However, doing so cannot guarantee real-time performance due to the complex matching process. To address these challenges, we propose a novel Global-Local Visual Localization (GLVL) network. Our GLVL network is a two-stage visual localization approach, combining a large-scale retrieval module that finds similar regions with the UAV flight scene, and a fine-grained matching module that localizes the precise UAV coordinate, enabling real-time and precise localization. The training process is jointly optimized in an end-to-end manner to further enhance the model capability. Experiments on six UAV flight scenes encompassing both texture-rich and texture-sparse regions demonstrate the ability of our model to achieve the real-time precise localization requirements of UAVs. Particularly, our method achieves a localization error of only 2.39 meters in 0.48 seconds in a village scene with sparse texture features.
Authors: Qiuhui Chen, Haiying Lyu, Xinyue Hu, Yong Lu, Yi Hong
Recently, weakly-supervised image segmentation using weak annotations like scribbles has gained great attention in computer vision and medical image analysis, since such annotations are much easier to obtain compared to time-consuming and labor-intensive labeling at the pixel/voxel level. However, due to a lack of structure supervision on regions of interest (ROIs), existing scribble-based methods suffer from poor boundary localization. Furthermore, most current methods are designed for 2D image segmentation, which do not fully leverage the volumetric information if directly applied to each image slice. In this paper, we propose a scribble-based volumetric image segmentation, Scribble2D5, which tackles 3D anisotropic image segmentation and aims to its improve boundary prediction. To achieve this, we augment a 2.5D attention UNet with a proposed label propagation module to extend semantic information from scribbles and use a combination of static and active boundary prediction to learn ROI's boundary and regularize its shape. Also, we propose an optional add-on component, which incorporates the shape prior information from unpaired segmentation masks to further improve model accuracy. Extensive experiments on three public datasets and one private dataset demonstrate our Scribble2D5 achieves state-of-the-art performance on volumetric image segmentation using scribbles and shape prior if available.
Authors: Haohan Weng, Tianyu Yang, Jianan Wang, Yu Li, Tong Zhang, C. L. Philip Chen, Lei Zhang
Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for downstream tasks like 3D reconstruction and image-to-3D generation. To empower consistency, we propose Consistent123 to synthesize novel views simultaneously by incorporating additional cross-view attention layers and the shared self-attention mechanism. The proposed attention mechanism improves the interaction across all synthesized views, as well as the alignment between the condition view and novel views. In the sampling stage, such architecture supports simultaneously generating an arbitrary number of views while training at a fixed length. We also introduce a progressive classifier-free guidance strategy to achieve the trade-off between texture and geometry for synthesized object views. Qualitative and quantitative experiments show that Consistent123 outperforms baselines in view consistency by a large margin. Furthermore, we demonstrate a significant improvement of Consistent123 on varying downstream tasks, showing its great potential in the 3D generation field. The project page is available at consistent-123.github.io.
Authors: Zijie Wu, Chaohui Yu, Zhen Zhu, Fan Wang, Xiang Bai
Recent progress in text-to-image (T2I) models enables high-quality image generation with flexible textual control. To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper embedding that aligns with the semantic space of the T2I model. However, these image-to-text (I2T) inversion methods typically need multiple source images containing the same concept or struggle with the imbalance between editing flexibility and visual fidelity. In this work, we point out that the critical problem lies in the foreground-background entanglement when learning an intended concept, and propose a simple and effective baseline for single-image I2T inversion, named SingleInsert. SingleInsert adopts a two-stage scheme. In the first stage, we regulate the learned embedding to concentrate on the foreground area without being associated with the irrelevant background. In the second stage, we finetune the T2I model for better visual resemblance and devise a semantic loss to prevent the language drift problem. With the proposed techniques, SingleInsert excels in single concept generation with high visual fidelity while allowing flexible editing. Additionally, SingleInsert can perform single-image novel view synthesis and multiple concepts composition without requiring joint training. To facilitate evaluation, we design an editing prompt list and introduce a metric named Editing Success Rate (ESR) for quantitative assessment of editing flexibility. Our project page is: https://jarrentwu1031.github.io/SingleInsert-web/
Authors: Beier Zhu, Kaihua Tang, Qianru Sun, Hanwang Zhang
Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Yet, the zero-shot performance is less competitive than a fully supervised one. Thus, to enhance the performance, fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that such prior work has overlooked the inherent biases in foundation models. Due to the highly imbalanced Web-scale training set, these foundation models are inevitably skewed toward frequent semantics, and thus the subsequent fine-tuning or ensembling is still biased. In this study, we systematically examine the biases in foundation models and demonstrate the efficacy of our proposed Generalized Logit Adjustment (GLA) method. Note that bias estimation in foundation models is challenging, as most pre-train data cannot be explicitly accessed like in traditional long-tailed classification tasks. To this end, GLA has an optimization-based bias estimation approach for debiasing foundation models. As our work resolves a fundamental flaw in the pre-training, the proposed GLA demonstrates significant improvements across a diverse range of tasks: it achieves 1.5 pp accuracy gains on ImageNet, an large average improvement (1.4-4.6 pp) on 11 few-shot datasets, 2.4 pp gains on long-tailed classification. Codes are in \url{https://github.com/BeierZhu/GLA}.
Authors: Takahiro Maeda, Keisuke Takeshita, Kazuhito Tanaka
For safe and sophisticated physical human-robot interactions (pHRI), a robot needs to estimate the accurate body pose or mesh of the target person. However, in these pHRI scenarios, the robot cannot fully observe the target person's body with equipped cameras because the target person is usually close to the robot. This leads to severe truncation and occlusions, and results in poor accuracy of human pose estimation. For better accuracy of human pose estimation or mesh recovery on this limited information from cameras, we propose an active measurement and sensor fusion framework of the equipped cameras and other sensors such as touch sensors and 2D LiDAR. These touch and LiDAR sensing are obtained attendantly through pHRI without additional costs. These sensor measurements are sparse but reliable and informative cues for human mesh recovery. In our active measurement process, camera viewpoints and sensor placements are optimized based on the uncertainty of the estimated pose, which is closely related to the truncated or occluded areas. In our sensor fusion process, we fuse the sensor measurements to the camera-based estimated pose by minimizing the distance between the estimated mesh and measured positions. Our method is agnostic to robot configurations. Experiments were conducted using the Toyota Human Support Robot, which has a camera, 2D LiDAR, and a touch sensor on the robot arm. Our proposed method demonstrated the superiority in the human pose estimation accuracy on the quantitative comparison. Furthermore, our proposed method reliably estimated the pose of the target person in practical settings such as target people occluded by a blanket and standing aid with the robot arm.
Authors: Xianghao Kong, Wentao Jiang, Jinrang Jia, Yifeng Shi, Runsheng Xu, Si Liu
Vehicle-to-Everything (V2X) collaborative perception is crucial for autonomous driving. However, achieving high-precision V2X perception requires a significant amount of annotated real-world data, which can always be expensive and hard to acquire. Simulated data have raised much attention since they can be massively produced at an extremely low cost. Nevertheless, the significant domain gap between simulated and real-world data, including differences in sensor type, reflectance patterns, and road surroundings, often leads to poor performance of models trained on simulated data when evaluated on real-world data. In addition, there remains a domain gap between real-world collaborative agents, e.g. different types of sensors may be installed on autonomous vehicles and roadside infrastructures with different extrinsics, further increasing the difficulty of sim2real generalization. To take full advantage of simulated data, we present a new unsupervised sim2real domain adaptation method for V2X collaborative detection named Decoupled Unsupervised Sim2Real Adaptation (DUSA). Our new method decouples the V2X collaborative sim2real domain adaptation problem into two sub-problems: sim2real adaptation and inter-agent adaptation. For sim2real adaptation, we design a Location-adaptive Sim2Real Adapter (LSA) module to adaptively aggregate features from critical locations of the feature map and align the features between simulated data and real-world data via a sim/real discriminator on the aggregated global feature. For inter-agent adaptation, we further devise a Confidence-aware Inter-agent Adapter (CIA) module to align the fine-grained features from heterogeneous agents under the guidance of agent-wise confidence maps. Experiments demonstrate the effectiveness of the proposed DUSA approach on unsupervised sim2real adaptation from the simulated V2XSet dataset to the real-world DAIR-V2X-C dataset.
Authors: Zijie Chen, Lichao Zhang, Fangsheng Weng, Lili Pan, Zhenzhong Lan
We propose a novel perspective of viewing large pretrained models as search engines, thereby enabling the repurposing of techniques previously used to enhance search engine performance. As an illustration, we employ a personalized query rewriting technique in the realm of text-to-image generation. Despite significant progress in the field, it is still challenging to create personalized visual representations that align closely with the desires and preferences of individual users. This process requires users to articulate their ideas in words that are both comprehensible to the models and accurately capture their vision, posing difficulties for many users. In this paper, we tackle this challenge by leveraging historical user interactions with the system to enhance user prompts. We propose a novel approach that involves rewriting user prompts based a new large-scale text-to-image dataset with over 300k prompts from 3115 users. Our rewriting model enhances the expressiveness and alignment of user prompts with their intended visual outputs. Experimental results demonstrate the superiority of our methods over baseline approaches, as evidenced in our new offline evaluation method and online tests. Our approach opens up exciting possibilities of applying more search engine techniques to build truly personalized large pretrained models.
Authors: Zehao Wang, Yiwen Guo, Qizhang Li, Guanglei Yang, Wangmeng Zuo
Data augmentation is a dominant method for reducing model overfitting and improving generalization. Most existing data augmentation methods tend to find a compromise in augmenting the data, \textit{i.e.}, increasing the amplitude of augmentation carefully to avoid degrading some data too much and doing harm to the model performance. We delve into the relationship between data augmentation and model performance, revealing that the performance drop with heavy augmentation comes from the presence of out-of-distribution (OOD) data. Nonetheless, as the same data transformation has different effects for different training samples, even for heavy augmentation, there remains part of in-distribution data which is beneficial to model training. Based on the observation, we propose a novel data augmentation method, named \textbf{DualAug}, to keep the augmentation in distribution as much as possible at a reasonable time and computational cost. We design a data mixing strategy to fuse augmented data from both the basic- and the heavy-augmentation branches. Extensive experiments on supervised image classification benchmarks show that DualAug improve various automated data augmentation method. Moreover, the experiments on semi-supervised learning and contrastive self-supervised learning demonstrate that our DualAug can also improve related method. Code is available at \href{https://github.com/shuguang99/DualAug}{https://github.com/shuguang99/DualAug}.
Authors: Xu Chen, Yunde Jia, Yuwei Wu
Face anti-spoofing plays a critical role in safeguarding facial recognition systems against presentation attacks. While existing deep learning methods show promising results, they still suffer from the lack of fine-grained annotations, which lead models to learn task-irrelevant or unfaithful features. In this paper, we propose a fine-grained annotation method for face anti-spoofing. Specifically, we first leverage the Segment Anything Model (SAM) to obtain pixel-wise segmentation masks by utilizing face landmarks as point prompts. The face landmarks provide segmentation semantics, which segments the face into regions. We then adopt these regions as masks and assemble them into three separate annotation maps: spoof, living, and background maps. Finally, we combine three separate maps into a three-channel map as annotations for model training. Furthermore, we introduce the Multi-Channel Region Exchange Augmentation (MCREA) to diversify training data and reduce overfitting. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches in both intra-dataset and cross-dataset evaluations.
Authors: Léo Milecki, Jonathan Porée, Hatim Belgharbi, Chloé Bourquin, Rafat Damseh, Patrick Delafontaine-Martel, Frédéric Lesage, Maxime Gasse, Jean Provost
Ultrasound Localization Microscopy can resolve the microvascular bed down to a few micrometers. To achieve such performance microbubble contrast agents must perfuse the entire microvascular network. Microbubbles are then located individually and tracked over time to sample individual vessels, typically over hundreds of thousands of images. To overcome the fundamental limit of diffraction and achieve a dense reconstruction of the network, low microbubble concentrations must be used, which lead to acquisitions lasting several minutes. Conventional processing pipelines are currently unable to deal with interference from multiple nearby microbubbles, further reducing achievable concentrations. This work overcomes this problem by proposing a Deep Learning approach to recover dense vascular networks from ultrasound acquisitions with high microbubble concentrations. A realistic mouse brain microvascular network, segmented from 2-photon microscopy, was used to train a three-dimensional convolutional neural network based on a V-net architecture. Ultrasound data sets from multiple microbubbles flowing through the microvascular network were simulated and used as ground truth to train the 3D CNN to track microbubbles. The 3D-CNN approach was validated in silico using a subset of the data and in vivo on a rat brain acquisition. In silico, the CNN reconstructed vascular networks with higher precision (81%) than a conventional ULM framework (70%). In vivo, the CNN could resolve micro vessels as small as 10 $\mu$m with an increase in resolution when compared against a conventional approach.
Authors: Kenan Morani
The accurate and efficient diagnosis of COVID-19 is of paramount importance, particularly in the context of large-scale medical imaging datasets. In this preprint paper, we propose a novel approach for COVID-19 diagnosis using CT images that leverages the power of Swin Transformer models, state-of-the-art solutions in computer vision tasks. Our method includes a systematic approach for patient-level predictions, where individual CT slices are classified as COVID-19 or non-COVID, and the patient's overall diagnosis is determined through majority voting. The application of the Swin Transformer in this context results in patient-level predictions that demonstrate exceptional diagnostic accuracy. In terms of evaluation metrics, our approach consistently outperforms the baseline, as well as numerous competing methods, showcasing its effectiveness in COVID-19 diagnosis. The macro F1 score achieved by our model exceeds the baseline and offers a robust solution for accurate diagnosis.
Authors: Giuseppe Floris, Raffaele Mura, Luca Scionis, Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio
Evaluating the adversarial robustness of machine learning models using gradient-based attacks is challenging. In this work, we show that hyperparameter optimization can improve fast minimum-norm attacks by automating the selection of the loss function, the optimizer and the step-size scheduler, along with the corresponding hyperparameters. Our extensive evaluation involving several robust models demonstrates the improved efficacy of fast minimum-norm attacks when hyper-up with hyperparameter optimization. We release our open-source code at https://github.com/pralab/HO-FMN.
Authors: Qiang Li, Dan Zhang, Shengzhao Lei, Xun Zhao, Shuyan Li, Porawit Kamnoedboon, WeiWei Li
The lack of standardized robustness metrics and the widespread reliance on numerous unrelated benchmark datasets for testing have created a gap between academically validated robust models and their often problematic practical adoption. To address this, we introduce XIMAGENET-12, an explainable benchmark dataset with over 200K images and 15,600 manual semantic annotations. Covering 12 categories from ImageNet to represent objects commonly encountered in practical life and simulating six diverse scenarios, including overexposure, blurring, color changing, etc., we further propose a novel robustness criterion that extends beyond model generation ability assessment. This benchmark dataset, along with related code, is available at https://sites.google.com/view/ximagenet-12/home. Researchers and practitioners can leverage this resource to evaluate the robustness of their visual models under challenging conditions and ultimately benefit from the demands of practical computer vision systems.
Authors: Jaewoo Lee, Jaehong Yoon, Wonjae Kim, Yunji Kim, Sung Ju Hwang
We present a lifelong audio-video masked autoencoder that continually learns the multimodal representations from a video stream containing audio-video pairs, while its distribution continually shifts over time. Specifically, we propose two novel ideas to tackle the problem: (1) Localized Alignment: We introduce a small trainable multimodal encoder that predicts the audio and video tokens that are well-aligned with each other. This allows the model to learn only the highly correlated audiovisual patches with accurate multimodal relationships. (2) Forget-robust multimodal patch selection: We compare the relative importance of each audio-video patch between the current and past data pair to mitigate unintended drift of the previously learned audio-video representations. Our proposed method, FLAVA (Forget-robust Localized Audio-Video Alignment), therefore, captures the complex relationships between the audio and video modalities during training on a sequence of pre-training tasks while alleviating the forgetting of learned audiovisual correlations. Our experiments validate that FLAVA outperforms the state-of-the-art continual learning methods on several benchmark datasets under continual audio-video representation learning scenarios.
Authors: Jinye Yang, Ji Xu
Long-tailed(LT) classification is an unavoidable and challenging problem in the real world. Most of the existing long-tailed classification methods focus only on solving the inter-class imbalance in which there are more samples in the head class than in the tail class, while ignoring the intra-lass imbalance in which the number of samples of the head attribute within the same class is much larger than the number of samples of the tail attribute. The deviation in the model is caused by both of these factors, and due to the fact that attributes are implicit in most datasets and the combination of attributes is very complex, the intra-class imbalance is more difficult to handle. For this purpose, we proposed a long-tailed classification framework, known as \textbf{\textsc{Cognisance}}, which is founded on Coarse-Grained Leading Forest (CLF) and Multi-Center Loss (MCL), aiming to build a multi-granularity joint solution model by means of invariant feature learning. In this method, we designed an unsupervised learning method, i.e., CLF, to better characterize the distribution of attributes within a class. Depending on the distribution of attributes, we can flexibly construct sampling strategies suitable for different environments. In addition, we introduce a new metric learning loss (MCL), which aims to gradually eliminate confusing attributes during the feature learning process. More importantly, this approach does not depend on a specific model structure and can be integrated with existing LT methods as an independent component. We have conducted extensive experiments and our approach has state-of-the-art performance in both existing benchmarks ImageNet-GLT and MSCOCO-GLT, and can improve the performance of existing LT methods. Our codes are available on GitHub: \url{https://github.com/jinyery/cognisance}
Authors: Preetha Vijayan, Prashant Bhat, Elahe Arani, Bahram Zonooz
Continual learning (CL) has remained a persistent challenge for deep neural networks due to catastrophic forgetting (CF) of previously learned tasks. Several techniques such as weight regularization, experience rehearsal, and parameter isolation have been proposed to alleviate CF. Despite their relative success, these research directions have predominantly remained orthogonal and suffer from several shortcomings, while missing out on the advantages of competing strategies. On the contrary, the brain continually learns, accommodates, and transfers knowledge across tasks by simultaneously leveraging several neurophysiological processes, including neurogenesis, active forgetting, neuromodulation, metaplasticity, experience rehearsal, and context-dependent gating, rarely resulting in CF. Inspired by how the brain exploits multiple mechanisms concurrently, we propose TriRE, a novel CL paradigm that encompasses retaining the most prominent neurons for each task, revising and solidifying the extracted knowledge of current and past tasks, and actively promoting less active neurons for subsequent tasks through rewinding and relearning. Across CL settings, TriRE significantly reduces task interference and surpasses different CL approaches considered in isolation.
Authors: Anand Sharma (MIET, Meerut), A. G. Ramakrishnan (IISc, Bengaluru)
Direction properties of online strokes are used to analyze them in terms of homogeneous regions or sub-strokes with points satisfying common geometric properties. Such sub-strokes are called sub-units. These properties are used to extract sub-units from Hindi ideal online characters. These properties along with some heuristics are used to extract sub-units from Hindi online handwritten characters.\\ A method is developed to extract point stroke, clockwise curve stroke, counter-clockwise curve stroke and loop stroke segments as sub-units from Hindi online handwritten characters. These extracted sub-units are close in structure to the sub-units of the corresponding Hindi online ideal characters.\\ Importance of local representation of online handwritten characters in terms of sub-units is assessed by training a classifier with sub-unit level local and character level global features extracted from characters for character recognition. The classifier has the recognition accuracy of 93.5\% on the testing set. This accuracy is the highest when compared with that of the classifiers trained only with global features extracted from characters in the same training set and evaluated on the same testing set.\\ Sub-unit extraction algorithm and the sub-unit based character classifier are tested on Hindi online handwritten character dataset. This dataset consists of samples from 96 different characters. There are 12832 and 2821 samples in the training and testing sets, respectively.
Authors: Paul Roetzer, Ahmed Abbas, Dongliang Cao, Florian Bernard, Paul Swoboda
In this work we propose to combine the advantages of learning-based and combinatorial formalisms for 3D shape matching. While learning-based shape matching solutions lead to state-of-the-art matching performance, they do not ensure geometric consistency, so that obtained matchings are locally unsmooth. On the contrary, axiomatic methods allow to take geometric consistency into account by explicitly constraining the space of valid matchings. However, existing axiomatic formalisms are impractical since they do not scale to practically relevant problem sizes, or they require user input for the initialisation of non-convex optimisation problems. In this work we aim to close this gap by proposing a novel combinatorial solver that combines a unique set of favourable properties: our approach is (i) initialisation free, (ii) massively parallelisable powered by a quasi-Newton method, (iii) provides optimality gaps, and (iv) delivers decreased runtime and globally optimal results for many instances.
Authors: Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu
Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. The prohibitively expensive training and data collection/curation costs of these models make them valuable Intellectual Property (IP) for organizations. This motivates a vendor-client paradigm, where a vendor trains a large-scale VLM and grants only input-output access to clients on a pay-per-query basis in a black-box setting. The client aims to minimize inference cost by distilling the VLM to a student model using the limited available task-specific data, and further deploying this student model in the downstream application. While naive distillation largely improves the In-Domain (ID) accuracy of the student, it fails to transfer the superior out-of-distribution (OOD) generalization of the VLM teacher using the limited available labeled images. To mitigate this, we propose Vision-Language to Vision-Align, Distill, Predict (VL2V-ADiP), which first aligns the vision and language modalities of the teacher model with the vision modality of a pre-trained student model, and further distills the aligned VLM embeddings to the student. This maximally retains the pre-trained features of the student, while also incorporating the rich representations of the VLM image encoder and the superior generalization of the text embeddings. The proposed approach achieves state-of-the-art results on the standard Domain Generalization benchmarks in a black-box teacher setting, and also when weights of the VLM are accessible.
Authors: Mauro Conti, Nicola Farronato, Stefanos Koffas, Luca Pajola, Stjepan Picek
Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents. Today, the state-of-the-art is achieved by exploiting deep neural networks. However, the cost of this performance is paid at the price of system vulnerability. For instance, in backdoor attacks, attackers compromise the training phase by inserting a backdoor in the victim's model that will be activated at testing time by specific patterns while leaving the overall model performance intact. This work proposes a backdoor attack for OCR resulting in the injection of non-readable characters from malicious input images. This simple but effective attack exposes the state-of-the-art OCR weakness, making the extracted text correct to human eyes but simultaneously unusable for the NLP application that uses OCR as a preprocessing step. Experimental results show that the attacked models successfully output non-readable characters for around 90% of the poisoned instances without harming their performance for the remaining instances.
Authors: Ziying Song, Haiyue Wei, Lin Bai, Lei Yang, Caiyan Jia
LiDAR and cameras are complementary sensors for 3D object detection in autonomous driving. However, it is challenging to explore the unnatural interaction between point clouds and images, and the critical factor is how to conduct feature alignment of heterogeneous modalities. Currently, many methods achieve feature alignment by projection calibration only, without considering the problem of coordinate conversion accuracy errors between sensors, leading to sub-optimal performance. In this paper, we present GraphAlign, a more accurate feature alignment strategy for 3D object detection by graph matching. Specifically, we fuse image features from a semantic segmentation encoder in the image branch and point cloud features from a 3D Sparse CNN in the LiDAR branch. To save computation, we construct the nearest neighbor relationship by calculating Euclidean distance within the subspaces that are divided into the point cloud features. Through the projection calibration between the image and point cloud, we project the nearest neighbors of point cloud features onto the image features. Then by matching the nearest neighbors with a single point cloud to multiple images, we search for a more appropriate feature alignment. In addition, we provide a self-attention module to enhance the weights of significant relations to fine-tune the feature alignment between heterogeneous modalities. Extensive experiments on nuScenes benchmark demonstrate the effectiveness and efficiency of our GraphAlign.
Authors: Qing Ma, Jiancheng Pan, Cong Bai
Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this problem, we propose a novel Direction-Oriented Visual-semantic Embedding Model (DOVE) to mine the relationship between vision and language. Concretely, a Regional-Oriented Attention Module (ROAM) adaptively adjusts the distance between the final visual and textual embeddings in the latent semantic space, oriented by regional visual features. Meanwhile, a lightweight Digging Text Genome Assistant (DTGA) is designed to expand the range of tractable textual representation and enhance global word-level semantic connections using less attention operations. Ultimately, we exploit a global visual-semantic constraint to reduce single visual dependency and serve as an external constraint for the final visual and textual representations. The effectiveness and superiority of our method are verified by extensive experiments including parameter evaluation, quantitative comparison, ablation studies and visual analysis, on two benchmark datasets, RSICD and RSITMD.
Authors: Yuxin Mao, Jing Zhang, Mochu Xiang, Yiran Zhong, Yuchao Dai
We propose an Explicit Conditional Multimodal Variational Auto-Encoder (ECMVAE) for audio-visual segmentation (AVS), aiming to segment sound sources in the video sequence. Existing AVS methods focus on implicit feature fusion strategies, where models are trained to fit the discrete samples in the dataset. With a limited and less diverse dataset, the resulting performance is usually unsatisfactory. In contrast, we address this problem from an effective representation learning perspective, aiming to model the contribution of each modality explicitly. Specifically, we find that audio contains critical category information of the sound producers, and visual data provides candidate sound producer(s). Their shared information corresponds to the target sound producer(s) shown in the visual data. In this case, cross-modal shared representation learning is especially important for AVS. To achieve this, our ECMVAE factorizes the representations of each modality with a modality-shared representation and a modality-specific representation. An orthogonality constraint is applied between the shared and specific representations to maintain the exclusive attribute of the factorized latent code. Further, a mutual information maximization regularizer is introduced to achieve extensive exploration of each modality. Quantitative and qualitative evaluations on the AVSBench demonstrate the effectiveness of our approach, leading to a new state-of-the-art for AVS, with a 3.84 mIOU performance leap on the challenging MS3 subset for multiple sound source segmentation.
Authors: Arpit Mittal, Harshil Jhaveri, Swapnil Mallick, Abhishek Ajmera
Few-shot object classification is the task of classifying objects in an image with limited number of examples as supervision. We propose a one-shot/few-shot classification model that can classify an object of any unseen class into a relatively general category in an hierarchically based classification. Our model uses a three-level hierarchical contrastive loss based ResNet152 classifier for classifying an object based on its features extracted from Image embedding, not used during the training phase. For our experimentation, we have used a subset of the ImageNet (ILSVRC-12) dataset that contains only the animal classes for training our model and created our own dataset of unseen classes for evaluating our trained model. Our model provides satisfactory results in classifying the unknown objects into a generic category which has been later discussed in greater detail.
Authors: Mohamed Ashraf Abdelsalam, Samrudhdhi B. Rangrej, Isma Hadji, Nikita Dvornik, Konstantinos G. Derpanis, Afsaneh Fazly
We study the problem of future step anticipation in procedural videos. Given a video of an ongoing procedural activity, we predict a plausible next procedure step described in rich natural language. While most previous work focus on the problem of data scarcity in procedural video datasets, another core challenge of future anticipation is how to account for multiple plausible future realizations in natural settings. This problem has been largely overlooked in previous work. To address this challenge, we frame future step prediction as modelling the distribution of all possible candidates for the next step. Specifically, we design a generative model that takes a series of video clips as input, and generates multiple plausible and diverse candidates (in natural language) for the next step. Following previous work, we side-step the video annotation scarcity by pretraining our model on a large text-based corpus of procedural activities, and then transfer the model to the video domain. Our experiments, both in textual and video domains, show that our model captures diversity in the next step prediction and generates multiple plausible future predictions. Moreover, our model establishes new state-of-the-art results on YouCookII, where it outperforms existing baselines on the next step anticipation. Finally, we also show that our model can successfully transfer from text to the video domain zero-shot, ie, without fine-tuning or adaptation, and produces good-quality future step predictions from video.
Authors: Magnus Malmström, Anton Kullberg, Isaac Skog, Daniel Axehill, Fredrik Gustafsson
This paper considers the problem of detecting and tracking objects in a sequence of images. The problem is formulated in a filtering framework, using the output of object-detection algorithms as measurements. An extension to the filtering formulation is proposed that incorporates class information from the previous frame to robustify the classification, even if the object-detection algorithm outputs an incorrect prediction. Further, the properties of the object-detection algorithm are exploited to quantify the uncertainty of the bounding box detection in each frame. The complete filtering method is evaluated on camera trap images of the four large Swedish carnivores, bear, lynx, wolf, and wolverine. The experiments show that the class tracking formulation leads to a more robust classification.
Authors: Dominik Hintersdorf, Lukas Struppek, Daniel Neider, Kristian Kersting
The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy attacks. Unfortunately, the task of removing specific information from the models without sacrificing performance is not straightforward and has proven to be challenging. We propose a rather easy yet effective defense based on backdoor attacks to remove private information such as names of individuals from models, and focus in this work on text encoders. Specifically, through strategic insertion of backdoors, we align the embeddings of sensitive phrases with those of neutral terms-"a person" instead of the person's name. Our empirical results demonstrate the effectiveness of our backdoor-based defense on CLIP by assessing its performance using a specialized privacy attack for zero-shot classifiers. Our approach provides not only a new "dual-use" perspective on backdoor attacks, but also presents a promising avenue to enhance the privacy of individuals within models trained on uncurated web-scraped data.
Authors: Yuhao Dong, Zhuoyang Zhang, Yunze Liu, Li Yi
Understanding 4D point cloud sequences online is of significant practical value in various scenarios such as VR/AR, robotics, and autonomous driving. The key goal is to continuously analyze the geometry and dynamics of a 3D scene as unstructured and redundant point cloud sequences arrive. And the main challenge is to effectively model the long-term history while keeping computational costs manageable. To tackle these challenges, we introduce a generic online 4D perception paradigm called NSM4D. NSM4D serves as a plug-and-play strategy that can be adapted to existing 4D backbones, significantly enhancing their online perception capabilities for both indoor and outdoor scenarios. To efficiently capture the redundant 4D history, we propose a neural scene model that factorizes geometry and motion information by constructing geometry tokens separately storing geometry and motion features. Exploiting the history becomes as straightforward as querying the neural scene model. As the sequence progresses, the neural scene model dynamically deforms to align with new observations, effectively providing the historical context and updating itself with the new observations. By employing token representation, NSM4D also exhibits robustness to low-level sensor noise and maintains a compact size through a geometric sampling scheme. We integrate NSM4D with state-of-the-art 4D perception backbones, demonstrating significant improvements on various online perception benchmarks in indoor and outdoor settings. Notably, we achieve a 9.6% accuracy improvement for HOI4D online action segmentation and a 3.4% mIoU improvement for SemanticKITTI online semantic segmentation. Furthermore, we show that NSM4D inherently offers excellent scalability to longer sequences beyond the training set, which is crucial for real-world applications.
Authors: Yishun Dou, Zhong Zheng, Qiaoqiao Jin, Bingbing Ni, Yugang Chen, Junxiang Ke
We propose a novel compact and efficient neural BRDF offering highly versatile material representation, yet with very-light memory and neural computation consumption towards achieving real-time rendering. The results in Figure 1, rendered at full HD resolution on a current desktop machine, show that our system achieves real-time rendering with a wide variety of appearances, which is approached by the following two designs. On the one hand, noting that bidirectional reflectance is distributed in a very sparse high-dimensional subspace, we propose to project the BRDF into two low-dimensional components, i.e., two hemisphere feature-grids for incoming and outgoing directions, respectively. On the other hand, learnable neural reflectance primitives are distributed on our highly-tailored spherical surface grid, which offer informative features for each component and alleviate the conventional heavy feature learning network to a much smaller one, leading to very fast evaluation. These primitives are centrally stored in a codebook and can be shared across multiple grids and even across materials, based on the low-cost indices stored in material-specific spherical surface grids. Our neural BRDF, which is agnostic to the material, provides a unified framework that can represent a variety of materials in consistent manner. Comprehensive experimental results on measured BRDF compression, Monte Carlo simulated BRDF acceleration, and extension to spatially varying effect demonstrate the superior quality and generalizability achieved by the proposed scheme.
Authors: Eve Le Guillou, Michael Will, Pierre Guillou, Jonas Lukasczyk, Pierre Fortin, Christoph Garth, Julien Tierny
This system paper presents a software framework for the support of topological analysis pipelines in a distributed-memory model. While several recent papers introduced topology-based approaches for distributed-memory environments, these were reporting experiments obtained with tailored, mono-algorithm implementations. In contrast, we describe in this paper a general-purpose, generic framework for topological analysis pipelines, i.e. a sequence of topological algorithms interacting together, possibly on distinct numbers of processes. Specifically, we instantiated our framework with the MPI model, within the Topology ToolKit (TTK). While developing this framework, we faced several algorithmic and software engineering challenges, which we document in this paper. We provide a taxonomy for the distributed-memory topological algorithms supported by TTK, depending on their communication needs and provide examples of hybrid MPI+thread parallelizations. Detailed performance analyses show that parallel efficiencies range from $20\%$ to $80\%$ (depending on the algorithms), and that the MPI-specific preconditioning introduced by our framework induces a negligible computation time overhead. We illustrate the new distributed-memory capabilities of TTK with an example of advanced analysis pipeline, combining multiple algorithms, run on the largest publicly available dataset we have found (120 billion vertices) on a standard cluster with 64 nodes (for a total of 1,536 cores). Finally, we provide a roadmap for the completion of TTK's MPI extension, along with generic recommendations for each algorithm communication category.
Authors: David Chuan-En Lin, Anastasis Germanidis, Cristóbal Valenzuela, Yining Shi, Nikolas Martelaro
In the art of video editing, sound helps add character to an object and immerse the viewer within a space. Through formative interviews with professional editors (N=10), we found that the task of adding sounds to video can be challenging. This paper presents Soundify, a system that assists editors in matching sounds to video. Given a video, Soundify identifies matching sounds, synchronizes the sounds to the video, and dynamically adjusts panning and volume to create spatial audio. In a human evaluation study (N=889), we show that Soundify is capable of matching sounds to video out-of-the-box for a diverse range of audio categories. In a within-subjects expert study (N=12), we demonstrate the usefulness of Soundify in helping video editors match sounds to video with lighter workload, reduced task completion time, and improved usability.
Authors: Daniel Wilson, Xiaohan Zhang, Waqas Sultani, Safwan Wshah
The concept of geo-localization refers to the process of determining where on earth some `entity' is located, typically using Global Positioning System (GPS) coordinates. The entity of interest may be an image, sequence of images, a video, satellite image, or even objects visible within the image. As massive datasets of GPS tagged media have rapidly become available due to smartphones and the internet, and deep learning has risen to enhance the performance capabilities of machine learning models, the fields of visual and object geo-localization have emerged due to its significant impact on a wide range of applications such as augmented reality, robotics, self-driving vehicles, road maintenance, and 3D reconstruction. This paper provides a comprehensive survey of geo-localization involving images, which involves either determining from where an image has been captured (Image geo-localization) or geo-locating objects within an image (Object geo-localization). We will provide an in-depth study, including a summary of popular algorithms, a description of proposed datasets, and an analysis of performance results to illustrate the current state of each field.
Authors: Zhuomin Zhang, Elizabeth C. Mansfield, Jia Li, John Russell, George S. Young, Catherine Adams, James Z. Wang
The British landscape painter John Constable is considered foundational for the Realist movement in 19th-century European painting. Constable's painted skies, in particular, were seen as remarkably accurate by his contemporaries, an impression shared by many viewers today. Yet, assessing the accuracy of realist paintings like Constable's is subjective or intuitive, even for professional art historians, making it difficult to say with certainty what set Constable's skies apart from those of his contemporaries. Our goal is to contribute to a more objective understanding of Constable's realism. We propose a new machine-learning-based paradigm for studying pictorial realism in an explainable way. Our framework assesses realism by measuring the similarity between clouds painted by artists noted for their skies, like Constable, and photographs of clouds. The experimental results of cloud classification show that Constable approximates more consistently than his contemporaries the formal features of actual clouds in his paintings. The study, as a novel interdisciplinary approach that combines computer vision and machine learning, meteorology, and art history, is a springboard for broader and deeper analyses of pictorial realism.
Authors: Nafaa Nacereddine, Djemel Ziou, Aicha Baya Goumeidane
Since the Radon transform (RT) consists in a line integral function, some modeling assumptions are made on Computed Tomography (CT) system, making image reconstruction analytical methods, such as Filtered Backprojection (FBP), sensitive to artifacts and noise. In the other hand, recently, a new integral transform, called Scale Space Radon Transform (SSRT), is introduced where, RT is a particular case. Thanks to its interesting properties, such as good scale space behavior, the SSRT has known number of new applications. In this paper, with the aim to improve the reconstructed image quality for these methods, we propose to model the X-ray beam with the Scale Space Radon Transform (SSRT) where, the assumptions done on the physical dimensions of the CT system elements reflect better the reality. After depicting the basic properties and the inversion of SSRT, the FBP algorithm is used to reconstruct the image from the SSRT sinogram where the RT spectrum used in FBP is replaced by SSRT and the Gaussian kernel, expressed in their frequency domain. PSNR and SSIM, as quality measures, are used to compare RT and SSRT-based image reconstruction on Shepp-Logan head and anthropomorphic abdominal phantoms. The first findings show that the SSRT-based method outperforms the methods based on RT, especially, when the number of projections is reduced, making it more appropriate for applications requiring low-dose radiation, such as medical X-ray CT. While SSRT-FBP and RT-FBP have utmost the same runtime, the experiments show that SSRT-FBP is more robust to Poisson-Gaussian noise corrupting CT data.
Authors: Han Wu, Holland Qian, Huaming Wu, Aad van Moorsel
While Identity Document Verification (IDV) technology on mobile devices becomes ubiquitous in modern business operations, the risk of identity theft and fraud is increasing. The identity document holder is normally required to participate in an online video interview to circumvent impostors. However, the current IDV process depends on an additional human workforce to support online step-by-step guidance which is inefficient and expensive. The performance of existing AI-based approaches cannot meet the real-time and lightweight demands of mobile devices. In this paper, we address those challenges by designing an edge intelligence-assisted approach for real-time IDV. Aiming at improving the responsiveness of the IDV process, we propose a new document localization model for mobile devices, LDRNet, to Localize the identity Document in Real-time. On the basis of a lightweight backbone network, we build three prediction branches for LDRNet, the corner points prediction, the line borders prediction and the document classification. We design novel supplementary targets, the equal-division points, and use a new loss function named Line Loss, to improve the speed and accuracy of our approach. In addition to the IDV process, LDRNet is an efficient and reliable document localization alternative for all kinds of mobile applications. As a matter of proof, we compare the performance of LDRNet with other popular approaches on localizing general document datasets. The experimental results show that LDRNet runs at a speed up to 790 FPS which is 47x faster, while still achieving comparable Jaccard Index(JI) in single-model and single-scale tests.
Authors: Li Zhang, Jiachen Lu, Sixiao Zheng, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng, Philip H.S. Torr
The emergence of vision transformers (ViTs) in image classification has shifted the methodologies for visual representation learning. In particular, ViTs learn visual representation at full receptive field per layer across all the image patches, in comparison to the increasing receptive fields of CNNs across layers and other alternatives (e.g., large kernels and atrous convolution). In this work, for the first time we explore the global context learning potentials of ViTs for dense visual prediction (e.g., semantic segmentation). Our motivation is that through learning global context at full receptive field layer by layer, ViTs may capture stronger long-range dependency information, critical for dense prediction tasks. We first demonstrate that encoding an image as a sequence of patches, a vanilla ViT without local convolution and resolution reduction can yield stronger visual representation for semantic segmentation. For example, our model, termed as SEgmentation TRansformer (SETR), excels on ADE20K (50.28% mIoU, the first position in the test leaderboard on the day of submission) and Pascal Context (55.83% mIoU), and performs competitively on Cityscapes. For tackling general dense visual prediction tasks in a cost-effective manner, we further formulate a family of Hierarchical Local-Global (HLG) Transformers, characterized by local attention within windows and global-attention across windows in a pyramidal architecture. Extensive experiments show that our methods achieve appealing performance on a variety of dense prediction tasks (e.g., object detection and instance segmentation and semantic segmentation) as well as image classification. Our code and models are available at https://github.com/fudan-zvg/SETR.
Authors: Tarun Kalluri, Astuti Sharma, Manmohan Chandraker
Practical real world datasets with plentiful categories introduce new challenges for unsupervised domain adaptation like small inter-class discriminability, that existing approaches relying on domain invariance alone cannot handle sufficiently well. In this work we propose MemSAC, which exploits sample level similarity across source and target domains to achieve discriminative transfer, along with architectures that scale to a large number of categories. For this purpose, we first introduce a memory augmented approach to efficiently extract pairwise similarity relations between labeled source and unlabeled target domain instances, suited to handle an arbitrary number of classes. Next, we propose and theoretically justify a novel variant of the contrastive loss to promote local consistency among within-class cross domain samples while enforcing separation between classes, thus preserving discriminative transfer from source to target. We validate the advantages of MemSAC with significant improvements over previous state-of-the-art on multiple challenging transfer tasks designed for large-scale adaptation, such as DomainNet with 345 classes and fine-grained adaptation on Caltech-UCSD birds dataset with 200 classes. We also provide in-depth analysis and insights into the effectiveness of MemSAC.
Authors: Ze Wang, Kailun Yang, Hao Shi, Peng Li, Fei Gao, Jian Bai, Kaiwei Wang
Simultaneous Localization And Mapping (SLAM) has become a crucial aspect in the fields of autonomous driving and robotics. One crucial component of visual SLAM is the Field-of-View (FoV) of the camera, as a larger FoV allows for a wider range of surrounding elements and features to be perceived. However, when the FoV of the camera reaches the negative half-plane, traditional methods for representing image feature points using [u,v,1]^T become ineffective. While the panoramic FoV is advantageous for loop closure, its benefits are not easily realized under large-attitude-angle differences where loop-closure frames cannot be easily matched by existing methods. As loop closure on wide-FoV panoramic data further comes with a large number of outliers, traditional outlier rejection methods are not directly applicable. To address these issues, we propose LF-VISLAM, a Visual Inertial SLAM framework for cameras with extremely Large FoV with loop closure. A three-dimensional vector with unit length is introduced to effectively represent feature points even on the negative half-plane. The attitude information of the SLAM system is leveraged to guide the feature point detection of the loop closure. Additionally, a new outlier rejection method based on the unit length representation is integrated into the loop closure module. We collect the PALVIO dataset using a Panoramic Annular Lens (PAL) system with an entire FoV of 360{\deg}x(40{\deg}~120{\deg}) and an Inertial Measurement Unit (IMU) for Visual Inertial Odometry (VIO) to address the lack of panoramic SLAM datasets. Experiments on the established PALVIO and public datasets show that the proposed LF-VISLAM outperforms state-of-the-art SLAM methods. Our code will be open-sourced at https://github.com/flysoaryun/LF-VISLAM.
Authors: Wachirawit Ponghiran, Chamika Mihiranga Liyanagedera, Kaushik Roy
Event cameras provide an advantage over traditional frame-based cameras when capturing fast-moving objects without a motion blur. They achieve this by recording changes in light intensity (known as events), thus allowing them to operate at a much higher frequency and making them suitable for capturing motions in a highly dynamic scene. Many recent studies have proposed methods to train neural networks (NNs) for predicting optical flow from events. However, they often rely on a spatio-temporal representation constructed from events over a fixed interval, such as 10Hz used in training on the DSEC dataset. This limitation restricts the flow prediction to the same interval (10Hz) whereas the fast speed of event cameras, which can operate up to 3kHz, has not been effectively utilized. In this work, we show that a temporally dense flow estimation at 100Hz can be achieved by treating the flow estimation as a sequential problem using two different variants of recurrent networks - Long-short term memory (LSTM) and spiking neural network (SNN). First, We utilize the NN model constructed similar to the popular EV-FlowNet but with LSTM layers to demonstrate the efficiency of our training method. The model not only produces 10x more frequent optical flow than the existing ones, but the estimated flows also have 13% lower errors than predictions from the baseline EV-FlowNet. Second, we construct an EV-FlowNet SNN but with leaky integrate and fire neurons to efficiently capture the temporal dynamics. We found that simple inherent recurrent dynamics of SNN lead to significant parameter reduction compared to the LSTM model. In addition, because of its event-driven computation, the spiking model is estimated to consume only 1.5% energy of the LSTM model, highlighting the efficiency of SNN in processing events and the potential for achieving temporally dense flow.
Authors: Tianwen Qian, Ran Cui, Jingjing Chen, Pai Peng, Xiaowei Guo, Yu-Gang Jiang
Video question answering (VideoQA) is an essential task in vision-language understanding, which has attracted numerous research attention recently. Nevertheless, existing works mostly achieve promising performances on short videos of duration within 15 seconds. For VideoQA on minute-level long-term videos, those methods are likely to fail because of lacking the ability to deal with noise and redundancy caused by scene changes and multiple actions in the video. Considering the fact that the question often remains concentrated in a short temporal range, we propose to first locate the question to a segment in the video and then infer the answer using the located segment only. Under this scheme, we propose "Locate before Answering" (LocAns), a novel approach that integrates a question locator and an answer predictor into an end-to-end model. During the training phase, the available answer label not only serves as the supervision signal of the answer predictor, but also is used to generate pseudo temporal labels for the question locator. Moreover, we design a decoupled alternative training strategy to update the two modules separately. In the experiments, LocAns achieves state-of-the-art performance on two modern long-term VideoQA datasets NExT-QA and ActivityNet-QA, and its qualitative examples show the reliable performance of the question localization.
Authors: Ziqi Gao, Yuntao Wang, Jianguo Chen, Junliang Xing, Shwetak Patel, Xin Liu, Yuanchun Shi
Multimodal sensors provide complementary information to develop accurate machine-learning methods for human activity recognition (HAR), but introduce significantly higher computational load, which reduces efficiency. This paper proposes an efficient multimodal neural architecture for HAR using an RGB camera and inertial measurement units (IMUs) called Multimodal Temporal Segment Attention Network (MMTSA). MMTSA first transforms IMU sensor data into a temporal and structure-preserving gray-scale image using the Gramian Angular Field (GAF), representing the inherent properties of human activities. MMTSA then applies a multimodal sparse sampling method to reduce data redundancy. Lastly, MMTSA adopts an inter-segment attention module for efficient multimodal fusion. Using three well-established public datasets, we evaluated MMTSA's effectiveness and efficiency in HAR. Results show that our method achieves superior performance improvements 11.13% of cross-subject F1-score on the MMAct dataset than the previous state-of-the-art (SOTA) methods. The ablation study and analysis suggest that MMTSA's effectiveness in fusing multimodal data for accurate HAR. The efficiency evaluation on an edge device showed that MMTSA achieved significantly better accuracy, lower computational load, and lower inference latency than SOTA methods.
Authors: Jiayun Luo, Boyang Li, Cyril Leung
In the evolution of agriculture to its next stage, Agriculture 5.0, artificial intelligence will play a central role. Controlled-environment agriculture, or CEA, is a special form of urban and suburban agricultural practice that offers numerous economic, environmental, and social benefits, including shorter transportation routes to population centers, reduced environmental impact, and increased productivity. Due to its ability to control environmental factors, CEA couples well with computer vision (CV) in the adoption of real-time monitoring of the plant conditions and autonomous cultivation and harvesting. The objective of this paper is to familiarize CV researchers with agricultural applications and agricultural practitioners with the solutions offered by CV. We identify five major CV applications in CEA, analyze their requirements and motivation, and survey the state of the art as reflected in 68 technical papers using deep learning methods. In addition, we discuss five key subareas of computer vision and how they related to these CEA problems, as well as eleven vision-based CEA datasets. We hope the survey will help researchers quickly gain a bird-eye view of the striving research area and will spark inspiration for new research and development.
Authors: Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu, Weiping Wang
Despite the excellent performance of vision-language pre-trained models (VLPs) on conventional VQA task, they still suffer from two problems: First, VLPs tend to rely on language biases in datasets and fail to generalize to out-of-distribution (OOD) data. Second, they are inefficient in terms of memory footprint and computation. Although promising progress has been made in both problems, most existing works tackle them independently. To facilitate the application of VLP to VQA tasks, it is imperative to jointly study VLP compression and OOD robustness, which, however, has not yet been explored. This paper investigates whether a VLP can be compressed and debiased simultaneously by searching sparse and robust subnetworks. To this end, we systematically study the design of a training and compression pipeline to search the subnetworks, as well as the assignment of sparsity to different modality-specific modules. Our experiments involve 3 VLPs, 2 compression methods, 4 training methods, 2 datasets and a range of sparsity levels and random seeds. Our results show that there indeed exist sparse and robust subnetworks, which are competitive with the debiased full VLP and clearly outperform the debiasing SoTAs with fewer parameters on OOD datasets VQA-CP v2 and VQA-VS. The codes can be found at https://github.com/PhoebusSi/Compress-Robust-VQA.
Authors: Wenguan Wang, Yi Yang, Fei Wu
Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years. As NeSy shows promise of reconciling the advantages of reasoning and interpretability of symbolic representation and robust learning in neural networks, it may serve as a catalyst for the next generation of AI. In the present paper, we provide a systematic overview of the recent developments and important contributions of NeSy research. Firstly, we introduce study history of this area, covering early work and foundations. We further discuss background concepts and identify key driving factors behind the development of NeSy. Afterward, we categorize recent landmark approaches along several main characteristics that underline this research paradigm, including neural-symbolic integration, knowledge representation, knowledge embedding, and functionality. Next, we briefly discuss the successful application of modern NeSy approaches in several domains. Then, we benchmark several NeSy methods on three representative application tasks. Finally, we identify the open problems together with potential future research directions. This survey is expected to help new researchers enter this rapidly evolving field and accelerate the progress towards data-and knowledge-driven AI.
Authors: Gang Li, Heliang Zheng, Chaoyue Wang, Chang Li, Changwen Zheng, Dacheng Tao
Text-guided diffusion models have shown superior performance in image/video generation and editing. While few explorations have been performed in 3D scenarios. In this paper, we discuss three fundamental and interesting problems on this topic. First, we equip text-guided diffusion models to achieve 3D-consistent generation. Specifically, we integrate a NeRF-like neural field to generate low-resolution coarse results for a given camera view. Such results can provide 3D priors as condition information for the following diffusion process. During denoising diffusion, we further enhance the 3D consistency by modeling cross-view correspondences with a novel two-stream (corresponding to two different views) asynchronous diffusion process. Second, we study 3D local editing and propose a two-step solution that can generate 360-degree manipulated results by editing an object from a single view. Step 1, we propose to perform 2D local editing by blending the predicted noises. Step 2, we conduct a noise-to-text inversion process that maps 2D blended noises into the view-independent text embedding space. Once the corresponding text embedding is obtained, 360-degree images can be generated. Last but not least, we extend our model to perform one-shot novel view synthesis by fine-tuning on a single image, firstly showing the potential of leveraging text guidance for novel view synthesis. Extensive experiments and various applications show the prowess of our 3DDesigner. The project page is available at https://3ddesigner-diffusion.github.io/.
Authors: Lintai Wu, Qijian Zhang, Junhui Hou, Yong Xu
Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the complete shape of an object based on its partial input. These methods can be broadly classified as supervised or unsupervised. However, both categories require a large number of 3D complete point clouds, which may be difficult to capture. In this paper, we propose Cross-PCC, an unsupervised point cloud completion method without requiring any 3D complete point clouds. We only utilize 2D images of the complete objects, which are easier to capture than 3D complete and clean point clouds. Specifically, to take advantage of the complementary information from 2D images, we use a single-view RGB image to extract 2D features and design a fusion module to fuse the 2D and 3D features extracted from the partial point cloud. To guide the shape of predicted point clouds, we project the predicted points of the object to the 2D plane and use the foreground pixels of its silhouette maps to constrain the position of the projected points. To reduce the outliers of the predicted point clouds, we propose a view calibrator to move the points projected to the background into the foreground by the single-view silhouette image. To the best of our knowledge, our approach is the first point cloud completion method that does not require any 3D supervision. The experimental results of our method are superior to those of the state-of-the-art unsupervised methods by a large margin. Moreover, our method even achieves comparable performance to some supervised methods. We will make the source code publicly available at https://github.com/ltwu6/cross-pcc.
Authors: Ziyan Wang, Giljoo Nam, Tuur Stuyck, Stephen Lombardi, Chen Cao, Jason Saragih, Michael Zollhoefer, Jessica Hodgins, Christoph Lassner
The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance, as well as exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently from the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states containing motion and appearance, via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage learns a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for de-noising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without having to rely on hair observations as a driving signal. Project page is here https://ziyanw1.github.io/neuwigs/.
Authors: Feng Lin, Wenze Hu, Yaowei Wang, Yonghong Tian, Guangming Lu, Fanglin Chen, Yong Xu, Xiaoyu Wang
Over the past few years, there has been growing interest in developing a broad, universal, and general-purpose computer vision system. Such systems have the potential to address a wide range of vision tasks simultaneously, without being limited to specific problems or data domains. This universality is crucial for practical, real-world computer vision applications. In this study, our focus is on a specific challenge: the large-scale, multi-domain universal object detection problem, which contributes to the broader goal of achieving a universal vision system. This problem presents several intricate challenges, including cross-dataset category label duplication, label conflicts, and the necessity to handle hierarchical taxonomies. To address these challenges, we introduce our approach to label handling, hierarchy-aware loss design, and resource-efficient model training utilizing a pre-trained large vision model. Our method has demonstrated remarkable performance, securing a prestigious second-place ranking in the object detection track of the Robust Vision Challenge 2022 (RVC 2022) on a million-scale cross-dataset object detection benchmark. We believe that our comprehensive study will serve as a valuable reference and offer an alternative approach for addressing similar challenges within the computer vision community. The source code for our work is openly available at https://github.com/linfeng93/Large-UniDet.
Authors: Jiaqi Liu, Guoyang Xie, Jinbao Wang, Shangnian Li, Chengjie Wang, Feng Zheng, Yaochu Jin
The recent rapid development of deep learning has laid a milestone in industrial Image Anomaly Detection (IAD). In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets. In addition, we extract the new setting from industrial manufacturing and review the current IAD approaches under our proposed our new setting. Moreover, we highlight several opening challenges for image anomaly detection. The merits and downsides of representative network architectures under varying supervision are discussed. Finally, we summarize the research findings and point out future research directions. More resources are available at https://github.com/M-3LAB/awesome-industrial-anomaly-detection.
Authors: Guoyang Xie, Jinbao Wang, Jiaqi Liu, Feng Zheng, Yaochu Jin
In the area of fewshot anomaly detection (FSAD), efficient visual feature plays an essential role in memory bank M-based methods. However, these methods do not account for the relationship between the visual feature and its rotated visual feature, drastically limiting the anomaly detection performance. To push the limits, we reveal that rotation-invariant feature property has a significant impact in industrial-based FSAD. Specifically, we utilize graph representation in FSAD and provide a novel visual isometric invariant feature (VIIF) as anomaly measurement feature. As a result, VIIF can robustly improve the anomaly discriminating ability and can further reduce the size of redundant features stored in M by a large amount. Besides, we provide a novel model GraphCore via VIIFs that can fast implement unsupervised FSAD training and can improve the performance of anomaly detection. A comprehensive evaluation is provided for comparing GraphCore and other SOTA anomaly detection models under our proposed fewshot anomaly detection setting, which shows GraphCore can increase average AUC by 5.8%, 4.1%, 3.4%, and 1.6% on MVTec AD and by 25.5%, 22.0%, 16.9%, and 14.1% on MPDD for 1, 2, 4, and 8-shot cases, respectively.
Authors: Guoyang Xie, Jinbao Wang, Jiaqi Liu, Jiayi Lyu, Yong Liu, Chengjie Wang, Feng Zheng, Yaochu Jin
Image anomaly detection (IAD) is an urgent issue that needs to be addressed in modern industrial manufacturing (IM). Recently, many advanced algorithms have been released, but their performance varies greatly due to non-uniformed settings. That is, researchers find it difficult to analyze because they are designed for different or specific cases in IM. To eliminate this problem, we first propose a uniform IAD setting to systematically assess the effectiveness of these algorithms, mainly considering three aspects of supervision level (unsupervised, fully supervised), learning paradigm (few-shot, continual, noisy label), and efficiency (memory usage, inference speed). Then, we skillfully construct a comprehensive image anomaly detection benchmark (IM-IAD), which includes 19 algorithms on 7 major datasets with the same setting. Our extensive experiments (17,017 total) provide new insights into the redesign or selection of the IAD algorithm under uniform conditions. Importantly, the proposed IM-IAD presents feasible challenges and future directions for further work. We believe that this work can have a significant impact on the IAD field. To foster reproducibility and accessibility, the source code of IM-IAD is uploaded on the website, https://github.com/M-3LAB/IM-IAD.
Authors: Zifan Yu, Meida Chen, Zhikang Zhang, Suya You, Raghuveer Rao, Sanjeev Agarwal, Fengbo Ren
Common image-based LiDAR point cloud semantic segmentation (LiDAR PCSS) approaches have bottlenecks resulting from the boundary-blurring problem of convolution neural networks (CNNs) and quantitation loss of spherical projection. In this work, we propose a transformer-based plug-and-play uncertain point refiner, i.e., TransUPR, to refine selected uncertain points in a learnable manner, which leads to an improved segmentation performance. Uncertain points are sampled from coarse semantic segmentation results of 2D image segmentation where uncertain points are located close to the object boundaries in the 2D range image representation and 3D spherical projection background points. Following that, the geometry and coarse semantic features of uncertain points are aggregated by neighbor points in 3D space without adding expensive computation and memory footprint. Finally, the transformer-based refiner, which contains four stacked self-attention layers, along with an MLP module, is utilized for uncertain point classification on the concatenated features of self-attention layers. As the proposed refiner is independent of 2D CNNs, our TransUPR can be easily integrated into any existing image-based LiDAR PCSS approaches, e.g., CENet. Our TransUPR with the CENet achieves state-of-the-art performance, i.e., 68.2% mean Intersection over Union (mIoU) on the Semantic KITTI benchmark, which provides a performance improvement of 0.6% on the mIoU compared to the original CENet.
Authors: Yang Chen, Hexiang Hu, Yi Luan, Haitian Sun, Soravit Changpinyo, Alan Ritter, Ming-Wei Chang
Pre-trained vision and language models have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and information-seeking. In this study, we introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge. Using InfoSeek, we analyze various pre-trained visual question answering models and gain insights into their characteristics. Our findings reveal that state-of-the-art pre-trained multi-modal models (e.g., PaLI-X, BLIP2, etc.) face challenges in answering visual information-seeking questions, but fine-tuning on the InfoSeek dataset elicits models to use fine-grained knowledge that was learned during their pre-training. Furthermore, we show that accurate visual entity recognition can be used to improve performance on InfoSeek by retrieving relevant documents, showing a significant space for improvement.
Authors: Kushagra Pandey, Stephan Mandt
Score-based Generative Models (SGMs) have demonstrated exceptional synthesis outcomes across various tasks. However, the current design landscape of the forward diffusion process remains largely untapped and often relies on physical heuristics or simplifying assumptions. Utilizing insights from the development of scalable Bayesian posterior samplers, we present a complete recipe for formulating forward processes in SGMs, ensuring convergence to the desired target distribution. Our approach reveals that several existing SGMs can be seen as specific manifestations of our framework. Building upon this method, we introduce Phase Space Langevin Diffusion (PSLD), which relies on score-based modeling within an augmented space enriched by auxiliary variables akin to physical phase space. Empirical results exhibit the superior sample quality and improved speed-quality trade-off of PSLD compared to various competing approaches on established image synthesis benchmarks. Remarkably, PSLD achieves sample quality akin to state-of-the-art SGMs (FID: 2.10 for unconditional CIFAR-10 generation). Lastly, we demonstrate the applicability of PSLD in conditional synthesis using pre-trained score networks, offering an appealing alternative as an SGM backbone for future advancements. Code and model checkpoints can be accessed at \url{https://github.com/mandt-lab/PSLD}.
Authors: Tina Dorosti, Manuel Schultheiss, Felix Hofmann, Johannes Thalhammer, Luisa Kirchner, Theresa Urban, Franz Pfeiffer, Florian Schaff, Tobias Lasser, Daniela Pfeiffer
We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7,194 CT images (3,597 with COPD; 3,597 healthy controls) from 78 subjects (43 with COPD; 35 healthy controls) were selected retrospectively (10.2018-12.2019) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3,392, 1,114, and 2,688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n=7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.
Authors: Chaoda Zheng, Xu Yan, Haiming Zhang, Baoyuan Wang, Shenghui Cheng, Shuguang Cui, Zhen Li
3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle LiDAR SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M^2-Track. At the 1st-stage, M^2-Track localizes the target within successive frames via motion transformation. Then it refines the target box through motion-assisted shape completion at the 2nd-stage. Due to the motion-centric nature, our method shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training. This inspires us to explore semi-supervised LiDAR SOT by incorporating a pseudo-label-based motion augmentation and a self-supervised loss term. Under the fully-supervised setting, extensive experiments confirm that M^2-Track significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS (~3%, ~11% and ~22% precision gains on KITTI, NuScenes, and Waymo Open Dataset respectively). While under the semi-supervised setting, our method performs on par with or even surpasses its fully-supervised counterpart using fewer than half of the labels from KITTI. Further analysis verifies each component's effectiveness and shows the motion-centric paradigm's promising potential for auto-labeling and unsupervised domain adaptation.
Authors: Diana Waldmannstetter, Benedikt Wiestler, Julian Schwarting, Ivan Ezhov, Marie Metz, Spyridon Bakas, Bhakti Baheti, Satrajit Chakrabarty, Daniel Rueckert, Jan S. Kirschke, Rolf A. Heckemann, Marie Piraud, Bjoern H. Menze, Florian Kofler
Even though simultaneous optimization of similarity metrics is a standard procedure in the field of semantic segmentation, surprisingly, this is much less established for image registration. To help closing this gap in the literature, we investigate in a complex multi-modal 3D setting whether simultaneous optimization of registration metrics, here implemented by means of primitive summation, can benefit image registration. We evaluate two challenging datasets containing collections of pre- to post-operative and pre- to intra-operative MR images of glioma. Employing the proposed optimization, we demonstrate improved registration accuracy in terms of TRE on expert neuroradiologists' landmark annotations.
Authors: Arvi Jonnarth, Yushan Zhang, Michael Felsberg
Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global average pooling (GAP) on convolutional feature maps. This enables the estimation of object locations based on class activation maps (CAMs), which identify the importance of image regions. The CAMs are then used to generate pseudo-labels, in the form of segmentation masks, to supervise a segmentation model in the absence of pixel-level ground truth. Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss, which utilizes a heuristic that object contours almost always align with color edges in images. However, both are based on the multinomial posterior with softmax, and implicitly assume that classes are mutually exclusive, which turns out suboptimal in our experiments. Thus, we reformulate both techniques based on binomial posteriors of multiple independent binary problems. This has two benefits; their performance is improved and they become more general, resulting in an add-on method that can boost virtually any WSSS method. This is demonstrated on a wide variety of baselines on the PASCAL VOC dataset, improving the region similarity and contour quality of all implemented state-of-the-art methods. Experiments on the MS COCO dataset show that our proposed add-on is well-suited for large-scale settings. Our code is available at https://github.com/arvijj/hfpl.
Authors: Xin Zhang, Chen Liu, Degang Yang, Tingting Song, Yichen Ye, Ke Li, Yingze Song
Spatial attention has been widely used to improve the performance of convolutional neural networks. However, it has certain limitations. In this paper, we propose a new perspective on the effectiveness of spatial attention, which is that the spatial attention mechanism essentially solves the problem of convolutional kernel parameter sharing. However, the information contained in the attention map generated by spatial attention is not sufficient for large-size convolutional kernels. Therefore, we propose a novel attention mechanism called Receptive-Field Attention (RFA). Existing spatial attention, such as Convolutional Block Attention Module (CBAM) and Coordinated Attention (CA) focus only on spatial features, which does not fully address the problem of convolutional kernel parameter sharing. In contrast, RFA not only focuses on the receptive-field spatial feature but also provides effective attention weights for large-size convolutional kernels. The Receptive-Field Attention convolutional operation (RFAConv), developed by RFA, represents a new approach to replace the standard convolution operation. It offers nearly negligible increment of computational cost and parameters, while significantly improving network performance. We conducted a series of experiments on ImageNet-1k, COCO, and VOC datasets to demonstrate the superiority of our approach. Of particular importance, we believe that it is time to shift focus from spatial features to receptive-field spatial features for current spatial attention mechanisms. In this way, we can further improve network performance and achieve even better results. The code and pre-trained models for the relevant tasks can be found at https://github.com/Liuchen1997/RFAConv.
Authors: Jiaze Sun, Zhixiang Chen, Tae-Kyun Kim
3D pose transfer is a challenging generation task that aims to transfer the pose of a source geometry onto a target geometry with the target identity preserved. Many prior methods require keypoint annotations to find correspondence between the source and target. Current pose transfer methods allow end-to-end correspondence learning but require the desired final output as ground truth for supervision. Unsupervised methods have been proposed for graph convolutional models but they require ground truth correspondence between the source and target inputs. We present a novel self-supervised framework for 3D pose transfer which can be trained in unsupervised, semi-supervised, or fully supervised settings without any correspondence labels. We introduce two contrastive learning constraints in the latent space: a mesh-level loss for disentangling global patterns including pose and identity, and a point-level loss for discriminating local semantics. We demonstrate quantitatively and qualitatively that our method achieves state-of-the-art results in supervised 3D pose transfer, with comparable results in unsupervised and semi-supervised settings. Our method is also generalisable to unseen human and animal data with complex topologies.
Authors: Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Youzuo Lin
This paper introduces a novel mathematical property applicable to diverse images, referred to as FINOLA (First-Order Norm+Linear Autoregressive). FINOLA represents each image in the latent space as a first-order autoregressive process, in which each regression step simply applies a shared linear model on the normalized value of its immediate neighbor. This intriguing property reveals a mathematical invariance that transcends individual images. Expanding from image grids to continuous coordinates, we unveil the presence of two underlying partial differential equations. We validate the FINOLA property from two distinct angles: image reconstruction and self-supervised learning. Firstly, we demonstrate the ability of FINOLA to auto-regress up to a 256x256 feature map (the same resolution to the image) from a single vector placed at the center, successfully reconstructing the original image by only using three 3x3 convolution layers as decoder. Secondly, we leverage FINOLA for self-supervised learning by employing a simple masked prediction approach. Encoding a single unmasked quadrant block, we autoregressively predict the surrounding masked region. Remarkably, this pre-trained representation proves highly effective in image classification and object detection tasks, even when integrated into lightweight networks, all without the need for extensive fine-tuning. The code will be made publicly available.
Authors: Sebastián Maldonado, Carla Vairetti, Katherine Jara, Miguel Carrasco, Julio López
In this paper, we propose a fuzzy adaptive loss function for enhancing deep learning performance in classification tasks. Specifically, we redefine the cross-entropy loss to effectively address class-level noise conditions, including the challenging problem of class imbalance. Our approach introduces aggregation operators, leveraging the power of fuzzy logic to improve classification accuracy. The rationale behind our proposed method lies in the iterative up-weighting of class-level components within the loss function, focusing on those with larger errors. To achieve this, we employ the ordered weighted average (OWA) operator and combine it with an adaptive scheme for gradient-based learning. Through extensive experimentation, our method outperforms other commonly used loss functions, such as the standard cross-entropy or focal loss, across various binary and multiclass classification tasks. Furthermore, we explore the influence of hyperparameters associated with the OWA operators and present a default configuration that performs well across different experimental settings.
Authors: Jiali Cui, Ying Nian Wu, Tian Han
This paper studies the fundamental problem of learning multi-layer generator models. The multi-layer generator model builds multiple layers of latent variables as a prior model on top of the generator, which benefits learning complex data distribution and hierarchical representations. However, such a prior model usually focuses on modeling inter-layer relations between latent variables by assuming non-informative (conditional) Gaussian distributions, which can be limited in model expressivity. To tackle this issue and learn more expressive prior models, we propose an energy-based model (EBM) on the joint latent space over all layers of latent variables with the multi-layer generator as its backbone. Such joint latent space EBM prior model captures the intra-layer contextual relations at each layer through layer-wise energy terms, and latent variables across different layers are jointly corrected. We develop a joint training scheme via maximum likelihood estimation (MLE), which involves Markov Chain Monte Carlo (MCMC) sampling for both prior and posterior distributions of the latent variables from different layers. To ensure efficient inference and learning, we further propose a variational training scheme where an inference model is used to amortize the costly posterior MCMC sampling. Our experiments demonstrate that the learned model can be expressive in generating high-quality images and capturing hierarchical features for better outlier detection.
Authors: Ziyan Wang, Hao Wang
Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced. In this paper, we propose a probabilistic deep learning model, dubbed variational imbalanced regression (VIR), which not only performs well in imbalanced regression but naturally produces reasonable uncertainty estimation as a byproduct. Different from typical variational autoencoders assuming I.I.D. representations (a data point's representation is not directly affected by other data points), our VIR borrows data with similar regression labels to compute the latent representation's variational distribution; furthermore, different from deterministic regression models producing point estimates, VIR predicts the entire normal-inverse-gamma distributions and modulates the associated conjugate distributions to impose probabilistic reweighting on the imbalanced data, thereby providing better uncertainty estimation. Experiments in several real-world datasets show that our VIR can outperform state-of-the-art imbalanced regression models in terms of both accuracy and uncertainty estimation. Code will soon be available at \url{https://github.com/Wang-ML-Lab/variational-imbalanced-regression}.
Authors: Priya Sundaresan, Suneel Belkhale, Dorsa Sadigh, Jeannette Bohg
While natural language offers a convenient shared interface for humans and robots, enabling robots to interpret and follow language commands remains a longstanding challenge in manipulation. A crucial step to realizing a performant instruction-following robot is achieving semantic manipulation, where a robot interprets language at different specificities, from high-level instructions like "Pick up the stuffed animal" to more detailed inputs like "Grab the left ear of the elephant." To tackle this, we propose Keypoints + Instructions to Execution (KITE), a two-step framework for semantic manipulation which attends to both scene semantics (distinguishing between different objects in a visual scene) and object semantics (precisely localizing different parts within an object instance). KITE first grounds an input instruction in a visual scene through 2D image keypoints, providing a highly accurate object-centric bias for downstream action inference. Provided an RGB-D scene observation, KITE then executes a learned keypoint-conditioned skill to carry out the instruction. The combined precision of keypoints and parameterized skills enables fine-grained manipulation with generalization to scene and object variations. Empirically, we demonstrate KITE in 3 real-world environments: long-horizon 6-DoF tabletop manipulation, semantic grasping, and a high-precision coffee-making task. In these settings, KITE achieves a 75%, 70%, and 71% overall success rate for instruction-following, respectively. KITE outperforms frameworks that opt for pre-trained visual language models over keypoint-based grounding, or omit skills in favor of end-to-end visuomotor control, all while being trained from fewer or comparable amounts of demonstrations. Supplementary material, datasets, code, and videos can be found on our website: this http URL
Authors: Jiahang Cao, Ziqing Wang, Hanzhong Guo, Hao Cheng, Qiang Zhang, Renjing Xu
Spiking neural networks (SNNs) have ultra-low energy consumption and high biological plausibility due to their binary and bio-driven nature compared with artificial neural networks (ANNs). While previous research has primarily focused on enhancing the performance of SNNs in classification tasks, the generative potential of SNNs remains relatively unexplored. In our paper, we put forward Spiking Denoising Diffusion Probabilistic Models (SDDPM), a new class of SNN-based generative models that achieve high sample quality. To fully exploit the energy efficiency of SNNs, we propose a purely Spiking U-Net architecture, which achieves comparable performance to its ANN counterpart using only 4 time steps, resulting in significantly reduced energy consumption. Extensive experimental results reveal that our approach achieves state-of-the-art on the generative tasks and substantially outperforms other SNN-based generative models, achieving up to $12\times$ and $6\times$ improvement on the CIFAR-10 and the CelebA datasets, respectively. Moreover, we propose a threshold-guided strategy that can further improve the performances by 16.7% in a training-free manner. The SDDPM symbolizes a significant advancement in the field of SNN generation, injecting new perspectives and potential avenues of exploration.
Authors: Xuanlin Li, Yunhao Fang, Minghua Liu, Zhan Ling, Zhuowen Tu, Hao Su
Large vision-language models have achieved outstanding performance, but their size and computational requirements make their deployment on resource-constrained devices and time-sensitive tasks impractical. Model distillation, the process of creating smaller, faster models that maintain the performance of larger models, is a promising direction towards the solution. This paper investigates the distillation of visual representations in large teacher vision-language models into lightweight student models using a small- or mid-scale dataset. Notably, this study focuses on open-vocabulary out-of-distribution (OOD) generalization, a challenging problem that has been overlooked in previous model distillation literature. We propose two principles from vision and language modality perspectives to enhance student's OOD generalization: (1) by better imitating teacher's visual representation space, and carefully promoting better coherence in vision-language alignment with the teacher; (2) by enriching the teacher's language representations with informative and finegrained semantic attributes to effectively distinguish between different labels. We propose several metrics and conduct extensive experiments to investigate their techniques. The results demonstrate significant improvements in zero-shot and few-shot student performance on open-vocabulary out-of-distribution classification, highlighting the effectiveness of our proposed approaches. Poster: https://xuanlinli17.github.io/pdfs/iccv23_large_vlm_distillation_poster.pdf Code: https://github.com/xuanlinli17/large_vlm_distillation_ood
Authors: Nicolás Gaggion, Candelaria Mosquera, Lucas Mansilla, Martina Aineseder, Diego H. Milone, Enzo Ferrante
The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of chest X-ray images have been released, most include disease diagnosis labels but lack detailed pixel-level anatomical segmentation labels. To address this gap, we introduce an extensive chest X-ray multi-center segmentation dataset with uniform and fine-grain anatomical annotations for images coming from six well-known publicly available databases: CANDID-PTX, ChestX-ray8, Chexpert, MIMIC-CXR-JPG, Padchest, and VinDr-CXR, resulting in 676,803 segmentation masks. Our methodology utilizes the HybridGNet model to ensure consistent and high-quality segmentations across all datasets. Rigorous validation, including expert physician evaluation and automatic quality control, was conducted to validate the resulting masks. Additionally, we provide individualized quality indices per mask and an overall quality estimation per dataset. This dataset serves as a valuable resource for the broader scientific community, streamlining the development and assessment of innovative methodologies in chest X-ray analysis. The CheXmask dataset is publicly available at: https://physionet.org/content/chexmask-cxr-segmentation-data/
Authors: Ke Cao, Ruiping Liu, Ze Wang, Kunyu Peng, Jiaming Zhang, Junwei Zheng, Zhifeng Teng, Kailun Yang, Rainer Stiefelhagen
The mobile robot relies on SLAM (Simultaneous Localization and Mapping) to provide autonomous navigation and task execution in complex and unknown environments. However, it is hard to develop a dedicated algorithm for mobile robots due to dynamic and challenging situations, such as poor lighting conditions and motion blur. To tackle this issue, we propose a tightly-coupled LiDAR-visual SLAM based on geometric features, which includes two sub-systems (LiDAR and monocular visual SLAM) and a fusion framework. The fusion framework associates the depth and semantics of the multi-modal geometric features to complement the visual line landmarks and to add direction optimization in Bundle Adjustment (BA). This further constrains visual odometry. On the other hand, the entire line segment detected by the visual subsystem overcomes the limitation of the LiDAR subsystem, which can only perform the local calculation for geometric features. It adjusts the direction of linear feature points and filters out outliers, leading to a higher accurate odometry system. Finally, we employ a module to detect the subsystem's operation, providing the LiDAR subsystem's output as a complementary trajectory to our system while visual subsystem tracking fails. The evaluation results on the public dataset M2DGR, gathered from ground robots across various indoor and outdoor scenarios, show that our system achieves more accurate and robust pose estimation compared to current state-of-the-art multi-modal methods.
Authors: Xiaohong Fan, Yin Yang, Ke Chen, Yujie Feng, Jianping Zhang
Proximal gradient-based optimization is one of the most common strategies to solve inverse problem of images, and it is easy to implement. However, these techniques often generate heavy artifacts in image reconstruction. One of the most popular refinement methods is to fine-tune the regularization parameter to alleviate such artifacts, but it may not always be sufficient or applicable due to increased computational costs. In this work, we propose a deep geometric incremental learning framework based on the second Nesterov proximal gradient optimization. The proposed end-to-end network not only has the powerful learning ability for high-/low-frequency image features, but also can theoretically guarantee that geometric texture details will be reconstructed from preliminary linear reconstruction. Furthermore, it can avoid the risk of intermediate reconstruction results falling outside the geometric decomposition domains and achieve fast convergence. Our reconstruction framework is decomposed into four modules including general linear reconstruction, cascade geometric incremental restoration, Nesterov acceleration, and post-processing. In the image restoration step, a cascade geometric incremental learning module is designed to compensate for missing texture information from different geometric spectral decomposition domains. Inspired by the overlap-tile strategy, we also develop a post-processing module to remove the block effect in patch-wise-based natural image reconstruction. All parameters in the proposed model are learnable, an adaptive initialization technique of physical parameters is also employed to make model flexibility and ensure converging smoothly. We compare the reconstruction performance of the proposed method with existing state-of-the-art methods to demonstrate its superiority. Our source codes are available at https://github.com/fanxiaohong/Nest-DGIL.
Authors: Zixuan He (1) (2), Salik Ram Khanal (1) (2), Xin Zhang (3), Manoj Karkee (1) (2), Qin Zhang (1) (2) ((1) Center for Precision and Automated Agricultural Systems, Washington State University, (2) Department of Biological Systems Engineering, Washington State University, (3) Department of Agricultural and Biological Engineering, Mississippi State University)
This study proposed a YOLOv5-based custom object detection model to detect strawberries in an outdoor environment. The original architecture of the YOLOv5s was modified by replacing the C3 module with the C2f module in the backbone network, which provided a better feature gradient flow. Secondly, the Spatial Pyramid Pooling Fast in the final layer of the backbone network of YOLOv5s was combined with Cross Stage Partial Net to improve the generalization ability over the strawberry dataset in this study. The proposed architecture was named YOLOv5s-Straw. The RGB images dataset of the strawberry canopy with three maturity classes (immature, nearly mature, and mature) was collected in open-field environment and augmented through a series of operations including brightness reduction, brightness increase, and noise adding. To verify the superiority of the proposed method for strawberry detection in open-field environment, four competitive detection models (YOLOv3-tiny, YOLOv5s, YOLOv5s-C2f, and YOLOv8s) were trained, and tested under the same computational environment and compared with YOLOv5s-Straw. The results showed that the highest mean average precision of 80.3% was achieved using the proposed architecture whereas the same was achieved with YOLOv3-tiny, YOLOv5s, YOLOv5s-C2f, and YOLOv8s were 73.4%, 77.8%, 79.8%, 79.3%, respectively. Specifically, the average precision of YOLOv5s-Straw was 82.1% in the immature class, 73.5% in the nearly mature class, and 86.6% in the mature class, which were 2.3% and 3.7%, respectively, higher than that of the latest YOLOv8s. The model included 8.6*10^6 network parameters with an inference speed of 18ms per image while the inference speed of YOLOv8s had a slower inference speed of 21.0ms and heavy parameters of 11.1*10^6, which indicates that the proposed model is fast enough for real time strawberry detection and localization for the robotic picking.
Authors: Emanuele Bugliarello, Hernan Moraldo, Ruben Villegas, Mohammad Babaeizadeh, Mohammad Taghi Saffar, Han Zhang, Dumitru Erhan, Vittorio Ferrari, Pieter-Jan Kindermans, Paul Voigtlaender
Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark for video generation requires data annotated over time, which contrasts with the single caption used often in video datasets. To fill this gap, we collect comprehensive human annotations on three existing datasets, and introduce StoryBench: a new, challenging multi-task benchmark to reliably evaluate forthcoming text-to-video models. Our benchmark includes three video generation tasks of increasing difficulty: action execution, where the next action must be generated starting from a conditioning video; story continuation, where a sequence of actions must be executed starting from a conditioning video; and story generation, where a video must be generated from only text prompts. We evaluate small yet strong text-to-video baselines, and show the benefits of training on story-like data algorithmically generated from existing video captions. Finally, we establish guidelines for human evaluation of video stories, and reaffirm the need of better automatic metrics for video generation. StoryBench aims at encouraging future research efforts in this exciting new area.
Authors: Usman Muhammad, Mourad Oussalah, Jorma Laaksonen
With the growing availability of databases for face presentation attack detection, researchers are increasingly focusing on video-based face anti-spoofing methods that involve hundreds to thousands of images for training the models. However, there is currently no clear consensus on the optimal number of frames in a video to improve face spoofing detection. Inspired by the visual saliency theory, we present a video summarization method for face anti-spoofing detection that aims to enhance the performance and efficiency of deep learning models by leveraging visual saliency. In particular, saliency information is extracted from the differences between the Laplacian and Wiener filter outputs of the source images, enabling identification of the most visually salient regions within each frame. Subsequently, the source images are decomposed into base and detail images, enhancing the representation of the most important information. Weighting maps are then computed based on the saliency information, indicating the importance of each pixel in the image. By linearly combining the base and detail images using the weighting maps, the method fuses the source images to create a single representative image that summarizes the entire video. The key contribution of the proposed method lies in demonstrating how visual saliency can be used as a data-centric approach to improve the performance and efficiency for face presentation attack detection. By focusing on the most salient images or regions within the images, a more representative and diverse training set can be created, potentially leading to more effective models. To validate the method's effectiveness, a simple CNN-RNN deep learning architecture was used, and the experimental results showcased state-of-the-art performance on five challenging face anti-spoofing datasets
Authors: Sushrut Thorat, Adrien Doerig, Tim C. Kietzmann
Recurrent neural networks (RNNs) have yielded promising results for both recognizing objects in challenging conditions and modeling aspects of primate vision. However, the representational dynamics of recurrent computations remain poorly understood, especially in large-scale visual models. Here, we studied such dynamics in RNNs trained for object classification on MiniEcoset, a novel subset of ecoset. We report two main insights. First, upon inference, representations continued to evolve after correct classification, suggesting a lack of the notion of being ``done with classification''. Second, focusing on ``readout zones'' as a way to characterize the activation trajectories, we observe that misclassified representations exhibit activation patterns with lower L2 norm, and are positioned more peripherally in the readout zones. Such arrangements help the misclassified representations move into the correct zones as time progresses. Our findings generalize to networks with lateral and top-down connections, and include both additive and multiplicative interactions with the bottom-up sweep. The results therefore contribute to a general understanding of RNN dynamics in naturalistic tasks. We hope that the analysis framework will aid future investigations of other types of RNNs, including understanding of representational dynamics in primate vision.
Authors: Nazmus Sakib Ahmed, Saad Sakib Noor, Ashraful Islam Shanto Sikder, Abhijit Paul
This paper focuses on enhancing Bengali Document Layout Analysis (DLA) using the YOLOv8 model and innovative post-processing techniques. We tackle challenges unique to the complex Bengali script by employing data augmentation for model robustness. After meticulous validation set evaluation, we fine-tune our approach on the complete dataset, leading to a two-stage prediction strategy for accurate element segmentation. Our ensemble model, combined with post-processing, outperforms individual base architectures, addressing issues identified in the BaDLAD dataset. By leveraging this approach, we aim to advance Bengali document analysis, contributing to improved OCR and document comprehension and BaDLAD serves as a foundational resource for this endeavor, aiding future research in the field. Furthermore, our experiments provided key insights to incorporate new strategies into the established solution.
Authors: Yuan Gan, Zongxin Yang, Xihang Yue, Lingyun Sun, Yi Yang
Audio-driven talking-head synthesis is a popular research topic for virtual human-related applications. However, the inflexibility and inefficiency of existing methods, which necessitate expensive end-to-end training to transfer emotions from guidance videos to talking-head predictions, are significant limitations. In this work, we propose the Emotional Adaptation for Audio-driven Talking-head (EAT) method, which transforms emotion-agnostic talking-head models into emotion-controllable ones in a cost-effective and efficient manner through parameter-efficient adaptations. Our approach utilizes a pretrained emotion-agnostic talking-head transformer and introduces three lightweight adaptations (the Deep Emotional Prompts, Emotional Deformation Network, and Emotional Adaptation Module) from different perspectives to enable precise and realistic emotion controls. Our experiments demonstrate that our approach achieves state-of-the-art performance on widely-used benchmarks, including LRW and MEAD. Additionally, our parameter-efficient adaptations exhibit remarkable generalization ability, even in scenarios where emotional training videos are scarce or nonexistent. Project website: https://yuangan.github.io/eat/
Authors: Zhengxiang Shi, Aldo Lipani
Prompt tuning (PT), where a small amount of trainable soft (continuous) prompt vectors is affixed to the input of language models (LM), has shown promising results across various tasks and models for parameter-efficient fine-tuning (PEFT). PT stands out from other PEFT approaches because it maintains competitive performance with fewer trainable parameters and does not drastically scale up its parameters as the model size expands. However, PT introduces additional soft prompt tokens, leading to longer input sequences, which significantly impacts training and inference time and memory usage due to the Transformer's quadratic complexity. Particularly concerning for Large Language Models (LLMs) that face heavy daily querying. To address this issue, we propose Decomposed Prompt Tuning (DePT), which decomposes the soft prompt into a shorter soft prompt and a pair of low-rank matrices that are then optimised with two different learning rates. This allows DePT to achieve better performance while saving over 20% memory and time costs compared to vanilla PT and its variants, without changing trainable parameter sizes. Through extensive experiments on 23 natural language processing (NLP) and vision-language (VL) tasks, we demonstrate that DePT outperforms state-of-the-art PEFT approaches, including the full fine-tuning baseline in some scenarios. Additionally, we empirically show that DEPT grows more efficient as the model size increases. Our further study reveals that DePT integrates seamlessly with parameter-efficient transfer learning in the few-shot learning setting and highlights its adaptability to various model architectures and sizes.
Authors: Mazvydas Gudelis, Michal Mackiewicz, Julie Bremner, Sophie Fielding
British Antarctic Survey (BAS) researchers launch annual expeditions to the Antarctic in order to estimate Antarctic Krill biomass and assess the change from previous years. These comparisons provide insight into the effects of the current environment on this key component of the marine food chain. In this work we have developed tools for automating the data collection and analysis process, using web-based image annotation tools and deep learning image classification and regression models. We achieve highly accurate krill instance segmentation results with an average 77.28% AP score, as well as separate maturity stage and length estimation of krill specimens with 62.99% accuracy and a 1.98mm length error respectively.
Authors: Qihang Fan, Huaibo Huang, Mingrui Chen, Hongmin Liu, Ran He
Transformer first appears in the field of natural language processing and is later migrated to the computer vision domain, where it demonstrates excellent performance in vision tasks. However, recently, Retentive Network (RetNet) has emerged as an architecture with the potential to replace Transformer, attracting widespread attention in the NLP community. Therefore, we raise the question of whether transferring RetNet's idea to vision can also bring outstanding performance to vision tasks. To address this, we combine RetNet and Transformer to propose RMT. Inspired by RetNet, RMT introduces explicit decay into the vision backbone, bringing prior knowledge related to spatial distances to the vision model. This distance-related spatial prior allows for explicit control of the range of tokens that each token can attend to. Additionally, to reduce the computational cost of global modeling, we decompose this modeling process along the two coordinate axes of the image. Abundant experiments have demonstrated that our RMT exhibits exceptional performance across various computer vision tasks. For example, RMT achieves 84.1% Top1-acc on ImageNet-1k using merely 4.5G FLOPs. To the best of our knowledge, among all models, RMT achieves the highest Top1-acc when models are of similar size and trained with the same strategy. Moreover, RMT significantly outperforms existing vision backbones in downstream tasks such as object detection, instance segmentation, and semantic segmentation. Our work is still in progress.
Authors: Eros Fanì, Marco Ciccone, Barbara Caputo
We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving. While the first version aims at studying the effect of domain shift of the visual features across clients, in this work, we focus on the distribution skewness of the labels. We propose six new federated scenarios to investigate how label skewness affects the performance of segmentation models and compare it with the effect of domain shift. Finally, we study the impact of using the domain information during testing. Official website: https://feddrive.github.io
Authors: Jiawei Yao, Chuming Li, Keqiang Sun, Yingjie Cai, Hao Li, Wanli Ouyang, Hongsheng Li
Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. In this paper, we identify several critical issues in current state-of-the-art methods, including the Feature Ambiguity of projected 2D features in the ray to the 3D space, the Pose Ambiguity of the 3D convolution, and the Computation Imbalance in the 3D convolution across different depth levels. To address these problems, we devise a novel Normalized Device Coordinates scene completion network (NDC-Scene) that directly extends the 2D feature map to a Normalized Device Coordinates (NDC) space, rather than to the world space directly, through progressive restoration of the dimension of depth with deconvolution operations. Experiment results demonstrate that transferring the majority of computation from the target 3D space to the proposed normalized device coordinates space benefits monocular SSC tasks. Additionally, we design a Depth-Adaptive Dual Decoder to simultaneously upsample and fuse the 2D and 3D feature maps, further improving overall performance. Our extensive experiments confirm that the proposed method consistently outperforms state-of-the-art methods on both outdoor SemanticKITTI and indoor NYUv2 datasets. Our code are available at https://github.com/Jiawei-Yao0812/NDCScene.
Authors: Fabian Mentzer, David Minnen, Eirikur Agustsson, Michael Tschannen
We propose to replace vector quantization (VQ) in the latent representation of VQ-VAEs with a simple scheme termed finite scalar quantization (FSQ), where we project the VAE representation down to a few dimensions (typically less than 10). Each dimension is quantized to a small set of fixed values, leading to an (implicit) codebook given by the product of these sets. By appropriately choosing the number of dimensions and values each dimension can take, we obtain the same codebook size as in VQ. On top of such discrete representations, we can train the same models that have been trained on VQ-VAE representations. For example, autoregressive and masked transformer models for image generation, multimodal generation, and dense prediction computer vision tasks. Concretely, we employ FSQ with MaskGIT for image generation, and with UViM for depth estimation, colorization, and panoptic segmentation. Despite the much simpler design of FSQ, we obtain competitive performance in all these tasks. We emphasize that FSQ does not suffer from codebook collapse and does not need the complex machinery employed in VQ (commitment losses, codebook reseeding, code splitting, entropy penalties, etc.) to learn expressive discrete representations.
Authors: Atsuyuki Miyai, Qing Yu, Go Irie, Kiyoharu Aizawa
Out-of-distribution (OOD) detection is critical for safety-sensitive machine learning applications and has been extensively studied, yielding a plethora of methods developed in the literature. However, most studies for OOD detection did not use pre-trained models and trained a backbone from scratch. In recent years, transferring knowledge from large pre-trained models to downstream tasks by lightweight tuning has become mainstream for training in-distribution (ID) classifiers. To bridge the gap between the practice of OOD detection and current classifiers, the unique and crucial problem is that the samples whose information networks know often come as OOD input. We consider that such data may significantly affect the performance of large pre-trained networks because the discriminability of these OOD data depends on the pre-training algorithm. Here, we define such OOD data as PT-OOD (Pre-Trained OOD) data. In this paper, we aim to reveal the effect of PT-OOD on the OOD detection performance of pre-trained networks from the perspective of pre-training algorithms. To achieve this, we explore the PT-OOD detection performance of supervised and self-supervised pre-training algorithms with linear-probing tuning, the most common efficient tuning method. Through our experiments and analysis, we find that the low linear separability of PT-OOD in the feature space heavily degrades the PT-OOD detection performance, and self-supervised models are more vulnerable to PT-OOD than supervised pre-trained models, even with state-of-the-art detection methods. To solve this vulnerability, we further propose a unique solution to large-scale pre-trained models: Leveraging powerful instance-by-instance discriminative representations of pre-trained models and detecting OOD in the feature space independent of the ID decision boundaries. The code will be available via https://github.com/AtsuMiyai/PT-OOD.
Authors: Adriano D'Alessandro, Ali Mahdavi-Amiri, Ghassan Hamarneh
Crowd counting is a critical task in computer vision, with several important applications. However, existing counting methods rely on labor-intensive density map annotations, necessitating the manual localization of each individual pedestrian. While recent efforts have attempted to alleviate the annotation burden through weakly or semi-supervised learning, these approaches fall short of significantly reducing the workload. We propose a novel approach to eliminate the annotation burden by leveraging latent diffusion models to generate synthetic data. However, these models struggle to reliably understand object quantities, leading to noisy annotations when prompted to produce images with a specific quantity of objects. To address this, we use latent diffusion models to create two types of synthetic data: one by removing pedestrians from real images, which generates ranked image pairs with a weak but reliable object quantity signal, and the other by generating synthetic images with a predetermined number of objects, offering a strong but noisy counting signal. Our method utilizes the ranking image pairs for pre-training and then fits a linear layer to the noisy synthetic images using these crowd quantity features. We report state-of-the-art results for unsupervised crowd counting.
Authors: Yefei He, Jing Liu, Weijia Wu, Hong Zhou, Bohan Zhuang
Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for low-latency real-world applications is constrained by substantial computational costs and latency issues. Quantization is a dominant way to compress and accelerate diffusion models, where post-training quantization (PTQ) and quantization-aware training (QAT) are two main approaches, each bearing its own properties. While PTQ exhibits efficiency in terms of both time and data usage, it may lead to diminished performance in low bit-width. On the other hand, QAT can alleviate performance degradation but comes with substantial demands on computational and data resources. To capitalize on the advantages while avoiding their respective drawbacks, we introduce a data-free and parameter-efficient fine-tuning framework for low-bit diffusion models, dubbed EfficientDM, to achieve QAT-level performance with PTQ-like efficiency. Specifically, we propose a quantization-aware variant of the low-rank adapter (QALoRA) that can be merged with model weights and jointly quantized to low bit-width. The fine-tuning process distills the denoising capabilities of the full-precision model into its quantized counterpart, eliminating the requirement for training data. We also introduce scale-aware optimization and employ temporal learned step-size quantization to further enhance performance. Extensive experimental results demonstrate that our method significantly outperforms previous PTQ-based diffusion models while maintaining similar time and data efficiency. Specifically, there is only a marginal 0.05 sFID increase when quantizing both weights and activations of LDM-4 to 4-bit on ImageNet 256x256. Compared to QAT-based methods, our EfficientDM also boasts a 16.2x faster quantization speed with comparable generation quality.
Authors: Yifan Xu, Pourya Shamsolmoali, Jie Yang
Visual place recognition (VPR) is a highly challenging task that has a wide range of applications, including robot navigation and self-driving vehicles. VPR is particularly difficult due to the presence of duplicate regions and the lack of attention to small objects in complex scenes, resulting in recognition deviations. In this paper, we present ClusVPR, a novel approach that tackles the specific issues of redundant information in duplicate regions and representations of small objects. Different from existing methods that rely on Convolutional Neural Networks (CNNs) for feature map generation, ClusVPR introduces a unique paradigm called Clustering-based Weighted Transformer Network (CWTNet). CWTNet leverages the power of clustering-based weighted feature maps and integrates global dependencies to effectively address visual deviations encountered in large-scale VPR problems. We also introduce the optimized-VLAD (OptLAD) layer that significantly reduces the number of parameters and enhances model efficiency. This layer is specifically designed to aggregate the information obtained from scale-wise image patches. Additionally, our pyramid self-supervised strategy focuses on extracting representative and diverse information from scale-wise image patches instead of entire images, which is crucial for capturing representative and diverse information in VPR. Extensive experiments on four VPR datasets show our model's superior performance compared to existing models while being less complex.
Authors: Denis Mbey Akola
This paper presents a study of two tracking algorithms (SORT~\cite{7533003} and Tracktor++~\cite{2019}) that were ranked first positions on the MOT Challenge leaderboard (The MOTChallenge web page: https://motchallenge.net ). The purpose of this study is to discover the techniques used and to provide useful insights about these algorithms in the tracking pipeline that could improve the performance of MOT tracking algorithms. To this end, we adopted the popular tracking-by-detection approach. We trained our own Pedestrian Detection model using the MOT17Det dataset (MOT17Det : https://motchallenge.net/data/MOT17Det/ ). We also used a re-identification model trained on MOT17 dataset (MOT17 : https://motchallenge.net/data/MOT17/ ) for Tracktor++ to reduce the false re-identification alarms. We then present experimental results which shows that Tracktor++ is a better multi-person tracking algorithm than SORT. We also performed ablation studies to discover the contribution of re-identification(RE-ID) network and motion to the results of Tracktor++. We finally conclude by providing some recommendations for future research.
Authors: Denis Mbey Akola, Gianni Franchi
This paper presents a new approach for training two-stage object detection ensemble models, more specifically, Faster R-CNN models to estimate uncertainty. We propose training one Region Proposal Network(RPN)~\cite{https://doi.org/10.48550/arxiv.1506.01497} and multiple Fast R-CNN prediction heads is all you need to build a robust deep ensemble network for estimating uncertainty in object detection. We present this approach and provide experiments to show that this approach is much faster than the naive method of fully training all $n$ models in an ensemble. We also estimate the uncertainty by measuring this ensemble model's Expected Calibration Error (ECE). We then further compare the performance of this model with that of Gaussian YOLOv3, a variant of YOLOv3 that models uncertainty using predicted bounding box coordinates. The source code is released at \url{https://github.com/Akola-Mbey-Denis/EfficientEnsemble}
Authors: Doyup Lee, Chiheon Kim, Minsu Cho, Wook-Shin Han
Generalizable implicit neural representation (INR) enables a single continuous function, i.e., a coordinate-based neural network, to represent multiple data instances by modulating its weights or intermediate features using latent codes. However, the expressive power of the state-of-the-art modulation is limited due to its inability to localize and capture fine-grained details of data entities such as specific pixels and rays. To address this issue, we propose a novel framework for generalizable INR that combines a transformer encoder with a locality-aware INR decoder. The transformer encoder predicts a set of latent tokens from a data instance to encode local information into each latent token. The locality-aware INR decoder extracts a modulation vector by selectively aggregating the latent tokens via cross-attention for a coordinate input and then predicts the output by progressively decoding with coarse-to-fine modulation through multiple frequency bandwidths. The selective token aggregation and the multi-band feature modulation enable us to learn locality-aware representation in spatial and spectral aspects, respectively. Our framework significantly outperforms previous generalizable INRs and validates the usefulness of the locality-aware latents for downstream tasks such as image generation.
Authors: Arief Purnama Muharram, Hollyana Puteri Haryono, Abassi Haji Juma, Ira Puspasari, Nugraha Priya Utama
Reading and interpreting chest X-ray images is one of the most radiologist's routines. However, it still can be challenging, even for the most experienced ones. Therefore, we proposed a multi-model deep learning-based automated chest X-ray report generator system designed to assist radiologists in their work. The basic idea of the proposed system is by utilizing multi binary-classification models for detecting multi abnormalities, with each model responsible for detecting one abnormality, in a single image. In this study, we limited the radiology abnormalities detection to only cardiomegaly, lung effusion, and consolidation. The system generates a radiology report by performing the following three steps: image pre-processing, utilizing deep learning models to detect abnormalities, and producing a report. The aim of the image pre-processing step is to standardize the input by scaling it to 128x128 pixels and slicing it into three segments, which covers the upper, lower, and middle parts of the lung. After pre-processing, each corresponding model classifies the image, resulting in a 0 (zero) for no abnormality detected and a 1 (one) for the presence of an abnormality. The prediction outputs of each model are then concatenated to form a 'result code'. The 'result code' is used to construct a report by selecting the appropriate pre-determined sentence for each detected abnormality in the report generation step. The proposed system is expected to reduce the workload of radiologists and increase the accuracy of chest X-ray diagnosis.
Authors: Tianlong Li, Wenhao Liu, Changze Lv, Jianhan Xu, Cenyuan Zhang, Muling Wu, Xiaoqing Zheng, Xuanjing Huang
Spiking neural networks (SNNs) have demonstrated the capability to achieve comparable performance to deep neural networks (DNNs) in both visual and linguistic domains while offering the advantages of improved energy efficiency and adherence to biological plausibility. However, the extension of such single-modality SNNs into the realm of multimodal scenarios remains an unexplored territory. Drawing inspiration from the concept of contrastive language-image pre-training (CLIP), we introduce a novel framework, named SpikeCLIP, to address the gap between two modalities within the context of spike-based computing through a two-step recipe involving ``Alignment Pre-training + Dual-Loss Fine-tuning". Extensive experiments demonstrate that SNNs achieve comparable results to their DNN counterparts while significantly reducing energy consumption across a variety of datasets commonly used for multimodal model evaluation. Furthermore, SpikeCLIP maintains robust performance in image classification tasks that involve class labels not predefined within specific categories.
Authors: Mouïn Ben Ammar, Nacim Belkhir, Sebastian Popescu, Antoine Manzanera, Gianni Franchi
Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits. We hypothesize that ``neural collapse'', a phenomenon affecting in-distribution data for models trained beyond loss convergence, also influences OOD data. To benefit from this interplay, we introduce NECO, a novel post-hoc method for OOD detection, which leverages the geometric properties of ``neural collapse'' and of principal component spaces to identify OOD data. Our extensive experiments demonstrate that NECO achieves state-of-the-art results on both small and large-scale OOD detection tasks while exhibiting strong generalization capabilities across different network architectures. Furthermore, we provide a theoretical explanation for the effectiveness of our method in OOD detection. We plan to release the code after the anonymity period.
Authors: Jia-Wang Bian, Wenjing Bian, Victor Adrian Prisacariu, Philip Torr
Neural surface reconstruction is sensitive to the camera pose noise, even if state-of-the-art pose estimators like COLMAP or ARKit are used. More importantly, existing Pose-NeRF joint optimisation methods have struggled to improve pose accuracy in challenging real-world scenarios. To overcome the challenges, we introduce the pose residual field (\textbf{PoRF}), a novel implicit representation that uses an MLP for regressing pose updates. This is more robust than the conventional pose parameter optimisation due to parameter sharing that leverages global information over the entire sequence. Furthermore, we propose an epipolar geometry loss to enhance the supervision that leverages the correspondences exported from COLMAP results without the extra computational overhead. Our method yields promising results. On the DTU dataset, we reduce the rotation error by 78\% for COLMAP poses, leading to the decreased reconstruction Chamfer distance from 3.48mm to 0.85mm. On the MobileBrick dataset that contains casually captured unbounded 360-degree videos, our method refines ARKit poses and improves the reconstruction F1 score from 69.18 to 75.67, outperforming that with the dataset provided ground-truth pose (75.14). These achievements demonstrate the efficacy of our approach in refining camera poses and improving the accuracy of neural surface reconstruction in real-world scenarios.
Authors: Adrian Hayler, Felix Wimbauer, Dominik Muhle, Christian Rupprecht, Daniel Cremers
3D semantic scene understanding is a fundamental challenge in computer vision. It enables mobile agents to autonomously plan and navigate arbitrary environments. SSC formalizes this challenge as jointly estimating dense geometry and semantic information from sparse observations of a scene. Current methods for SSC are generally trained on 3D ground truth based on aggregated LiDAR scans. This process relies on special sensors and annotation by hand which are costly and do not scale well. To overcome this issue, our work presents the first self-supervised approach to SSC called S4C that does not rely on 3D ground truth data. Our proposed method can reconstruct a scene from a single image and only relies on videos and pseudo segmentation ground truth generated from off-the-shelf image segmentation network during training. Unlike existing methods, which use discrete voxel grids, we represent scenes as implicit semantic fields. This formulation allows querying any point within the camera frustum for occupancy and semantic class. Our architecture is trained through rendering-based self-supervised losses. Nonetheless, our method achieves performance close to fully supervised state-of-the-art methods. Additionally, our method demonstrates strong generalization capabilities and can synthesize accurate segmentation maps for far away viewpoints.
Authors: Weijie Kuang, Hann Woei Ho, Ye Zhou, Shahrel Azmin Suandi, Farzad Ismail
Unmanned Aerial Vehicles (UAVs) are considered cutting-edge technology with highly cost-effective and flexible usage scenarios. Although many papers have reviewed the application of UAVs in agriculture, the review of the application for tree detection is still insufficient. This paper focuses on tree detection methods applied to UAV data collected by UAVs. There are two kinds of data, the point cloud and the images, which are acquired by the Light Detection and Ranging (LiDAR) sensor and camera, respectively. Among the detection methods using point-cloud data, this paper mainly classifies these methods according to LiDAR and Digital Aerial Photography (DAP). For the detection methods using images directly, this paper reviews these methods by whether or not to use the Deep Learning (DL) method. Our review concludes and analyses the comparison and combination between the application of LiDAR-based and DAP-based point cloud data. The performance, relative merits, and application fields of the methods are also introduced. Meanwhile, this review counts the number of tree detection studies using different methods in recent years. From our statics, the detection task using DL methods on the image has become a mainstream trend as the number of DL-based detection researches increases to 45% of the total number of tree detection studies up to 2022. As a result, this review could help and guide researchers who want to carry out tree detection on specific forests and for farmers to use UAVs in managing agriculture production.