Authors: Xiaozhou Ye, Kevin I-Kai Wang
Abstract: In human activity recognition (HAR), the assumption that training and testing data are independent and identically distributed (i.i.d.) often fails, particularly in cross-user scenarios where data distributions vary significantly. This discrepancy highlights the limitations of conventional domain adaptation methods in HAR, which typically overlook the inherent temporal relations in time-series data. To bridge this gap, our study introduces a Conditional Variational Autoencoder with Universal Sequence Mapping (CVAE-USM) approach, which addresses the unique challenges of time-series domain adaptation in HAR by relaxing the i.i.d. assumption and leveraging temporal relations to align data distributions effectively across different users. This method combines the strengths of Variational Autoencoder (VAE) and Universal Sequence Mapping (USM) to capture and utilize common temporal patterns between users for improved activity recognition. Our results, evaluated on two public HAR datasets (OPPT and PAMAP2), demonstrate that CVAE-USM outperforms existing state-of-the-art methods, offering a more accurate and generalizable solution for cross-user activity recognition.
Authors: Murat Onur Yildirim, Elif Ceren Gok Yildirim, Decebal Constantin Mocanu, Joaquin Vanschoren
Abstract: Class incremental learning (CIL) in an online continual learning setting strives to acquire knowledge on a series of novel classes from a data stream, using each data point only once for training. This is more realistic compared to offline modes, where it is assumed that all data from novel class(es) is readily available. Current online CIL approaches store a subset of the previous data which creates heavy overhead costs in terms of both memory and computation, as well as privacy issues. In this paper, we propose a new online CIL approach called FOCIL. It fine-tunes the main architecture continually by training a randomly pruned sparse subnetwork for each task. Then, it freezes the trained connections to prevent forgetting. FOCIL also determines the sparsity level and learning rate per task adaptively and ensures (almost) zero forgetting across all tasks without storing any replay data. Experimental results on 10-Task CIFAR100, 20-Task CIFAR100, and 100-Task TinyImagenet, demonstrate that our method outperforms the SOTA by a large margin. The code is publicly available at https://github.com/muratonuryildirim/FOCIL.
Authors: Xidong Wu, Shangqian Gao, Zeyu Zhang, Zhenzhen Li, Runxue Bao, Yanfu Zhang, Xiaoqian Wang, Heng Huang
Abstract: Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption challenging. To address the limitation, the Only-Train-Once (OTO) and OTOv2 are proposed to eliminate the need for additional fine-tuning steps by directly training and compressing a general DNN from scratch. Nevertheless, the static design of optimizers (in OTO) can lead to convergence issues of local optima. In this paper, we proposed the Auto-Train-Once (ATO), an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. During the model training phase, our approach not only trains the target model but also leverages a controller network as an architecture generator to guide the learning of target model weights. Furthermore, we developed a novel stochastic gradient algorithm that enhances the coordination between model training and controller network training, thereby improving pruning performance. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures (including ResNet18, ResNet34, ResNet50, ResNet56, and MobileNetv2) on standard benchmark datasets (CIFAR-10, CIFAR-100, and ImageNet).
Authors: Ahmad Mahmood, Ashmal Vayani, Muzammal Naseer, Salman Khan, Fahad Khan
Abstract: Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In contrast, this paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of LLMs. Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal input and output demonstrations within a contextual framework. By presenting LLMs with pairs of instructions and their corresponding high-level programs, we harness their contextual learning capabilities to generate executable visual programs for video understanding. To enhance program's accuracy and robustness, we implement two important strategies. Firstly, we employ a feedback-generation approach, powered by GPT-3.5, to rectify errors in programs utilizing unsupported functions. Secondly, taking motivation from recent works on self refinement of LLM outputs, we introduce an iterative procedure for improving the quality of the in-context examples by aligning the initial outputs to the outputs that would have been generated had the LLM not been bound by the structure of the in-context examples. Our results on several video-specific tasks, including visual QA, video anticipation, pose estimation and multi-video QA illustrate the efficacy of these enhancements in improving the performance of visual programming approaches for video tasks. Our Codes and data will be publicly released.
Authors: Weipeng Deng, Runyu Ding, Jihan Yang, Jiahui Liu, Yijiang Li, Xiaojuan Qi, Edith Ngai
Abstract: Rapid advancements in 3D vision-language (3D-VL) tasks have opened up new avenues for human interaction with embodied agents or robots using natural language. Despite this progress, we find a notable limitation: existing 3D-VL models exhibit sensitivity to the styles of language input, struggling to understand sentences with the same semantic meaning but written in different variants. This observation raises a critical question: Can 3D vision-language models truly understand natural language? To test the language understandability of 3D-VL models, we first propose a language robustness task for systematically assessing 3D-VL models across various tasks, benchmarking their performance when presented with different language style variants. Importantly, these variants are commonly encountered in applications requiring direct interaction with humans, such as embodied robotics, given the diversity and unpredictability of human language. We propose a 3D Language Robustness Dataset, designed based on the characteristics of human language, to facilitate the systematic study of robustness. Our comprehensive evaluation uncovers a significant drop in the performance of all existing models across various 3D-VL tasks. Even the state-of-the-art 3D-LLM fails to understand some variants of the same sentences. Further in-depth analysis suggests that the existing models have a fragile and biased fusion module, which stems from the low diversity of the existing dataset. Finally, we propose a training-free module driven by LLM, which improves language robustness. Datasets and code will be available at github.
Authors: Sayanton V. Dibbo, Adam Breuer, Juston Moore, Michael Teti
Abstract: Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private training data just by repeatedly querying the network and inspecting its outputs. In this work, we develop a novel network architecture that leverages sparse-coding layers to obtain superior robustness to this class of attacks. Three decades of computer science research has studied sparse coding in the context of image denoising, object recognition, and adversarial misclassification settings, but to the best of our knowledge, its connection to state-of-the-art privacy vulnerabilities remains unstudied. However, sparse coding architectures suggest an advantageous means to defend against model inversion attacks because they allow us to control the amount of irrelevant private information encoded in a network's intermediate representations in a manner that can be computed efficiently during training and that is known to have little effect on classification accuracy. Specifically, compared to networks trained with a variety of state-of-the-art defenses, our sparse-coding architectures maintain comparable or higher classification accuracy while degrading state-of-the-art training data reconstructions by factors of 1.1 to 18.3 across a variety of reconstruction quality metrics (PSNR, SSIM, FID). This performance advantage holds across 5 datasets ranging from CelebA faces to medical images and CIFAR-10, and across various state-of-the-art SGD-based and GAN-based inversion attacks, including Plug-&-Play attacks. We provide a cluster-ready PyTorch codebase to promote research and standardize defense evaluations.
Authors: Roberto Henschel, Levon Khachatryan, Daniil Hayrapetyan, Hayk Poghosyan, Vahram Tadevosyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
Abstract: Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video generation (typically 16 or 24 frames), ending up with hard-cuts when naively extended to the case of long video synthesis. To overcome these limitations, we introduce StreamingT2V, an autoregressive approach for long video generation of 80, 240, 600, 1200 or more frames with smooth transitions. The key components are:(i) a short-term memory block called conditional attention module (CAM), which conditions the current generation on the features extracted from the previous chunk via an attentional mechanism, leading to consistent chunk transitions, (ii) a long-term memory block called appearance preservation module, which extracts high-level scene and object features from the first video chunk to prevent the model from forgetting the initial scene, and (iii) a randomized blending approach that enables to apply a video enhancer autoregressively for infinitely long videos without inconsistencies between chunks. Experiments show that StreamingT2V generates high motion amount. In contrast, all competing image-to-video methods are prone to video stagnation when applied naively in an autoregressive manner. Thus, we propose with StreamingT2V a high-quality seamless text-to-long video generator that outperforms competitors with consistency and motion. Our code will be available at: https://github.com/Picsart-AI-Research/StreamingT2V
Authors: Yiwei Zhou, Xiaobo Xia, Zhiwei Lin, Bo Han, Tongliang Liu
Abstract: The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Inspired by the success of vision-language foundation models, previous efforts achieved zero-shot adversarial robustness by aligning adversarial visual features with text supervision. However, in practice, they are still unsatisfactory due to several issues, including heavy adaptation cost, suboptimal text supervision, and uncontrolled natural generalization capacity. In this paper, to address these issues, we propose a few-shot adversarial prompt framework where adapting input sequences with limited data makes significant adversarial robustness improvement. Specifically, we achieve this by providing adversarially correlated text supervision that is end-to-end learned from adversarial examples. We also propose a novel training objective that enhances the consistency of multi-modal features while encourages differentiated uni-modal features between natural and adversarial examples. The proposed framework gives access to learn adversarial text supervision, which provides superior cross-modal adversarial alignment and matches state-of-the-art zero-shot adversarial robustness with only 1% training data.
Authors: Qianyu Guo, Jiaming Fu, Yawen Lu, Dongming Gan
Abstract: In Virtual Reality (VR), adversarial attack remains a significant security threat. Most deep learning-based methods for physical and digital adversarial attacks focus on enhancing attack performance by crafting adversarial examples that contain large printable distortions that are easy for human observers to identify. However, attackers rarely impose limitations on the naturalness and comfort of the appearance of the generated attack image, resulting in a noticeable and unnatural attack. To address this challenge, we propose a framework to incorporate style transfer to craft adversarial inputs of natural styles that exhibit minimal detectability and maximum natural appearance, while maintaining superior attack capabilities.
Authors: Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, Siyu Zhu
Abstract: In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques. The methodology utilizes the SMPL(Skinned Multi-Person Linear) model as the 3D human parametric model to establish a unified representation of body shape and pose. This facilitates the accurate capture of intricate human geometry and motion characteristics from source videos. Specifically, we incorporate rendered depth images, normal maps, and semantic maps obtained from SMPL sequences, alongside skeleton-based motion guidance, to enrich the conditions to the latent diffusion model with comprehensive 3D shape and detailed pose attributes. A multi-layer motion fusion module, integrating self-attention mechanisms, is employed to fuse the shape and motion latent representations in the spatial domain. By representing the 3D human parametric model as the motion guidance, we can perform parametric shape alignment of the human body between the reference image and the source video motion. Experimental evaluations conducted on benchmark datasets demonstrate the methodology's superior ability to generate high-quality human animations that accurately capture both pose and shape variations. Furthermore, our approach also exhibits superior generalization capabilities on the proposed wild dataset. Project page: https://fudan-generative-vision.github.io/champ.
Authors: Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor
Abstract: This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to overcome the limitations of foundation models in object detection and counting by using specialized agents as tools. Unlike existing approaches, our study focuses on the system's performance without fine-tuning it on specific VQA datasets, making it more practical and robust in the open world. We present preliminary experimental results under zero-shot scenarios and highlight some failure cases, offering new directions for future research.
Authors: Claudio Vittorio Ragaglia, Francesco Guarnera, Sebastiano Battiato
Abstract: {The study of frequency components derived from Discrete Cosine Transform (DCT) has been widely used in image analysis. In recent years it has been observed that significant information can be extrapolated from them about the lifecycle of the image, but no study has focused on the analysis between them and the source resolution of the image. In this work, we investigated a novel image resolution classifier that employs DCT statistics with the goal to detect the original resolution of images; in particular the insight was exploited to address the challenge of identifying cropped images. Training a Machine Learning (ML) classifier on entire images (not cropped), the generated model can leverage this information to detect cropping. The results demonstrate the classifier's reliability in distinguishing between cropped and not cropped images, providing a dependable estimation of their original resolution. This advancement has significant implications for image processing applications, including digital security, authenticity verification, and visual quality analysis, by offering a new tool for detecting image manipulations and enhancing qualitative image assessment. This work opens new perspectives in the field, with potential to transform image analysis and usage across multiple domains.}
Authors: Luca Piano, Pietro Basci, Fabrizio Lamberti, Lia Morra
Abstract: Generative techniques for image anonymization have great potential to generate datasets that protect the privacy of those depicted in the images, while achieving high data fidelity and utility. Existing methods have focused extensively on preserving facial attributes, but failed to embrace a more comprehensive perspective that considers the scene and background into the anonymization process. This paper presents, to the best of our knowledge, the first approach to image anonymization based on Latent Diffusion Models (LDMs). Every element of a scene is maintained to convey the same meaning, yet manipulated in a way that makes re-identification difficult. We propose two LDMs for this purpose: CAMOUFLaGE-Base exploits a combination of pre-trained ControlNets, and a new controlling mechanism designed to increase the distance between the real and anonymized images. CAMOFULaGE-Light is based on the Adapter technique, coupled with an encoding designed to efficiently represent the attributes of different persons in a scene. The former solution achieves superior performance on most metrics and benchmarks, while the latter cuts the inference time in half at the cost of fine-tuning a lightweight module. We show through extensive experimental comparison that the proposed method is competitive with the state-of-the-art concerning identity obfuscation whilst better preserving the original content of the image and tackling unresolved challenges that current solutions fail to address.
Authors: Gaurav Bhatt, James Ross, Leonid Sigal
Abstract: Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks. Despite notable progress in continual classification, systems designed for complex vision tasks such as detection or segmentation still struggle to attain satisfactory performance. In this work, we introduce a memory-based detection transformer architecture to adapt a pre-trained DETR-style detector to new tasks while preserving knowledge from previous tasks. We propose a novel localized query function for efficient information retrieval from memory units, aiming to minimize forgetting. Furthermore, we identify a fundamental challenge in continual detection referred to as background relegation. This arises when object categories from earlier tasks reappear in future tasks, potentially without labels, leading them to be implicitly treated as background. This is an inevitable issue in continual detection or segmentation. The introduced continual optimization technique effectively tackles this challenge. Finally, we assess the performance of our proposed system on continual detection benchmarks and demonstrate that our approach surpasses the performance of existing state-of-the-art resulting in 5-7% improvements on MS-COCO and PASCAL-VOC on the task of continual detection.
Authors: Peipei Song, Jing Zhang, Piotr Koniusz, Nick Barnes
Abstract: Existing eye fixation prediction methods perform the mapping from input images to the corresponding dense fixation maps generated from raw fixation points. However, due to the stochastic nature of human fixation, the generated dense fixation maps may be a less-than-ideal representation of human fixation. To provide a robust fixation model, we introduce Gaussian Representation for eye fixation modeling. Specifically, we propose to model the eye fixation map as a mixture of probability distributions, namely a Gaussian Mixture Model. In this new representation, we use several Gaussian distribution components as an alternative to the provided fixation map, which makes the model more robust to the randomness of fixation. Meanwhile, we design our framework upon some lightweight backbones to achieve real-time fixation prediction. Experimental results on three public fixation prediction datasets (SALICON, MIT1003, TORONTO) demonstrate that our method is fast and effective.
Authors: Alberto Baldrati, Davide Morelli, Marcella Cornia, Marco Bertini, Rita Cucchiara
Abstract: Fashion illustration is a crucial medium for designers to convey their creative vision and transform design concepts into tangible representations that showcase the interplay between clothing and the human body. In the context of fashion design, computer vision techniques have the potential to enhance and streamline the design process. Departing from prior research primarily focused on virtual try-on, this paper tackles the task of multimodal-conditioned fashion image editing. Our approach aims to generate human-centric fashion images guided by multimodal prompts, including text, human body poses, garment sketches, and fabric textures. To address this problem, we propose extending latent diffusion models to incorporate these multiple modalities and modifying the structure of the denoising network, taking multimodal prompts as input. To condition the proposed architecture on fabric textures, we employ textual inversion techniques and let diverse cross-attention layers of the denoising network attend to textual and texture information, thus incorporating different granularity conditioning details. Given the lack of datasets for the task, we extend two existing fashion datasets, Dress Code and VITON-HD, with multimodal annotations. Experimental evaluations demonstrate the effectiveness of our proposed approach in terms of realism and coherence concerning the provided multimodal inputs.
Authors: Zining Cheng, Guanzhou Ji
Abstract: This paper presents the use of panoramic 3D estimation in lighting simulation. Conventional lighting simulation necessitates detailed modeling as input, resulting in significant labor effort and time cost. The 3D layout estimation method directly takes a single panorama as input and generates a lighting simulation model with room geometry and window aperture. We evaluate the simulation results by comparing the luminance errors between on-site High Dynamic Range (HDR) photographs, 3D estimation model, and detailed model in panoramic representation and fisheye perspective. Given the selected scene, the results demonstrate the estimated room layout is reliable for lighting simulation.
Authors: Opher Bar Nathan, Deborah Levy, Tali Treibitz, Dan Rosenbaum
Abstract: Underwater image restoration is a challenging task because of strong water effects that increase dramatically with distance. This is worsened by lack of ground truth data of clean scenes without water. Diffusion priors have emerged as strong image restoration priors. However, they are often trained with a dataset of the desired restored output, which is not available in our case. To overcome this critical issue, we show how to leverage in-air images to train diffusion priors for underwater restoration. We also observe that only color data is insufficient, and augment the prior with a depth channel. We train an unconditional diffusion model prior on the joint space of color and depth, using standard RGBD datasets of natural outdoor scenes in air. Using this prior together with a novel guidance method based on the underwater image formation model, we generate posterior samples of clean images, removing the water effects. Even though our prior did not see any underwater images during training, our method outperforms state-of-the-art baselines for image restoration on very challenging scenes. Data, models and code are published in the project page.
Authors: Gerry Chen, Sunil Kumar Narayanan, Thomas Gautier Ottou, Benjamin Missaoui, Harsh Muriki, C\'edric Pradalier, Yongsheng Chen
Abstract: Hyperspectral Imagery (HSI) has been used in many applications to non-destructively determine the material and/or chemical compositions of samples. There is growing interest in creating 3D hyperspectral reconstructions, which could provide both spatial and spectral information while also mitigating common HSI challenges such as non-Lambertian surfaces and translucent objects. However, traditional 3D reconstruction with HSI is difficult due to technological limitations of hyperspectral cameras. In recent years, Neural Radiance Fields (NeRFs) have seen widespread success in creating high quality volumetric 3D representations of scenes captured by a variety of camera models. Leveraging recent advances in NeRFs, we propose computing a hyperspectral 3D reconstruction in which every point in space and view direction is characterized by wavelength-dependent radiance and transmittance spectra. To evaluate our approach, a dataset containing nearly 2000 hyperspectral images across 8 scenes and 2 cameras was collected. We perform comparisons against traditional RGB NeRF baselines and apply ablation testing with alternative spectra representations. Finally, we demonstrate the potential of hyperspectral NeRFs for hyperspectral super-resolution and imaging sensor simulation. We show that our hyperspectral NeRF approach enables creating fast, accurate volumetric 3D hyperspectral scenes and enables several new applications and areas for future study.
Authors: Minchul Kim, Yiyang Su, Feng Liu, Anil Jain, Xiaoming Liu
Abstract: In this paper, we address the challenge of making ViT models more robust to unseen affine transformations. Such robustness becomes useful in various recognition tasks such as face recognition when image alignment failures occur. We propose a novel method called KP-RPE, which leverages key points (e.g.~facial landmarks) to make ViT more resilient to scale, translation, and pose variations. We begin with the observation that Relative Position Encoding (RPE) is a good way to bring affine transform generalization to ViTs. RPE, however, can only inject the model with prior knowledge that nearby pixels are more important than far pixels. Keypoint RPE (KP-RPE) is an extension of this principle, where the significance of pixels is not solely dictated by their proximity but also by their relative positions to specific keypoints within the image. By anchoring the significance of pixels around keypoints, the model can more effectively retain spatial relationships, even when those relationships are disrupted by affine transformations. We show the merit of KP-RPE in face and gait recognition. The experimental results demonstrate the effectiveness in improving face recognition performance from low-quality images, particularly where alignment is prone to failure. Code and pre-trained models are available.
Authors: Mamshad Nayeem Rizve, Fan Fei, Jayakrishnan Unnikrishnan, Son Tran, Benjamin Z. Yao, Belinda Zeng, Mubarak Shah, Trishul Chilimbi
Abstract: In this paper, we propose VidLA, an approach for video-language alignment at scale. There are two major limitations of previous video-language alignment approaches. First, they do not capture both short-range and long-range temporal dependencies and typically employ complex hierarchical deep network architectures that are hard to integrate with existing pretrained image-text foundation models. To effectively address this limitation, we instead keep the network architecture simple and use a set of data tokens that operate at different temporal resolutions in a hierarchical manner, accounting for the temporally hierarchical nature of videos. By employing a simple two-tower architecture, we are able to initialize our video-language model with pretrained image-text foundation models, thereby boosting the final performance. Second, existing video-language alignment works struggle due to the lack of semantically aligned large-scale training data. To overcome it, we leverage recent LLMs to curate the largest video-language dataset to date with better visual grounding. Furthermore, unlike existing video-text datasets which only contain short clips, our dataset is enriched with video clips of varying durations to aid our temporally hierarchical data tokens in extracting better representations at varying temporal scales. Overall, empirical results show that our proposed approach surpasses state-of-the-art methods on multiple retrieval benchmarks, especially on longer videos, and performs competitively on classification benchmarks.
Authors: Blake Gella, Howard Zhang, Rishi Upadhyay, Tiffany Chang, Nathan Wei, Matthew Waliman, Yunhao Bao, Celso de Melo, Alex Wong, Achuta Kadambi
Abstract: We propose a method to infer semantic segmentation maps from images captured under adverse weather conditions. We begin by examining existing models on images degraded by weather conditions such as rain, fog, or snow, and found that they exhibit a large performance drop as compared to those captured under clear weather. To control for changes in scene structures, we propose WeatherProof, the first semantic segmentation dataset with accurate clear and adverse weather image pairs that share an underlying scene. Through this dataset, we analyze the error modes in existing models and found that they were sensitive to the highly complex combination of different weather effects induced on the image during capture. To improve robustness, we propose a way to use language as guidance by identifying contributions of adverse weather conditions and injecting that as "side information". Models trained using our language guidance exhibit performance gains by up to 10.2% in mIoU on WeatherProof, up to 8.44% in mIoU on the widely used ACDC dataset compared to standard training techniques, and up to 6.21% in mIoU on the ACDC dataset as compared to previous SOTA methods.
Authors: Zeeshan Hayder, Xuming He
Abstract: Scene graph generation aims to capture detailed spatial and semantic relationships between objects in an image, which is challenging due to incomplete labelling, long-tailed relationship categories, and relational semantic overlap. Existing Transformer-based methods either employ distinct queries for objects and predicates or utilize holistic queries for relation triplets and hence often suffer from limited capacity in learning low-frequency relationships. In this paper, we present a new Transformer-based method, called DSGG, that views scene graph detection as a direct graph prediction problem based on a unique set of graph-aware queries. In particular, each graph-aware query encodes a compact representation of both the node and all of its relations in the graph, acquired through the utilization of a relaxed sub-graph matching during the training process. Moreover, to address the problem of relational semantic overlap, we utilize a strategy for relation distillation, aiming to efficiently learn multiple instances of semantic relationships. Extensive experiments on the VG and the PSG datasets show that our model achieves state-of-the-art results, showing a significant improvement of 3.5\% and 6.7\% in mR@50 and mR@100 for the scene-graph generation task and achieves an even more substantial improvement of 8.5\% and 10.3\% in mR@50 and mR@100 for the panoptic scene graph generation task. Code is available at \url{https://github.com/zeeshanhayder/DSGG}.
Authors: El Hadji S. Diop, Thierno Fall, Alioune Mbengue, Mohamed Daoudi
Abstract: Content and image generation consist in creating or generating data from noisy information by extracting specific features such as texture, edges, and other thin image structures. We are interested here in generative models, and two main problems are addressed. Firstly, the improvements of specific feature extraction while accounting at multiscale levels intrinsic geometric features; and secondly, the equivariance of the network to reduce its complexity and provide a geometric interpretability. To proceed, we propose a geometric generative model based on an equivariant partial differential equation (PDE) for group convolution neural networks (G-CNNs), so called PDE-G-CNNs, built on morphology operators and generative adversarial networks (GANs). Equivariant morphological PDE layers are composed of multiscale dilations and erosions formulated in Riemannian manifolds, while group symmetries are defined on a Lie group. We take advantage of the Lie group structure to properly integrate the equivariance in layers, and are able to use the Riemannian metric to solve the multiscale morphological operations. Each point of the Lie group is associated with a unique point in the manifold, which helps us derive a metric on the Riemannian manifold from a tensor field invariant under the Lie group so that the induced metric has the same symmetries. The proposed geometric morphological GAN (GM-GAN) is obtained by using the proposed morphological equivariant convolutions in PDE-G-CNNs to bring nonlinearity in classical CNNs. GM-GAN is evaluated on MNIST data and compared with GANs. Preliminary results show that GM-GAN model outperforms classical GAN.
Authors: SangHyuk Kim, Edward Gaibor, Daniel Haehn
Abstract: Melanoma is the most aggressive form of skin cancer, and early detection can significantly increase survival rates and prevent cancer spread. However, developing reliable automated detection techniques is difficult due to the lack of standardized datasets and evaluation methods. This study introduces a unified melanoma classification approach that supports 54 combinations of 11 datasets and 24 state-of-the-art deep learning architectures. It enables a fair comparison of 1,296 experiments and results in a lightweight model deployable to the web-based MeshNet architecture named Mela-D. This approach can run up to 33x faster by reducing parameters 24x to yield an analogous 88.8\% accuracy comparable with ResNet50 on previously unseen images. This allows efficient and accurate melanoma detection in real-world settings that can run on consumer-level hardware.
Authors: Shixiong Xu, Gaofeng Meng, Xing Nie, Bolin Ni, Bin Fan, Shiming Xiang
Abstract: We observe a high level of imbalance in the accuracy of different classes in the same old task for the first time. This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting. This discovery remains previously unidentified due to the reliance on average incremental accuracy as the measurement for CIL, which assumes that the accuracy of classes within the same task is similar. However, this assumption is invalid in the face of catastrophic forgetting. Further empirical studies indicate that this imbalanced forgetting is caused by conflicts in representation between semantically similar old and new classes. These conflicts are rooted in the data imbalance present in replay-based CIL methods. Building on these insights, we propose CLass-Aware Disentanglement (CLAD) to predict the old classes that are more likely to be forgotten and enhance their accuracy. Importantly, CLAD can be seamlessly integrated into existing CIL methods. Extensive experiments demonstrate that CLAD consistently improves current replay-based methods, resulting in performance gains of up to 2.56%.
Authors: Jiayi Liu, Manolis Savva, Ali Mahdavi-Amiri
Abstract: 3D modeling of articulated objects is a research problem within computer vision, graphics, and robotics. Its objective is to understand the shape and motion of the articulated components, represent the geometry and mobility of object parts, and create realistic models that reflect articulated objects in the real world. This survey provides a comprehensive overview of the current state-of-the-art in 3D modeling of articulated objects, with a specific focus on the task of articulated part perception and articulated object creation (reconstruction and generation). We systematically review and discuss the relevant literature from two perspectives: geometry processing and articulation modeling. Through this survey, we highlight the substantial progress made in these areas, outline the ongoing challenges, and identify gaps for future research. Our survey aims to serve as a foundational reference for researchers and practitioners in computer vision and graphics, offering insights into the complexities of articulated object modeling.
Authors: Yifei Zeng, Yanqin Jiang, Siyu Zhu, Yuanxun Lu, Youtian Lin, Hao Zhu, Weiming Hu, Xun Cao, Yao Yao
Abstract: Recent progress in pre-trained diffusion models and 3D generation have spurred interest in 4D content creation. However, achieving high-fidelity 4D generation with spatial-temporal consistency remains a challenge. In this work, we propose STAG4D, a novel framework that combines pre-trained diffusion models with dynamic 3D Gaussian splatting for high-fidelity 4D generation. Drawing inspiration from 3D generation techniques, we utilize a multi-view diffusion model to initialize multi-view images anchoring on the input video frames, where the video can be either real-world captured or generated by a video diffusion model. To ensure the temporal consistency of the multi-view sequence initialization, we introduce a simple yet effective fusion strategy to leverage the first frame as a temporal anchor in the self-attention computation. With the almost consistent multi-view sequences, we then apply the score distillation sampling to optimize the 4D Gaussian point cloud. The 4D Gaussian spatting is specially crafted for the generation task, where an adaptive densification strategy is proposed to mitigate the unstable Gaussian gradient for robust optimization. Notably, the proposed pipeline does not require any pre-training or fine-tuning of diffusion networks, offering a more accessible and practical solution for the 4D generation task. Extensive experiments demonstrate that our method outperforms prior 4D generation works in rendering quality, spatial-temporal consistency, and generation robustness, setting a new state-of-the-art for 4D generation from diverse inputs, including text, image, and video.
Authors: Seungdae Han, Joohee Kim
Abstract: There has been a significant progress in text conditional image generation models. Recent advancements in this field depend not only on improvements in model structures, but also vast quantities of text-image paired datasets. However, creating these kinds of datasets is very costly and requires a substantial amount of labor. Famous face datasets don't have corresponding text captions, making it difficult to develop text conditional image generation models on these datasets. Some research has focused on developing text to image generation models using only images without text captions. Here, we propose CLIP-VQDiffusion, which leverage the pretrained CLIP model to provide multimodal text-image representations and strong image generation capabilities. On the FFHQ dataset, our model outperformed previous state-of-the-art methods by 4.4% in clipscore and generated very realistic images even when the text was both in and out of distribution. The pretrained models and codes will soon be available at https://github.com/INFINIQ-AI1/CLIPVQDiffusion
Authors: Haoxuan Qu, Ziyan Guo, Jun Liu
Abstract: Recently, while text-driven human motion generation has received massive research attention, most existing text-driven motion generators are generally only designed to generate motion sequences in a blank background. While this is the case, in practice, human beings naturally perform their motions in 3D scenes, rather than in a blank background. Considering this, we here aim to perform scene-aware text-drive motion generation instead. Yet, intuitively training a separate scene-aware motion generator in a supervised way can require a large amount of motion samples to be troublesomely collected and annotated in a large scale of different 3D scenes. To handle this task rather in a relatively convenient manner, in this paper, we propose a novel GPT-connect framework. In GPT-connect, we enable scene-aware motion sequences to be generated directly utilizing the existing blank-background human motion generator, via leveraging ChatGPT to connect the existing motion generator with the 3D scene in a totally training-free manner. Extensive experiments demonstrate the efficacy and generalizability of our proposed framework.
Authors: Kyungmin Lee, Kihyuk Sohn, Jinwoo Shin
Abstract: Recent progress in text-to-3D generation has been achieved through the utilization of score distillation methods: they make use of the pre-trained text-to-image (T2I) diffusion models by distilling via the diffusion model training objective. However, such an approach inevitably results in the use of random timesteps at each update, which increases the variance of the gradient and ultimately prolongs the optimization process. In this paper, we propose to enhance the text-to-3D optimization by leveraging the T2I diffusion prior in the generative sampling process with a predetermined timestep schedule. To this end, we interpret text-to3D optimization as a multi-view image-to-image translation problem, and propose a solution by approximating the probability flow. By leveraging the proposed novel optimization algorithm, we design DreamFlow, a practical three-stage coarseto-fine text-to-3D optimization framework that enables fast generation of highquality and high-resolution (i.e., 1024x1024) 3D contents. For example, we demonstrate that DreamFlow is 5 times faster than the existing state-of-the-art text-to-3D method, while producing more photorealistic 3D contents. Visit our project page (https://kyungmnlee.github.io/dreamflow.github.io/) for visualizations.
Authors: Jiayun Wang, Stella X. Yu, Yubei Chen
Abstract: Self-supervised learning (SSL) has proven effective in learning high-quality representations for various downstream tasks, with a primary focus on semantic tasks. However, its application in geometric tasks remains underexplored, partially due to the absence of a standardized evaluation method for geometric representations. To address this gap, we introduce a new pose-estimation benchmark for assessing SSL geometric representations, which demands training without semantic or pose labels and achieving proficiency in both semantic and geometric downstream tasks. On this benchmark, we study enhancing SSL geometric representations without sacrificing semantic classification accuracy. We find that leveraging mid-layer representations improves pose-estimation performance by 10-20%. Further, we introduce an unsupervised trajectory-regularization loss, which improves performance by an additional 4% and improves generalization ability on out-of-distribution data. We hope the proposed benchmark and methods offer new insights and improvements in self-supervised geometric representation learning.
Authors: Rui Wang, Dengpan Ye, Long Tang, Yunming Zhang, Jiacheng Deng
Abstract: With the continuous improvements of deepfake methods, forgery messages have transitioned from single-modality to multi-modal fusion, posing new challenges for existing forgery detection algorithms. In this paper, we propose AVT2-DWF, the Audio-Visual dual Transformers grounded in Dynamic Weight Fusion, which aims to amplify both intra- and cross-modal forgery cues, thereby enhancing detection capabilities. AVT2-DWF adopts a dual-stage approach to capture both spatial characteristics and temporal dynamics of facial expressions. This is achieved through a face transformer with an n-frame-wise tokenization strategy encoder and an audio transformer encoder. Subsequently, it uses multi-modal conversion with dynamic weight fusion to address the challenge of heterogeneous information fusion between audio and visual modalities. Experiments on DeepfakeTIMIT, FakeAVCeleb, and DFDC datasets indicate that AVT2-DWF achieves state-of-the-art performance intra- and cross-dataset Deepfake detection. Code is available at https://github.com/raining-dev/AVT2-DWF.
Authors: Shubhang Bhatnagar, Narendra Ahuja
Abstract: Unsupervised deep metric learning (UDML) focuses on learning a semantic representation space using only unlabeled data. This challenging problem requires accurately estimating the similarity between data points, which is used to supervise a deep network. For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point. These neighborhoods are used to estimate similarity between data points. We empirically show that this similarity estimate correlates better with the ground truth than the similarity estimates of current state-of-the-art techniques. We also show that proxies, commonly used in supervised metric learning, can be used to model the piecewise-linear manifold in an unsupervised setting, helping improve performance. Our method outperforms existing unsupervised metric learning approaches on standard zero-shot image retrieval benchmarks.
Authors: Xulu Zhang, Wengyu Zhang, Xiao-Yong Wei, Jinlin Wu, Zhaoxiang Zhang, Zhen Lei, Qing Li
Abstract: This paper presents a pilot study that explores the application of active learning, traditionally studied in the context of discriminative models, to generative models. We specifically focus on image synthesis personalization tasks. The primary challenge in conducting active learning on generative models lies in the open-ended nature of querying, which differs from the closed form of querying in discriminative models that typically target a single concept. We introduce the concept of anchor directions to transform the querying process into a semi-open problem. We propose a direction-based uncertainty sampling strategy to enable generative active learning and tackle the exploitation-exploration dilemma. Extensive experiments are conducted to validate the effectiveness of our approach, demonstrating that an open-source model can achieve superior performance compared to closed-source models developed by large companies, such as Google's StyleDrop. The source code is available at https://github.com/zhangxulu1996/GAL4Personalization.
Authors: Wenlve Zhou, Zhiheng Zhou, Tianlei Wang, Delu Zeng
Abstract: Unsupervised Domain Adaptation (UDA) endeavors to adjust models trained on a source domain to perform well on a target domain without requiring additional annotations. In the context of domain adaptive semantic segmentation, which tackles UDA for dense prediction, the goal is to circumvent the need for costly pixel-level annotations. Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps. However, such approaches generate synthetic data that diverge from real-world distributions, potentially leading the model astray from the true target distribution. To address this challenge, we propose a novel auxiliary task called Guidance Training. This task facilitates the effective utilization of cross-domain mixed sampling techniques while mitigating distribution shifts from the real world. Specifically, Guidance Training guides the model to extract and reconstruct the target-domain feature distribution from mixed data, followed by decoding the reconstructed target-domain features to make pseudo-label predictions. Importantly, integrating Guidance Training incurs minimal training overhead and imposes no additional inference burden. We demonstrate the efficacy of our approach by integrating it with existing methods, consistently improving performance. The implementation will be available at https://github.com/Wenlve-Zhou/Guidance-Training.
Authors: Novendra Setyawan, Ghufron Wahyu Kurniawan, Chi-Chia Sun, Jun-Wei Hsieh, Hui-Kai Su, Wen-Kai Kuo
Abstract: This work presents ParFormer as an enhanced transformer architecture that allows the incorporation of different token mixers into a single stage, hence improving feature extraction capabilities. Integrating both local and global data allows for precise representation of short- and long-range spatial relationships without the need for computationally intensive methods such as shifting windows. Along with the parallel token mixer encoder, We offer the Convolutional Attention Patch Embedding (CAPE) as an enhancement of standard patch embedding to improve token mixer extraction with a convolutional attention module. Our comprehensive evaluation demonstrates that our ParFormer outperforms CNN-based and state-of-the-art transformer-based architectures in image classification and several complex tasks such as object recognition. The proposed CAPE has been demonstrated to benefit the overall MetaFormer architecture, even while utilizing the Identity Mapping Token Mixer, resulting in a 0.5\% increase in accuracy. The ParFormer models outperformed ConvNeXt and Swin Transformer for the pure convolution and transformer model in accuracy. Furthermore, our model surpasses the current leading hybrid transformer by reaching competitive Top-1 scores in the ImageNet-1K classification test. Specifically, our model variants with 11M, 23M, and 34M parameters achieve scores of 80.4\%, 82.1\%, and 83.1\%, respectively. Code: https://github.com/novendrastywn/ParFormer-CAPE-2024
Authors: Zhiqiang Yan, Yuankai Lin, Kun Wang, Yupeng Zheng, Yufei Wang, Zhenyu Zhang, Jun Li, Jian Yang
Abstract: Depth completion is a vital task for autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. However, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this challenge, we introduce Tri-Perspective view Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPV affinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Furthermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sensor and the color camera on smartphones. Project page: https://yanzq95.github.io/projectpage/TOFDC/index.html
URLs: https://yanzq95.github.io/projectpage/TOFDC/index.html
Authors: Jinbo Wu, Xing Liu, Chenming Wu, Xiaobo Gao, Jialun Liu, Xinqi Liu, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang
Abstract: This paper presents TexRO, a novel method for generating delicate textures of a known 3D mesh by optimizing its UV texture. The key contributions are two-fold. We propose an optimal viewpoint selection strategy, that finds the most miniature set of viewpoints covering all the faces of a mesh. Our viewpoint selection strategy guarantees the completeness of a generated result. We propose a recursive optimization pipeline that optimizes a UV texture at increasing resolutions, with an adaptive denoising method that re-uses existing textures for new texture generation. Through extensive experimentation, we demonstrate the superior performance of TexRO in terms of texture quality, detail preservation, visual consistency, and, notably runtime speed, outperforming other current methods. The broad applicability of TexRO is further confirmed through its successful use on diverse 3D models.
Authors: Dazhong Rong, Shuheng Shen, Xinyi Fu, Peng Qian, Jianhai Chen, Qinming He, Xing Fu, Weiqiang Wang
Abstract: To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely regarded as secure, even in cases where some annotated errors occur, as the impact of these minor inaccuracies on the final performance of the models is negligible and existing backdoor attacks require attacker's ability to poison the training images. Nevertheless, in this paper, we propose clean-image backdoor attacks which uncover that backdoors can still be injected via a fraction of incorrect labels without modifying the training images. Specifically, in our attacks, the attacker first seeks a trigger feature to divide the training images into two parts: those with the feature and those without it. Subsequently, the attacker falsifies the labels of the former part to a backdoor class. The backdoor will be finally implanted into the target model after it is trained on the poisoned data. During the inference phase, the attacker can activate the backdoor in two ways: slightly modifying the input image to obtain the trigger feature, or taking an image that naturally has the trigger feature as input. We conduct extensive experiments to demonstrate the effectiveness and practicality of our attacks. According to the experimental results, we conclude that our attacks seriously jeopardize the fairness and robustness of image classification models, and it is necessary to be vigilant about the incorrect labels in outsourced labeling.
Authors: Timo Kaiser, Maximilian Schier, Bodo Rosenhahn
Abstract: Cell tracking and segmentation assist biologists in extracting insights from large-scale microscopy time-lapse data. Driven by local accuracy metrics, current tracking approaches often suffer from a lack of long-term consistency. To address this issue, we introduce an uncertainty estimation technique for neural tracking-by-regression frameworks and incorporate it into our novel extended Poisson multi-Bernoulli mixture tracker. Our uncertainty estimation identifies uncertain associations within high-performing tracking-by-regression methods using problem-specific test-time augmentations. Leveraging this uncertainty, along with a novel mitosis-aware assignment problem formulation, our tracker resolves false associations and mitosis detections stemming from long-term conflicts. We evaluate our approach on nine competitive datasets and demonstrate that it outperforms the current state-of-the-art on biologically relevant metrics substantially, achieving improvements by a factor of approximately $5.75$. Furthermore, we uncover new insights into the behavior of tracking-by-regression uncertainty.
Authors: Minsuk Chang, Seokhyeon Park, Hyeon Jeon, Aeri Cho, Soohyun Lee, Jinwook Seo
Abstract: In image classification, a significant problem arises from bias in the datasets. When it contains only specific types of images, the classifier begins to rely on shortcuts - simplistic and erroneous rules for decision-making. This leads to high performance on the training dataset but inferior results on new, varied images, as the classifier's generalization capability is reduced. For example, if the images labeled as mustache consist solely of male figures, the model may inadvertently learn to classify images by gender rather than the presence of a mustache. One approach to mitigate such biases is to direct the model's attention toward the target object's location, usually marked using bounding boxes or polygons for annotation. However, collecting such annotations requires substantial time and human effort. Therefore, we propose a novel patch-labeling method that integrates AI assistance with crowdsourcing to capture human attention from images, which can be a viable solution for mitigating bias. Our method consists of two steps. First, we extract the approximate location of a target using a pre-trained saliency detection model supplemented by human verification for accuracy. Then, we determine the human-attentive area in the image by iteratively dividing the image into smaller patches and employing crowdsourcing to ascertain whether each patch can be classified as the target object. We demonstrated the effectiveness of our method in mitigating bias through improved classification accuracy and the refined focus of the model. Also, crowdsourced experiments validate that our method collects human annotation up to 3.4 times faster than annotating object locations with polygons, significantly reducing the need for human resources. We conclude the paper by discussing the advantages of our method in a crowdsourcing context, mainly focusing on aspects of human errors and accessibility.
Authors: Hamam Mokayed, Rajkumar Saini, Oluwatosin Adewumi, Lama Alkhaled, Bjorn Backe, Palaiahnakote Shivakumara, Olle Hagner, Yan Chai Hum
Abstract: This paper addresses the critical challenge of vehicle detection in the harsh winter conditions in the Nordic regions, characterized by heavy snowfall, reduced visibility, and low lighting. Due to their susceptibility to environmental distortions and occlusions, traditional vehicle detection methods have struggled in these adverse conditions. The advanced proposed deep learning architectures brought promise, yet the unique difficulties of detecting vehicles in Nordic winters remain inadequately addressed. This study uses the Nordic Vehicle Dataset (NVD), which has UAV images from northern Sweden, to evaluate the performance of state-of-the-art vehicle detection algorithms under challenging weather conditions. Our methodology includes a comprehensive evaluation of single-stage, two-stage, and transformer-based detectors against the NVD. We propose a series of enhancements tailored to each detection framework, including data augmentation, hyperparameter tuning, transfer learning, and novel strategies designed explicitly for the DETR model. Our findings not only highlight the limitations of current detection systems in the Nordic environment but also offer promising directions for enhancing these algorithms for improved robustness and accuracy in vehicle detection amidst the complexities of winter landscapes. The code and the dataset are available at https://nvd.ltu-ai.dev
URLs: https://nvd.ltu-ai.dev
Authors: Jiahao Lu, Jiacheng Deng, Tianzhu Zhang
Abstract: 3D instance segmentation (3DIS) is a crucial task, but point-level annotations are tedious in fully supervised settings. Thus, using bounding boxes (bboxes) as annotations has shown great potential. The current mainstream approach is a two-step process, involving the generation of pseudo-labels from box annotations and the training of a 3DIS network with the pseudo-labels. However, due to the presence of intersections among bboxes, not every point has a determined instance label, especially in overlapping areas. To generate higher quality pseudo-labels and achieve more precise weakly supervised 3DIS results, we propose the Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation (BSNet), which devises a novel pseudo-labeler called Simulation-assisted Transformer. The labeler consists of two main components. The first is Simulation-assisted Mean Teacher, which introduces Mean Teacher for the first time in this task and constructs simulated samples to assist the labeler in acquiring prior knowledge about overlapping areas. To better model local-global structure, we also propose Local-Global Aware Attention as the decoder for teacher and student labelers. Extensive experiments conducted on the ScanNetV2 and S3DIS datasets verify the superiority of our designs. Code is available at \href{https://github.com/peoplelu/BSNet}{https://github.com/peoplelu/BSNet}.
URLs: https://github.com/peoplelu/BSNet, https://github.com/peoplelu/BSNet
Authors: Chenyao Yu, Yingfeng Cai, Jiaxin Zhang, Hui Kong, Wei Sui, Cong Yang
Abstract: As a part of the perception results of intelligent driving systems, static object detection (SOD) in 3D space provides crucial cues for driving environment understanding. With the rapid deployment of deep neural networks for SOD tasks, the demand for high-quality training samples soars. The traditional, also reliable, way is manual labeling over the dense LiDAR point clouds and reference images. Though most public driving datasets adopt this strategy to provide SOD ground truth (GT), it is still expensive (requires LiDAR scanners) and low-efficient (time-consuming and unscalable) in practice. This paper introduces VRSO, a visual-centric approach for static object annotation. VRSO is distinguished in low cost, high efficiency, and high quality: (1) It recovers static objects in 3D space with only camera images as input, and (2) manual labeling is barely involved since GT for SOD tasks is generated based on an automatic reconstruction and annotation pipeline. (3) Experiments on the Waymo Open Dataset show that the mean reprojection error from VRSO annotation is only 2.6 pixels, around four times lower than the Waymo labeling (10.6 pixels). Source code is available at: https://github.com/CaiYingFeng/VRSO.
Authors: Zilin Xie, Kangning Li, Jinbao Jiang, Jinzhong Yang, Xiaojun Qiao, Deshuai Yuan, Cheng Nie
Abstract: Open-pit mine change detection (CD) in high-resolution (HR) remote sensing images plays a crucial role in mineral development and environmental protection. Significant progress has been made in this field in recent years, largely due to the advancement of deep learning techniques. However, existing deep-learning-based CD methods encounter challenges in effectively integrating neighborhood and scale information, resulting in suboptimal performance. Therefore, by exploring the influence patterns of neighborhood and scale information, this paper proposes an Integrated Neighborhood and Scale Information Network (INSINet) for open-pit mine CD in HR remote sensing images. Specifically, INSINet introduces 8-neighborhood-image information to acquire a larger receptive field, improving the recognition of center image boundary regions. Drawing on techniques of skip connection, deep supervision, and attention mechanism, the multi-path deep supervised attention (MDSA) module is designed to enhance multi-scale information fusion and change feature extraction. Experimental analysis reveals that incorporating neighborhood and scale information enhances the F1 score of INSINet by 6.40%, with improvements of 3.08% and 3.32% respectively. INSINet outperforms existing methods with an Overall Accuracy of 97.69%, Intersection over Union of 71.26%, and F1 score of 83.22%. INSINet shows significance for open-pit mine CD in HR remote sensing images.
Authors: Qiaoqiao Jin, Xuanhong Chen, Meiguang Jin, Ying Cheng, Rui Shi, Yucheng Zheng, Yupeng Zhu, Bingbing Ni
Abstract: Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet they grapple with the challenges of inaccurate supervision (e.g., face misalignment) and sophisticated facial prompts (including face parsing, and landmark detection). These challenges prohibit low-cost deployment of facial makeup models, especially on mobile devices. To solve above problems, we propose a brand-new learning paradigm, termed "Data Amplify Learning (DAL)," alongside a compact makeup model named "TinyBeauty." The core idea of DAL lies in employing a Diffusion-based Data Amplifier (DDA) to "amplify" limited images for the model training, thereby enabling accurate pixel-to-pixel supervision with merely a handful of annotations. Two pivotal innovations in DDA facilitate the above training approach: (1) A Residual Diffusion Model (RDM) is designed to generate high-fidelity detail and circumvent the detail vanishing problem in the vanilla diffusion models; (2) A Fine-Grained Makeup Module (FGMM) is proposed to achieve precise makeup control and combination while retaining face identity. Coupled with DAL, TinyBeauty necessitates merely 80K parameters to achieve a state-of-the-art performance without intricate face prompts. Meanwhile, TinyBeauty achieves a remarkable inference speed of up to 460 fps on the iPhone 13. Extensive experiments show that DAL can produce highly competitive makeup models using only 5 image pairs.
Authors: Zhuofan Wen, Fengyu Zhang, Siyuan Zhang, Haiyang Sun, Mingyu Xu, Licai Sun, Zheng Lian, Bin Liu, Jianhua Tao
Abstract: Multimodal fusion is a significant method for most multimodal tasks. With the recent surge in the number of large pre-trained models, combining both multimodal fusion methods and pre-trained model features can achieve outstanding performance in many multimodal tasks. In this paper, we present our approach, which leverages both advantages for addressing the task of Expression (Expr) Recognition and Valence-Arousal (VA) Estimation. We evaluate the Aff-Wild2 database using pre-trained models, then extract the final hidden layers of the models as features. Following preprocessing and interpolation or convolution to align the extracted features, different models are employed for modal fusion. Our code is available at GitHub - FulgenceWen/ABAW6th.
Authors: Bumsoo Kim, Wonseop Shin, Kyuchul Lee, Sanghyun Seo
Abstract: Large-scale Text-to-Image (TTI) models have become a common approach for generating training data in various generative fields. However, visual hallucinations, which contain perceptually critical defects, remain a concern, especially in non-photorealistic styles like cartoon characters. We propose a novel visual hallucination detection system for cartoon character images generated by TTI models. Our approach leverages pose-aware in-context visual learning (PA-ICVL) with Vision-Language Models (VLMs), utilizing both RGB images and pose information. By incorporating pose guidance from a fine-tuned pose estimator, we enable VLMs to make more accurate decisions. Experimental results demonstrate significant improvements in identifying visual hallucinations compared to baseline methods relying solely on RGB images. This research advances TTI models by mitigating visual hallucinations, expanding their potential in non-photorealistic domains.
Authors: Seongjun Jeong, Gi-Cheon Kang, Seongho Choi, Joochan Kim, Byoung-Tak Zhang
Abstract: Vision-and-Language Navigation (VLN) agents navigate to a destination using natural language instructions and the visual information they observe. Existing methods for training VLN agents presuppose fixed datasets, leading to a significant limitation: the introduction of new environments necessitates retraining with previously encountered environments to preserve their knowledge. This makes it difficult to train VLN agents that operate in the ever-changing real world. To address this limitation, we present the Continual Vision-and-Language Navigation (CVLN) paradigm, designed to evaluate agents trained through a continual learning process. For the training and evaluation of CVLN agents, we re-arrange existing VLN datasets to propose two datasets: CVLN-I, focused on navigation via initial-instruction interpretation, and CVLN-D, aimed at navigation through dialogue with other agents. Furthermore, we propose two novel rehearsal-based methods for CVLN, Perplexity Replay (PerpR) and Episodic Self-Replay (ESR). PerpR prioritizes replaying challenging episodes based on action perplexity, while ESR replays previously predicted action logits to preserve learned behaviors. We demonstrate the effectiveness of the proposed methods on CVLN through extensive experiments.
Authors: Zhichao Wei, Qingkun Su, Long Qin, Weizhi Wang
Abstract: Recent advances in tuning-free personalized image generation based on diffusion models are impressive. However, to improve subject fidelity, existing methods either retrain the diffusion model or infuse it with dense visual embeddings, both of which suffer from poor generalization and efficiency. Also, these methods falter in multi-subject image generation due to the unconstrained cross-attention mechanism. In this paper, we propose MM-Diff, a unified and tuning-free image personalization framework capable of generating high-fidelity images of both single and multiple subjects in seconds. Specifically, to simultaneously enhance text consistency and subject fidelity, MM-Diff employs a vision encoder to transform the input image into CLS and patch embeddings. CLS embeddings are used on the one hand to augment the text embeddings, and on the other hand together with patch embeddings to derive a small number of detail-rich subject embeddings, both of which are efficiently integrated into the diffusion model through the well-designed multimodal cross-attention mechanism. Additionally, MM-Diff introduces cross-attention map constraints during the training phase, ensuring flexible multi-subject image sampling during inference without any predefined inputs (e.g., layout). Extensive experiments demonstrate the superior performance of MM-Diff over other leading methods.
Authors: Heng Guo, Jianfeng Zhang, Jiaxing Huang, Tony C. W. Mok, Dazhou Guo, Ke Yan, Le Lu, Dakai Jin, Minfeng Xu
Abstract: Segment anything model (SAM) demonstrates strong generalization ability on natural image segmentation. However, its direct adaption in medical image segmentation tasks shows significant performance drops with inferior accuracy and unstable results. It may also requires an excessive number of prompt points to obtain a reasonable accuracy. For segmenting 3D radiological CT or MRI scans, a 2D SAM model has to separately handle hundreds of 2D slices. Although quite a few studies explore adapting SAM into medical image volumes, the efficiency of 2D adaption methods is unsatisfactory and 3D adaptation methods only capable of segmenting specific organs/tumors. In this work, we propose a comprehensive and scalable 3D SAM model for whole-body CT segmentation, named CT-SAM3D. Instead of adapting SAM, we propose a 3D promptable segmentation model using a (nearly) fully labeled CT dataset. To train CT-SAM3D effectively, ensuring the model's accurate responses to higher-dimensional spatial prompts is crucial, and 3D patch-wise training is required due to GPU memory constraints. For this purpose, we propose two key technical developments: 1) a progressively and spatially aligned prompt encoding method to effectively encode click prompts in local 3D space; and 2) a cross-patch prompt learning scheme to capture more 3D spatial context, which is beneficial for reducing the editing workloads when interactively prompting on large organs. CT-SAM3D is trained and validated using a curated dataset of 1204 CT scans containing 107 whole-body anatomies, reporting significantly better quantitative performance against all previous SAM-derived models by a large margin with much fewer click prompts. Our model can handle segmenting unseen organ as well. Code, data, and our 3D interactive segmentation tool with quasi-real-time responses will be made publicly available.
Authors: Raza Yunus, Jan Eric Lenssen, Michael Niemeyer, Yiyi Liao, Christian Rupprecht, Christian Theobalt, Gerard Pons-Moll, Jia-Bin Huang, Vladislav Golyanik, Eddy Ilg
Abstract: Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie industry and AR/VR applications. It also facilitates the content creation necessary in computer games and AR/VR by avoiding laborious manual design processes. Further, such models are fundamental for intelligent computing systems that need to interpret real-world scenes and actions to act and interact safely with the human world. Notably, the world surrounding us is dynamic, and reconstructing models of dynamic, non-rigidly moving scenes is a severely underconstrained and challenging problem. This state-of-the-art report (STAR) offers the reader a comprehensive summary of state-of-the-art techniques with monocular and multi-view inputs such as data from RGB and RGB-D sensors, among others, conveying an understanding of different approaches, their potential applications, and promising further research directions. The report covers 3D reconstruction of general non-rigid scenes and further addresses the techniques for scene decomposition, editing and controlling, and generalizable and generative modeling. More specifically, we first review the common and fundamental concepts necessary to understand and navigate the field and then discuss the state-of-the-art techniques by reviewing recent approaches that use traditional and machine-learning-based neural representations, including a discussion on the newly enabled applications. The STAR is concluded with a discussion of the remaining limitations and open challenges.
Authors: Zhonghua Zhai, Chen Ju, Jinsong Lan, Shuai Xiao
Abstract: In this work, we propose Cell Variational Information Bottleneck Network (cellVIB), a convolutional neural network using information bottleneck mechanism, which can be combined with the latest feedforward network architecture in an end-to-end training method. Our Cell Variational Information Bottleneck Network is constructed by stacking VIB cells, which generate feature maps with uncertainty. As layers going deeper, the regularization effect will gradually increase, instead of directly adding excessive regular constraints to the output layer of the model as in Deep VIB. Under each VIB cell, the feedforward process learns an independent mean term and an standard deviation term, and predicts the Gaussian distribution based on them. The feedback process is based on reparameterization trick for effective training. This work performs an extensive analysis on MNIST dataset to verify the effectiveness of each VIB cells, and provides an insightful analysis on how the VIB cells affect mutual information. Experiments conducted on CIFAR-10 also prove that our cellVIB is robust against noisy labels during training and against corrupted images during testing. Then, we validate our method on PACS dataset, whose results show that the VIB cells can significantly improve the generalization performance of the basic model. Finally, in a more complex representation learning task, face recognition, our network structure has also achieved very competitive results.
Authors: Shreyas Chandgothia, Ardhendu Sekhar, Amit Sethi
Abstract: Training a computer vision system to segment a novel class typically requires collecting and painstakingly annotating lots of images with objects from that class. Few-shot segmentation techniques reduce the required number of images to learn to segment a new class, but careful annotations of object boundaries are still required. On the other hand, interactive segmentation techniques only focus on incrementally improving the segmentation of one object at a time (typically, using clicks given by an expert) in a class-agnostic manner. We combine the two concepts to drastically reduce the effort required to train segmentation models for novel classes. Instead of trivially feeding interactive segmentation masks as ground truth to a few-shot segmentation model, we propose IFSENet, which can accept sparse supervision on a single or few support images in the form of clicks to generate masks on support (training, at least clicked upon once) as well as query (test, never clicked upon) images. To trade-off effort for accuracy flexibly, the number of images and clicks can be incrementally added to the support set to further improve the segmentation of support as well as query images. The proposed model approaches the accuracy of previous state-of-the-art few-shot segmentation models with considerably lower annotation effort (clicks instead of maps), when tested on Pascal and SBD datasets on query images. It also works well as an interactive segmentation method on support images.
Authors: Lan Feng, Mohammadhossein Bahari, Kaouther Messaoud Ben Amor, \'Eloi Zablocki, Matthieu Cord, Alexandre Alahi
Abstract: Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be studied by employing multiple datasets, it is challenging due to several discrepancies, \textit{e.g.,} in data formats, map resolution, and semantic annotation types. To address these challenges, we introduce UniTraj, a comprehensive framework that unifies various datasets, models, and evaluation criteria, presenting new opportunities for the vehicle trajectory prediction field. In particular, using UniTraj, we conduct extensive experiments and find that model performance significantly drops when transferred to other datasets. However, enlarging data size and diversity can substantially improve performance, leading to a new state-of-the-art result for the nuScenes dataset. We provide insights into dataset characteristics to explain these findings. The code can be found here: \hyperlink{https://github.com/vita-epfl/UniTraj}{https://github.com/vita-epfl/UniTraj}.
URLs: https://github.com/vita-epfl/UniTraj, https://github.com/vita-epfl/UniTraj
Authors: Lei Zhang, Xiaowei Fu, Fuxiang Huang, Yi Yang, Xinbo Gao
Abstract: Person re-identification (ReID) has made great strides thanks to the data-driven deep learning techniques. However, the existing benchmark datasets lack diversity, and models trained on these data cannot generalize well to dynamic wild scenarios. To meet the goal of improving the explicit generalization of ReID models, we develop a new Open-World, Diverse, Cross-Spatial-Temporal dataset named OWD with several distinct features. 1) Diverse collection scenes: multiple independent open-world and highly dynamic collecting scenes, including streets, intersections, shopping malls, etc. 2) Diverse lighting variations: long time spans from daytime to nighttime with abundant illumination changes. 3) Diverse person status: multiple camera networks in all seasons with normal/adverse weather conditions and diverse pedestrian appearances (e.g., clothes, personal belongings, poses, etc.). 4) Protected privacy: invisible faces for privacy critical applications. To improve the implicit generalization of ReID, we further propose a Latent Domain Expansion (LDE) method to develop the potential of source data, which decouples discriminative identity-relevant and trustworthy domain-relevant features and implicitly enforces domain-randomized identity feature space expansion with richer domain diversity to facilitate domain invariant representations. Our comprehensive evaluations with most benchmark datasets in the community are crucial for progress, although this work is far from the grand goal toward open-world and dynamic wild applications.
Authors: Vladyslav Zalevskyi, Kristoffer Hougaard Madsen
Abstract: Bipolar disorder (BD) and schizophrenia (SZ) are severe mental disorders with profound societal impact. Identifying risk markers early is crucial for understanding disease progression and enabling preventive measures. The Danish High Risk and Resilience Study (VIA) focuses on understanding early disease processes, particularly in children with familial high risk (FHR). Understanding structural brain changes associated with these diseases during early stages is essential for effective interventions. The central sulcus (CS) is a prominent brain landmark related to brain regions involved in motor and sensory processing. Analyzing CS morphology can provide valuable insights into neurodevelopmental abnormalities in the FHR group. However, segmenting the central sulcus (CS) presents challenges due to its variability, especially in adolescents. This study introduces two novel approaches to improve CS segmentation: synthetic data generation to model CS variability and self-supervised pre-training with multi-task learning to adapt models to new cohorts. These methods aim to enhance segmentation performance across diverse populations, eliminating the need for extensive preprocessing.
Authors: Kailing Wang, Chen Yang, Yuehao Wang, Sikuang Li, Yan Wang, Qi Dou, Xiaokang Yang, Wei Shen
Abstract: Precise camera tracking, high-fidelity 3D tissue reconstruction, and real-time online visualization are critical for intrabody medical imaging devices such as endoscopes and capsule robots. However, existing SLAM (Simultaneous Localization and Mapping) methods often struggle to achieve both complete high-quality surgical field reconstruction and efficient computation, restricting their intraoperative applications among endoscopic surgeries. In this paper, we introduce EndoGSLAM, an efficient SLAM approach for endoscopic surgeries, which integrates streamlined Gaussian representation and differentiable rasterization to facilitate over 100 fps rendering speed during online camera tracking and tissue reconstructing. Extensive experiments show that EndoGSLAM achieves a better trade-off between intraoperative availability and reconstruction quality than traditional or neural SLAM approaches, showing tremendous potential for endoscopic surgeries. The project page is at https://EndoGSLAM.loping151.com
Authors: Jiaming Li, Xiangru Lin, Wei Zhang, Xiao Tan, Yingying Li, Junyu Han, Errui Ding, Jingdong Wang, Guanbin Li
Abstract: Current semi-supervised object detection (SSOD) algorithms typically assume class balanced datasets (PASCAL VOC etc.) or slightly class imbalanced datasets (MS-COCO, etc). This assumption can be easily violated since real world datasets can be extremely class imbalanced in nature, thus making the performance of semi-supervised object detectors far from satisfactory. Besides, the research for this problem in SSOD is severely under-explored. To bridge this research gap, we comprehensively study the class imbalance problem for SSOD under more challenging scenarios, thus forming the first experimental setting for class imbalanced SSOD (CI-SSOD). Moreover, we propose a simple yet effective gradient-based sampling framework that tackles the class imbalance problem from the perspective of two types of confirmation biases. To tackle confirmation bias towards majority classes, the gradient-based reweighting and gradient-based thresholding modules leverage the gradients from each class to fully balance the influence of the majority and minority classes. To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module. Experiments on three proposed sub-tasks, namely MS-COCO, MS-COCO to Object365 and LVIS, suggest that our method outperforms current class imbalanced object detectors by clear margins, serving as a baseline for future research in CI-SSOD. Code will be available at https://github.com/nightkeepers/CI-SSOD.
Authors: Jun Cheng, Dong Liang, Shan Tan
Abstract: Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise, their susceptibility to out-of-distribution (OOD) noise remains a significant challenge. The recent emergence of contrastive language-image pre-training (CLIP) model has showcased exceptional capabilities in open-world image recognition and segmentation. Yet, the potential for leveraging CLIP to enhance the robustness of low-level tasks remains largely unexplored. This paper uncovers that certain dense features extracted from the frozen ResNet image encoder of CLIP exhibit distortion-invariant and content-related properties, which are highly desirable for generalizable denoising. Leveraging these properties, we devise an asymmetrical encoder-decoder denoising network, which incorporates dense features including the noisy image and its multi-scale features from the frozen ResNet encoder of CLIP into a learnable image decoder to achieve generalizable denoising. The progressive feature augmentation strategy is further proposed to mitigate feature overfitting and improve the robustness of the learnable decoder. Extensive experiments and comparisons conducted across diverse OOD noises, including synthetic noise, real-world sRGB noise, and low-dose CT image noise, demonstrate the superior generalization ability of our method.
Authors: Yuanbang Liang, Bhavesh Garg, Paul L Rosin, Yipeng Qin
Abstract: In this paper, we propose Image Downscaling Assessment by Rate-Distortion (IDA-RD), a novel measure to quantitatively evaluate image downscaling algorithms. In contrast to image-based methods that measure the quality of downscaled images, ours is process-based that draws ideas from rate-distortion theory to measure the distortion incurred during downscaling. Our main idea is that downscaling and super-resolution (SR) can be viewed as the encoding and decoding processes in the rate-distortion model, respectively, and that a downscaling algorithm that preserves more details in the resulting low-resolution (LR) images should lead to less distorted high-resolution (HR) images in SR. In other words, the distortion should increase as the downscaling algorithm deteriorates. However, it is non-trivial to measure this distortion as it requires the SR algorithm to be blind and stochastic. Our key insight is that such requirements can be met by recent SR algorithms based on deep generative models that can find all matching HR images for a given LR image on their learned image manifolds. Extensive experimental results show the effectiveness of our IDA-RD measure.
Authors: Md Abdul Kadir, Hasan Md Tusfiqur Alam, Pascale Maul, Hans-J\"urgen Profitlich, Moritz Wolf, Daniel Sonntag
Abstract: Image annotation is one of the most essential tasks for guaranteeing proper treatment for patients and tracking progress over the course of therapy in the field of medical imaging and disease diagnosis. However, manually annotating a lot of 2D and 3D imaging data can be extremely tedious. Deep Learning (DL) based segmentation algorithms have completely transformed this process and made it possible to automate image segmentation. By accurately segmenting medical images, these algorithms can greatly minimize the time and effort necessary for manual annotation. Additionally, by incorporating Active Learning (AL) methods, these segmentation algorithms can perform far more effectively with a smaller amount of ground truth data. We introduce MedDeepCyleAL, an end-to-end framework implementing the complete AL cycle. It provides researchers with the flexibility to choose the type of deep learning model they wish to employ and includes an annotation tool that supports the classification and segmentation of medical images. The user-friendly interface allows for easy alteration of the AL and DL model settings through a configuration file, requiring no prior programming experience. While MedDeepCyleAL can be applied to any kind of image data, we have specifically applied it to ophthalmology data in this project.
Authors: Lucas Iijima, Tania Stathaki
Abstract: Image generators are gaining vast amount of popularity and have rapidly changed how digital content is created. With the latest AI technology, millions of high quality images are being generated by the public, which are constantly motivating the research community to push the limits of generative models to create more complex and realistic images. This paper focuses on Cross-Domain Image Retrieval (CDIR) which can be used as an additional tool to inspect collections of generated images by determining the level of similarity between images in a dataset. An ideal retrieval system would be able to generalize to unseen complex images from multiple domains (e.g., photos, drawings and paintings). To address this goal, we propose a novel caption-matching approach that leverages multimodal language-vision architectures pre-trained on large datasets. The method is tested on DomainNet and Office-Home datasets and consistently achieves state-of-the-art performance over the latest approaches in the literature for cross-domain image retrieval. In order to verify the effectiveness with AI-generated images, the method was also put to test with a database composed by samples collected from Midjourney, which is a widely used generative platform for content creation.
Authors: Florian Langer, Jihong Ju, Georgi Dikov, Gerhard Reitmayr, Mohsen Ghafoorian
Abstract: Digitising the 3D world into a clean, CAD model-based representation has important applications for augmented reality and robotics. Current state-of-the-art methods are computationally intensive as they individually encode each detected object and optimise CAD alignments in a second stage. In this work, we propose FastCAD, a real-time method that simultaneously retrieves and aligns CAD models for all objects in a given scene. In contrast to previous works, we directly predict alignment parameters and shape embeddings. We achieve high-quality shape retrievals by learning CAD embeddings in a contrastive learning framework and distilling those into FastCAD. Our single-stage method accelerates the inference time by a factor of 50 compared to other methods operating on RGB-D scans while outperforming them on the challenging Scan2CAD alignment benchmark. Further, our approach collaborates seamlessly with online 3D reconstruction techniques. This enables the real-time generation of precise CAD model-based reconstructions from videos at 10 FPS. Doing so, we significantly improve the Scan2CAD alignment accuracy in the video setting from 43.0% to 48.2% and the reconstruction accuracy from 22.9% to 29.6%.
Authors: Tuo Feng, Wenguan Wang, Fan Ma, Yi Yang
Abstract: Autonomous systems need to process large-scale, sparse, and irregular point clouds with limited compute resources. Consequently, it is essential to develop LiDAR perception methods that are both efficient and effective. Although naively enlarging 3D kernel size can enhance performance, it will also lead to a cubically-increasing overhead. Therefore, it is crucial to develop streamlined 3D large kernel designs that eliminate redundant weights and work effectively with larger kernels. In this paper, we propose an efficient and effective Large Sparse Kernel 3D Neural Network (LSK3DNet) that leverages dynamic pruning to amplify the 3D kernel size. Our method comprises two core components: Spatial-wise Dynamic Sparsity (SDS) and Channel-wise Weight Selection (CWS). SDS dynamically prunes and regrows volumetric weights from the beginning to learn a large sparse 3D kernel. It not only boosts performance but also significantly reduces model size and computational cost. Moreover, CWS selects the most important channels for 3D convolution during training and subsequently prunes the redundant channels to accelerate inference for 3D vision tasks. We demonstrate the effectiveness of LSK3DNet on three benchmark datasets and five tracks compared with classical models and large kernel designs. Notably, LSK3DNet achieves the state-of-the-art performance on SemanticKITTI (i.e., 75.6% on single-scan and 63.4% on multi-scan), with roughly 40% model size reduction and 60% computing operations reduction compared to the naive large 3D kernel model.
Authors: Yimeng Fan, Wei Zhang, Changsong Liu, Mingyang Li, Wenrui Lu
Abstract: Event cameras, characterized by high temporal resolution, high dynamic range, low power consumption, and high pixel bandwidth, offer unique capabilities for object detection in specialized contexts. Despite these advantages, the inherent sparsity and asynchrony of event data pose challenges to existing object detection algorithms. Spiking Neural Networks (SNNs), inspired by the way the human brain codes and processes information, offer a potential solution to these difficulties. However, their performance in object detection using event cameras is limited in current implementations. In this paper, we propose the Spiking Fusion Object Detector (SFOD), a simple and efficient approach to SNN-based object detection. Specifically, we design a Spiking Fusion Module, achieving the first-time fusion of feature maps from different scales in SNNs applied to event cameras. Additionally, through integrating our analysis and experiments conducted during the pretraining of the backbone network on the NCAR dataset, we delve deeply into the impact of spiking decoding strategies and loss functions on model performance. Thereby, we establish state-of-the-art classification results based on SNNs, achieving 93.7\% accuracy on the NCAR dataset. Experimental results on the GEN1 detection dataset demonstrate that the SFOD achieves a state-of-the-art mAP of 32.1\%, outperforming existing SNN-based approaches. Our research not only underscores the potential of SNNs in object detection with event cameras but also propels the advancement of SNNs. Code is available at https://github.com/yimeng-fan/SFOD.
Authors: Sofia Casarin, Cynthia I. Ugwu, Sergio Escalera, Oswald Lanz
Abstract: The landscape of deep learning research is moving towards innovative strategies to harness the true potential of data. Traditionally, emphasis has been on scaling model architectures, resulting in large and complex neural networks, which can be difficult to train with limited computational resources. However, independently of the model size, data quality (i.e. amount and variability) is still a major factor that affects model generalization. In this work, we propose a novel technique to exploit available data through the use of automatic data augmentation for the tasks of image classification and semantic segmentation. We introduce the first Differentiable Augmentation Search method (DAS) to generate variations of images that can be processed as videos. Compared to previous approaches, DAS is extremely fast and flexible, allowing the search on very large search spaces in less than a GPU day. Our intuition is that the increased receptive field in the temporal dimension provided by DAS could lead to benefits also to the spatial receptive field. More specifically, we leverage DAS to guide the reshaping of the spatial receptive field by selecting task-dependant transformations. As a result, compared to standard augmentation alternatives, we improve in terms of accuracy on ImageNet, Cifar10, Cifar100, Tiny-ImageNet, Pascal-VOC-2012 and CityScapes datasets when plugging-in our DAS over different light-weight video backbones.
Authors: Taeheon Kim, Sangyun Chung, Damin Yeom, Youngjoon Yu, Hak Gu Kim, Yong Man Ro
Abstract: Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in obvious cases, especially due to the modality bias learned from statistically biased datasets. From these problems, we anticipate that maybe understanding the complementary information itself is difficult to achieve from vision-only models. Accordingly, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework, which incorporates Large Language Models (LLMs) to understand the complementary information at the semantic level and further enhance the fusion process. Specifically, we generate text descriptions of the pedestrian in each RGB and thermal modality and design a Multispectral Chain-of-Thought (MSCoT) prompting, which models a step-by-step process to facilitate cross-modal reasoning at the semantic level and perform accurate detection. Moreover, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing vision-driven and language-driven detections. Extensive experiments validate that MSCoTDet improves multispectral pedestrian detection.
Authors: Lei Jiang, Weixin Yang, Xin Zhang, Hao Ni
Abstract: Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision. The recent state-of-the-art models for SAR are primarily based on graph convolutional neural networks (GCNs), which are powerful in extracting the spatial information of skeleton data. However, it is yet clear that such GCN-based models can effectively capture the temporal dynamics of human action sequences. To this end, we propose the DevLSTM module, which exploits the path development -- a principled and parsimonious representation for sequential data by leveraging the Lie group structure. The path development, originated from Rough path theory, can effectively capture the order of events in high-dimensional stream data with massive dimension reduction and consequently enhance the LSTM module substantially. Our proposed G-DevLSTM module can be conveniently plugged into the temporal graph, complementing existing advanced GCN-based models. Our empirical studies on the NTU60, NTU120 and Chalearn2013 datasets demonstrate that our proposed hybrid model significantly outperforms the current best-performing methods in SAR tasks. The code is available at https://github.com/DeepIntoStreams/GCN-DevLSTM.
Authors: Pranav Kulkarni, Adway Kanhere, Dharmam Savani, Andrew Chan, Devina Chatterjee, Paul H. Yi, Vishwa S. Parekh
Abstract: Curating annotations for medical image segmentation is a labor-intensive and time-consuming task that requires domain expertise, resulting in "narrowly" focused deep learning (DL) models with limited translational utility. Recently, foundation models like the Segment Anything Model (SAM) have revolutionized semantic segmentation with exceptional zero-shot generalizability across various domains, including medical imaging, and hold a lot of promise for streamlining the annotation process. However, SAM has yet to be evaluated in a crowd-sourced setting to curate annotations for training 3D DL segmentation models. In this work, we explore the potential of SAM for crowd-sourcing "sparse" annotations from non-experts to generate "dense" segmentation masks for training 3D nnU-Net models, a state-of-the-art DL segmentation model. Our results indicate that while SAM-generated annotations exhibit high mean Dice scores compared to ground-truth annotations, nnU-Net models trained on SAM-generated annotations perform significantly worse than nnU-Net models trained on ground-truth annotations ($p<0.001$, all).
Authors: Soyeon Yoon, Kwan Yun, Kwanggyoon Seo, Sihun Cha, Jung Eun Yoo, Junyong Noh
Abstract: Recent advances in 3D face stylization have made significant strides in few to zero-shot settings. However, the degree of stylization achieved by existing methods is often not sufficient for practical applications because they are mostly based on statistical 3D Morphable Models (3DMM) with limited variations. To this end, we propose a method that can produce a highly stylized 3D face model with desired topology. Our methods train a surface deformation network with 3DMM and translate its domain to the target style using a paired exemplar. The network achieves stylization of the 3D face mesh by mimicking the style of the target using a differentiable renderer and directional CLIP losses. Additionally, during the inference process, we utilize a Mesh Agnostic Encoder (MAGE) that takes deformation target, a mesh of diverse topologies as input to the stylization process and encodes its shape into our latent space. The resulting stylized face model can be animated by commonly used 3DMM blend shapes. A set of quantitative and qualitative evaluations demonstrate that our method can produce highly stylized face meshes according to a given style and output them in a desired topology. We also demonstrate example applications of our method including image-based stylized avatar generation, linear interpolation of geometric styles, and facial animation of stylized avatars.
Authors: Qingyang Liu, Junqi You, Jianting Wang, Xinhao Tao, Bo Zhang, Li Niu
Abstract: In the realm of image composition, generating realistic shadow for the inserted foreground remains a formidable challenge. Previous works have developed image-to-image translation models which are trained on paired training data. However, they are struggling to generate shadows with accurate shapes and intensities, hindered by data scarcity and inherent task complexity. In this paper, we resort to foundation model with rich prior knowledge of natural shadow images. Specifically, we first adapt ControlNet to our task and then propose intensity modulation modules to improve the shadow intensity. Moreover, we extend the small-scale DESOBA dataset to DESOBAv2 using a novel data acquisition pipeline. Experimental results on both DESOBA and DESOBAv2 datasets as well as real composite images demonstrate the superior capability of our model for shadow generation task. The dataset, code, and model are released at https://github.com/bcmi/Object-Shadow-Generation-Dataset-DESOBAv2.
URLs: https://github.com/bcmi/Object-Shadow-Generation-Dataset-DESOBAv2.
Authors: Junbo Yin, Jianbing Shen, Runnan Chen, Wei Li, Ruigang Yang, Pascal Frossard, Wenguan Wang
Abstract: Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-Fusion, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-Fusion essentially differs from existing approaches that only focus on the BEV scene-level fusion by explicitly incorporating instance-level multimodal information, thus facilitating the instance-centric tasks like 3D object detection. It comprises a Hierarchical Scene Fusion (HSF) module and an Instance-Guided Fusion (IGF) module. HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities. IGF mines instance candidates, explores their relationships, and aggregates the local multimodal context for each instance. These instances then serve as guidance to enhance the scene feature and yield an instance-aware BEV representation. On the challenging nuScenes benchmark, IS-Fusion outperforms all the published multimodal works to date. Code is available at: https://github.com/yinjunbo/IS-Fusion.
Authors: Jian Li, Pu Ren, Yang Liu, Hao Sun
Abstract: Object-centric learning aims to break down complex visual scenes into more manageable object representations, enhancing the understanding and reasoning abilities of machine learning systems toward the physical world. Recently, slot-based video models have demonstrated remarkable proficiency in segmenting and tracking objects, but they overlook the importance of the effective reasoning module. In the real world, reasoning and predictive abilities play a crucial role in human perception and object tracking; in particular, these abilities are closely related to human intuitive physics. Inspired by this, we designed a novel reasoning module called the Slot-based Time-Space Transformer with Memory buffer (STATM) to enhance the model's perception ability in complex scenes. The memory buffer primarily serves as storage for slot information from upstream modules, the Slot-based Time-Space Transformer makes predictions through slot-based spatiotemporal attention computations and fusion. Our experiment results on various datasets show that STATM can significantly enhance object-centric learning capabilities of slot-based video models.
Authors: Sudhir Sornapudi (Corteva Agriscience, Indianapolis, USA), Rajhans Singh (Corteva Agriscience, Indianapolis, USA)
Abstract: Computer vision in agriculture is game-changing with its ability to transform farming into a data-driven, precise, and sustainable industry. Deep learning has empowered agriculture vision to analyze vast, complex visual data, but heavily rely on the availability of large annotated datasets. This remains a bottleneck as manual labeling is error-prone, time-consuming, and expensive. The lack of efficient labeling approaches inspired us to consider self-supervised learning as a paradigm shift, learning meaningful feature representations from raw agricultural image data. In this work, we explore how self-supervised representation learning unlocks the potential applicability to diverse agriculture vision tasks by eliminating the need for large-scale annotated datasets. We propose a lightweight framework utilizing SimCLR, a contrastive learning approach, to pre-train a ResNet-50 backbone on a large, unannotated dataset of real-world agriculture field images. Our experimental analysis and results indicate that the model learns robust features applicable to a broad range of downstream agriculture tasks discussed in the paper. Additionally, the reduced reliance on annotated data makes our approach more cost-effective and accessible, paving the way for broader adoption of computer vision in agriculture.
Authors: Geon Yeong Park, Hyeonho Jeong, Sang Wan Lee, Jong Chul Ye
Abstract: The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion, etc. Despite these advances, challenges persist in accurately distilling motion information from video frames. While existing works leverage the consecutive frame residual as the target motion vector, they inherently lack global motion context and are vulnerable to frame-wise distortions. To address this, we present Spectral Motion Alignment (SMA), a novel framework that refines and aligns motion vectors using Fourier and wavelet transforms. SMA learns motion patterns by incorporating frequency-domain regularization, facilitating the learning of whole-frame global motion dynamics, and mitigating spatial artifacts. Extensive experiments demonstrate SMA's efficacy in improving motion transfer while maintaining computational efficiency and compatibility across various video customization frameworks.
Authors: Alvaro Gonzalez-Jimenez, Simone Lionetti, Dena Bazazian, Philippe Gottfrois, Fabian Gr\"oger, Marc Pouly, Alexander Navarini
Abstract: Out-Of-Distribution (OOD) detection is critical to deploy deep learning models in safety-critical applications. However, the inherent hierarchical concept structure of visual data, which is instrumental to OOD detection, is often poorly captured by conventional methods based on Euclidean geometry. This work proposes a metric framework that leverages the strengths of Hyperbolic geometry for OOD detection. Inspired by previous works that refine the decision boundary for OOD data with synthetic outliers, we extend this method to Hyperbolic space. Interestingly, we find that synthetic outliers do not benefit OOD detection in Hyperbolic space as they do in Euclidean space. Furthermore we explore the relationship between OOD detection performance and Hyperbolic embedding dimension, addressing practical concerns in resource-constrained environments. Extensive experiments show that our framework improves the FPR95 for OOD detection from 22\% to 15\% and from 49% to 28% on CIFAR-10 and CIFAR-100 respectively compared to Euclidean methods.
Authors: Jialu Wang, Kaichen Zhou, Andrew Markham, Niki Trigoni
Abstract: Despite the advancements in deep learning for camera relocalization tasks, obtaining ground truth pose labels required for the training process remains a costly endeavor. While current weakly supervised methods excel in lightweight label generation, their performance notably declines in scenarios with sparse views. In response to this challenge, we introduce WSCLoc, a system capable of being customized to various deep learning-based relocalization models to enhance their performance under weakly-supervised and sparse view conditions. This is realized with two stages. In the initial stage, WSCLoc employs a multilayer perceptron-based structure called WFT-NeRF to co-optimize image reconstruction quality and initial pose information. To ensure a stable learning process, we incorporate temporal information as input. Furthermore, instead of optimizing SE(3), we opt for $\mathfrak{sim}(3)$ optimization to explicitly enforce a scale constraint. In the second stage, we co-optimize the pre-trained WFT-NeRF and WFT-Pose. This optimization is enhanced by Time-Encoding based Random View Synthesis and supervised by inter-frame geometric constraints that consider pose, depth, and RGB information. We validate our approaches on two publicly available datasets, one outdoor and one indoor. Our experimental results demonstrate that our weakly-supervised relocalization solutions achieve superior pose estimation accuracy in sparse-view scenarios, comparable to state-of-the-art camera relocalization methods. We will make our code publicly available.
Authors: Teresa Yeo, Andrei Atanov, Harold Benoit, Aleksandr Alekseev, Ruchira Ray, Pooya Esmaeil Akhoondi, Amir Zamir
Abstract: In this work, we present a method to control a text-to-image generative model to produce training data specifically "useful" for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a language model or human expertise, we develop an automated closed-loop system which involves two feedback mechanisms. The first mechanism uses feedback from a given supervised model and finds adversarial prompts that result in image generations that maximize the model loss. While these adversarial prompts result in diverse data informed by the model, they are not informed of the target distribution, which can be inefficient. Therefore, we introduce the second feedback mechanism that guides the generation process towards a certain target distribution. We call the method combining these two mechanisms Guided Adversarial Prompts. We perform our evaluations on different tasks, datasets and architectures, with different types of distribution shifts (spuriously correlated data, unseen domains) and demonstrate the efficiency of the proposed feedback mechanisms compared to open-loop approaches.
Authors: Nicolas Baumann, Michael Baumgartner, Edoardo Ghignone, Jonas K\"uhne, Tobias Fischer, Yung-Hsu Yang, Marc Pollefeys, Michele Magno
Abstract: Accurate detection and tracking of surrounding objects is essential to enable self-driving vehicles. While Light Detection and Ranging (LiDAR) sensors have set the benchmark for high performance, the appeal of camera-only solutions lies in their cost-effectiveness. Notably, despite the prevalent use of Radio Detection and Ranging (RADAR) sensors in automotive systems, their potential in 3D detection and tracking has been largely disregarded due to data sparsity and measurement noise. As a recent development, the combination of RADARs and cameras is emerging as a promising solution. This paper presents Camera-RADAR 3D Detection and Tracking (CR3DT), a camera-RADAR fusion model for 3D object detection, and Multi-Object Tracking (MOT). Building upon the foundations of the State-of-the-Art (SotA) camera-only BEVDet architecture, CR3DT demonstrates substantial improvements in both detection and tracking capabilities, by incorporating the spatial and velocity information of the RADAR sensor. Experimental results demonstrate an absolute improvement in detection performance of 5.3% in mean Average Precision (mAP) and a 14.9% increase in Average Multi-Object Tracking Accuracy (AMOTA) on the nuScenes dataset when leveraging both modalities. CR3DT bridges the gap between high-performance and cost-effective perception systems in autonomous driving, by capitalizing on the ubiquitous presence of RADAR in automotive applications.
Authors: Hongzhi Gao, Zheng Chen, Zehui Chen, Lin Chen, Jiaming Liu, Shanghang Zhang, Feng Zhao
Abstract: Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for practical applications in 3D detection, which is not only more accessible and less expensive but also provides strong spatial information for object localization.In this paper, we empirically discover that it is non-trivial to merely adapt Point-DETR to its 3D form, encountering two main bottlenecks: 1) it fails to encode strong 3D prior into the model, and 2) it generates low-quality pseudo labels in distant regions due to the extreme sparsity of LiDAR points. To overcome these challenges, we introduce Point-DETR3D, a teacher-student framework for weakly semi-supervised 3D detection, designed to fully capitalize on point-wise supervision within a constrained instance-wise annotation budget.Different from Point-DETR which encodes 3D positional information solely through a point encoder, we propose an explicit positional query initialization strategy to enhance the positional prior. Considering the low quality of pseudo labels at distant regions produced by the teacher model, we enhance the detector's perception by incorporating dense imagery data through a novel Cross-Modal Deformable RoI Fusion (D-RoI).Moreover, an innovative point-guided self-supervised learning technique is proposed to allow for fully exploiting point priors, even in student models.Extensive experiments on representative nuScenes dataset demonstrate our Point-DETR3D obtains significant improvements compared to previous works. Notably, with only 5% of labeled data, Point-DETR3D achieves over 90% performance of its fully supervised counterpart.
Authors: Jimyeong Kim, Jungwon Park, Wonjong Rhee
Abstract: In text-to-image personalization, a timely and crucial challenge is the tendency of generated images overfitting to the biases present in the reference images. We initiate our study with a comprehensive categorization of the biases into background, nearby-object, tied-object, substance (in style re-contextualization), and pose biases. These biases manifest in the generated images due to their entanglement into the subject embedding. This undesired embedding entanglement not only results in the reflection of biases from the reference images into the generated images but also notably diminishes the alignment of the generated images with the given generation prompt. To address this challenge, we propose SID~(Selectively Informative Description), a text description strategy that deviates from the prevalent approach of only characterizing the subject's class identification. SID is generated utilizing multimodal GPT-4 and can be seamlessly integrated into optimization-based models. We present comprehensive experimental results along with analyses of cross-attention maps, subject-alignment, non-subject-disentanglement, and text-alignment.
Authors: Aziliz Guezou-Philippe, Arnaud Clav\'e, Ehouarn Maguet, Ludivine Maintier, Charles Garraud, Jean-Rassaire Fouefack, Val\'erie Burdin, Eric Stindel, Guillaume Dardenne
Abstract: Arthroplasty is commonly performed to treat joint osteoarthritis, reducing pain and improving mobility. While arthroplasty has known several technical improvements, a significant share of patients are still unsatisfied with their surgery. Personalised arthroplasty improves surgical outcomes however current solutions require delays, making it difficult to integrate in clinical routine. We propose a fully automated workflow to design patient-specific implants, presented for total knee arthroplasty, the most widely performed arthroplasty in the world nowadays. The proposed pipeline first uses artificial neural networks to segment the proximal and distal extremities of the femur and tibia. Then the full bones are reconstructed using augmented statistical shape models, combining shape and landmarks information. Finally, 77 morphological parameters are computed to design patient-specific implants. The developed workflow has been trained using 91 CT scans of lower limb and evaluated on 41 CT scans manually segmented, in terms of accuracy and execution time. The workflow accuracy was $0.4\pm0.2mm$ for the segmentation, $1.2\pm0.4mm$ for the full bones reconstruction, and $2.8\pm2.2mm$ for the anatomical landmarks determination. The custom implants fitted the patients' anatomy with $0.6\pm0.2mm$ accuracy. The whole process from segmentation to implants' design lasted about 5 minutes. The proposed workflow allows for a fast and reliable personalisation of knee implants, directly from the patient CT image without requiring any manual intervention. It establishes a patient-specific pre-operative planning for TKA in a very short time making it easily available for all patients. Combined with efficient implant manufacturing techniques, this solution could help answer the growing number of arthroplasties while reducing complications and improving the patients' satisfaction.
Authors: Zhitong Xiong, Yi Wang, Fahong Zhang, Adam J. Stewart, Jo\"elle Hanna, Damian Borth, Ioannis Papoutsis, Bertrand Le Saux, Gustau Camps-Valls, Xiao Xiang Zhu
Abstract: The development of foundation models has revolutionized our ability to interpret the Earth's surface using satellite observational data. Traditional models have been siloed, tailored to specific sensors or data types like optical, radar, and hyperspectral, each with its own unique characteristics. This specialization hinders the potential for a holistic analysis that could benefit from the combined strengths of these diverse data sources. Our novel approach introduces the Dynamic One-For-All (DOFA) model, leveraging the concept of neural plasticity in brain science to integrate various data modalities into a single framework adaptively. This dynamic hypernetwork, adjusting to different wavelengths, enables a single versatile Transformer jointly trained on data from five sensors to excel across 12 distinct Earth observation tasks, including sensors never seen during pretraining. DOFA's innovative design offers a promising leap towards more accurate, efficient, and unified Earth observation analysis, showcasing remarkable adaptability and performance in harnessing the potential of multimodal Earth observation data.
Authors: Badri N. Patro, Vijay S. Agneeswaran
Abstract: Transformers have widely adopted attention networks for sequence mixing and MLPs for channel mixing, playing a pivotal role in achieving breakthroughs across domains. However, recent literature highlights issues with attention networks, including low inductive bias and quadratic complexity concerning input sequence length. State Space Models (SSMs) like S4 and others (Hippo, Global Convolutions, liquid S4, LRU, Mega, and Mamba), have emerged to address the above issues to help handle longer sequence lengths. Mamba, while being the state-of-the-art SSM, has a stability issue when scaled to large networks for computer vision datasets. We propose SiMBA, a new architecture that introduces Einstein FFT (EinFFT) for channel modeling by specific eigenvalue computations and uses the Mamba block for sequence modeling. Extensive performance studies across image and time-series benchmarks demonstrate that SiMBA outperforms existing SSMs, bridging the performance gap with state-of-the-art transformers. Notably, SiMBA establishes itself as the new state-of-the-art SSM on ImageNet and transfer learning benchmarks such as Stanford Car and Flower as well as task learning benchmarks as well as seven time series benchmark datasets. The project page is available on this website ~\url{https://github.com/badripatro/Simba}.
Authors: Xiaoling Hu
Abstract: In many scenarios, especially biomedical applications, the correct delineation of complex fine-scaled structures such as neurons, tissues, and vessels is critical for downstream analysis. Despite the strong predictive power of deep learning methods, they do not provide a satisfactory representation of these structures, thus creating significant barriers in scalable annotation and downstream analysis. In this dissertation, we tackle such challenges by proposing novel representations of these topological structures in a deep learning framework. We leverage the mathematical tools from topological data analysis, i.e., persistent homology and discrete Morse theory, to develop principled methods for better segmentation and uncertainty estimation, which will become powerful tools for scalable annotation.
Authors: Aqeel Anwar, Tae Eun Choe, Zian Wang, Sanja Fidler, Minwoo Park
Abstract: Detecting a diverse range of objects under various driving scenarios is essential for the effectiveness of autonomous driving systems. However, the real-world data collected often lacks the necessary diversity presenting a long-tail distribution. Although synthetic data has been utilized to overcome this issue by generating virtual scenes, it faces hurdles such as a significant domain gap and the substantial efforts required from 3D artists to create realistic environments. To overcome these challenges, we present ARSim, a fully automated, comprehensive, modular framework designed to enhance real multi-view image data with 3D synthetic objects of interest. The proposed method integrates domain adaptation and randomization strategies to address covariate shift between real and simulated data by inferring essential domain attributes from real data and employing simulation-based randomization for other attributes. We construct a simplified virtual scene using real data and strategically place 3D synthetic assets within it. Illumination is achieved by estimating light distribution from multiple images capturing the surroundings of the vehicle. Camera parameters from real data are employed to render synthetic assets in each frame. The resulting augmented multi-view consistent dataset is used to train a multi-camera perception network for autonomous vehicles. Experimental results on various AV perception tasks demonstrate the superior performance of networks trained on the augmented dataset.
Authors: Yi Wang, Kunchang Li, Xinhao Li, Jiashuo Yu, Yinan He, Guo Chen, Baoqi Pei, Rongkun Zheng, Jilan Xu, Zun Wang, Yansong Shi, Tianxiang Jiang, Songze Li, Hongjie Zhang, Yifei Huang, Yu Qiao, Yali Wang, Limin Wang
Abstract: We introduce InternVideo2, a new video foundation model (ViFM) that achieves the state-of-the-art performance in action recognition, video-text tasks, and video-centric dialogue. Our approach employs a progressive training paradigm that unifies the different self- or weakly-supervised learning frameworks of masked video token reconstruction, cross-modal contrastive learning, and next token prediction. Different training stages would guide our model to capture different levels of structure and semantic information through different pretext tasks. At the data level, we prioritize the spatiotemporal consistency by semantically segmenting videos and generating video-audio-speech captions. This improves the alignment between video and text. We scale both data and model size for our InternVideo2. Through extensive experiments, we validate our designs and demonstrate the state-of-the-art performance on over 60 video and audio tasks. Notably, our model outperforms others on various video-related captioning, dialogue, and long video understanding benchmarks, highlighting its ability to reason and comprehend long temporal contexts. Code and models are available at https://github.com/OpenGVLab/InternVideo2/.
Authors: Beichen Zhang, Pan Zhang, Xiaoyi Dong, Yuhang Zang, Jiaqi Wang
Abstract: Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text modalities. Despite its widespread adoption, a significant limitation of CLIP lies in the inadequate length of text input. The length of the text token is restricted to 77, and an empirical study shows the actual effective length is even less than 20. This prevents CLIP from handling detailed descriptions, limiting its applications for image retrieval and text-to-image generation with extensive prerequisites. To this end, we propose Long-CLIP as a plug-and-play alternative to CLIP that supports long-text input, retains or even surpasses its zero-shot generalizability, and aligns the CLIP latent space, making it readily replace CLIP without any further adaptation in downstream frameworks. Nevertheless, achieving this goal is far from straightforward, as simplistic fine-tuning can result in a significant degradation of CLIP's performance. Moreover, substituting the text encoder with a language model supporting longer contexts necessitates pretraining with vast amounts of data, incurring significant expenses. Accordingly, Long-CLIP introduces an efficient fine-tuning solution on CLIP with two novel strategies designed to maintain the original capabilities, including (1) a knowledge-preserved stretching of positional embedding and (2) a primary component matching of CLIP features. With leveraging just one million extra long text-image pairs, Long-CLIP has shown the superiority to CLIP for about 20% in long caption text-image retrieval and 6% in traditional text-image retrieval tasks, e.g., COCO and Flickr30k. Furthermore, Long-CLIP offers enhanced capabilities for generating images from detailed text descriptions by replacing CLIP in a plug-and-play manner.
Authors: Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi
Abstract: We introduce DragAPart, a method that, given an image and a set of drags as input, can generate a new image of the same object in a new state, compatible with the action of the drags. Differently from prior works that focused on repositioning objects, DragAPart predicts part-level interactions, such as opening and closing a drawer. We study this problem as a proxy for learning a generalist motion model, not restricted to a specific kinematic structure or object category. To this end, we start from a pre-trained image generator and fine-tune it on a new synthetic dataset, Drag-a-Move, which we introduce. Combined with a new encoding for the drags and dataset randomization, the new model generalizes well to real images and different categories. Compared to prior motion-controlled generators, we demonstrate much better part-level motion understanding.
Authors: Zhenwei Wang, Tengfei Wang, Gerhard Hancke, Ziwei Liu, Rynson W. H. Lau
Abstract: Real-world applications often require a large gallery of 3D assets that share a consistent theme. While remarkable advances have been made in general 3D content creation from text or image, synthesizing customized 3D assets following the shared theme of input 3D exemplars remains an open and challenging problem. In this work, we present ThemeStation, a novel approach for theme-aware 3D-to-3D generation. ThemeStation synthesizes customized 3D assets based on given few exemplars with two goals: 1) unity for generating 3D assets that thematically align with the given exemplars and 2) diversity for generating 3D assets with a high degree of variations. To this end, we design a two-stage framework that draws a concept image first, followed by a reference-informed 3D modeling stage. We propose a novel dual score distillation (DSD) loss to jointly leverage priors from both the input exemplars and the synthesized concept image. Extensive experiments and user studies confirm that ThemeStation surpasses prior works in producing diverse theme-aware 3D models with impressive quality. ThemeStation also enables various applications such as controllable 3D-to-3D generation.
Authors: Kevin Xie, Jonathan Lorraine, Tianshi Cao, Jun Gao, James Lucas, Antonio Torralba, Sanja Fidler, Xiaohui Zeng
Abstract: Recent text-to-3D generation approaches produce impressive 3D results but require time-consuming optimization that can take up to an hour per prompt. Amortized methods like ATT3D optimize multiple prompts simultaneously to improve efficiency, enabling fast text-to-3D synthesis. However, they cannot capture high-frequency geometry and texture details and struggle to scale to large prompt sets, so they generalize poorly. We introduce LATTE3D, addressing these limitations to achieve fast, high-quality generation on a significantly larger prompt set. Key to our method is 1) building a scalable architecture and 2) leveraging 3D data during optimization through 3D-aware diffusion priors, shape regularization, and model initialization to achieve robustness to diverse and complex training prompts. LATTE3D amortizes both neural field and textured surface generation to produce highly detailed textured meshes in a single forward pass. LATTE3D generates 3D objects in 400ms, and can be further enhanced with fast test-time optimization.
Authors: Yuzhang Shang, Mu Cai, Bingxin Xu, Yong Jae Lee, Yan Yan
Abstract: Large Multimodal Models (LMMs) have shown significant reasoning capabilities by connecting a visual encoder and a large language model. LMMs typically use a fixed amount of visual tokens, such as the penultimate layer features in the CLIP visual encoder, as the prefix content. Recent LMMs incorporate more complex visual inputs, such as high-resolution images and videos, which increase the number of visual tokens significantly. However, due to the design of the Transformer architecture, computational costs associated with these models tend to increase quadratically with the number of input tokens. To tackle this problem, we explore a token reduction mechanism and find, similar to prior work, that many visual tokens are spatially redundant. Based on this, we propose PruMerge, a novel adaptive visual token reduction approach, which largely reduces the number of visual tokens while maintaining comparable model performance. We first select the unpruned visual tokens based on their similarity to class tokens and spatial tokens. We then cluster the pruned tokens based on key similarity and merge the clustered tokens with the unpruned tokens to supplement their information. Empirically, when applied to LLaVA-1.5, our approach can compress the visual tokens by 14.4 times on average, and achieve comparable performance across diverse visual question-answering and reasoning tasks. Code and checkpoints are at https://llava-prumerge.github.io/.
Authors: Hanrong Ye, Dan Xu
Abstract: Recently, there has been an increased interest in the practical problem of learning multiple dense scene understanding tasks from partially annotated data, where each training sample is only labeled for a subset of the tasks. The missing of task labels in training leads to low-quality and noisy predictions, as can be observed from state-of-the-art methods. To tackle this issue, we reformulate the partially-labeled multi-task dense prediction as a pixel-level denoising problem, and propose a novel multi-task denoising diffusion framework coined as DiffusionMTL. It designs a joint diffusion and denoising paradigm to model a potential noisy distribution in the task prediction or feature maps and generate rectified outputs for different tasks. To exploit multi-task consistency in denoising, we further introduce a Multi-Task Conditioning strategy, which can implicitly utilize the complementary nature of the tasks to help learn the unlabeled tasks, leading to an improvement in the denoising performance of the different tasks. Extensive quantitative and qualitative experiments demonstrate that the proposed multi-task denoising diffusion model can significantly improve multi-task prediction maps, and outperform the state-of-the-art methods on three challenging multi-task benchmarks, under two different partial-labeling evaluation settings. The code is available at https://prismformore.github.io/diffusionmtl/.
Authors: Davide Maltoni, Lorenzo Pellegrini
Abstract: TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgetting of previous knowledge. Each experience (a.k.a. task) is learned in three phases characterized by different rules and learning dynamics, aimed at removing the class-bias problem (due to class unbalancing) and limiting gradient-based corrections to prevent forgetting of underrepresented classes. Several experiments on complex datasets demonstrate its accuracy and efficiency advantages over competitive existing approaches. The algorithm and all the results presented in this paper are fully reproducible thanks to its publication on the Avalanche open framework for continual learning.
Authors: Guoxuan Xia, Olivier Laurent, Gianni Franchi, Christos-Savvas Bouganis
Abstract: Label smoothing (LS) is a popular regularisation method for training deep neural network classifiers due to its effectiveness in improving test accuracy and its simplicity in implementation. "Hard" one-hot labels are "smoothed" by uniformly distributing probability mass to other classes, reducing overfitting. In this work, we reveal that LS negatively affects selective classification (SC) - where the aim is to reject misclassifications using a model's predictive uncertainty. We first demonstrate empirically across a range of tasks and architectures that LS leads to a consistent degradation in SC. We then explain this by analysing logit-level gradients, showing that LS exacerbates overconfidence and underconfidence by regularising the max logit more when the probability of error is low, and less when the probability of error is high. This elucidates previously reported experimental results where strong classifiers underperform in SC. We then demonstrate the empirical effectiveness of logit normalisation for recovering lost SC performance caused by LS. Furthermore, based on our gradient analysis, we explain why such normalisation is effective. We will release our code shortly.
Authors: Qilong Wu, Varun Chandrasekaran
Abstract: Watermarking approaches are proposed to identify if text being circulated is human or large language model (LLM) generated. The state-of-the-art watermarking strategy of Kirchenbauer et al. (2023a) biases the LLM to generate specific (``green'') tokens. However, determining the robustness of this watermarking method is an open problem. Existing attack methods fail to evade detection for longer text segments. We overcome this limitation, and propose {\em Self Color Testing-based Substitution (SCTS)}, the first ``color-aware'' attack. SCTS obtains color information by strategically prompting the watermarked LLM and comparing output tokens frequencies. It uses this information to determine token colors, and substitutes green tokens with non-green ones. In our experiments, SCTS successfully evades watermark detection using fewer number of edits than related work. Additionally, we show both theoretically and empirically that SCTS can remove the watermark for arbitrarily long watermarked text.
Authors: Edrina Gashi, Jiankang Deng, Ismail Elezi
Abstract: We conduct a comprehensive evaluation of state-of-the-art deep active learning methods. Surprisingly, under general settings, no single-model method decisively outperforms entropy-based active learning, and some even fall short of random sampling. We delve into overlooked aspects like starting budget, budget step, and pretraining's impact, revealing their significance in achieving superior results. Additionally, we extend our evaluation to other tasks, exploring the active learning effectiveness in combination with semi-supervised learning, and object detection. Our experiments provide valuable insights and concrete recommendations for future active learning studies. By uncovering the limitations of current methods and understanding the impact of different experimental settings, we aim to inspire more efficient training of deep learning models in real-world scenarios with limited annotation budgets. This work contributes to advancing active learning's efficacy in deep learning and empowers researchers to make informed decisions when applying active learning to their tasks.
Authors: Janek Gr\"ohl, Kylie Yeung, Kevin Gu, Thomas R. Else, Monika Golinska, Ellie V. Bunce, Lina Hacker, Sarah E. Bohndiek
Abstract: Significance: Photoacoustic imaging (PAI) promises to measure spatially-resolved blood oxygen saturation, but suffers from a lack of accurate and robust spectral unmixing methods to deliver on this promise. Accurate blood oxygenation estimation could have important clinical applications, from cancer detection to quantifying inflammation. Aim: This study addresses the inflexibility of existing data-driven methods for estimating blood oxygenation in PAI by introducing a recurrent neural network architecture. Approach: We created 25 simulated training dataset variations to assess neural network performance. We used a long short-term memory network to implement a wavelength-flexible network architecture and proposed the Jensen-Shannon divergence to predict the most suitable training dataset. Results: The network architecture can handle arbitrary input wavelengths and outperforms linear unmixing and the previously proposed learned spectral decolouring method. Small changes in the training data significantly affect the accuracy of our method, but we find that the Jensen-Shannon divergence correlates with the estimation error and is thus suitable for predicting the most appropriate training datasets for any given application. Conclusions: A flexible data-driven network architecture combined with the Jensen-Shannon Divergence to predict the best training data set provides a promising direction that might enable robust data-driven photoacoustic oximetry for clinical use cases.
Authors: Yoshihide Sawada, Ryuji Saiin, Kazuma Suetake
Abstract: Recently, the number of parameters in DNNs has explosively increased, as exemplified by LLMs (Large Language Models), making inference on small-scale computers more difficult. Model compression technology is, therefore, essential for integration into products. In this paper, we propose a method of quantization-aware training. We introduce a novel normalization (Layer-Batch Normalization) that is independent of the mini-batch size and does not require any additional computation cost during inference. Then, we quantize the weights by the scaled round-clip function with the weight standardization. We also quantize activation functions using the same function and apply surrogate gradients to train the model with both quantized weights and the quantized activation functions. We call this method Magic for the age of Quantised DNNs (MaQD). Experimental results show that our quantization method can be achieved with minimal accuracy degradation.
Authors: Paul San Sebastian, Mikel Ca\~nizo, Rom\'an Or\'us
Abstract: Variational quantum algorithms are gaining attention as an early application of Noisy Intermediate-Scale Quantum (NISQ) devices. One of the main problems of variational methods lies in the phenomenon of Barren Plateaus, present in the optimization of variational parameters. Adding geometric inductive bias to the quantum models has been proposed as a potential solution to mitigate this problem, leading to a new field called Geometric Quantum Machine Learning. In this work, an equivariant architecture for variational quantum classifiers is introduced to create a label-invariant model for image classification with $C_4$ rotational label symmetry. The equivariant circuit is benchmarked against two different architectures, and it is experimentally observed that the geometric approach boosts the model's performance. Finally, a classical equivariant convolution operation is proposed to extend the quantum model for the processing of larger images, employing the resources available in NISQ devices.
Authors: Abhinau K. Venkataramanan, Alan C. Bovik
Abstract: High Dynamic Range (HDR) videos are able to represent wider ranges of contrasts and colors than Standard Dynamic Range (SDR) videos, giving more vivid experiences. Due to this, HDR videos are expected to grow into the dominant video modality of the future. However, HDR videos are incompatible with existing SDR displays, which form the majority of affordable consumer displays on the market. Because of this, HDR videos must be processed by tone-mapping them to reduced bit-depths to service a broad swath of SDR-limited video consumers. Here, we analyze the impact of tone-mapping operators on the visual quality of streaming HDR videos. To this end, we built the first large-scale subjectively annotated open-source database of compressed tone-mapped HDR videos, containing 15,000 tone-mapped sequences derived from 40 unique HDR source contents. The videos in the database were labeled with more than 750,000 subjective quality annotations, collected from more than 1,600 unique human observers. We demonstrate the usefulness of the new subjective database by benchmarking objective models of visual quality on it. We envision that the new LIVE Tone-Mapped HDR (LIVE-TMHDR) database will enable significant progress on HDR video tone mapping and quality assessment in the future. To this end, we make the database freely available to the community at https://live.ece.utexas.edu/research/LIVE_TMHDR/index.html
URLs: https://live.ece.utexas.edu/research/LIVE_TMHDR/index.html
Authors: Victor Iba\~nez, Przemyslaw Szostak, Quincy Wong, Konstanty Korski, Samaneh Abbasi-Sureshjani, Alvaro Gomariz
Abstract: Graph convolutional networks (GCNs) have emerged as a powerful alternative to multiple instance learning with convolutional neural networks in digital pathology, offering superior handling of structural information across various spatial ranges - a crucial aspect of learning from gigapixel H&E-stained whole slide images (WSI). However, graph message-passing algorithms often suffer from oversmoothing when aggregating a large neighborhood. Hence, effective modeling of multi-range interactions relies on the careful construction of the graph. Our proposed multi-scale GCN (MS-GCN) tackles this issue by leveraging information across multiple magnification levels in WSIs. MS-GCN enables the simultaneous modeling of long-range structural dependencies at lower magnifications and high-resolution cellular details at higher magnifications, akin to analysis pipelines usually conducted by pathologists. The architecture's unique configuration allows for the concurrent modeling of structural patterns at lower magnifications and detailed cellular features at higher ones, while also quantifying the contribution of each magnification level to the prediction. Through testing on different datasets, MS-GCN demonstrates superior performance over existing single-magnification GCN methods. The enhancement in performance and interpretability afforded by our method holds promise for advancing computational pathology models, especially in tasks requiring extensive spatial context.
Authors: Vladyslav Zalevskyi, Thomas Sanchez, Margaux Roulet, Jordina Aviles Verddera, Jana Hutter, Hamza Kebiri, Meritxell Bach Cuadra
Abstract: Segmentation of fetal brain tissue from magnetic resonance imaging (MRI) plays a crucial role in the study of in utero neurodevelopment. However, automated tools face substantial domain shift challenges as they must be robust to highly heterogeneous clinical data, often limited in numbers and lacking annotations. Indeed, high variability of the fetal brain morphology, MRI acquisition parameters, and superresolution reconstruction (SR) algorithms adversely affect the model's performance when evaluated out-of-domain. In this work, we introduce FetalSynthSeg, a domain randomization method to segment fetal brain MRI, inspired by SynthSeg. Our results show that models trained solely on synthetic data outperform models trained on real data in out-ofdomain settings, validated on a 120-subject cross-domain dataset. Furthermore, we extend our evaluation to 40 subjects acquired using lowfield (0.55T) MRI and reconstructed with novel SR models, showcasing robustness across different magnetic field strengths and SR algorithms. Leveraging a generative synthetic approach, we tackle the domain shift problem in fetal brain MRI and offer compelling prospects for applications in fields with limited and highly heterogeneous data.
Authors: Adrian R\"ofer, Nick Heppert, Abdallah Ayman, Eugenio Chisari, Abhinav Valada
Abstract: Humans seemingly incorporate potential touch signals in their perception. Our goal is to equip robots with a similar capability, which we term \ourmodel. \ourmodel aims to predict the expected touch signal based on a visual patch representing the touched area. We frame this problem as the task of learning a low-dimensional visual-tactile embedding, wherein we encode a depth patch from which we decode the tactile signal. To accomplish this task, we employ ReSkin, an inexpensive and replaceable magnetic-based tactile sensor. Using ReSkin, we collect and train PseudoTouch on a dataset comprising aligned tactile and visual data pairs obtained through random touching of eight basic geometric shapes. We demonstrate the efficacy of PseudoTouch through its application to two downstream tasks: object recognition and grasp stability prediction. In the object recognition task, we evaluate the learned embedding's performance on a set of five basic geometric shapes and five household objects. Using PseudoTouch, we achieve an object recognition accuracy 84% after just ten touches, surpassing a proprioception baseline. For the grasp stability task, we use ACRONYM labels to train and evaluate a grasp success predictor using PseudoTouch's predictions derived from virtual depth information. Our approach yields an impressive 32% absolute improvement in accuracy compared to the baseline relying on partial point cloud data. We make the data, code, and trained models publicly available at http://pseudotouch.cs.uni-freiburg.de.
Authors: V\'ictor Toscano-Dur\'an, Javier Perera-Lago, Eduardo Paluzo-Hidalgo, Roc\'io Gonzalez-Diaz, Miguel \'Angel Gutierrez-Naranjo, Matteo Rucco
Abstract: In recent years, Deep Learning has gained popularity for its ability to solve complex classification tasks, increasingly delivering better results thanks to the development of more accurate models, the availability of huge volumes of data and the improved computational capabilities of modern computers. However, these improvements in performance also bring efficiency problems, related to the storage of datasets and models, and to the waste of energy and time involved in both the training and inference processes. In this context, data reduction can help reduce energy consumption when training a deep learning model. In this paper, we present up to eight different methods to reduce the size of a tabular training dataset, and we develop a Python package to apply them. We also introduce a representativeness metric based on topology to measure how similar are the reduced datasets and the full training dataset. Additionally, we develop a methodology to apply these data reduction methods to image datasets for object detection tasks. Finally, we experimentally compare how these data reduction methods affect the representativeness of the reduced dataset, the energy consumption and the predictive performance of the model.
Authors: Yukuan Jia, Jiawen Zhang, Shimeng Lu, Baokang Fan, Ruiqing Mao, Sheng Zhou, Zhisheng Niu
Abstract: Environmental perception in Automated Valet Parking (AVP) has been a challenging task due to severe occlusions in parking garages. Although Collaborative Perception (CP) can be applied to broaden the field of view of connected vehicles, the limited bandwidth of vehicular communications restricts its application. In this work, we propose a BEV feature-based CP network architecture for infrastructure-assisted AVP systems. The model takes the roadside camera and LiDAR as optional inputs and adaptively fuses them with onboard sensors in a unified BEV representation. Autoencoder and downsampling are applied for channel-wise and spatial-wise dimension reduction, while sparsification and quantization further compress the feature map with little loss in data precision. Combining these techniques, the size of a BEV feature map is effectively compressed to fit in the feasible data rate of the NR-V2X network. With the synthetic AVP dataset, we observe that CP can effectively increase perception performance, especially for pedestrians. Moreover, the advantage of infrastructure-assisted CP is demonstrated in two typical safety-critical scenarios in the AVP setting, increasing the maximum safe cruising speed by up to 3m/s in both scenarios.
Authors: Gijs Bellaard, Sei Sakata, Bart M. N. Smets, Remco Duits
Abstract: PDE-based Group Convolutional Neural Networks (PDE-G-CNNs) utilize solvers of geometrically meaningful evolution PDEs as substitutes for the conventional components in G-CNNs. PDE-G-CNNs offer several key benefits all at once: fewer parameters, inherent equivariance, better performance, data efficiency, and geometric interpretability. In this article we focus on Euclidean equivariant PDE-G-CNNs where the feature maps are two dimensional throughout. We call this variant of the framework a PDE-CNN. We list several practically desirable axioms and derive from these which PDEs should be used in a PDE-CNN. Here our approach to geometric learning via PDEs is inspired by the axioms of classical linear and morphological scale-space theory, which we generalize by introducing semifield-valued signals. Furthermore, we experimentally confirm for small networks that PDE-CNNs offer fewer parameters, better performance, and data efficiency in comparison to CNNs. We also investigate what effect the use of different semifields has on the performance of the models.
Authors: Nick Heppert, Max Argus, Tim Welschehold, Thomas Brox, Abhinav Valada
Abstract: Teaching robots new skills quickly and conveniently is crucial for the broader adoption of robotic systems. In this work, we address the problem of one-shot imitation from a single human demonstration, given by an RGB-D video recording through a two-stage process. In the first stage which is offline, we extract the trajectory of the demonstration. This entails segmenting manipulated objects and determining their relative motion in relation to secondary objects such as containers. Subsequently, in the live online trajectory generation stage, we first \mbox{re-detect} all objects, then we warp the demonstration trajectory to the current scene, and finally, we trace the trajectory with the robot. To complete these steps, our method makes leverages several ancillary models, including those for segmentation, relative object pose estimation, and grasp prediction. We systematically evaluate different combinations of correspondence and re-detection methods to validate our design decision across a diverse range of tasks. Specifically, we collect demonstrations of ten different tasks including pick-and-place tasks as well as articulated object manipulation. Finally, we perform extensive evaluations on a real robot system to demonstrate the effectiveness and utility of our approach in real-world scenarios. We make the code publicly available at http://ditto.cs.uni-freiburg.de.
Authors: Abhinav Sharma, Bojing Liu, Mattias Rantalainen
Abstract: Deep learning enables the modelling of high-resolution histopathology whole-slide images (WSI). Weakly supervised learning of tile-level data is typically applied for tasks where labels only exist on the patient or WSI level (e.g. patient outcomes or histological grading). In this context, there is a need for improved spatial interpretability of predictions from such models. We propose a novel method, Wsi rEgion sElection aPproach (WEEP), for model interpretation. It provides a principled yet straightforward way to establish the spatial area of WSI required for assigning a particular prediction label. We demonstrate WEEP on a binary classification task in the area of breast cancer computational pathology. WEEP is easy to implement, is directly connected to the model-based decision process, and offers information relevant to both research and diagnostic applications.
Authors: Patryk Rygiel, Dieuwertje Alblas, Christoph Brune, Kak Khee Yeung, Jelmer M. Wolterink
Abstract: Personalized 3D vascular models can aid in a range of diagnostic, prognostic, and treatment-planning tasks relevant to cardiovascular disease management. Deep learning provides a means to automatically obtain such models. Ideally, a user should have control over the exact region of interest (ROI) to be included in a vascular model, and the model should be watertight and highly accurate. To this end, we propose a combination of a global controller leveraging voxel mask segmentations to provide boundary conditions for vessels of interest to a local, iterative vessel segmentation model. We introduce the preservation of scale- and rotational symmetries in the local segmentation model, leading to generalisation to vessels of unseen sizes and orientations. Combined with the global controller, this enables flexible 3D vascular model building, without additional retraining. We demonstrate the potential of our method on a dataset containing abdominal aortic aneurysms (AAAs). Our method performs on par with a state-of-the-art segmentation model in the segmentation of AAAs, iliac arteries and renal arteries, while providing a watertight, smooth surface segmentation. Moreover, we demonstrate that by adapting the global controller, we can easily extend vessel sections in the 3D model.
Authors: Yuxin Zhang, Cl\'ement Huneau, J\'er\^ome Idier, Diana Mateus
Abstract: Despite today's prevalence of ultrasound imaging in medicine, ultrasound signal-to-noise ratio is still affected by several sources of noise and artefacts. Moreover, enhancing ultrasound image quality involves balancing concurrent factors like contrast, resolution, and speckle preservation. Recently, there has been progress in both model-based and learning-based approaches addressing the problem of ultrasound image reconstruction. Bringing the best from both worlds, we propose a hybrid reconstruction method combining an ultrasound linear direct model with a learning-based prior coming from a generative Denoising Diffusion model. More specifically, we rely on the unsupervised fine-tuning of a pre-trained Denoising Diffusion Restoration Model (DDRM). Given the nature of multiplicative noise inherent to ultrasound, this paper proposes an empirical model to characterize the stochasticity of diffusion reconstruction of ultrasound images, and shows the interest of its variance as an echogenicity map estimator. We conduct experiments on synthetic, in-vitro, and in-vivo data, demonstrating the efficacy of our variance imaging approach in achieving high-quality image reconstructions from single plane-wave acquisitions and in comparison to state-of-the-art methods.
Authors: Xi Zhao, Wei Feng, Zheng Zhang, Jingjing Lv, Xin Zhu, Zhangang Lin, Jinghe Hu, Jingping Shao
Abstract: Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the expansion process is difficult to achieve a favorable accuracy-speed trade-off. In this paper, we propose a Context-aware and Boundary-guided Network (CBN) to tackle these problems. In CBN, a basic text detector is firstly used to predict initial segmentation results. Then, we propose a context-aware module to enhance text kernel feature representations, which considers both global and local contexts. Finally, we introduce a boundary-guided module to expand enhanced text kernels adaptively with only the pixels on the contours, which not only obtains accurate text boundaries but also keeps high speed, especially on high-resolution output maps. In particular, with a lightweight backbone, the basic detector equipped with our proposed CBN achieves state-of-the-art results on several popular benchmarks, and our proposed CBN can be plugged into several segmentation-based methods. Code is available at https://github.com/XiiZhao/cbn.pytorch.
Authors: Xiyang Wang, Chunyun Fu, Jiawei He, Mingguang Huang, Ting Meng, Siyu Zhang, Hangning Zhou, Ziyao Xu, Chi Zhang
Abstract: In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance. In this paper, a new end-to-end multi-object tracking framework is proposed, which integrates object detection and multi-object tracking into a single model. The proposed tracking framework eliminates the complex data association process in the classical TBD paradigm, and requires no additional training. Secondly, the regression confidence of historical trajectories is investigated, and the possible states of a trajectory (weak object or strong object) in the current frame are predicted. Then, a confidence fusion module is designed to guide non-maximum suppression for trajectories and detections to achieve ordered and robust tracking. Thirdly, by integrating historical trajectory features, the regression performance of the detector is enhanced, which better reflects the occlusion and disappearance patterns of objects in real world. Lastly, extensive experiments are conducted on the commonly used KITTI and Waymo datasets. The results show that the proposed framework can achieve robust tracking by using only a 2D detector and a 3D detector, and it is proven more accurate than many of the state-of-the-art TBD-based multi-modal tracking methods. The source codes of the proposed method are available at https://github.com/wangxiyang2022/YONTD-MOT.
Authors: Kunping Huang, Sen Zhang, Jing Zhang, Dacheng Tao
Abstract: In recent decades, visual simultaneous localization and mapping (vSLAM) has gained significant interest in both academia and industry. It estimates camera motion and reconstructs the environment concurrently using visual sensors on a moving robot. However, conventional cameras are limited by hardware, including motion blur and low dynamic range, which can negatively impact performance in challenging scenarios like high-speed motion and high dynamic range illumination. Recent studies have demonstrated that event cameras, a new type of bio-inspired visual sensor, offer advantages such as high temporal resolution, dynamic range, low power consumption, and low latency. This paper presents a timely and comprehensive review of event-based vSLAM algorithms that exploit the benefits of asynchronous and irregular event streams for localization and mapping tasks. The review covers the working principle of event cameras and various event representations for preprocessing event data. It also categorizes event-based vSLAM methods into four main categories: feature-based, direct, motion-compensation, and deep learning methods, with detailed discussions and practical guidance for each approach. Furthermore, the paper evaluates the state-of-the-art methods on various benchmarks, highlighting current challenges and future opportunities in this emerging research area. A public repository will be maintained to keep track of the rapid developments in this field at {\url{https://github.com/kun150kun/ESLAM-survey}}.
Authors: Bolin Lai, Fiona Ryan, Wenqi Jia, Miao Liu, James M. Rehg
Abstract: Egocentric gaze anticipation serves as a key building block for the emerging capability of Augmented Reality. Notably, gaze behavior is driven by both visual cues and audio signals during daily activities. Motivated by this observation, we introduce the first model that leverages both the video and audio modalities for egocentric gaze anticipation. Specifically, we propose a Contrastive Spatial-Temporal Separable (CSTS) fusion approach that adopts two modules to separately capture audio-visual correlations in spatial and temporal dimensions, and applies a contrastive loss on the re-weighted audio-visual features from fusion modules for representation learning. We conduct extensive ablation studies and thorough analysis using two egocentric video datasets: Ego4D and Aria, to validate our model design. We demonstrate the audio improves the performance by +2.5% and +2.4% on the two datasets. Our model also outperforms the prior state-of-the-art methods by at least +1.9% and +1.6%. Moreover, we provide visualizations to show the gaze anticipation results and provide additional insights into audio-visual representation learning. The code and data split are available on our website (https://bolinlai.github.io/CSTS-EgoGazeAnticipation/).
URLs: https://bolinlai.github.io/CSTS-EgoGazeAnticipation/).
Authors: Hang Xu, Xinyuan Liu, Haonan Xu, Yike Ma, Zunjie Zhu, Chenggang Yan, Feng Dai
Abstract: Oriented object detection has been developed rapidly in the past few years, where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when objects rotate, but severe mutation in angular prediction is sometimes observed when objects rotate near the boundary angle, which is well-known boundary discontinuity problem. The problem has been long believed to be caused by the sharp loss increase at the angular boundary, and widely used joint-optim IoU-like methods deal with this problem by loss-smoothing. However, we experimentally find that even state-of-the-art IoU-like methods actually fail to solve the problem. On further analysis, we find that the key to solution lies in encoding mode of the smoothing function rather than in joint or independent optimization. In existing IoU-like methods, the model essentially attempts to fit the angular relationship between box and object, where the break point at angular boundary makes the predictions highly unstable.To deal with this issue, we propose a dual-optimization paradigm for angles. We decouple reversibility and joint-optim from single smoothing function into two distinct entities, which for the first time achieves the objectives of both correcting angular boundary and blending angle with other parameters.Extensive experiments on multiple datasets show that boundary discontinuity problem is well-addressed. Moreover, typical IoU-like methods are improved to the same level without obvious performance gap. The code is available at https://github.com/hangxu-cv/cvpr24acm.
Authors: Zerun Wang, Ling Xiao, Liuyu Xiang, Zhaotian Weng, Toshihiko Yamasaki
Abstract: Open-set semi-supervised object detection (OSSOD) task leverages practical open-set unlabeled datasets that comprise both in-distribution (ID) and out-of-distribution (OOD) instances for conducting semi-supervised object detection (SSOD). The main challenge in OSSOD is distinguishing and filtering the OOD instances (i.e., outliers) during pseudo-labeling since OODs will affect the performance. The only OSSOD work employs an additional offline OOD detection network trained solely with labeled data to solve this problem. However, the limited labeled data restricts the potential for improvement. Meanwhile, the offline strategy results in low efficiency. To alleviate these issues, this paper proposes an end-to-end online OSSOD framework that improves performance and efficiency: 1) We propose a semi-supervised outlier filtering method that more effectively filters the OOD instances using both labeled and unlabeled data. 2) We propose a threshold-free Dual Competing OOD head that further improves the performance by suppressing the error accumulation during semi-supervised outlier filtering. 3) Our proposed method is an online end-to-end trainable OSSOD framework. Experimental results show that our method achieves state-of-the-art performance on several OSSOD benchmarks compared to existing methods. Moreover, additional experiments show that our method is more efficient and can be easily applied to different SSOD frameworks to boost their performance.
Authors: Binzhu Xie, Sicheng Zhang, Zitang Zhou, Bo Li, Yuanhan Zhang, Jack Hessel, Jingkang Yang, Ziwei Liu
Abstract: Surprising videos, such as funny clips, creative performances, or visual illusions, attract significant attention. Enjoyment of these videos is not simply a response to visual stimuli; rather, it hinges on the human capacity to understand (and appreciate) commonsense violations depicted in these videos. We introduce FunQA, a challenging video question-answering (QA) dataset specifically designed to evaluate and enhance the depth of video reasoning based on counter-intuitive and fun videos. Unlike most video QA benchmarks which focus on less surprising contexts, e.g., cooking or instructional videos, FunQA covers three previously unexplored types of surprising videos: 1) HumorQA, 2) CreativeQA, and 3) MagicQA. For each subset, we establish rigorous QA tasks designed to assess the model's capability in counter-intuitive timestamp localization, detailed video description, and reasoning around counter-intuitiveness. We also pose higher-level tasks, such as attributing a fitting and vivid title to the video and scoring the video creativity. In total, the FunQA benchmark consists of 312K free-text QA pairs derived from 4.3K video clips, spanning a total of 24 video hours. Moreover, we propose FunMentor, an agent designed for Vision-Language Models (VLMs) that uses multi-turn dialogues to enhance models' understanding of counter-intuitiveness. Extensive experiments with existing VLMs demonstrate the effectiveness of FunMentor and reveal significant performance gaps for the FunQA videos across spatial-temporal reasoning, visual-centered reasoning, and free-text generation.
Authors: Tserendorj Adiya, Jae Shin Yoon, Jungeun Lee, Sanghun Kim, Hwasup Lim
Abstract: We introduce a method to generate temporally coherent human animation from a single image, a video, or a random noise. This problem has been formulated as modeling of an auto-regressive generation, i.e., to regress past frames to decode future frames. However, such unidirectional generation is highly prone to motion drifting over time, generating unrealistic human animation with significant artifacts such as appearance distortion. We claim that bidirectional temporal modeling enforces temporal coherence on a generative network by largely suppressing the motion ambiguity of human appearance. To prove our claim, we design a novel human animation framework using a denoising diffusion model: a neural network learns to generate the image of a person by denoising temporal Gaussian noises whose intermediate results are cross-conditioned bidirectionally between consecutive frames. In the experiments, our method demonstrates strong performance compared to existing unidirectional approaches with realistic temporal coherence.
Authors: Jiaqi Yang, Yucong Chen, Xiangting Meng, Chenxin Yan, Min Li, Ran Cheng, Lige Liu, Tao Sun, Laurent Kneip
Abstract: Recently there has been a growing interest in category-level object pose and size estimation, and prevailing methods commonly rely on single view RGB-D images. However, one disadvantage of such methods is that they require accurate depth maps which cannot be produced by consumer-grade sensors. Furthermore, many practical real-world situations involve a moving camera that continuously observes its surroundings, and the temporal information of the input video streams is simply overlooked by single-view methods. We propose a novel solution that makes use of RGB video streams. Our framework consists of three modules: a scale-aware monocular dense SLAM solution, a lightweight object pose predictor, and an object-level pose graph optimizer. The SLAM module utilizes a video stream and additional scale-sensitive readings to estimate camera poses and metric depth. The object pose predictor then generates canonical object representations from RGB images. The object pose is estimated through geometric registration of these canonical object representations with estimated object depth points. All per-view estimates finally undergo optimization within a pose graph, culminating in the output of robust and accurate canonical object poses. Our experimental results demonstrate that when utilizing public dataset sequences with high-quality depth information, the proposed method exhibits comparable performance to state-of-the-art RGB-D methods. We also collect and evaluate on new datasets containing depth maps of varying quality to further quantitatively benchmark the proposed method alongside previous RGB-D based methods. We demonstrate a significant advantage in scenarios where depth input is absent or the quality of depth sensing is limited.
Authors: Jiawei Liu, Qiang Wang, Huijie Fan, Yinong Wang, Yandong Tang, Liangqiong Qu
Abstract: We propose residual denoising diffusion models (RDDM), a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion. This dual diffusion framework expands the denoising-based diffusion models, initially uninterpretable for image restoration, into a unified and interpretable model for both image generation and restoration by introducing residuals. Specifically, our residual diffusion represents directional diffusion from the target image to the degraded input image and explicitly guides the reverse generation process for image restoration, while noise diffusion represents random perturbations in the diffusion process. The residual prioritizes certainty, while the noise emphasizes diversity, enabling RDDM to effectively unify tasks with varying certainty or diversity requirements, such as image generation and restoration. We demonstrate that our sampling process is consistent with that of DDPM and DDIM through coefficient transformation, and propose a partially path-independent generation process to better understand the reverse process. Notably, our RDDM enables a generic UNet, trained with only an L1 loss and a batch size of 1, to compete with state-of-the-art image restoration methods. We provide code and pre-trained models to encourage further exploration, application, and development of our innovative framework (https://github.com/nachifur/RDDM).
Authors: Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Chao Liao, Jianchao Tan, Quzhe Huang, Bin Chen, Chenyi Lei, An Liu, Chengru Song, Xiaoqiang Lei, Di Zhang, Wenwu Ou, Kun Gai, Yadong Mu
Abstract: Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. However, the prevailing approaches primarily regard the visual input as a prompt and focus exclusively on optimizing the text generation process conditioned upon vision content by a frozen LLM. Such an inequitable treatment of vision and language heavily constrains the model's potential. In this paper, we break through this limitation by representing both vision and language in a unified form. Specifically, we introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language that LLM can read. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. Coped with this tokenizer, the presented foundation model called LaVIT can handle both image and text indiscriminately under the same generative learning paradigm. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously. Extensive experiments further showcase that it outperforms the existing models by a large margin on massive vision-language tasks. Our code and models are available at https://github.com/jy0205/LaVIT.
Authors: Yu Gao, Lutong Su, Hao Liang, Yufeng Yue, Yi Yang, Mengyin Fu
Abstract: Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic parameters and frequent pose changes. Most previous NeRF-based methods assume a unique camera and rarely consider multi-camera scenarios. Besides, some NeRF methods that can optimize intrinsic and extrinsic parameters still remain susceptible to suboptimal solutions when these parameters are poor initialized. In this paper, we propose MC-NeRF, a method that enables joint optimization of both intrinsic and extrinsic parameters alongside NeRF. The method also supports each image corresponding to independent camera parameters. First, we tackle coupling issue and the degenerate case that arise from the joint optimization between intrinsic and extrinsic parameters. Second, based on the proposed solutions, we introduce an efficient calibration image acquisition scheme for multi-camera systems, including the design of calibration object. Finally, we present an end-to-end network with training sequence that enables the estimation of intrinsic and extrinsic parameters, along with the rendering network. Furthermore, recognizing that most existing datasets are designed for a unique camera, we construct a real multi-camera image acquisition system and create a corresponding new dataset, which includes both simulated data and real-world captured images. Experiments confirm the effectiveness of our method when each image corresponds to different camera parameters. Specifically, we use multi-cameras, each with different intrinsic and extrinsic parameters in real-world system, to achieve 3D scene representation without providing initial poses.
Authors: Minh-Tuan Tran, Trung Le, Xuan-May Le, Mehrtash Harandi, Quan Hung Tran, Dinh Phung
Abstract: Data-Free Knowledge Distillation (DFKD) has made significant recent strides by transferring knowledge from a teacher neural network to a student neural network without accessing the original data. Nonetheless, existing approaches encounter a significant challenge when attempting to generate samples from random noise inputs, which inherently lack meaningful information. Consequently, these models struggle to effectively map this noise to the ground-truth sample distribution, resulting in prolonging training times and low-quality outputs. In this paper, we propose a novel Noisy Layer Generation method (NAYER) which relocates the random source from the input to a noisy layer and utilizes the meaningful constant label-text embedding (LTE) as the input. LTE is generated by using the language model once, and then it is stored in memory for all subsequent training processes. The significance of LTE lies in its ability to contain substantial meaningful inter-class information, enabling the generation of high-quality samples with only a few training steps. Simultaneously, the noisy layer plays a key role in addressing the issue of diversity in sample generation by preventing the model from overemphasizing the constrained label information. By reinitializing the noisy layer in each iteration, we aim to facilitate the generation of diverse samples while still retaining the method's efficiency, thanks to the ease of learning provided by LTE. Experiments carried out on multiple datasets demonstrate that our NAYER not only outperforms the state-of-the-art methods but also achieves speeds 5 to 15 times faster than previous approaches. The code is available at https://github.com/tmtuan1307/nayer.
Authors: Javier P\'erez de Frutos, Ragnhild Holden Helland, Shreya Desai, Line Cathrine Nymoen, Thomas Lang{\o}, Theodor Remman, Abhijit Sen
Abstract: Background: Dental caries diagnosis requires the manual inspection of diagnostic bitewing images of the patient, followed by a visual inspection and probing of the identified dental pieces with potential lesions. Yet the use of artificial intelligence, and in particular deep-learning, has the potential to aid in the diagnosis by providing a quick and informative analysis of the bitewing images. Methods: A dataset of 13,887 bitewings from the HUNT4 Oral Health Study were annotated individually by six different experts, and used to train three different object detection deep-learning architectures: RetinaNet (ResNet50), YOLOv5 (M size), and EfficientDet (D0 and D1 sizes). A consensus dataset of 197 images, annotated jointly by the same six dentist, was used for evaluation. A five-fold cross validation scheme was used to evaluate the performance of the AI models. Results: he trained models show an increase in average precision and F1-score, and decrease of false negative rate, with respect to the dental clinicians. When compared against the dental clinicians, the YOLOv5 model shows the largest improvement, reporting 0.647 mean average precision, 0.548 mean F1-score, and 0.149 mean false negative rate. Whereas the best annotators on each of these metrics reported 0.299, 0.495, and 0.164 respectively. Conclusion: Deep-learning models have shown the potential to assist dental professionals in the diagnosis of caries. Yet, the task remains challenging due to the artifacts natural to the bitewing images.
Authors: Vincent Leroy, Jerome Revaud, Thomas Lucas, Philippe Weinzaepfel
Abstract: Transformers have become the standard in state-of-the-art vision architectures, achieving impressive performance on both image-level and dense pixelwise tasks. However, training vision transformers for high-resolution pixelwise tasks has a prohibitive cost. Typical solutions boil down to hierarchical architectures, fast and approximate attention, or training on low-resolution crops. This latter solution does not constrain architectural choices, but it leads to a clear performance drop when testing at resolutions significantly higher than that used for training, thus requiring ad-hoc and slow post-processing schemes. In this paper, we propose a novel strategy for efficient training and inference of high-resolution vision transformers. The key principle is to mask out most of the high-resolution inputs during training, keeping only N random windows. This allows the model to learn local interactions between tokens inside each window, and global interactions between tokens from different windows. As a result, the model can directly process the high-resolution input at test time without any special trick. We show that this strategy is effective when using relative positional embedding such as rotary embeddings. It is 4 times faster to train than a full-resolution network, and it is straightforward to use at test time compared to existing approaches. We apply this strategy to three dense prediction tasks with high-resolution data. First, we show on the task of semantic segmentation that a simple setting with 2 windows performs best, hence the name of our method: Win-Win. Second, we confirm this result on the task of monocular depth prediction. Third, we further extend it to the binocular task of optical flow, reaching state-of-the-art performance on the Spring benchmark that contains Full-HD images with an order of magnitude faster inference than the best competitor.
Authors: Romain Thoreau, Laurent Risser, V\'eronique Achard, B\'eatrice Berthelot, Xavier Briottet
Abstract: Airborne hyperspectral images can be used to map the land cover in large urban areas, thanks to their very high spatial and spectral resolutions on a wide spectral domain. While the spectral dimension of hyperspectral images is highly informative of the chemical composition of the land surface, the use of state-of-the-art machine learning algorithms to map the land cover has been dramatically limited by the availability of training data. To cope with the scarcity of annotations, semi-supervised and self-supervised techniques have lately raised a lot of interest in the community. Yet, the publicly available hyperspectral data sets commonly used to benchmark machine learning models are not totally suited to evaluate their generalization performances due to one or several of the following properties: a limited geographical coverage (which does not reflect the spectral diversity in metropolitan areas), a small number of land cover classes and a lack of appropriate standard train / test splits for semi-supervised and self-supervised learning. Therefore, we release in this paper the Toulouse Hyperspectral Data Set that stands out from other data sets in the above-mentioned respects in order to meet key issues in spectral representation learning and classification over large-scale hyperspectral images with very few labeled pixels. Besides, we discuss and experiment self-supervised techniques for spectral representation learning, including the Masked Autoencoder, and establish a baseline for pixel-wise classification achieving 85% overall accuracy and 77% F1 score. The Toulouse Hyperspectral Data Set and our code are publicly available at https://www.toulouse-hyperspectral-data-set.com and https://www.github.com/Romain3Ch216/tlse-experiments, respectively.
URLs: https://www.toulouse-hyperspectral-data-set.com, https://www.github.com/Romain3Ch216/tlse-experiments,
Authors: Yamei Chen, Yan Di, Guangyao Zhai, Fabian Manhardt, Chenyangguang Zhang, Ruida Zhang, Federico Tombari, Nassir Navab, Benjamin Busam
Abstract: Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this variation. To address this issue, we present SecondPose, a novel approach integrating object-specific geometric features with semantic category priors from DINOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object representation under SE(3) transformations, facilitating the mapping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive experiments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin.
Authors: Daichi Horita, Naoto Inoue, Kotaro Kikuchi, Kota Yamaguchi, Kiyoharu Aizawa
Abstract: Content-aware graphic layout generation aims to automatically arrange visual elements along with a given content, such as an e-commerce product image. In this paper, we argue that the current layout generation approaches suffer from the limited training data for the high-dimensional layout structure. We show that a simple retrieval augmentation can significantly improve the generation quality. Our model, which is named Retrieval-Augmented Layout Transformer (RALF), retrieves nearest neighbor layout examples based on an input image and feeds these results into an autoregressive generator. Our model can apply retrieval augmentation to various controllable generation tasks and yield high-quality layouts within a unified architecture. Our extensive experiments show that RALF successfully generates content-aware layouts in both constrained and unconstrained settings and significantly outperforms the baselines.
Authors: Bowen Fu, Gu Wang, Chenyangguang Zhang, Yan Di, Ziqin Huang, Zhiying Leng, Fabian Manhardt, Xiangyang Ji, Federico Tombari
Abstract: Reconstructing hand-held objects from a single RGB image is a challenging task in computer vision. In contrast to prior works that utilize deterministic modeling paradigms, we employ a point cloud denoising diffusion model to account for the probabilistic nature of this problem. In the core, we introduce centroid-fixed dual-stream conditional diffusion for monocular hand-held object reconstruction (D-SCo), tackling two predominant challenges. First, to avoid the object centroid from deviating, we utilize a novel hand-constrained centroid fixing paradigm, enhancing the stability of diffusion and reverse processes and the precision of feature projection. Second, we introduce a dual-stream denoiser to semantically and geometrically model hand-object interactions with a novel unified hand-object semantic embedding, enhancing the reconstruction performance of the hand-occluded region of the object. Experiments on the synthetic ObMan dataset and three real-world datasets HO3D, MOW and DexYCB demonstrate that our approach can surpass all other state-of-the-art methods. Codes will be released.
Authors: Yichen Bai, Zongbo Han, Changqing Zhang, Bing Cao, Xiaoheng Jiang, Qinghua Hu
Abstract: Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. However, they may still face limitations in effectively distinguishing between the most challenging OOD samples that are much like in-distribution (ID) data, i.e., \idlike samples. To this end, we propose a novel OOD detection framework that discovers \idlike outliers using CLIP \cite{DBLP:conf/icml/RadfordKHRGASAM21} from the vicinity space of the ID samples, thus helping to identify these most challenging OOD samples. Then a prompt learning framework is proposed that utilizes the identified \idlike outliers to further leverage the capabilities of CLIP for OOD detection. Benefiting from the powerful CLIP, we only need a small number of ID samples to learn the prompts of the model without exposing other auxiliary outlier datasets. By focusing on the most challenging \idlike OOD samples and elegantly exploiting the capabilities of CLIP, our method achieves superior few-shot learning performance on various real-world image datasets (e.g., in 4-shot OOD detection on the ImageNet-1k dataset, our method reduces the average FPR95 by 12.16\% and improves the average AUROC by 2.76\%, compared to state-of-the-art methods). Code is available at https://github.com/ycfate/ID-like.
Authors: Jiawang Bai, Kuofeng Gao, Shaobo Min, Shu-Tao Xia, Zhifeng Li, Wei Liu
Abstract: Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented backdoor. On downstream tasks, one victim model performs well on clean samples but predicts a specific target class whenever a specific trigger is present. For injecting a backdoor, existing attacks depend on a large amount of additional data to maliciously fine-tune the entire pre-trained CLIP model, which makes them inapplicable to data-limited scenarios. In this work, motivated by the recent success of learnable prompts, we address this problem by injecting a backdoor into the CLIP model in the prompt learning stage. Our method named BadCLIP is built on a novel and effective mechanism in backdoor attacks on CLIP, i.e., influencing both the image and text encoders with the trigger. It consists of a learnable trigger applied to images and a trigger-aware context generator, such that the trigger can change text features via trigger-aware prompts, resulting in a powerful and generalizable attack. Extensive experiments conducted on 11 datasets verify that the clean accuracy of BadCLIP is similar to those of advanced prompt learning methods and the attack success rate is higher than 99% in most cases. BadCLIP is also generalizable to unseen classes, and shows a strong generalization capability under cross-dataset and cross-domain settings.
Authors: Rohan Myer Krishnan, Zitian Tang, Zhiqiu Yu, Chen Sun
Abstract: Learning from videos is an emerging research area that enables robots to acquire skills from human demonstrations, such as procedural videos. To do this, video-language models must be able to obtain structured understandings, such as the temporal segmentation of a demonstration into sequences of actions and skills, and to generalize the understandings to novel domains. In pursuit of this goal, we introduce Spacewalk-18, a benchmark containing two tasks: (1) step recognition and (2) intra-video retrieval over a dataset of temporally segmented and labeled tasks in International Space Station spacewalk recordings. In tandem, the two tasks quantify a model's ability to make use of: (1) out-of-domain visual information; (2) a high temporal context window; and (3) multimodal (e.g. visual and speech) domains. This departs from existing benchmarks for procedural video understanding, which typically deal with short context lengths and can be solved with a single modality. Spacewalk-18, with its inherent multimodal and long-form complexity, exposes the high difficulty of task recognition and segmentation. We find that state-of-the-art methods perform poorly on our benchmark, but improvements can be obtained by incorporating information from longer-range temporal context across different modalities. Our experiments underscore the need to develop new approaches to these tasks. Data, model, and code will be released at https://brown-palm.github.io/Spacewalk-18/.
Authors: Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen
Abstract: Sampling from diffusion models can be treated as solving the corresponding ordinary differential equations (ODEs), with the aim of obtaining an accurate solution with as few number of function evaluations (NFE) as possible. Recently, various fast samplers utilizing higher-order ODE solvers have emerged and achieved better performance than the initial first-order one. However, these numerical methods inherently result in certain approximation errors, which significantly degrades sample quality with extremely small NFE (e.g., around 5). In contrast, based on the geometric observation that each sampling trajectory almost lies in a two-dimensional subspace embedded in the ambient space, we propose Approximate MEan-Direction Solver (AMED-Solver) that eliminates truncation errors by directly learning the mean direction for fast diffusion sampling. Besides, our method can be easily used as a plugin to further improve existing ODE-based samplers. Extensive experiments on image synthesis with the resolution ranging from 32 to 512 demonstrate the effectiveness of our method. With only 5 NFE, we achieve 6.61 FID on CIFAR-10, 10.74 FID on ImageNet 64$\times$64, and 13.20 FID on LSUN Bedroom. Our code is available at https://github.com/zju-pi/diff-sampler.
Authors: Yizhou Wang, Yixuan Wu, Shixiang Tang, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang
Abstract: Human-centric perception tasks, e.g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis. There is a recent surge to develop human-centric foundation models that can benefit a broad range of human-centric perception tasks. While many human-centric foundation models have achieved success, they did not explore 3D and vision-language tasks for human-centric and required task-specific finetuning. These limitations restrict their application to more downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing 2D vision, 3D vision, skeleton-based, and vision-language tasks without task-specific finetuning. The key to achieving this is condensing various task-specific heads into two general heads, one for discrete representations, e.g., languages, and the other for continuous representations, e.g., location coordinates. The outputs of two heads can be further stacked into four distinct input and output modalities. This uniform representation enables Hulk to treat diverse human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. Comprehensive evaluations of Hulk on 12 benchmarks covering 8 human-centric tasks demonstrate the superiority of our proposed method, achieving state-of-the-art performance in 11 benchmarks. The code is available on https://github.com/OpenGVLab/Hulk.
Authors: Weiwei Sun, Eduard Trulls, Yang-Che Tseng, Sneha Sambandam, Gopal Sharma, Andrea Tagliasacchi, Kwang Moo Yi
Abstract: Point clouds offer an attractive source of information to complement images in neural scene representations, especially when few images are available. Neural rendering methods based on point clouds do exist, but they do not perform well when the point cloud quality is low -- e.g., sparse or incomplete, which is often the case with real-world data. We overcome these problems with a simple representation that aggregates point clouds at multiple scale levels with sparse voxel grids at different resolutions. To deal with point cloud sparsity, we average across multiple scale levels -- but only among those that are valid, i.e., that have enough neighboring points in proximity to the ray of a pixel. To help model areas without points, we add a global voxel at the coarsest scale, thus unifying ``classical'' and point-based NeRF formulations. We validate our method on the NeRF Synthetic, ScanNet, and KITTI-360 datasets, outperforming the state of the art, with a significant gap compared to other NeRF-based methods, especially on more challenging scenes.
Authors: Shuangquan Feng, Junhua Ma, Virginia R. de Sa
Abstract: Researchers have proposed to use data of human preference feedback to fine-tune text-to-image generative models. However, the scalability of human feedback collection has been limited by its reliance on manual annotation. Therefore, we develop and test a method to automatically annotate user preferences from their spontaneous facial expression reaction to the generated images. We collect a dataset of Facial Expression Reaction to Generated Images (FERGI) and show that the activations of multiple facial action units (AUs) are highly correlated with user evaluations of the generated images. Specifically, AU4 (brow lowerer) is reflective of negative evaluations of the generated image whereas AU12 (lip corner puller) is reflective of positive evaluations. These can be useful in two ways. Firstly, we can automatically annotate user preferences between image pairs with substantial difference in these AU responses with an accuracy significantly outperforming state-of-the-art scoring models. Secondly, directly integrating the AU responses with the scoring models improves their consistency with human preferences. Finally, this method of automatic annotation with facial expression analysis can be potentially generalized to other generation tasks. The code is available at https://github.com/ShuangquanFeng/FERGI, and the dataset is also available at the same link for research purposes.
Authors: Hongyang Li, Yang Li, Huijie Wang, Jia Zeng, Huilin Xu, Pinlong Cai, Li Chen, Junchi Yan, Feng Xu, Lu Xiong, Jingdong Wang, Futang Zhu, Chunjing Xu, Tiancai Wang, Fei Xia, Beipeng Mu, Zhihui Peng, Dahua Lin, Yu Qiao
Abstract: With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. Current autonomous driving datasets can broadly be categorized into two generations. The first-generation autonomous driving datasets are characterized by relatively simpler sensor modalities, smaller data scale, and is limited to perception-level tasks. KITTI, introduced in 2012, serves as a prominent representative of this initial wave. In contrast, the second-generation datasets exhibit heightened complexity in sensor modalities, greater data scale and diversity, and an expansion of tasks from perception to encompass prediction and control. Leading examples of the second generation include nuScenes and Waymo, introduced around 2019. This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets, the pivotal role of data engine systems, and the utilization of generative foundation models to facilitate scalable data generation. Furthermore, this review undertakes an exhaustive analysis and discourse regarding the characteristics and data scales that future third-generation autonomous driving datasets should possess. It also delves into the scientific and technical challenges that warrant resolution. These endeavors are pivotal in advancing autonomous innovation and fostering technological enhancement in critical domains. For further details, please refer to https://github.com/OpenDriveLab/DriveAGI.
Authors: Bolin Lai, Xiaoliang Dai, Lawrence Chen, Guan Pang, James M. Rehg, Miao Liu
Abstract: Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to synthesize an image depicting an action in the user's context (i.e., action frame) by conditioning on a user prompt and an input egocentric image. Notably, existing egocentric action datasets lack the detailed annotations that describe the execution of actions. Additionally, existing diffusion-based image manipulation models are sub-optimal in controlling the state transition of an action in egocentric image pixel space because of the domain gap. To this end, we propose to Learn EGOcentric (LEGO) action frame generation via visual instruction tuning. First, we introduce a prompt enhancement scheme to generate enriched action descriptions from a visual large language model (VLLM) by visual instruction tuning. Then we propose a novel method to leverage image and text embeddings from the VLLM as additional conditioning to improve the performance of a diffusion model. We validate our model on two egocentric datasets -- Ego4D and Epic-Kitchens. Our experiments show substantial improvement over prior image manipulation models in both quantitative and qualitative evaluation. We also conduct detailed ablation studies and analysis to provide insights in our method. More details of the dataset and code are available on the website (https://bolinlai.github.io/Lego_EgoActGen/).
Authors: Yankai Jiang, Zhongzhen Huang, Rongzhao Zhang, Xiaofan Zhang, Shaoting Zhang
Abstract: The long-tailed distribution problem in medical image analysis reflects a high prevalence of common conditions and a low prevalence of rare ones, which poses a significant challenge in developing a unified model capable of identifying rare or novel tumor categories not encountered during training. In this paper, we propose a new zero-shot pan-tumor segmentation framework (ZePT) based on query-disentangling and self-prompting to segment unseen tumor categories beyond the training set. ZePT disentangles the object queries into two subsets and trains them in two stages. Initially, it learns a set of fundamental queries for organ segmentation through an object-aware feature grouping strategy, which gathers organ-level visual features. Subsequently, it refines the other set of advanced queries that focus on the auto-generated visual prompts for unseen tumor segmentation. Moreover, we introduce query-knowledge alignment at the feature level to enhance each query's discriminative representation and generalizability. Extensive experiments on various tumor segmentation tasks demonstrate the performance superiority of ZePT, which surpasses the previous counterparts and evidence the promising ability for zero-shot tumor segmentation in real-world settings.
Authors: Thuan Hoang Nguyen, Anh Tran
Abstract: Despite their ability to generate high-resolution and diverse images from text prompts, text-to-image diffusion models often suffer from slow iterative sampling processes. Model distillation is one of the most effective directions to accelerate these models. However, previous distillation methods fail to retain the generation quality while requiring a significant amount of images for training, either from real data or synthetically generated by the teacher model. In response to this limitation, we present a novel image-free distillation scheme named $\textbf{SwiftBrush}$. Drawing inspiration from text-to-3D synthesis, in which a 3D neural radiance field that aligns with the input prompt can be obtained from a 2D text-to-image diffusion prior via a specialized loss without the use of any 3D data ground-truth, our approach re-purposes that same loss for distilling a pretrained multi-step text-to-image model to a student network that can generate high-fidelity images with just a single inference step. In spite of its simplicity, our model stands as one of the first one-step text-to-image generators that can produce images of comparable quality to Stable Diffusion without reliance on any training image data. Remarkably, SwiftBrush achieves an FID score of $\textbf{16.67}$ and a CLIP score of $\textbf{0.29}$ on the COCO-30K benchmark, achieving competitive results or even substantially surpassing existing state-of-the-art distillation techniques.
Authors: Tanveer Hannan, Md Mohaiminul Islam, Thomas Seidl, Gedas Bertasius
Abstract: Locating specific moments within long videos (20-120 minutes) presents a significant challenge, akin to finding a needle in a haystack. Adapting existing short video (5-30 seconds) grounding methods to this problem yields poor performance. Since most real life videos, such as those on YouTube and AR/VR, are lengthy, addressing this issue is crucial. Existing methods typically operate in two stages: clip retrieval and grounding. However, this disjoint process limits the retrieval module's fine-grained event understanding, crucial for specific moment detection. We propose RGNet which deeply integrates clip retrieval and grounding into a single network capable of processing long videos into multiple granular levels, e.g., clips and frames. Its core component is a novel transformer encoder, RG-Encoder, that unifies the two stages through shared features and mutual optimization. The encoder incorporates a sparse attention mechanism and an attention loss to model both granularity jointly. Moreover, we introduce a contrastive clip sampling technique to mimic the long video paradigm closely during training. RGNet surpasses prior methods, showcasing state-of-the-art performance on long video temporal grounding (LVTG) datasets MAD and Ego4D.
Authors: Vladimir Yugay, Yue Li, Theo Gevers, Martin R. Oswald
Abstract: We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD videos. To this end, we propose a novel effective strategy for seeding new Gaussians for newly explored areas and their effective online optimization that is independent of the scene size and thus scalable to larger scenes. This is achieved by organizing the scene into sub-maps which are independently optimized and do not need to be kept in memory. We further accomplish frame-to-model camera tracking by minimizing photometric and geometric losses between the input and rendered frames. The Gaussian representation allows for high-quality photo-realistic real-time rendering of real-world scenes. Evaluation on synthetic and real-world datasets demonstrates competitive or superior performance in mapping, tracking, and rendering compared to existing neural dense SLAM methods.
Authors: Xin Guo, Jiangwei Lao, Bo Dang, Yingying Zhang, Lei Yu, Lixiang Ru, Liheng Zhong, Ziyuan Huang, Kang Wu, Dingxiang Hu, Huimei He, Jian Wang, Jingdong Chen, Ming Yang, Yongjun Zhang, Yansheng Li
Abstract: Prior studies on Remote Sensing Foundation Model (RSFM) reveal immense potential towards a generic model for Earth Observation. Nevertheless, these works primarily focus on a single modality without temporal and geo-context modeling, hampering their capabilities for diverse tasks. In this study, we present SkySense, a generic billion-scale model, pre-trained on a curated multi-modal Remote Sensing Imagery (RSI) dataset with 21.5 million temporal sequences. SkySense incorporates a factorized multi-modal spatiotemporal encoder taking temporal sequences of optical and Synthetic Aperture Radar (SAR) data as input. This encoder is pre-trained by our proposed Multi-Granularity Contrastive Learning to learn representations across different modal and spatial granularities. To further enhance the RSI representations by the geo-context clue, we introduce Geo-Context Prototype Learning to learn region-aware prototypes upon RSI's multi-modal spatiotemporal features. To our best knowledge, SkySense is the largest Multi-Modal RSFM to date, whose modules can be flexibly combined or used individually to accommodate various tasks. It demonstrates remarkable generalization capabilities on a thorough evaluation encompassing 16 datasets over 7 tasks, from single- to multi-modal, static to temporal, and classification to localization. SkySense surpasses 18 recent RSFMs in all test scenarios. Specifically, it outperforms the latest models such as GFM, SatLas and Scale-MAE by a large margin, i.e., 2.76%, 3.67% and 3.61% on average respectively. We will release the pre-trained weights to facilitate future research and Earth Observation applications.
Authors: Tianjie Dai, Ruipeng Zhang, Feng Hong, Jiangchao Yao, Ya Zhang, Yanfeng Wang
Abstract: Vision-Language Pre-training (VLP) that utilizes the multi-modal information to promote the training efficiency and effectiveness, has achieved great success in vision recognition of natural domains and shown promise in medical imaging diagnosis for the Chest X-Rays (CXRs). However, current works mainly pay attention to the exploration on single dataset of CXRs, which locks the potential of this powerful paradigm on larger hybrid of multi-source CXRs datasets. We identify that although blending samples from the diverse sources offers the advantages to improve the model generalization, it is still challenging to maintain the consistent superiority for the task of each source due to the existing heterogeneity among sources. To handle this dilemma, we design a Conquer-and-Divide pre-training framework, termed as UniChest, aiming to make full use of the collaboration benefit of multiple sources of CXRs while reducing the negative influence of the source heterogeneity. Specially, the ``Conquer" stage in UniChest encourages the model to sufficiently capture multi-source common patterns, and the ``Divide" stage helps squeeze personalized patterns into different small experts (query networks). We conduct thorough experiments on many benchmarks, e.g., ChestX-ray14, CheXpert, Vindr-CXR, Shenzhen, Open-I and SIIM-ACR Pneumothorax, verifying the effectiveness of UniChest over a range of baselines, and release our codes and pre-training models at https://github.com/Elfenreigen/UniChest.
Authors: Yunhao Gou, Zhili Liu, Kai Chen, Lanqing Hong, Hang Xu, Aoxue Li, Dit-Yan Yeung, James T. Kwok, Yu Zhang
Abstract: Instruction tuning of Large Vision-language Models (LVLMs) has revolutionized the development of versatile models with zero-shot generalization across a wide range of downstream vision-language tasks. However, the diversity of training tasks of different sources and formats would lead to inevitable task conflicts, where different tasks conflict for the same set of model parameters, resulting in sub-optimal instructionfollowing abilities. To address that, we propose the Mixture of Clusterconditional LoRA Experts (MoCLE), a novel Mixture of Experts (MoE) architecture designed to activate the task-customized model parameters based on the instruction clusters. A separate universal expert is further incorporated to improve generalization capabilities of MoCLE for novel instructions. Extensive experiments on 11 zero-shot tasks demonstrate the effectiveness of MoCLE.
Authors: Yiming Zhang, Zhening Xing, Yanhong Zeng, Youqing Fang, Kai Chen
Abstract: Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation, empowering non-experts to generate stunning images with unique styles. While promising, adding realistic motions into these personalized images by text poses significant challenges in preserving distinct styles, high-fidelity details, and achieving motion controllability by text. In this paper, we present PIA, a Personalized Image Animator that excels in aligning with condition images, achieving motion controllability by text, and the compatibility with various personalized T2I models without specific tuning. To achieve these goals, PIA builds upon a base T2I model with well-trained temporal alignment layers, allowing for the seamless transformation of any personalized T2I model into an image animation model. A key component of PIA is the introduction of the condition module, which utilizes the condition frame and inter-frame affinity as input to transfer appearance information guided by the affinity hint for individual frame synthesis in the latent space. This design mitigates the challenges of appearance-related image alignment within and allows for a stronger focus on aligning with motion-related guidance.
Authors: Dan Kondratyuk, Lijun Yu, Xiuye Gu, Jos\'e Lezama, Jonathan Huang, Grant Schindler, Rachel Hornung, Vighnesh Birodkar, Jimmy Yan, Ming-Chang Chiu, Krishna Somandepalli, Hassan Akbari, Yair Alon, Yong Cheng, Josh Dillon, Agrim Gupta, Meera Hahn, Anja Hauth, David Hendon, Alonso Martinez, David Minnen, Mikhail Sirotenko, Kihyuk Sohn, Xuan Yang, Hartwig Adam, Ming-Hsuan Yang, Irfan Essa, Huisheng Wang, David A. Ross, Bryan Seybold, Lu Jiang
Abstract: We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
Authors: Li Xu, Haoxuan Qu, Yujun Cai, Jun Liu
Abstract: Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds. Meanwhile, diffusion models have shown appealing performance in generating high-quality images from random noise with high indeterminacy through step-by-step denoising. Inspired by their denoising capability, we propose a novel diffusion-based framework (6D-Diff) to handle the noise and indeterminacy in object pose estimation for better performance. In our framework, to establish accurate 2D-3D correspondence, we formulate 2D keypoints detection as a reverse diffusion (denoising) process. To facilitate such a denoising process, we design a Mixture-of-Cauchy-based forward diffusion process and condition the reverse process on the object features. Extensive experiments on the LM-O and YCB-V datasets demonstrate the effectiveness of our framework.
Authors: Xianjie Liu, Keren Fu, Qijun Zhao
Abstract: The Segment Anything Model (SAM) represents a significant breakthrough into foundation models for computer vision, providing a large-scale image segmentation model. However, despite SAM's zero-shot performance, its segmentation masks lack fine-grained details, particularly in accurately delineating object boundaries. We have high expectations regarding whether SAM, as a foundation model, can be improved towards highly accurate object segmentation, which is known as dichotomous image segmentation (DIS). To address this issue, we propose DIS-SAM, which advances SAM towards DIS with extremely accurate details. DIS-SAM is a framework specifically tailored for highly accurate segmentation, maintaining SAM's promptable design. DIS-SAM employs a two-stage approach, integrating SAM with a modified IS-Net dedicated to DIS. Despite its simplicity, DIS-SAM demonstrates significantly enhanced segmentation accuracy compared to SAM and HQ-SAM.
Authors: Xingyu Zhou, Leheng Zhang, Xiaorui Zhao, Keze Wang, Leida Li, Shuhang Gu
Abstract: Recently, Vision Transformer has achieved great success in recovering missing details in low-resolution sequences, i.e., the video super-resolution (VSR) task. Despite its superiority in VSR accuracy, the heavy computational burden as well as the large memory footprint hinder the deployment of Transformer-based VSR models on constrained devices. In this paper, we address the above issue by proposing a novel feature-level masked processing framework: VSR with Masked Intra and inter frame Attention (MIA-VSR). The core of MIA-VSR is leveraging feature-level temporal continuity between adjacent frames to reduce redundant computations and make more rational use of previously enhanced SR features. Concretely, we propose an intra-frame and inter-frame attention block which takes the respective roles of past features and input features into consideration and only exploits previously enhanced features to provide supplementary information. In addition, an adaptive block-wise mask prediction module is developed to skip unimportant computations according to feature similarity between adjacent frames. We conduct detailed ablation studies to validate our contributions and compare the proposed method with recent state-of-the-art VSR approaches. The experimental results demonstrate that MIA-VSR improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy. The code is available at https://github.com/LabShuHangGU/MIA-VSR.
Authors: Ragav Sachdeva, Andrew Zisserman
Abstract: In the past few decades, Japanese comics, commonly referred to as Manga, have transcended both cultural and linguistic boundaries to become a true worldwide sensation. Yet, the inherent reliance on visual cues and illustration within manga renders it largely inaccessible to individuals with visual impairments. In this work, we seek to address this substantial barrier, with the aim of ensuring that manga can be appreciated and actively engaged by everyone. Specifically, we tackle the problem of diarisation i.e. generating a transcription of who said what and when, in a fully automatic way. To this end, we make the following contributions: (1) we present a unified model, Magi, that is able to (a) detect panels, text boxes and character boxes, (b) cluster characters by identity (without knowing the number of clusters apriori), and (c) associate dialogues to their speakers; (2) we propose a novel approach that is able to sort the detected text boxes in their reading order and generate a dialogue transcript; (3) we annotate an evaluation benchmark for this task using publicly available [English] manga pages. The code, evaluation datasets and the pre-trained model can be found at: https://github.com/ragavsachdeva/magi.
Authors: Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu
Abstract: Large vision-language models (VLMs) such as GPT-4 have achieved exceptional performance across various multi-modal tasks. However, the deployment of VLMs necessitates substantial energy consumption and computational resources. Once attackers maliciously induce high energy consumption and latency time (energy-latency cost) during inference of VLMs, it will exhaust computational resources. In this paper, we explore this attack surface about availability of VLMs and aim to induce high energy-latency cost during inference of VLMs. We find that high energy-latency cost during inference of VLMs can be manipulated by maximizing the length of generated sequences. To this end, we propose verbose images, with the goal of crafting an imperceptible perturbation to induce VLMs to generate long sentences during inference. Concretely, we design three loss objectives. First, a loss is proposed to delay the occurrence of end-of-sequence (EOS) token, where EOS token is a signal for VLMs to stop generating further tokens. Moreover, an uncertainty loss and a token diversity loss are proposed to increase the uncertainty over each generated token and the diversity among all tokens of the whole generated sequence, respectively, which can break output dependency at token-level and sequence-level. Furthermore, a temporal weight adjustment algorithm is proposed, which can effectively balance these losses. Extensive experiments demonstrate that our verbose images can increase the length of generated sequences by 7.87 times and 8.56 times compared to original images on MS-COCO and ImageNet datasets, which presents potential challenges for various applications. Our code is available at https://github.com/KuofengGao/Verbose_Images.
Authors: Yang Li, Songlin Yang, Wei Wang, Jing Dong
Abstract: Advanced diffusion-based Text-to-Image (T2I) models, such as the Stable Diffusion Model, have made significant progress in generating diverse and high-quality images using text prompts alone. However, when non-famous users require personalized image generation for their identities (IDs), the T2I models fail to accurately generate their ID-related images. The main problem is that pre-trained T2I models do not learn the mapping between the new ID prompts and their corresponding visual content. The previous methods either failed to accurately fit the face region or lost the interactive generative ability with other existing concepts in T2I models. In other words, they are unable to generate T2I-aligned and semantic-fidelity images for the given prompts with other concepts such as scenes (``Eiffel Tower''), actions (``holding a basketball''), and facial attributes (``eyes closed''). In this paper, we focus on inserting accurate and interactive ID embedding into the Stable Diffusion Model for semantic-fidelity personalized generation. We address this challenge from two perspectives: face-wise region fitting and semantic-fidelity token optimization. Specifically, we first visualize the attention overfit problem and propose a face-wise attention loss to fit the face region instead of entangling ID-unrelated information, such as face layout and background. This key trick significantly enhances the ID accuracy and interactive generative ability with other existing concepts. Then, we optimize one ID representation as multiple per-stage tokens where each token contains two disentangled features. This expansion of the textual conditioning space improves semantic-fidelity control. Extensive experiments validate that our results exhibit superior ID accuracy, text-based manipulation ability, and generalization compared to previous methods.
Authors: Bumsoo Kim, Abdul Muqeet, Kyuchul Lee, Sanghyun Seo
Abstract: Face re-aging is a prominent field in computer vision and graphics, with significant applications in photorealistic domains such as movies, advertising, and live streaming. Recently, the need to apply face re-aging to non-photorealistic images, like comics, illustrations, and animations, has emerged as an extension in various entertainment sectors. However, the lack of a network that can seamlessly edit the apparent age in NPR images has limited these tasks to a naive, sequential approach. This often results in unpleasant artifacts and a loss of facial attributes due to domain discrepancies. In this paper, we introduce a novel one-stage method for face re-aging combined with portrait style transfer, executed in a single generative step. We leverage existing face re-aging and style transfer networks, both trained within the same PR domain. Our method uniquely fuses distinct latent vectors, each responsible for managing aging-related attributes and NPR appearance. By adopting an exemplar-based approach, our method offers greater flexibility compared to domain-level fine-tuning approaches, which typically require separate training or fine-tuning for each domain. This effectively addresses the limitation of requiring paired datasets for re-aging and domain-level, data-driven approaches for stylization. Our experiments show that our model can effortlessly generate re-aged images while simultaneously transferring the style of examples, maintaining both natural appearance and controllability.
Authors: Jiaheng Xie, Ruicheng Liang, Yidong Chai, Yang Liu, Daniel Zeng
Abstract: While short-form videos head to reshape the entire social media landscape, experts are exceedingly worried about their depressive impacts on viewers, as evidenced by medical studies. To prevent widespread consequences, platforms are eager to predict these videos' impact on viewers' mental health. Subsequently, they can take intervention measures, such as revising recommendation algorithms and displaying viewer discretion. Nevertheless, applicable predictive methods lack relevance to well-established medical knowledge, which outlines clinically proven external and environmental factors of depression. To account for such medical knowledge, we resort to an emergent methodological discipline, seeded Neural Topic Models (NTMs). However, existing seeded NTMs suffer from the limitations of single-origin topics, unknown topic sources, unclear seed supervision, and suboptimal convergence. To address those challenges, we develop a novel Knowledge-guided Multimodal NTM to predict a short-form video's depressive impact on viewers. Extensive empirical analyses using TikTok and Douyin datasets prove that our method outperforms state-of-the-art benchmarks. Our method also discovers medically relevant topics from videos that are linked to depressive impact. We contribute to IS with a novel video analytics method that is generalizable to other video classification problems. Practically, our method can help platforms understand videos' mental impacts, thus adjusting recommendations and video topic disclosure.
Authors: Lingji Chen
Abstract: Conventional tracking paradigm takes in instantaneous measurements such as range and bearing, and produces object tracks across time. In applications such as autonomous driving, lidar measurements in the form of point clouds are usually passed through a "virtual sensor" realized by a deep learning model, to produce "measurements" such as bounding boxes, which are in turn ingested by a tracking module to produce object tracks. Very often multiple lidar sweeps are accumulated in a buffer to merge and become the input to the virtual sensor. We argue in this paper that such an input already contains temporal information, and therefore the virtual sensor output should also contain temporal information, not just instantaneous values for the time corresponding to the end of the buffer. In particular, we present the deep learning model called MULti-Sweep PAired Detector (MULSPAD) that produces, for each detected object, a pair of bounding boxes at both the end time and the beginning time of the input buffer. This is achieved with fairly straightforward changes in commonly used lidar detection models, and with only marginal extra processing, but the resulting symmetry is satisfying. Such paired detections make it possible not only to construct rudimentary trackers fairly easily, but also to construct more sophisticated trackers that can exploit the extra information conveyed by the pair and be robust to choices of motion models and object birth/death models. We have conducted preliminary training and experimentation using Waymo Open Dataset, which shows the efficacy of our proposed method.
Authors: Xiaohan Lei, Min Wang, Wengang Zhou, Li Li, Houqiang Li
Abstract: As a new embodied vision task, Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment. The main challenge of this task lies in identifying the target object from different viewpoints while rejecting similar distractors. Existing ImageGoal Navigation methods usually adopt the simple Exploration-Exploitation framework and ignore the identification of specific instance during navigation. In this work, we propose to imitate the human behaviour of ``getting closer to confirm" when distinguishing objects from a distance. Specifically, we design a new modular navigation framework named Instance-aware Exploration-Verification-Exploitation (IEVE) for instance-level image goal navigation. Our method allows for active switching among the exploration, verification, and exploitation actions, thereby facilitating the agent in making reasonable decisions under different situations. On the challenging HabitatMatterport 3D semantic (HM3D-SEM) dataset, our method surpasses previous state-of-the-art work, with a classical segmentation model (0.684 vs. 0.561 success) or a robust model (0.702 vs. 0.561 success)
Authors: Dingqiang Ye, Chao Fan, Jingzhe Ma, Xiaoming Liu, Shiqi Yu
Abstract: Gait recognition stands as one of the most pivotal remote identification technologies and progressively expands across research and industry communities. However, existing gait recognition methods heavily rely on task-specific upstream driven by supervised learning to provide explicit gait representations like silhouette sequences, which inevitably introduce expensive annotation costs and potential error accumulation. Escaping from this trend, this work explores effective gait representations based on the all-purpose knowledge produced by task-agnostic Large Vision Models (LVMs) and proposes a simple yet efficient gait framework, termed BigGait. Specifically, the Gait Representation Extractor (GRE) within BigGait draws upon design principles from established gait representations, effectively transforming all-purpose knowledge into implicit gait representations without requiring third-party supervision signals. Experiments on CCPG, CAISA-B* and SUSTech1K indicate that BigGait significantly outperforms the previous methods in both within-domain and cross-domain tasks in most cases, and provides a more practical paradigm for learning the next-generation gait representation. Finally, we delve into prospective challenges and promising directions in LVMs-based gait recognition, aiming to inspire future work in this emerging topic. The source code is available at https://github.com/ShiqiYu/OpenGait.
Authors: Chun-Peng Chang, Shaoxiang Wang, Alain Pagani, Didier Stricker
Abstract: 3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object encoder and an original multi-key-anchor technique, enhancing object recognition accuracy and the understanding of spatial relationships. Furthermore, MiKASA improves the explainability of decision-making, facilitating error diagnosis. Our model achieves the highest overall accuracy in the Referit3D challenge for both the Sr3D and Nr3D datasets, particularly excelling by a large margin in categories that require viewpoint-dependent descriptions.
Authors: Ali Hassani, Wen-Mei Hwu, Humphrey Shi
Abstract: Neighborhood attention reduces the cost of self attention by restricting each token's attention span to its nearest neighbors. This restriction, parameterized by a window size and dilation factor, draws a spectrum of possible attention patterns between linear projection and self attention. Neighborhood attention, and more generally sliding window attention patterns, have long been bounded by infrastructure, particularly in higher-rank spaces (2-D and 3-D), calling for the development of custom kernels, which have been limited in either functionality, or performance, if not both. In this work, we first show that neighborhood attention can be represented as a batched GEMM problem, similar to standard attention, and implement it for 1-D and 2-D neighborhood attention. These kernels on average provide 895% and 272% improvement in full precision latency compared to existing naive kernels for 1-D and 2-D neighborhood attention respectively. We find certain inherent inefficiencies in all unfused neighborhood attention kernels that bound their performance and lower-precision scalability. We also developed fused neighborhood attention; an adaptation of fused dot-product attention kernels that allow fine-grained control over attention across different spatial axes. Known for reducing the quadratic time complexity of self attention to a linear complexity, neighborhood attention can now enjoy a reduced and constant memory footprint, and record-breaking half precision latency. We observe that our fused kernels successfully circumvent some of the unavoidable inefficiencies in unfused implementations. While our unfused GEMM-based kernels only improve half precision performance compared to naive kernels by an average of 496% and 113% in 1-D and 2-D problems respectively, our fused kernels improve naive kernels by an average of 1607% and 581% in 1-D and 2-D problems respectively.
Authors: Xingyi Li, Zhiguo Cao, Yizheng Wu, Kewei Wang, Ke Xian, Zhe Wang, Guosheng Lin
Abstract: Current 3D stylization methods often assume static scenes, which violates the dynamic nature of our real world. To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields. However, stylizing dynamic 3D scenes is inherently challenging due to the limited availability of stylized reference images along the temporal axis. Our key insight lies in introducing additional temporal cues besides the provided reference. To this end, we generate temporal pseudo-references from the given stylized reference. These pseudo-references facilitate the propagation of style information from the reference to the entire dynamic 3D scene. For coarse style transfer, we enforce novel views and times to mimic the style details present in pseudo-references at the feature level. To preserve high-frequency details, we create a collection of stylized temporal pseudo-rays from temporal pseudo-references. These pseudo-rays serve as detailed and explicit stylization guidance for achieving fine style transfer. Experiments on both synthetic and real-world datasets demonstrate that our method yields plausible stylized results of space-time view synthesis on dynamic 3D scenes.
Authors: Xianzu Wu, Xianfeng Wu, Tianyu Luan, Yajing Bai, Zhongyuan Lai, Junsong Yuan
Abstract: While previous studies have demonstrated successful 3D object shape completion with a sufficient number of points, they often fail in scenarios when a few points, e.g. tens of points, are observed. Surprisingly, via entropy analysis, we find that even a few points, e.g. 64 points, could retain substantial information to help recover the 3D shape of the object. To address the challenge of shape completion with very sparse point clouds, we then propose Few-point Shape Completion (FSC) model, which contains a novel dual-branch feature extractor for handling extremely sparse inputs, coupled with an extensive branch for maximal point utilization with a saliency branch for dynamic importance assignment. This model is further bolstered by a two-stage revision network that refines both the extracted features and the decoder output, enhancing the detail and authenticity of the completed point cloud. Our experiments demonstrate the feasibility of recovering 3D shapes from a few points. The proposed Few-point Shape Completion (FSC) model outperforms previous methods on both few-point inputs and many-point inputs, and shows good generalizability to different object categories.
Authors: Minje Kim, Tae-Kyun Kim
Abstract: Creating personalized hand avatars is important to offer a realistic experience to users on AR / VR platforms. While most prior studies focused on reconstructing 3D hand shapes, some recent work has tackled the reconstruction of hand textures on top of shapes. However, these methods are often limited to capturing pixels on the visible side of a hand, requiring diverse views of the hand in a video or multiple images as input. In this paper, we propose a novel method, BiTT(Bi-directional Texture reconstruction of Two hands), which is the first end-to-end trainable method for relightable, pose-free texture reconstruction of two interacting hands taking only a single RGB image, by three novel components: 1) bi-directional (left $\leftrightarrow$ right) texture reconstruction using the texture symmetry of left / right hands, 2) utilizing a texture parametric model for hand texture recovery, and 3) the overall coarse-to-fine stage pipeline for reconstructing personalized texture of two interacting hands. BiTT first estimates the scene light condition and albedo image from an input image, then reconstructs the texture of both hands through the texture parametric model and bi-directional texture reconstructor. In experiments using InterHand2.6M and RGB2Hands datasets, our method significantly outperforms state-of-the-art hand texture reconstruction methods quantitatively and qualitatively. The code is available at https://github.com/yunminjin2/BiTT
Authors: Chris Kelly, Luhui Hu, Jiayin Hu, Yu Tian, Deshun Yang, Bang Yang, Cindy Yang, Zihao Li, Zaoshan Huang, Yuexian Zou
Abstract: The evolution of text to visual components facilitates people's daily lives, such as generating image, videos from text and identifying the desired elements within the images. Computer vision models involving the multimodal abilities in the previous days are focused on image detection, classification based on well-defined objects. Large language models (LLMs) introduces the transformation from nature language to visual objects, which present the visual layout for text contexts. OpenAI GPT-4 has emerged as the pinnacle in LLMs, while the computer vision (CV) domain boasts a plethora of state-of-the-art (SOTA) models and algorithms to convert 2D images to their 3D representations. However, the mismatching between the algorithms with the problem could lead to undesired results. In response to this challenge, we propose an unified VisionGPT-3D framework to consolidate the state-of-the-art vision models, thereby facilitating the development of vision-oriented AI. VisionGPT-3D provides a versatile multimodal framework building upon the strengths of multimodal foundation models. It seamlessly integrates various SOTA vision models and brings the automation in the selection of SOTA vision models, identifies the suitable 3D mesh creation algorithms corresponding to 2D depth maps analysis, generates optimal results based on diverse multimodal inputs such as text prompts. Keywords: VisionGPT-3D, 3D vision understanding, Multimodal agent
Authors: Yunhao Gou, Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung, James T. Kwok, Yu Zhang
Abstract: Multimodal large language models (MLLMs) have shown impressive reasoning abilities, which, however, are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting unsafe responses, we observe that safety mechanisms of the pre-aligned LLMs in MLLMs can be easily bypassed due to the introduction of image features. To construct robust MLLMs, we propose ECSO(Eyes Closed, Safety On), a novel training-free protecting approach that exploits the inherent safety awareness of MLLMs, and generates safer responses via adaptively transforming unsafe images into texts to activate intrinsic safety mechanism of pre-aligned LLMs in MLLMs. Experiments on five state-of-the-art (SoTA) MLLMs demonstrate that our ECSO enhances model safety significantly (e.g., a 37.6% improvement on the MM-SafetyBench (SD+OCR), and 71.3% on VLSafe for the LLaVA-1.5-7B), while consistently maintaining utility results on common MLLM benchmarks. Furthermore, we show that ECSO can be used as a data engine to generate supervised-finetuning (SFT) data for MLLM alignment without extra human intervention.
Authors: Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier, Sam Dodge, Bowen Zhang, Philipp Dufter, Dhruti Shah, Xianzhi Du, Futang Peng, Floris Weers, Anton Belyi, Haotian Zhang, Karanjeet Singh, Doug Kang, Ankur Jain, Hongyu H\`e, Max Schwarzer, Tom Gunter, Xiang Kong, Aonan Zhang, Jianyu Wang, Chong Wang, Nan Du, Tao Lei, Sam Wiseman, Guoli Yin, Mark Lee, Zirui Wang, Ruoming Pang, Peter Grasch, Alexander Toshev, Yinfei Yang
Abstract: In this work, we discuss building performant Multimodal Large Language Models (MLLMs). In particular, we study the importance of various architecture components and data choices. Through careful and comprehensive ablations of the image encoder, the vision language connector, and various pre-training data choices, we identified several crucial design lessons. For example, we demonstrate that for large-scale multimodal pre-training using a careful mix of image-caption, interleaved image-text, and text-only data is crucial for achieving state-of-the-art (SOTA) few-shot results across multiple benchmarks, compared to other published pre-training results. Further, we show that the image encoder together with image resolution and the image token count has substantial impact, while the vision-language connector design is of comparatively negligible importance. By scaling up the presented recipe, we build MM1, a family of multimodal models up to 30B parameters, including both dense models and mixture-of-experts (MoE) variants, that are SOTA in pre-training metrics and achieve competitive performance after supervised fine-tuning on a range of established multimodal benchmarks. Thanks to large-scale pre-training, MM1 enjoys appealing properties such as enhanced in-context learning, and multi-image reasoning, enabling few-shot chain-of-thought prompting.
Authors: Yuwei Zhang, Yan Wu, Yanming Liu, Xinyue Peng
Abstract: Object detection methods under known single degradations have been extensively investigated. However, existing approaches require prior knowledge of the degradation type and train a separate model for each, limiting their practical applications in unpredictable environments. To address this challenge, we propose a chain-of-thought (CoT) prompted adaptive enhancer, CPA-Enhancer, for object detection under unknown degradations. Specifically, CPA-Enhancer progressively adapts its enhancement strategy under the step-by-step guidance of CoT prompts, that encode degradation-related information. To the best of our knowledge, it's the first work that exploits CoT prompting for object detection tasks. Overall, CPA-Enhancer is a plug-and-play enhancement model that can be integrated into any generic detectors to achieve substantial gains on degraded images, without knowing the degradation type priorly. Experimental results demonstrate that CPA-Enhancer not only sets the new state of the art for object detection but also boosts the performance of other downstream vision tasks under unknown degradations.
Authors: Minh Tran, Winston Bounsavy, Khoa Vo, Anh Nguyen, Tri Nguyen, Ngan Le
Abstract: Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bidirectional approach, encompassing both the transition from amodal features to visible features (amodal-to-visible) and from visible features to amodal features (visible-to-amodal). Our observation shows that the utilization of amodal features through the amodal-to-visible can confuse the visible features due to the extra information of occluded/hidden segments not presented in visible display. Consequently, this compromised quality of visible features during the subsequent visible-to-amodal transition. To tackle this issue, we introduce ShapeFormer, a decoupled Transformer-based model with a visible-to-amodal transition. It facilitates the explicit relationship between output segmentations and avoids the need for amodal-to-visible transitions. ShapeFormer comprises three key modules: (i) Visible-Occluding Mask Head for predicting visible segmentation with occlusion awareness, (ii) Shape-Prior Amodal Mask Head for predicting amodal and occluded masks, and (iii) Category-Specific Shape Prior Retriever aims to provide shape prior knowledge. Comprehensive experiments and extensive ablation studies across various AIS benchmarks demonstrate the effectiveness of our ShapeFormer. The code is available at: https://github.com/UARK-AICV/ShapeFormer
Authors: Yuxuan Li, Xiang Li, Yimain Dai, Qibin Hou, Li Liu, Yongxiang Liu, Ming-Ming Cheng, Jian Yang
Abstract: Remote sensing images pose distinct challenges for downstream tasks due to their inherent complexity. While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios. Such prior knowledge can be useful because remote sensing objects may be mistakenly recognized without referencing a sufficiently long-range context, which can vary for different objects. This paper considers these priors and proposes a lightweight Large Selective Kernel Network (LSKNet) backbone. LSKNet can dynamically adjust its large spatial receptive field to better model the ranging context of various objects in remote sensing scenarios. To our knowledge, large and selective kernel mechanisms have not been previously explored in remote sensing images. Without bells and whistles, our lightweight LSKNet sets new state-of-the-art scores on standard remote sensing classification, object detection and semantic segmentation benchmarks. Our comprehensive analysis further validated the significance of the identified priors and the effectiveness of LSKNet. The code is available at https://github.com/zcablii/LSKNet.
Authors: Boqi Chen, Junier Oliva, Marc Niethammer
Abstract: Medical records often consist of different modalities, such as images, text, and tabular information. Integrating all modalities offers a holistic view of a patient's condition, while analyzing them longitudinally provides a better understanding of disease progression. However, real-world longitudinal medical records present challenges: 1) patients may lack some or all of the data for a specific timepoint, and 2) certain modalities or views might be absent for all patients during a particular period. In this work, we introduce a unified model for longitudinal multi-modal multi-view prediction with missingness. Our method allows as many timepoints as desired for input, and aims to leverage all available data, regardless of their availability. We conduct extensive experiments on the knee osteoarthritis dataset from the Osteoarthritis Initiative for pain and Kellgren-Lawrence grade prediction at a future timepoint. We demonstrate the effectiveness of our method by comparing results from our unified model to specific models that use the same modality and view combinations during training and evaluation. We also show the benefit of having extended temporal data and provide post-hoc analysis for a deeper understanding of each modality/view's importance for different tasks.
Authors: Xu Zheng, Pengyuan Zhou, Athanasios V. Vasilakos, Lin Wang
Abstract: This paper addresses an interesting yet challenging problem -- source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation -- given only a pinhole image-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is nontrivial due to the semantic mismatches, style discrepancies, and inevitable distortion of panoramic images. To this end, we propose a novel method that utilizes Tangent Projection (TP) as it has less distortion and meanwhile slits the equirectangular projection (ERP) with a fixed FoV to mimic the pinhole images. Both projections are shown effective in extracting knowledge from the source model. However, the distinct projection discrepancies between source and target domains impede the direct knowledge transfer; thus, we propose a panoramic prototype adaptation module (PPAM) to integrate panoramic prototypes from the extracted knowledge for adaptation. We then impose the loss constraints on both predictions and prototypes and propose a cross-dual attention module (CDAM) at the feature level to better align the spatial and channel characteristics across the domains and projections. Both knowledge extraction and transfer processes are synchronously updated to reach the best performance. Extensive experiments on the synthetic and real-world benchmarks, including outdoor and indoor scenarios, demonstrate that our method achieves significantly better performance than prior SFUDA methods for pinhole-to-panoramic adaptation.
Authors: Seongbo Ha, Jiung Yeon, Hyeonwoo Yu
Abstract: Simultaneous Localization and Mapping (SLAM) with dense representation plays a key role in robotics, Virtual Reality (VR), and Augmented Reality (AR) applications. Recent advancements in dense representation SLAM have highlighted the potential of leveraging neural scene representation and 3D Gaussian representation for high-fidelity spatial representation. In this paper, we propose a novel dense representation SLAM approach with a fusion of Generalized Iterative Closest Point (G-ICP) and 3D Gaussian Splatting (3DGS). In contrast to existing methods, we utilize a single Gaussian map for both tracking and mapping, resulting in mutual benefits. Through the exchange of covariances between tracking and mapping processes with scale alignment techniques, we minimize redundant computations and achieve an efficient system. Additionally, we enhance tracking accuracy and mapping quality through our keyframe selection methods. Experimental results demonstrate the effectiveness of our approach, showing an incredibly fast speed up to 107 FPS (for the entire system) and superior quality of the reconstructed map.
Authors: Zhengqing Yuan, Ruoxi Chen, Zhaoxu Li, Haolong Jia, Lifang He, Chi Wang, Lichao Sun
Abstract: Sora is the first large-scale generalist video generation model that garnered significant attention across society. Since its launch by OpenAI in February 2024, no other video generation models have paralleled {Sora}'s performance or its capacity to support a broad spectrum of video generation tasks. Additionally, there are only a few fully published video generation models, with the majority being closed-source. To address this gap, this paper proposes a new multi-agent framework Mora, which incorporates several advanced visual AI agents to replicate generalist video generation demonstrated by Sora. In particular, Mora can utilize multiple visual agents and successfully mimic Sora's video generation capabilities in various tasks, such as (1) text-to-video generation, (2) text-conditional image-to-video generation, (3) extend generated videos, (4) video-to-video editing, (5) connect videos and (6) simulate digital worlds. Our extensive experimental results show that Mora achieves performance that is proximate to that of Sora in various tasks. However, there exists an obvious performance gap between our work and Sora when assessed holistically. In summary, we hope this project can guide the future trajectory of video generation through collaborative AI agents.
Authors: Haoran Lang, Yuxuan Ge, Zheng Tian
Abstract: Diffusion models have achieved great success in image generation. However, when leveraging this idea for video generation, we face significant challenges in maintaining the consistency and continuity across video frames. This is mainly caused by the lack of an effective framework to align frames of videos with desired temporal features while preserving consistent semantic and stochastic features. In this work, we propose a novel Sector-Shaped Diffusion Model (S2DM) whose sector-shaped diffusion region is formed by a set of ray-shaped reverse diffusion processes starting at the same noise point. S2DM can generate a group of intrinsically related data sharing the same semantic and stochastic features while varying on temporal features with appropriate guided conditions. We apply S2DM to video generation tasks, and explore the use of optical flow as temporal conditions. Our experimental results show that S2DM outperforms many existing methods in the task of video generation without any temporal-feature modelling modules. For text-to-video generation tasks where temporal conditions are not explicitly given, we propose a two-stage generation strategy which can decouple the generation of temporal features from semantic-content features. We show that, without additional training, our model integrated with another temporal conditions generative model can still achieve comparable performance with existing works. Our results can be viewd at https://s2dm.github.io/S2DM/.
Authors: Jaihoon Kim, Juil Koo, Kyeongmin Yeo, Minhyuk Sung
Abstract: We introduce a general framework for generating diverse visual content, including ambiguous images, panorama images, mesh textures, and Gaussian splat textures, by synchronizing multiple diffusion processes. We present exhaustive investigation into all possible scenarios for synchronizing multiple diffusion processes through a canonical space and analyze their characteristics across applications. In doing so, we reveal a previously unexplored case: averaging the outputs of Tweedie's formula while conducting denoising in multiple instance spaces. This case also provides the best quality with the widest applicability to downstream tasks. We name this case SyncTweedies. In our experiments generating visual content aforementioned, we demonstrate the superior quality of generation by SyncTweedies compared to other synchronization methods, optimization-based and iterative-update-based methods.
Authors: Max Ku, Cong Wei, Weiming Ren, Harry Yang, Wenhu Chen
Abstract: Video-to-video editing involves editing a source video along with additional control (such as text prompts, subjects, or styles) to generate a new video that aligns with the source video and the provided control. Traditional methods have been constrained to certain editing types, limiting their ability to meet the wide range of user demands. In this paper, we introduce AnyV2V, a novel training-free framework designed to simplify video editing into two primary steps: (1) employing an off-the-shelf image editing model (e.g. InstructPix2Pix, InstantID, etc) to modify the first frame, (2) utilizing an existing image-to-video generation model (e.g. I2VGen-XL) for DDIM inversion and feature injection. In the first stage, AnyV2V can plug in any existing image editing tools to support an extensive array of video editing tasks. Beyond the traditional prompt-based editing methods, AnyV2V also can support novel video editing tasks, including reference-based style transfer, subject-driven editing, and identity manipulation, which were unattainable by previous methods. In the second stage, AnyV2V can plug in any existing image-to-video models to perform DDIM inversion and intermediate feature injection to maintain the appearance and motion consistency with the source video. On the prompt-based editing, we show that AnyV2V can outperform the previous best approach by 35\% on prompt alignment, and 25\% on human preference. On the three novel tasks, we show that AnyV2V also achieves a high success rate. We believe AnyV2V will continue to thrive due to its ability to seamlessly integrate the fast-evolving image editing methods. Such compatibility can help AnyV2V to increase its versatility to cater to diverse user demands.
Authors: Han Zhao, Min Zhang, Wei Zhao, Pengxiang Ding, Siteng Huang, Donglin Wang
Abstract: In recent years, the application of multimodal large language models (MLLM) in various fields has achieved remarkable success. However, as the foundation model for many downstream tasks, current MLLMs are composed of the well-known Transformer network, which has a less efficient quadratic computation complexity. To improve the efficiency of such basic models, we propose Cobra, a linear computational complexity MLLM. Specifically, Cobra integrates the efficient Mamba language model into the visual modality. Moreover, we explore and study various modal fusion schemes to create an effective multi-modal Mamba. Extensive experiments demonstrate that (1) Cobra achieves extremely competitive performance with current computationally efficient state-of-the-art methods, e.g., LLaVA-Phi, TinyLLaVA, and MobileVLM v2, and has faster speed due to Cobra's linear sequential modeling. (2) Interestingly, the results of closed-set challenging prediction benchmarks show that Cobra performs well in overcoming visual illusions and spatial relationship judgments. (3) Notably, Cobra even achieves comparable performance to LLaVA with about 43% of the number of parameters. We will make all codes of Cobra open-source and hope that the proposed method can facilitate future research on complexity problems in MLLM. Our project page is available at: https://sites.google.com/view/cobravlm.
Authors: Xiang Fan, Anand Bhattad, Ranjay Krishna
Abstract: We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative inpainting, to modify the first frame; it automatically propagates those changes, with semantic, spatial, and temporally consistent motion, to the remaining frames. Unlike existing methods that enable edits only through imprecise textual instructions, Videoshop allows users to add or remove objects, semantically change objects, insert stock photos into videos, etc. with fine-grained control over locations and appearance. We achieve this through image-based video editing by inverting latents with noise extrapolation, from which we generate videos conditioned on the edited image. Videoshop produces higher quality edits against 6 baselines on 2 editing benchmarks using 10 evaluation metrics.
Authors: Qinghao Ye, Haiyang Xu, Guohai Xu, Jiabo Ye, Ming Yan, Yiyang Zhou, Junyang Wang, Anwen Hu, Pengcheng Shi, Yaya Shi, Chenliang Li, Yuanhong Xu, Hehong Chen, Junfeng Tian, Qi Qian, Ji Zhang, Fei Huang, Jingren Zhou
Abstract: Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-modal generation. In this study, we introduce mPLUG-Owl, a novel training paradigm that equips LLMs with multi-modal abilities through modularized learning of foundation LLM, a visual knowledge module, and a visual abstractor module. This approach can support multiple modalities and facilitate diverse unimodal and multimodal abilities through modality collaboration. The training paradigm of mPLUG-Owl involves a two-stage method for aligning image and text, which learns visual knowledge with the assistance of LLM while maintaining and even improving the generation abilities of LLM. In the first stage, the visual knowledge module and abstractor module are trained with a frozen LLM module to align the image and text. In the second stage, language-only and multi-modal supervised datasets are used to jointly fine-tune a low-rank adaption (LoRA) module on LLM and the abstractor module by freezing the visual knowledge module. We carefully build a visually-related instruction evaluation set OwlEval. Experimental results show that our model outperforms existing multi-modal models, demonstrating mPLUG-Owl's impressive instruction and visual understanding ability, multi-turn conversation ability, and knowledge reasoning ability. Besides, we observe some unexpected and exciting abilities such as multi-image correlation and scene text understanding, which makes it possible to leverage it for harder real scenarios, such as vision-only document comprehension. Our code, pre-trained model, instruction-tuned models, and evaluation set are available at https://github.com/X-PLUG/mPLUG-Owl. The online demo is available at https://www.modelscope.cn/studios/damo/mPLUG-Owl.
URLs: https://github.com/X-PLUG/mPLUG-Owl., https://www.modelscope.cn/studios/damo/mPLUG-Owl.
Authors: Yihao Xue, Ali Payani, Yu Yang, Baharan Mirzasoleiman
Abstract: Pretrained machine learning models need to be adapted to distribution shifts when deployed in new target environments. When obtaining labeled data from the target distribution is expensive, few-shot adaptation with only a few examples from the target distribution becomes essential. In this work, we propose MixPro, a lightweight and highly data-efficient approach for few-shot adaptation. MixPro first generates a relatively large dataset by mixing (linearly combining) pre-trained embeddings of large source data with those of the few target examples. This process preserves important features of both source and target distributions, while mitigating the specific noise in the small target data. Then, it trains a linear classifier on the mixed embeddings to effectively adapts the model to the target distribution without overfitting the small target data. Theoretically, we demonstrate the advantages of MixPro over previous methods. Our experiments, conducted across various model architectures on 8 datasets featuring different types of distribution shifts, reveal that MixPro can outperform baselines by up to 7\%, with only 2-4 target examples.
Authors: Taimeng Fu, Shaoshu Su, Yiren Lu, Chen Wang
Abstract: Simultaneous Localization and Mapping (SLAM) stands as one of the critical challenges in robot navigation. A SLAM system often consists of a front-end component for motion estimation and a back-end system for eliminating estimation drifts. Recent advancements suggest that data-driven methods are highly effective for front-end tasks, while geometry-based methods continue to be essential in the back-end processes. However, such a decoupled paradigm between the data-driven front-end and geometry-based back-end can lead to sub-optimal performance, consequently reducing the system's capabilities and generalization potential. To solve this problem, we proposed a novel self-supervised imperative learning framework, named imperative SLAM (iSLAM), which fosters reciprocal correction between the front-end and back-end, thus enhancing performance without necessitating any external supervision. Specifically, we formulate the SLAM problem as a bilevel optimization so that the front-end and back-end are bidirectionally connected. As a result, the front-end model can learn global geometric knowledge obtained through pose graph optimization by back-propagating the residuals from the back-end component. We showcase the effectiveness of this new framework through an application of stereo-inertial SLAM. The experiments show that the iSLAM training strategy achieves an accuracy improvement of 22% on average over a baseline model. To the best of our knowledge, iSLAM is the first SLAM system showing that the front-end and back-end components can mutually correct each other in a self-supervised manner.
Authors: Jinyi Hu, Yuan Yao, Chongyi Wang, Shan Wang, Yinxu Pan, Qianyu Chen, Tianyu Yu, Hanghao Wu, Yue Zhao, Haoye Zhang, Xu Han, Yankai Lin, Jiao Xue, Dahai Li, Zhiyuan Liu, Maosong Sun
Abstract: Recently there has been a significant surge in multimodal learning in terms of both image-to-text and text-to-image generation. However, the success is typically limited to English, leaving other languages largely behind. Building a competitive counterpart in other languages is highly challenging due to the low-resource nature of non-English multimodal data (i.e., lack of large-scale, high-quality image-text data). In this work, we propose MPM, an effective training paradigm for training large multimodal models in non-English languages. MPM demonstrates that Multilingual language models can Pivot zero-shot Multimodal learning across languages. Specifically, based on a strong multilingual large language model, multimodal models pretrained on English-only image-text data can well generalize to other languages in a (quasi)-zero-shot manner, even surpassing models trained on image-text data in native languages. Taking Chinese as a practice of MPM, we build large multimodal models VisCPM in image-to-text and text-to-image generation, which achieve state-of-the-art (open-source) performance in Chinese. To facilitate future research, we open-source codes and model weights at https://github.com/OpenBMB/VisCPM.git.
Authors: Chunwei Tian, Xuanyu Zhang, Qi Zhang, Mingming Yang, Zhaojie Ju
Abstract: Convolutional neural networks (CNNs) depend on deep network architectures to extract accurate information for image super-resolution. However, obtained information of these CNNs cannot completely express predicted high-quality images for complex scenes. In this paper, we present a dynamic network for image super-resolution (DSRNet), which contains a residual enhancement block, wide enhancement block, feature refinement block and construction block. The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super-resolution. To enhance robustness of obtained super-resolution model for complex scenes, a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super-resolution model for varying scenes. To prevent interference of components in a wide enhancement block, a refinement block utilizes a stacked architecture to accurately learn obtained features. Also, a residual learning operation is embedded in the refinement block to prevent long-term dependency problem. Finally, a construction block is responsible for reconstructing high-quality images. Designed heterogeneous architecture can not only facilitate richer structural information, but also be lightweight, which is suitable for mobile digital devices. Experimental results shows that our method is more competitive in terms of performance and recovering time of image super-resolution and complexity. The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.
Authors: Yongchao Chen
Abstract: Human fingerprints serve as one unique and powerful characteristic for each person, from which policemen can recognize the identity. Similar to humans, many natural bodies and intrinsic mechanical qualities can also be uniquely identified from surface characteristics. To measure the elasto-plastic properties of one material, one formally sharp indenter is pushed into the measured body under constant force and retracted, leaving a unique residual imprint of the minute size from several micrometers to nanometers. However, one great challenge is how to map the optical image of this residual imprint into the real wanted mechanical properties, \ie, the tensile force curve. In this paper, we propose a novel method to use multi-fidelity neural networks (MFNN) to solve this inverse problem. We first build up the NN model via pure simulation data, and then bridge the sim-to-real gap via transfer learning. Considering the difficulty of collecting real experimental data, we use NN to dig out the unknown physics and also implant the known physics into the transfer learning framework, thus highly improving the model stability and decreasing the data requirement. The final constructed model only needs three-shot calibration of real materials. We tested the final model across 20 real materials and achieved satisfying accuracy. This work serves as one great example of applying machine learning into scientific research, especially under the constraints of data limitation and fidelity variance.
Authors: H. R. Tizhoosh, Liron Pantanowitz
Abstract: Pathology images of histopathology can be acquired from camera-mounted microscopes or whole slide scanners. Utilizing similarity calculations to match patients based on these images holds significant potential in research and clinical contexts. Recent advancements in search technologies allow for implicit quantification of tissue morphology across diverse primary sites, facilitating comparisons and enabling inferences about diagnosis, and potentially prognosis, and predictions for new patients when compared against a curated database of diagnosed and treated cases. In this paper, we comprehensively review the latest developments in image search technologies for histopathology, offering a concise overview tailored for computational pathology researchers seeking effective, fast and efficient image search methods in their work.
Authors: Rohan Asthana, Joschua Conrad, Youssef Dawoud, Maurits Ortmanns, Vasileios Belagiannis
Abstract: Neural architecture search automates the design of neural network architectures usually by exploring a large and thus complex architecture search space. To advance the architecture search, we present a graph diffusion-based NAS approach that uses discrete conditional graph diffusion processes to generate high-performing neural network architectures. We then propose a multi-conditioned classifier-free guidance approach applied to graph diffusion networks to jointly impose constraints such as high accuracy and low hardware latency. Unlike the related work, our method is completely differentiable and requires only a single model training. In our evaluations, we show promising results on six standard benchmarks, yielding novel and unique architectures at a fast speed, i.e. less than 0.2 seconds per architecture. Furthermore, we demonstrate the generalisability and efficiency of our method through experiments on ImageNet dataset.
Authors: Joel Shor, Carson McNeil, Yotam Intrator, Joseph R Ledsam, Hiro-o Yamano, Daisuke Tsurumaru, Hiroki Kayama, Atsushi Hamabe, Koji Ando, Mitsuhiko Ota, Haruei Ogino, Hiroshi Nakase, Kaho Kobayashi, Masaaki Miyo, Eiji Oki, Ichiro Takemasa, Ehud Rivlin, Roman Goldenberg
Abstract: $\textbf{Background}$: Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. $\textbf{Methods}$: We use a "Masked Siamese Network" (MSN) to identify novel phenomena in unseen data and predict polyp detector performance. MSN is trained to predict masked out regions of polyp images, without any labels. We test MSN's ability to be trained on data only from Israel and detect unseen techniques, narrow-band imaging (NBI) and chromendoscoy (CE), on colonoscopes from Japan (354 videos, 128 hours). We also test MSN's ability to predict performance of Computer Aided Detection (CADe) of polyps on colonoscopies from both countries, even though MSN is not trained on data from Japan. $\textbf{Results}$: MSN correctly identifies NBI and CE as less similar to Israel whitelight than Japan whitelight (bootstrapped z-test, |z| > 496, p < 10^-8 for both) using the label-free Frechet distance. MSN detects NBI with 99% accuracy, predicts CE better than our heuristic (90% vs 79% accuracy) despite being trained only on whitelight, and is the only method that is robust to noisy labels. MSN predicts CADe polyp detector performance on in-domain Israel and out-of-domain Japan colonoscopies (r=0.79, 0.37 respectively). With few examples of Japan detector performance to train on, MSN prediction of Japan performance improves (r=0.56). $\textbf{Conclusion}$: Our technique can identify distribution shifts in clinical data and can predict CADe detector performance on unseen data, without labels. Our self-supervised approach can aid in detecting when data in practice is different from training, such as between hospitals or data has meaningfully shifted from training. MSN has potential for application to medical image domains beyond colonoscopy.
Authors: Kevin Xu, Yeganeh Kordi, Kate Sanders, Yizhong Wang, Adam Byerly, Jack Zhang, Benjamin Van Durme, Daniel Khashabi
Abstract: Recent chatbots have demonstrated impressive ability to understand and communicate in raw-text form. However, there is more to the world than raw text. For example, humans spend long hours of their time on web pages, where text is intertwined with other modalities and tasks are accomplished in the form of various complex interactions. Can state-of-the-art multi-modal models generalize to such complex domains? To address this question, we introduce TurkingBench, a benchmark of tasks formulated as web pages containing textual instructions with multi-modal context. Unlike existing work which employs artificially synthesized web pages, here we use natural HTML pages that were originally designed for crowdsourcing workers for various annotation purposes. The HTML instructions of each task are also instantiated with various values (obtained from the crowdsourcing tasks) to form new instances of the task. This benchmark contains 32.2K instances distributed across 158 tasks. Additionally, to facilitate the evaluation on TurkingBench, we develop an evaluation framework that connects the responses of chatbots to modifications on web pages (modifying a text box, checking a radio, etc.). We evaluate the performance of state-of-the-art models, including language-only, vision-only, and layout-only models, and their combinations, on this benchmark. Our findings reveal that these models perform significantly better than random chance, yet considerable room exists for improvement. We hope this benchmark will help facilitate the evaluation and development of web-based agents.