Authors: F. Terhag, P. Knechtges, A. Basermann, R. Tempone
Recent studies have confirmed cardiovascular diseases remain responsible for highest death toll amongst non-communicable diseases. Accurate left ventricular (LV) volume estimation is critical for valid diagnosis and management of various cardiovascular conditions, but poses significant challenge due to inherent uncertainties associated with segmentation algorithms in magnetic resonance imaging (MRI). Recent machine learning advancements, particularly U-Net-like convolutional networks, have facilitated automated segmentation for medical images, but struggles under certain pathologies and/or different scanner vendors and imaging protocols. This study proposes a novel methodology for post-hoc uncertainty estimation in LV volume prediction using It\^{o} stochastic differential equations (SDEs) to model path-wise behavior for the prediction error. The model describes the area of the left ventricle along the heart's long axis. The method is agnostic to the underlying segmentation algorithm, facilitating its use with various existing and future segmentation technologies. The proposed approach provides a mechanism for quantifying uncertainty, enabling medical professionals to intervene for unreliable predictions. This is of utmost importance in critical applications such as medical diagnosis, where prediction accuracy and reliability can directly impact patient outcomes. The method is also robust to dataset changes, enabling application for medical centers with limited access to labeled data. Our findings highlight the proposed uncertainty estimation methodology's potential to enhance automated segmentation robustness and generalizability, paving the way for more reliable and accurate LV volume estimation in clinical settings as well as opening new avenues for uncertainty quantification in biomedical image segmentation, providing promising directions for future research.
Authors: Tim Z. Xiao, Johannes Zenn, Robert Bamler
The Street View House Numbers (SVHN) dataset is a popular benchmark dataset in deep learning. Originally designed for digit classification tasks, the SVHN dataset has been widely used as a benchmark for various other tasks including generative modeling. However, with this work, we aim to warn the community about an issue of the SVHN dataset as a benchmark for generative modeling tasks: we discover that the official split into training set and test set of the SVHN dataset are not drawn from the same distribution. We empirically show that this distribution mismatch has little impact on the classification task (which may explain why this issue has not been detected before), but it severely affects the evaluation of probabilistic generative models, such as Variational Autoencoders and diffusion models. As a workaround, we propose to mix and re-split the official training and test set when SVHN is used for tasks other than classification. We publish a new split and the indices we used to create it at https://jzenn.github.io/svhn-remix/ .
Authors: Stephan Wenninger, Fabian Kemper, Ulrich Schwanecke, Mario Botsch
Human shape spaces have been extensively studied, as they are a core element of human shape and pose inference tasks. Classic methods for creating a human shape model register a surface template mesh to a database of 3D scans and use dimensionality reduction techniques, such as Principal Component Analysis, to learn a compact representation. While these shape models enable global shape modifications by correlating anthropometric measurements with the learned subspace, they only provide limited localized shape control. We instead register a volumetric anatomical template, consisting of skeleton bones and soft tissue, to the surface scans of the CAESAR database. We further enlarge our training data to the full Cartesian product of all skeletons and all soft tissues using physically plausible volumetric deformation transfer. This data is then used to learn an anatomically constrained volumetric human shape model in a self-supervised fashion. The resulting TailorMe model enables shape sampling, localized shape manipulation, and fast inference from given surface scans.
Authors: Duc-Anh Nguyen, Cuong Pham, Nhien-An Le-Khac
Various types of sensors can be used for Human Activity Recognition (HAR), and each of them has different strengths and weaknesses. Sometimes a single sensor cannot fully observe the user's motions from its perspective, which causes wrong predictions. While sensor fusion provides more information for HAR, it comes with many inherent drawbacks like user privacy and acceptance, costly set-up, operation, and maintenance. To deal with this problem, we propose Virtual Fusion - a new method that takes advantage of unlabeled data from multiple time-synchronized sensors during training, but only needs one sensor for inference. Contrastive learning is adopted to exploit the correlation among sensors. Virtual Fusion gives significantly better accuracy than training with the same single sensor, and in some cases, it even surpasses actual fusion using multiple sensors at test time. We also extend this method to a more general version called Actual Fusion within Virtual Fusion (AFVF), which uses a subset of training sensors during inference. Our method achieves state-of-the-art accuracy and F1-score on UCI-HAR and PAMAP2 benchmark datasets. Implementation is available upon request.
Authors: Joseph Paul Cohen, Louis Blankemeier, Akshay Chaudhari
Models driven by spurious correlations often yield poor generalization performance. We propose the counterfactual alignment method to detect and explore spurious correlations of black box classifiers. Counterfactual images generated with respect to one classifier can be input into other classifiers to see if they also induce changes in the outputs of these classifiers. The relationship between these responses can be quantified and used to identify specific instances where a spurious correlation exists as well as compute aggregate statistics over a dataset. Our work demonstrates the ability to detect spurious correlations in face attribute classifiers. This is validated by observing intuitive trends in a face attribute classifier as well as fabricating spurious correlations and detecting their presence, both visually and quantitatively. Further, utilizing the CF alignment method, we demonstrate that we can rectify spurious correlations identified in classifiers.
Authors: Hammad A. Ayyubi, Tianqi Liu, Arsha Nagrani, Xudong Lin, Mingda Zhang, Anurag Arnab, Feng Han, Yukun Zhu, Jialu Liu, Shih-Fu Chang
Existing popular video captioning benchmarks and models deal with generic captions devoid of specific person, place or organization named entities. In contrast, news videos present a challenging setting where the caption requires such named entities for meaningful summarization. As such, we propose the task of summarizing news video directly to entity-aware captions. We also release a large-scale dataset, VIEWS (VIdeo NEWS), to support research on this task. Further, we propose a method that augments visual information from videos with context retrieved from external world knowledge to generate entity-aware captions. We demonstrate the effectiveness of our approach on three video captioning models. We also show that our approach generalizes to existing news image captions dataset. With all the extensive experiments and insights, we believe we establish a solid basis for future research on this challenging task.
Authors: Pengsheng Guo, Hans Hao, Adam Caccavale, Zhongzheng Ren, Edward Zhang, Qi Shan, Aditya Sankar, Alexander G. Schwing, Alex Colburn, Fangchang Ma
In the realm of text-to-3D generation, utilizing 2D diffusion models through score distillation sampling (SDS) frequently leads to issues such as blurred appearances and multi-faced geometry, primarily due to the intrinsically noisy nature of the SDS loss. Our analysis identifies the core of these challenges as the interaction among noise levels in the 2D diffusion process, the architecture of the diffusion network, and the 3D model representation. To overcome these limitations, we present StableDreamer, a methodology incorporating three advances. First, inspired by InstructNeRF2NeRF, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. This finding provides a novel tool to debug SDS, which we use to show the impact of time-annealing noise levels on reducing multi-faced geometries. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition. Based on this observation, StableDreamer introduces a two-stage training strategy that effectively combines these aspects, resulting in high-fidelity 3D models. Third, we adopt an anisotropic 3D Gaussians representation, replacing Neural Radiance Fields (NeRFs), to enhance the overall quality, reduce memory usage during training, and accelerate rendering speeds, and better capture semi-transparent objects. StableDreamer reduces multi-face geometries, generates fine details, and converges stably.
Authors: Karran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy Mitra
Diffusion Handles is a novel approach to enabling 3D object edits on diffusion images. We accomplish these edits using existing pre-trained diffusion models, and 2D image depth estimation, without any fine-tuning or 3D object retrieval. The edited results remain plausible, photo-real, and preserve object identity. Diffusion Handles address a critically missing facet of generative image based creative design, and significantly advance the state-of-the-art in generative image editing. Our key insight is to lift diffusion activations for an object to 3D using a proxy depth, 3D-transform the depth and associated activations, and project them back to image space. The diffusion process applied to the manipulated activations with identity control, produces plausible edited images showing complex 3D occlusion and lighting effects. We evaluate Diffusion Handles: quantitatively, on a large synthetic data benchmark; and qualitatively by a user study, showing our output to be more plausible, and better than prior art at both, 3D editing and identity control.
Authors: Lingyu Zhang, Ting Hua, Yilin Shen, Hongxia Jin
Open World Compositional Zero-Shot Learning (OW-CZSL) is known to be an extremely challenging task, which aims to recognize unseen compositions formed from seen attributes and objects without any prior assumption of the output space. In order to achieve this goal, a model has to be "smart" and "knowledgeable". To be smart, a model should be good at reasoning the interactions between attributes and objects from the seen compositions. While "knowledgeable" means the model owns "common sense" to the open world that can "foresee" some features of the unseen compositions. Most previous work focuses on the "smart" part, while few of them provided an effective solution to achieve the "knowledgeable" goal. In this paper, we proposed a framework named Multi-Modal Prompt Tuning (MMPT) to inherit the "knowledgeable" property from the large pre-trained vision-language model. Extensive experiments show that our proposed MMPT obtains new state-of-the-art results in OW-CZSL task. On the UT-Zappos dataset, MMPT pushes the AUC score to $29.8$, while the previous best score is $26.5$. On the more challenging MIT-States dataset, the AUC score of MMPT is 1.5 times better than the current state-of-the-art.
Authors: Uy Dieu Tran, Minh Luu, Phong Nguyen, Janne Heikkila, Khoi Nguyen, Binh-Son Hua
Text-to-3D synthesis has recently emerged as a new approach to sampling 3D models by adopting pretrained text-to-image models as guiding visual priors. An intriguing but underexplored problem with existing text-to-3D methods is that 3D models obtained from the sampling-by-optimization procedure tend to have mode collapses, and hence poor diversity in their results. In this paper, we provide an analysis and identify potential causes of such a limited diversity, and then devise a new method that considers the joint generation of different 3D models from the same text prompt, where we propose to use augmented text prompts via textual inversion of reference images to diversify the joint generation. We show that our method leads to improved diversity in text-to-3D synthesis qualitatively and quantitatively.
Authors: Utku Mert Topcuoglu, Erdem Akagündüz
In this paper, we present an innovative approach to self-supervised learning for Vision Transformers (ViTs), integrating local masked image modeling with progressive layer freezing. This method focuses on enhancing the efficiency and speed of initial layer training in ViTs. By systematically freezing specific layers at strategic points during training, we reduce computational demands while maintaining or improving learning capabilities. Our approach employs a novel multi-scale reconstruction process that fosters efficient learning in initial layers and enhances semantic comprehension across scales. The results demonstrate a substantial reduction in training time (~12.5\%) with a minimal impact on model accuracy (decrease in top-1 accuracy by 0.6\%). Our method achieves top-1 and top-5 accuracies of 82.6\% and 96.2\%, respectively, underscoring its potential in scenarios where computational resources and time are critical. This work marks an advancement in the field of self-supervised learning for computer vision. The implementation of our approach is available at our project's GitHub repository: github.com/utkutpcgl/ViTFreeze.
Authors: Yu Zhang, Songpengcheng Xia, Lei Chu, Jiarui Yang, Qi Wu, Ling Pei
This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages a diverse array of real inertial motion capture data from different skeleton formats to improve motion diversity and model generalization. This method features two innovative components: a pseudo-velocity regression model for dynamic motion capture with inertial sensors, and a part-based model dividing the body and sensor data into three regions, each focusing on their unique characteristics. The approach demonstrates superior performance over state-of-the-art models across five public datasets, notably reducing pose error by 19\% on the DIP-IMU dataset, thus representing a significant improvement in inertial sensor-based human pose estimation. We will make the implementation of our model available for public use.
Authors: Yuanbiao Gou, Haiyu Zhao, Boyun Li, Xinyan Xiao, Xi Peng
All-in-one aims to solve various tasks of image restoration in a single model. To this end, we present a feasible way of exploiting the image priors captured by the pretrained diffusion model, through addressing the two challenges, i.e., degradation modeling and diffusion guidance. The former aims to simulate the process of the clean image degenerated by certain degradations, and the latter aims at guiding the diffusion model to generate the corresponding clean image. With the motivations, we propose a zero-shot framework for all-in-one image restoration, termed ZeroAIR, which alternatively performs the test-time degradation modeling (TDM) and the three-stage diffusion guidance (TDG) at each timestep of the reverse sampling. To be specific, TDM exploits the diffusion priors to learn a degradation model from a given degraded image, and TDG divides the timesteps into three stages for taking full advantage of the varying diffusion priors. Thanks to their degradation-agnostic property, the all-in-one image restoration could be achieved in a zero-shot way by ZeroAIR. Through extensive experiments, we show that our ZeroAIR achieves comparable even better performance than those task-specific methods. The code will be available on Github.
Authors: Jeremy Irvin, Lucas Tao, Joanne Zhou, Yuntao Ma, Langston Nashold, Benjamin Liu, Andrew Y. Ng
Large, self-supervised vision models have led to substantial advancements for automatically interpreting natural images. Recent works have begun tailoring these methods to remote sensing data which has rich structure with multi-sensor, multi-spectral, and temporal information providing massive amounts of self-labeled data that can be used for self-supervised pre-training. In this work, we develop a new encoder architecture called USat that can input multi-spectral data from multiple sensors for self-supervised pre-training. USat is a vision transformer with modified patch projection layers and positional encodings to model spectral bands with varying spatial scales from multiple sensors. We integrate USat into a Masked Autoencoder (MAE) self-supervised pre-training procedure and find that a pre-trained USat outperforms state-of-the-art self-supervised MAE models trained on remote sensing data on multiple remote sensing benchmark datasets (up to 8%) and leads to improvements in low data regimes (up to 7%). Code and pre-trained weights are available at https://github.com/stanfordmlgroup/USat .
Authors: Maya Srikanth, Jeremy Irvin, Brian Wesley Hill, Felipe Godoy, Ishan Sabane, Andrew Y. Ng
Major advancements in computer vision can primarily be attributed to the use of labeled datasets. However, acquiring labels for datasets often results in errors which can harm model performance. Recent works have proposed methods to automatically identify mislabeled images, but developing strategies to effectively implement them in real world datasets has been sparsely explored. Towards improved data-centric methods for cleaning real world vision datasets, we first conduct more than 200 experiments carefully benchmarking recently developed automated mislabel detection methods on multiple datasets under a variety of synthetic and real noise settings with varying noise levels. We compare these methods to a Simple and Efficient Mislabel Detector (SEMD) that we craft, and find that SEMD performs similarly to or outperforms prior mislabel detection approaches. We then apply SEMD to multiple real world computer vision datasets and test how dataset size, mislabel removal strategy, and mislabel removal amount further affect model performance after retraining on the cleaned data. With careful design of the approach, we find that mislabel removal leads per-class performance improvements of up to 8% of a retrained classifier in smaller data regimes.
Authors: Peng Wang, Yichun Shi
We introduce "ImageDream," an innovative image-prompt, multi-view diffusion model for 3D object generation. ImageDream stands out for its ability to produce 3D models of higher quality compared to existing state-of-the-art, image-conditioned methods. Our approach utilizes a canonical camera coordination for the objects in images, improving visual geometry accuracy. The model is designed with various levels of control at each block inside the diffusion model based on the input image, where global control shapes the overall object layout and local control fine-tunes the image details. The effectiveness of ImageDream is demonstrated through extensive evaluations using a standard prompt list. For more information, visit our project page at https://Image-Dream.github.io.
Authors: Gopal Sharma, Daniel Rebain, Kwang Moo Yi, Andrea Tagliasacchi
We propose a novel Neural Radiance Field (NeRF) representation for non-opaque scenes that allows fast inference by utilizing textured polygons. Despite the high-quality novel view rendering that NeRF provides, a critical limitation is that it relies on volume rendering that can be computationally expensive and does not utilize the advancements in modern graphics hardware. Existing methods for this problem fall short when it comes to modelling volumetric effects as they rely purely on surface rendering. We thus propose to model the scene with polygons, which can then be used to obtain the quadrature points required to model volumetric effects, and also their opacity and colour from the texture. To obtain such polygonal mesh, we train a specialized field whose zero-crossings would correspond to the quadrature points when volume rendering, and perform marching cubes on this field. We then rasterize the polygons and utilize the fragment shaders to obtain the final colour image. Our method allows rendering on various devices and easy integration with existing graphics frameworks while keeping the benefits of volume rendering alive.
Authors: Neha Kalibhat, Warren Morningstar, Alex Bijamov, Luyang Liu, Karan Singhal, Philip Mansfield
Self-Supervised Learning (SSL) enables training performant models using limited labeled data. One of the pillars underlying vision SSL is the use of data augmentations/perturbations of the input which do not significantly alter its semantic content. For audio and other temporal signals, augmentations are commonly used alongside format transforms such as Fourier transforms or wavelet transforms. Unlike augmentations, format transforms do not change the information contained in the data; rather, they express the same information in different coordinates. In this paper, we study the effects of format transforms and augmentations both separately and together on vision SSL. We define augmentations in frequency space called Fourier Domain Augmentations (FDA) and show that training SSL models on a combination of these and image augmentations can improve the downstream classification accuracy by up to 1.3% on ImageNet-1K. We also show improvements against SSL baselines in few-shot and transfer learning setups using FDA. Surprisingly, we also observe that format transforms can improve the quality of learned representations even without augmentations; however, the combination of the two techniques yields better quality.
Authors: Xiaojun Jia, Jindong Gu, Yihao Huang, Simeng Qin, Qing Guo, Yang Liu, Xiaochun Cao
Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferability of adversarial examples on semantic segmentation has been largely overlooked. In this paper, we propose an effective two-stage adversarial attack strategy to improve the transferability of adversarial examples on semantic segmentation, dubbed TranSegPGD. Specifically, at the first stage, every pixel in an input image is divided into different branches based on its adversarial property. Different branches are assigned different weights for optimization to improve the adversarial performance of all pixels.We assign high weights to the loss of the hard-to-attack pixels to misclassify all pixels. At the second stage, the pixels are divided into different branches based on their transferable property which is dependent on Kullback-Leibler divergence. Different branches are assigned different weights for optimization to improve the transferability of the adversarial examples. We assign high weights to the loss of the high-transferability pixels to improve the transferability of adversarial examples. Extensive experiments with various segmentation models are conducted on PASCAL VOC 2012 and Cityscapes datasets to demonstrate the effectiveness of the proposed method. The proposed adversarial attack method can achieve state-of-the-art performance.
Authors: Kangcheng Liu
Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level understanding tasks, especially when labels are extremely limited. This work presents a general and simple framework to tackle point clouds understanding when labels are limited. We propose a novel unsupervised region expansion based clustering method for generating clusters. More importantly, we innovatively propose to learn to merge the over-divided clusters based on the local low-level geometric property similarities and the learned high-level feature similarities supervised by weak labels. Hence, the true weak labels guide pseudo labels merging taking both geometric and semantic feature correlations into consideration. Finally, the self-supervised reconstruction and data augmentation optimization modules are proposed to guide the propagation of labels among semantically similar points within a scene. Experimental Results demonstrate that our framework has the best performance among the three most important weakly supervised point clouds understanding tasks including semantic segmentation, instance segmentation, and object detection even when limited points are labeled, under the data-efficient settings for the large-scale 3D semantic scene parsing. The developed techniques have postentials to be applied to downstream tasks for better representations in robotic manipulation and robotic autonomous navigation. Codes and models are publicly available at: https://github.com/KangchengLiu.
Authors: Fan Yang, Tianyi Chen, Xiaosheng He, Zhongang Cai, Lei Yang, Si Wu, Guosheng Lin
Editable 3D-aware generation, which supports user-interacted editing, has witnessed rapid development recently. However, existing editable 3D GANs either fail to achieve high-accuracy local editing or suffer from huge computational costs. We propose AttriHuman-3D, an editable 3D human generation model, which address the aforementioned problems with attribute decomposition and indexing. The core idea of the proposed model is to generate all attributes (e.g. human body, hair, clothes and so on) in an overall attribute space with six feature planes, which are then decomposed and manipulated with different attribute indexes. To precisely extract features of different attributes from the generated feature planes, we propose a novel attribute indexing method as well as an orthogonal projection regularization to enhance the disentanglement. We also introduce a hyper-latent training strategy and an attribute-specific sampling strategy to avoid style entanglement and misleading punishment from the discriminator. Our method allows users to interactively edit selected attributes in the generated 3D human avatars while keeping others fixed. Both qualitative and quantitative experiments demonstrate that our model provides a strong disentanglement between different attributes, allows fine-grained image editing and generates high-quality 3D human avatars.
Authors: Gabriel L. Asher, Bassem I. Zaki, Gregory A. Russo, Gobind S. Gill, Charles R. Thomas, Temiloluwa O. Prioleau, Rongxiao Zhang, Brady Hunt
Purpose: This study assesses the effectiveness of Deep Learning (DL) for creating synthetic CT (sCT) images in MR-guided adaptive radiation therapy (MRgART).
Methods: A Cycle-GAN model was trained with MRI and CT scan slices from MR-LINAC treatments, generating sCT volumes. The analysis involved retrospective treatment plan data from patients with various tumors. sCT images were compared with standard CT scans using mean absolute error in Hounsfield Units (HU) and image similarity metrics (SSIM, PSNR, NCC). sCT volumes were integrated into a clinical treatment system for dosimetric re-evaluation.
Results: The model, trained on 8405 frames from 57 patients and tested on 357 sCT frames from 17 patients, showed sCTs comparable to dCTs in electron density and structural similarity with MRI scans. The MAE between sCT and dCT was 49.2 +/- 13.2 HU, with sCT NCC exceeding dCT by 0.06, and SSIM and PSNR at 0.97 +/- 0.01 and 19.9 +/- 1.6 respectively. Dosimetric evaluations indicated minimal differences between sCTs and dCTs, with sCTs showing better air-bubble reconstruction.
Conclusions: DL-based sCT generation on MR-Linacs is accurate for dose calculation and optimization in MRgART. This could facilitate MR-only treatment planning, enhancing simulation and adaptive planning efficiency on MR-Linacs.
Authors: Jin Liu, Huaibo Huang, Chao Jin, Ran He
Face stylization refers to the transformation of a face into a specific portrait style. However, current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models so that they demand lots of time and storage space and fail to achieve detailed style transformation. This paper proposes a training-free face stylization framework, named Portrait Diffusion. This framework leverages off-the-shelf text-to-image diffusion models, eliminating the need for fine-tuning specific examples. Specifically, the content and style images are first inverted into latent codes. Then, during image reconstruction using the corresponding latent code, the content and style features in the attention space are delicately blended through a modified self-attention operation called Style Attention Control. Additionally, a Chain-of-Painting method is proposed for the gradual redrawing of unsatisfactory areas from rough adjustments to fine-tuning. Extensive experiments validate the effectiveness of our Portrait Diffusion method and demonstrate the superiority of Chain-of-Painting in achieving precise face stylization. Code will be released at \url{https://github.com/liujin112/PortraitDiffusion}.
Authors: Jun Xiang, Xuan Gao, Yudong Guo, Juyong Zhang
We propose FlashAvatar, a novel and lightweight 3D animatable avatar representation that could reconstruct a digital avatar from a short monocular video sequence in minutes and render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU. To achieve this, we maintain a uniform 3D Gaussian field embedded in the surface of a parametric face model and learn extra spatial offset to model non-surface regions and subtle facial details. While full use of geometric priors can capture high-frequency facial details and preserve exaggerated expressions, proper initialization can help reduce the number of Gaussians, thus enabling super-fast rendering speed. Extensive experimental results demonstrate that FlashAvatar outperforms existing works regarding visual quality and personalized details and is almost an order of magnitude faster in rendering speed. Project page: https://ustc3dv.github.io/FlashAvatar/
Authors: Yufan Deng, Ruida Wang, Yuhao Zhang, Yu-Wing Tai, Chi-Keung Tang
Editing visual content on videos remains a formidable challenge with two main issues: 1) direct and easy user control to produce 2) natural editing results without unsightly distortion and artifacts after changing shape, expression and layout. Inspired by DragGAN, a recent image-based drag-style editing technique, we address above issues by proposing DragVideo, where a similar drag-style user interaction is adopted to edit video content while maintaining temporal consistency. Empowered by recent diffusion models as in DragDiffusion, DragVideo contains the novel Drag-on-Video U-Net (DoVe) editing method, which optimizes diffused video latents generated by video U-Net to achieve the desired control. Specifically, we use Sample-specific LoRA fine-tuning and Mutual Self-Attention control to ensure faithful reconstruction of video from the DoVe method. We also present a series of testing examples for drag-style video editing and conduct extensive experiments across a wide array of challenging editing tasks, such as motion editing, skeleton editing, etc, underscoring DragVideo's versatility and generality. Our codes including the DragVideo web user interface will be released.
Authors: Adrian Azzarelli, Nantheera Anantrasirichai, David R Bull
Dynamic Neural Radiance Fields (Dynamic NeRF) enhance NeRF technology to model moving scenes. However, they are resource intensive and challenging to compress. To address this issue, this paper presents WavePlanes, a fast and more compact explicit model. We propose a multi-scale space and space-time feature plane representation using N-level 2-D wavelet coefficients. The inverse discrete wavelet transform reconstructs N feature signals at varying detail, which are linearly decoded to approximate the color and density of volumes in a 4-D grid. Exploiting the sparsity of wavelet coefficients, we compress a Hash Map containing only non-zero coefficients and their locations on each plane. This results in a compressed model size of ~12 MB. Compared with state-of-the-art plane-based models, WavePlanes is up to 15x smaller, less computationally demanding and achieves comparable results in as little as one hour of training - without requiring custom CUDA code or high performance computing resources. Additionally, we propose new feature fusion schemes that work as well as previously proposed schemes while providing greater interpretability. Our code is available at: https://github.com/azzarelli/waveplanes/
Authors: Andrés Villa, Juan Carlos León Alcázar, Alvaro Soto, Bernard Ghanem
Large Vision and Language Models have enabled significant advances in fully supervised and zero-shot vision tasks. These large pre-trained architectures serve as the baseline to what is currently known as Instruction Tuning Large Vision and Language models (IT-LVLMs). IT-LVLMs are general-purpose multi-modal assistants whose responses are modulated by natural language instructions and arbitrary visual data. Despite this versatility, IT-LVLM effectiveness in fundamental computer vision problems remains unclear, primarily due to the absence of a standardized evaluation benchmark. This paper introduces a Multi-modal Evaluation Benchmark named MERLIM, a scalable test-bed to assess the performance of IT-LVLMs on fundamental computer vision tasks. MERLIM contains over 279K image-question pairs, and has a strong focus on detecting cross-modal "hallucination" events in IT-LVLMs, where the language output refers to visual concepts that lack any effective grounding in the image. Our results show that state-of-the-art IT-LVMLs are still limited at identifying fine-grained visual concepts, object hallucinations are common across tasks, and their results are strongly biased by small variations in the input query, even if the queries have the very same semantics. Our findings also suggest that these models have weak visual groundings but they can still make adequate guesses by global visual patterns or textual biases contained in the LLM component.
Authors: Amit Baras, Alon Zolfi, Yuval Elovici, Asaf Shabtai
In recent years, there has been a significant trend in deep neural networks (DNNs), particularly transformer-based models, of developing ever-larger and more capable models. While they demonstrate state-of-the-art performance, their growing scale requires increased computational resources (e.g., GPUs with greater memory capacity). To address this problem, quantization techniques (i.e., low-bit-precision representation and matrix multiplication) have been proposed. Most quantization techniques employ a static strategy in which the model parameters are quantized, either during training or inference, without considering the test-time sample. In contrast, dynamic quantization techniques, which have become increasingly popular, adapt during inference based on the input provided, while maintaining full-precision performance. However, their dynamic behavior and average-case performance assumption makes them vulnerable to a novel threat vector -- adversarial attacks that target the model's efficiency and availability. In this paper, we present QuantAttack, a novel attack that targets the availability of quantized models, slowing down the inference, and increasing memory usage and energy consumption. We show that carefully crafted adversarial examples, which are designed to exhaust the resources of the operating system, can trigger worst-case performance. In our experiments, we demonstrate the effectiveness of our attack on vision transformers on a wide range of tasks, both uni-modal and multi-modal. We also examine the effect of different attack variants (e.g., a universal perturbation) and the transferability between different models.
Authors: Yizhi Wang, Wallace Lira, Wenqi Wang, Ali Mahdavi-Amiri, Hao Zhang
We introduce multi-slice reasoning, a new notion for single-view 3D reconstruction which challenges the current and prevailing belief that multi-view synthesis is the most natural conduit between single-view and 3D. Our key observation is that object slicing is more advantageous than altering views to reveal occluded structures. Specifically, slicing is more occlusion-revealing since it can peel through any occluders without obstruction. In the limit, i.e., with infinitely many slices, it is guaranteed to unveil all hidden object parts. We realize our idea by developing Slice3D, a novel method for single-view 3D reconstruction which first predicts multi-slice images from a single RGB image and then integrates the slices into a 3D model using a coordinate-based transformer network for signed distance prediction. The slice images can be regressed or generated, both through a U-Net based network. For the former, we inject a learnable slice indicator code to designate each decoded image into a spatial slice location, while the slice generator is a denoising diffusion model operating on the entirety of slice images stacked on the input channels. We conduct extensive evaluation against state-of-the-art alternatives to demonstrate superiority of our method, especially in recovering complex and severely occluded shape structures, amid ambiguities. All Slice3D results were produced by networks trained on a single Nvidia A40 GPU, with an inference time less than 20 seconds.
Authors: Xiaochen Zhao, Jingxiang Sun, Lizhen Wang, Yebin Liu
While high fidelity and efficiency are central to the creation of digital head avatars, recent methods relying on 2D or 3D generative models often experience limitations such as shape distortion, expression inaccuracy, and identity flickering. Additionally, existing one-shot inversion techniques fail to fully leverage multiple input images for detailed feature extraction. We propose a novel framework, \textbf{Incremental 3D GAN Inversion}, that enhances avatar reconstruction performance using an algorithm designed to increase the fidelity from multiple frames, resulting in improved reconstruction quality proportional to frame count. Our method introduces a unique animatable 3D GAN prior with two crucial modifications for enhanced expression controllability alongside an innovative neural texture encoder that categorizes texture feature spaces based on UV parameterization. Differentiating from traditional techniques, our architecture emphasizes pixel-aligned image-to-image translation, mitigating the need to learn correspondences between observation and canonical spaces. Furthermore, we incorporate ConvGRU-based recurrent networks for temporal data aggregation from multiple frames, boosting geometry and texture detail reconstruction. The proposed paradigm demonstrates state-of-the-art performance on one-shot and few-shot avatar animation tasks.
Authors: Xiao Guo, Vishal Asnani, Sijia Liu, Xiaoming Liu
Model Parsing defines the research task of predicting hyperparameters of the generative model (GM), given a generated image as input. Since a diverse set of hyperparameters is jointly employed by the generative model, and dependencies often exist among them, it is crucial to learn these hyperparameter dependencies for the improved model parsing performance. To explore such important dependencies, we propose a novel model parsing method called Learnable Graph Pooling Network (LGPN). Specifically, we transform model parsing into a graph node classification task, using graph nodes and edges to represent hyperparameters and their dependencies, respectively. Furthermore, LGPN incorporates a learnable pooling-unpooling mechanism tailored to model parsing, which adaptively learns hyperparameter dependencies of GMs used to generate the input image. We also extend our proposed method to CNN-generated image detection and coordinate attacks detection. Empirically, we achieve state-of-the-art results in model parsing and its extended applications, showing the effectiveness of our method. Our source code are available.
Authors: Alessandro Farace di Villaforesta, Lucie Charlotte Magister, Pietro Barbiero, Pietro Liò
To address the challenge of the ``black-box" nature of deep learning in medical settings, we combine GCExplainer - an automated concept discovery solution - along with Logic Explained Networks to provide global explanations for Graph Neural Networks. We demonstrate this using a generally applicable graph construction and classification pipeline, involving panoptic segmentation with HoVer-Net and cancer prediction with Graph Convolution Networks. By training on H&E slides of breast cancer, we show promising results in offering explainable and trustworthy AI tools for clinicians.
Authors: Chengyou Jia, Minnan Luo, Xiaojun Chang, Zhuohang Dang, Mingfei Han, Mengmeng Wang, Guang Dai, Sizhe Dang, Jingdong Wang
Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing methods typically adapt pretrained image-text models to the video domain, capitalizing on their inherent strengths in generalization. A common thread among such methods is the augmentation of visual embeddings with temporal information to improve the recognition of seen actions. Yet, they compromise with standard less-informative action descriptions, thus faltering when confronted with novel actions. Drawing inspiration from human cognitive processes, we argue that augmenting text embeddings with human prior knowledge is pivotal for open-vocabulary video action recognition. To realize this, we innovatively blend video models with Large Language Models (LLMs) to devise Action-conditioned Prompts. Specifically, we harness the knowledge in LLMs to produce a set of descriptive sentences that contain distinctive features for identifying given actions. Building upon this foundation, we further introduce a multi-modal action knowledge alignment mechanism to align concepts in video and textual knowledge encapsulated within the prompts. Extensive experiments on various video benchmarks, including zero-shot, few-shot, and base-to-novel generalization settings, demonstrate that our method not only sets new SOTA performance but also possesses excellent interpretability.
Authors: Zhongwei Ren, Zhicheng Huang, Yunchao Wei, Yao Zhao, Dongmei Fu, Jiashi Feng, Xiaojie Jin
While large multimodal models (LMMs) have achieved remarkable progress, generating pixel-level masks for image reasoning tasks involving multiple open-world targets remains a challenge. To bridge this gap, we introduce PixelLM, an effective and efficient LMM for pixel-level reasoning and understanding. Central to PixelLM is a novel, lightweight pixel decoder and a comprehensive segmentation codebook. The decoder efficiently produces masks from the hidden embeddings of the codebook tokens, which encode detailed target-relevant information. With this design, PixelLM harmonizes with the structure of popular LMMs and avoids the need for additional costly segmentation models. Furthermore, we propose a target refinement loss to enhance the model's ability to differentiate between multiple targets, leading to substantially improved mask quality. To advance research in this area, we construct MUSE, a high-quality multi-target reasoning segmentation benchmark. PixelLM excels across various pixel-level image reasoning and understanding tasks, outperforming well-established methods in multiple benchmarks, including MUSE, single- and multi-referring segmentation. Comprehensive ablations confirm the efficacy of each proposed component. All code, models, and datasets will be publicly available.
Authors: Caoyuan Ma, Yu-Lun Liu, Zhixiang Wang, Wu Liu, Xinchen Liu, Zheng Wang
We present HumanNeRF-SE, which can synthesize diverse novel pose images with simple input. Previous HumanNeRF studies require large neural networks to fit the human appearance and prior knowledge. Subsequent methods build upon this approach with some improvements. Instead, we reconstruct this approach, combining explicit and implicit human representations with both general and specific mapping processes. Our key insight is that explicit shape can filter the information used to fit implicit representation, and frozen general mapping combined with point-specific mapping can effectively avoid overfitting and improve pose generalization performance. Our explicit and implicit human represent combination architecture is extremely effective. This is reflected in our model's ability to synthesize images under arbitrary poses with few-shot input and increase the speed of synthesizing images by 15 times through a reduction in computational complexity without using any existing acceleration modules. Compared to the state-of-the-art HumanNeRF studies, HumanNeRF-SE achieves better performance with fewer learnable parameters and less training time (see Figure 1).
Authors: Ling Yang, Zhanyu Wang, Luping Zhou
Despite the success of Large Language Models (LLMs) in general image tasks, a gap persists in the medical field for a multimodal large model adept at handling the nuanced diversity of medical images. Addressing this, we propose MedXChat, a unified multimodal large model designed for seamless interactions between medical assistants and users. MedXChat encompasses three key functionalities: CXR(Chest X-ray)-to-Report generation, CXR-based visual question-answering (VQA), and Text-to-CXR synthesis. Our contributions are as follows. Firstly, our model showcases exceptional cross-task adaptability, displaying adeptness across all three defined tasks and outperforming the benchmark models on the MIMIC dataset in medical multimodal applications. Secondly, we introduce an innovative Text-to-CXR synthesis approach that utilizes instruction-following capabilities within the Stable Diffusion (SD) architecture. This technique integrates smoothly with the existing model framework, requiring no extra parameters, thereby maintaining the SD's generative strength while also bestowing upon it the capacity to render fine-grained medical images with high fidelity. Comprehensive experiments validate MedXChat's synergistic enhancement across all tasks. Our instruction data and model will be open-sourced.
Authors: Jiakai Zhang, Qihe Chen, Yan Zeng, Wenyuan Gao, Xuming He, Zhijie Liu, Jingyi Yu
In the past decade, deep conditional generative models have revolutionized the generation of realistic images, extending their application from entertainment to scientific domains. Single-particle cryo-electron microscopy (cryo-EM) is crucial in resolving near-atomic resolution 3D structures of proteins, such as the SARS-COV-2 spike protein. To achieve high-resolution reconstruction, AI models for particle picking and pose estimation have been adopted. However, their performance is still limited as they lack high-quality annotated datasets. To address this, we introduce physics-informed generative cryo-electron microscopy (GenEM), which for the first time integrates physical-based cryo-EM simulation with a generative unpaired noise translation to generate physically correct synthetic cryo-EM datasets with realistic noises. Initially, GenEM simulates the cryo-EM imaging process based on a virtual specimen. To generate realistic noises, we leverage an unpaired noise translation via contrastive learning with a novel mask-guided sampling scheme. Extensive experiments show that GenEM is capable of generating realistic cryo-EM images. The generated dataset can further enhance particle picking and pose estimation models, eventually improving the reconstruction resolution. We will release our code and annotated synthetic datasets.
Authors: Guanlin Li, Naishan Zheng, Man Zhou, Jie Zhang, Tianwei Zhang
Adversarial examples are one of the most severe threats to deep learning models. Numerous works have been proposed to study and defend adversarial examples. However, these works lack analysis of adversarial information or perturbation, which cannot reveal the mystery of adversarial examples and lose proper interpretation. In this paper, we aim to fill this gap by studying adversarial information as unstructured noise, which does not have a clear pattern. Specifically, we provide some empirical studies with singular value decomposition, by decomposing images into several matrices, to analyze adversarial information for different attacks. Based on the analysis, we propose a new module to regularize adversarial information and combine information bottleneck theory, which is proposed to theoretically restrict intermediate representations. Therefore, our method is interpretable. Moreover, the fashion of our design is a novel principle that is general and unified. Equipped with our new module, we evaluate two popular model structures on two mainstream datasets with various adversarial attacks. The results indicate that the improvement in robust accuracy is significant. On the other hand, we prove that our method is efficient with only a few additional parameters and able to be explained under regional faithfulness analysis.
Authors: Lingmin Ran, Xiaodong Cun, JiaWei Liu, Rui Zhao, Song Zijie, Xintao Wang, Jussi Keppo, Mike Zheng Shou
We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X-Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model.
Authors: Aniruddh Sikdar, Jayant Teotia, Suresh Sundaram
Improving the performance of semantic segmentation models using multispectral information is crucial, especially for environments with low-light and adverse conditions. Multi-modal fusion techniques pursue either the learning of cross-modality features to generate a fused image or engage in knowledge distillation but address multimodal and missing modality scenarios as distinct issues, which is not an optimal approach for multi-sensor models. To address this, a novel multi-modal fusion approach called CSK-Net is proposed, which uses a contrastive learning-based spectral knowledge distillation technique along with an automatic mixed feature exchange mechanism for semantic segmentation in optical (EO) and infrared (IR) images. The distillation scheme extracts detailed textures from the optical images and distills them into the optical branch of CSK-Net. The model encoder consists of shared convolution weights with separate batch norm (BN) layers for both modalities, to capture the multi-spectral information from different modalities of the same objects. A Novel Gated Spectral Unit (GSU) and mixed feature exchange strategy are proposed to increase the correlation of modality-shared information and decrease the modality-specific information during the distillation process. Comprehensive experiments show that CSK-Net surpasses state-of-the-art models in multi-modal tasks and for missing modalities when exclusively utilizing IR data for inference across three public benchmarking datasets. For missing modality scenarios, the performance increase is achieved without additional computational costs compared to the baseline segmentation models.
Authors: Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi
Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs). Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking the inherent and expressible point cloud geometric structure. Geometrically similar or close regions can be exploited for bolstering point cloud understanding as they are likely to share semantic information. To this end, we introduce the first training-free aggregation technique that leverages the point cloud's 3D geometric structure to improve the quality of the transferred Vision-Language Models. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. We benchmark our approach on three downstream tasks, including classification, part segmentation, and semantic segmentation, with a variety of datasets representing both synthetic/real-world, and indoor/outdoor scenarios. Our approach achieves new state-of-the-art results in all benchmarks. We will release the source code publicly.
Authors: Gabriel della Maggiora, Luis Alberto Croquevielle, Nikita Desphande, Harry Horsley, Thomas Heinis, Artur Yakimovich
Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic solutions and their good mathematical properties. Despite their success, an important drawback of diffusion models is their sensitivity to the choice of variance schedule, which controls the dynamics of the diffusion process. Fine-tuning this schedule for specific applications is crucial but time-costly and does not guarantee an optimal result. We propose a novel approach for learning the schedule as part of the training process. Our method supports probabilistic conditioning on data, provides high-quality solutions, and is flexible, proving able to adapt to different applications with minimum overhead. This approach is tested in two unrelated inverse problems: super-resolution microscopy and quantitative phase imaging, yielding comparable or superior results to previous methods and fine-tuned diffusion models. We conclude that fine-tuning the schedule by experimentation should be avoided because it can be learned during training in a stable way that yields better results.
Authors: Razvan Caramalau, Binod Bhattarai, Danail Stoyanov
In this paper, we introduce Active Learning framework in Federated Learning for Target Domain Generalisation, harnessing the strength from both learning paradigms. Our framework, FEDALV, composed of Active Learning (AL) and Federated Domain Generalisation (FDG), enables generalisation of an image classification model trained from limited source domain client's data without sharing images to an unseen target domain. To this end, our FDG, FEDA, consists of two optimisation updates during training, one at the client and another at the server level. For the client, the introduced losses aim to reduce feature complexity and condition alignment, while in the server, the regularisation limits free energy biases between source and target obtained by the global model. The remaining component of FEDAL is AL with variable budgets, which queries the server to retrieve and sample the most informative local data for the targeted client. We performed multiple experiments on FDG w/ and w/o AL and compared with both conventional FDG baselines and Federated Active Learning baselines. Our extensive quantitative experiments demonstrate the superiority of our method in accuracy and efficiency compared to the multiple contemporary methods. FEDALV manages to obtain the performance of the full training target accuracy while sampling as little as 5% of the source client's data.
Authors: Jiaxin Ge, Sanjay Subramanian, Baifeng Shi, Roei Herzig, Trevor Darrell
Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.
Authors: Xiaoqian Shen, Mohamed Elhoseiny
Recent generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts. Nevertheless, a significant challenge remains in applying these models for the more intricate task of story visualization. Since it requires resolving pronouns (he, she, they) in the frame descriptions, i.e., anaphora resolution, and ensuring consistent characters and background synthesis across frames. Yet, the emerging Large Language Model (LLM) showcases robust reasoning abilities to navigate through ambiguous references and process extensive sequences. Therefore, we introduce \textbf{StoryGPT-V}, which leverages the merits of the latent diffusion (LDM) and LLM to produce images with consistent and high-quality characters grounded on given story descriptions. First, we train a character-aware LDM, which takes character-augmented semantic embedding as input and includes the supervision of the cross-attention map using character segmentation masks, aiming to enhance character generation accuracy and faithfulness. In the second stage, we enable an alignment between the output of LLM and the character-augmented embedding residing in the input space of the first-stage model. This harnesses the reasoning ability of LLM to address ambiguous references and the comprehension capability to memorize the context. We conduct comprehensive experiments on two visual story visualization benchmarks. Our model reports superior quantitative results and consistently generates accurate characters of remarkable quality with low memory consumption. Our code will be made publicly available.
Authors: Zhuoran Yu, Chenchen Zhu, Sean Culatana, Raghuraman Krishnamoorthi, Fanyi Xiao, Yong Jae Lee
Recent advances in generative deep learning have enabled the creation of high-quality synthetic images in text-to-image generation. Prior work shows that fine-tuning a pretrained diffusion model on ImageNet and generating synthetic training images from the finetuned model can enhance an ImageNet classifier's performance. However, performance degrades as synthetic images outnumber real ones. In this paper, we explore whether generative fine-tuning is essential for this improvement and whether it is possible to further scale up training using more synthetic data. We present a new framework leveraging off-the-shelf generative models to generate synthetic training images, addressing multiple challenges: class name ambiguity, lack of diversity in naive prompts, and domain shifts. Specifically, we leverage large language models (LLMs) and CLIP to resolve class name ambiguity. To diversify images, we propose contextualized diversification (CD) and stylized diversification (SD) methods, also prompted by LLMs. Finally, to mitigate domain shifts, we leverage domain adaptation techniques with auxiliary batch normalization for synthetic images. Our framework consistently enhances recognition model performance with more synthetic data, up to 6x of original ImageNet size showcasing the potential of synthetic data for improved recognition models and strong out-of-domain generalization.
Authors: Felix Tristram, Stefano Gasperini, Federico Tombari, Nassir Navab, Benjamin Busam
Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesis capabilities even in large-scale, unbounded scenes, albeit requiring hundreds of views or introducing artifacts in sparser settings. Their optimization suffers from shape-radiance ambiguities wherever only a small visual overlap is available. This leads to erroneous scene geometry and artifacts. In this paper, we propose Re-Nerfing, a simple and general multi-stage approach that leverages NeRF's own view synthesis to address these limitations. With Re-Nerfing, we increase the scene's coverage and enhance the geometric consistency of novel views as follows: First, we train a NeRF with the available views. Then, we use the optimized NeRF to synthesize pseudo-views next to the original ones to simulate a stereo or trifocal setup. Finally, we train a second NeRF with both original and pseudo views while enforcing structural, epipolar constraints via the newly synthesized images. Extensive experiments on the mip-NeRF 360 dataset show the effectiveness of Re-Nerfing across denser and sparser input scenarios, bringing improvements to the state-of-the-art Zip-NeRF, even when trained with all views.
Authors: Wenyang Zhou, Zhiyang Dou, Zeyu Cao, Zhouyingcheng Liao, Jingbo Wang, Wenjia Wang, Yuan Liu, Taku Komura, Wenping Wang, Lingjie Liu
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Although previous motion diffusion models have shown impressive results, they struggle to achieve fast generation while maintaining high-quality human motions. Motion latent diffusion has been proposed for efficient motion generation. However, effectively learning a latent space can be non-trivial in such a two-stage manner. Meanwhile, accelerating motion sampling by increasing the step size, e.g., DDIM, typically leads to a decline in motion quality due to the inapproximation of complex data distributions when naively increasing the step size. In this paper, we propose EMDM that allows for much fewer sample steps for fast motion generation by modeling the complex denoising distribution during multiple sampling steps. Specifically, we develop a Conditional Denoising Diffusion GAN to capture multimodal data distributions conditioned on both control signals, i.e., textual description and denoising time step. By modeling the complex data distribution, a larger sampling step size and fewer steps are achieved during motion synthesis, significantly accelerating the generation process. To effectively capture the human dynamics and reduce undesired artifacts, we employ motion geometric loss during network training, which improves the motion quality and training efficiency. As a result, EMDM achieves a remarkable speed-up at the generation stage while maintaining high-quality motion generation in terms of fidelity and diversity.
Authors: Zhenyu Li, Shariq Farooq Bhat, Peter Wonka
Single image depth estimation is a foundational task in computer vision and generative modeling. However, prevailing depth estimation models grapple with accommodating the increasing resolutions commonplace in today's consumer cameras and devices. Existing high-resolution strategies show promise, but they often face limitations, ranging from error propagation to the loss of high-frequency details. We present PatchFusion, a novel tile-based framework with three key components to improve the current state of the art: (1) A patch-wise fusion network that fuses a globally-consistent coarse prediction with finer, inconsistent tiled predictions via high-level feature guidance, (2) A Global-to-Local (G2L) module that adds vital context to the fusion network, discarding the need for patch selection heuristics, and (3) A Consistency-Aware Training (CAT) and Inference (CAI) approach, emphasizing patch overlap consistency and thereby eradicating the necessity for post-processing. Experiments on UnrealStereo4K, MVS-Synth, and Middleburry 2014 demonstrate that our framework can generate high-resolution depth maps with intricate details. PatchFusion is independent of the base model for depth estimation. Notably, our framework built on top of SOTA ZoeDepth brings improvements for a total of 17.3% and 29.4% in terms of the root mean squared error (RMSE) on UnrealStereo4K and MVS-Synth, respectively.
Authors: Ayush Gupta, Rama Chellappa
While gait recognition has seen many advances in recent years, the occlusion problem has largely been ignored. This problem is especially important for gait recognition from uncontrolled outdoor sequences at range - since any small obstruction can affect the recognition system. Most current methods assume the availability of complete body information while extracting the gait features. When parts of the body are occluded, these methods may hallucinate and output a corrupted gait signature as they try to look for body parts which are not present in the input at all. To address this, we exploit the learned occlusion type while extracting identity features from videos. Thus, in this work, we propose an occlusion aware gait recognition method which can be used to model intrinsic occlusion awareness into potentially any state-of-the-art gait recognition method. Our experiments on the challenging GREW and BRIAR datasets show that networks enhanced with this occlusion awareness perform better at recognition tasks than their counterparts trained on similar occlusions.
Authors: Jiaxin Gao, Qinglong Cao, Yuntian Chen
Automatic Modulation Classification (AMC) plays a vital role in time series analysis, such as signal classification and identification within wireless communications. Deep learning-based AMC models have demonstrated significant potential in this domain. However, current AMC models inadequately consider the disparities in handling signals under conditions of low and high Signal-to-Noise Ratio (SNR), resulting in an unevenness in their performance. In this study, we propose MoE-AMC, a novel Mixture-of-Experts (MoE) based model specifically crafted to address AMC in a well-balanced manner across varying SNR conditions. Utilizing the MoE framework, MoE-AMC seamlessly combines the strengths of LSRM (a Transformer-based model) for handling low SNR signals and HSRM (a ResNet-based model) for high SNR signals. This integration empowers MoE-AMC to achieve leading performance in modulation classification, showcasing its efficacy in capturing distinctive signal features under diverse SNR scenarios. We conducted experiments using the RML2018.01a dataset, where MoE-AMC achieved an average classification accuracy of 71.76% across different SNR levels, surpassing the performance of previous SOTA models by nearly 10%. This study represents a pioneering application of MoE techniques in the realm of AMC, offering a promising avenue for elevating signal classification accuracy within wireless communication systems.
Authors: Yizhou Wang, Ruiyi Zhang, Haoliang Wang, Uttaran Bhattacharya, Yun Fu, Gang Wu
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, the focus of prior research has been predominantly on devising a projection layer that maps video features to tokens, an approach that is both rudimentary and inefficient. In our study, we introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings, which enables a more aligned selection of frames with the given question. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer (abbreviated as VQ-Former), which bolsters the interplay between the input question and the video features. We also discover that incorporating a simple prompt, "Please be critical", into the LLM input can substantially enhance its video comprehension capabilities. Our experimental results indicate that VaQuitA consistently sets a new benchmark for zero-shot video question-answering tasks and is adept at producing high-quality, multi-turn video dialogues with users.
Authors: Lukas Schäfer, Logan Jones, Anssi Kanervisto, Yuhan Cao, Tabish Rashid, Raluca Georgescu, Dave Bignell, Siddhartha Sen, Andrea Treviño Gavito, Sam Devlin
Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community. Recent progress in the research, development and open release of large vision models has the potential to amortize some of these costs across the community. However, it is currently unclear which of these models have learnt representations that retain information critical for sequential decision making. Towards enabling wider participation in the research of gameplaying agents in modern games, we present a systematic study of imitation learning with publicly available visual encoders compared to the typical, task-specific, end-to-end training approach in Minecraft, Minecraft Dungeons and Counter-Strike: Global Offensive.
Authors: Ari Goodman, Glenn Shevach, Sean Zabriskie, Dr. Chris Thajudeen
The cable-based arrestment systems are integral to the launch and recovery of aircraft onboard carriers and on expeditionary land-based installations. These modern arrestment systems rely on various mechanisms to absorb energy from an aircraft during an arrestment cycle to bring the aircraft to a full stop. One of the primary components of this system is the cable interface to the engine. The formation of slack in the cable at this interface can result in reduced efficiency and drives maintenance efforts to remove the slack prior to continued operations. In this paper, a machine vision based slack detection system is presented. A situational awareness camera is utilized to collect video data of the cable interface region, machine vision algorithms are applied to reduce noise, remove background clutter, focus on regions of interest, and detect changes in the image representative of slack formations. Some algorithms employed in this system include bilateral image filters, least squares polynomial fit, Canny Edge Detection, K-Means clustering, Gaussian Mixture-based Background/Foreground Segmentation for background subtraction, Hough Circle Transforms, and Hough line Transforms. The resulting detections are filtered and highlighted to create an indication to the shipboard operator of the presence of slack and a need for a maintenance action. A user interface was designed to provide operators with an easy method to redefine regions of interest and adjust the methods to specific locations. The algorithms were validated on shipboard footage and were able to accurately identify slack with minimal false positives.
Authors: Xiangru Zhu, Penglei Sun, Chengyu Wang, Jingping Liu, Zhixu Li, Yanghua Xiao, Jun Huang
Text-to-image (T2I) synthesis has recently achieved significant advancements. However, challenges remain in the model's compositionality, which is the ability to create new combinations from known components. We introduce Winoground-T2I, a benchmark designed to evaluate the compositionality of T2I models. This benchmark includes 11K complex, high-quality contrastive sentence pairs spanning 20 categories. These contrastive sentence pairs with subtle differences enable fine-grained evaluations of T2I synthesis models. Additionally, to address the inconsistency across different metrics, we propose a strategy that evaluates the reliability of various metrics by using comparative sentence pairs. We use Winoground-T2I with a dual objective: to evaluate the performance of T2I models and the metrics used for their evaluation. Finally, we provide insights into the strengths and weaknesses of these metrics and the capabilities of current T2I models in tackling challenges across a range of complex compositional categories. Our benchmark is publicly available at https://github.com/zhuxiangru/Winoground-T2I .
Authors: Anton Pollak, Rajesh Menon
Image-to-Image translation (I2I) is a subtype of Machine Learning (ML) that has tremendous potential in applications where two domains of images and the need for translation between the two exist, such as the removal of fog. For example, this could be useful for autonomous vehicles, which currently struggle with adverse weather conditions like fog. However, datasets for I2I tasks are not abundant and typically hard to acquire. Here, we introduce STEREOFOG, a dataset comprised of $10,067$ paired fogged and clear images, captured using a custom-built device, with the purpose of exploring I2I's potential in this domain. It is the only real-world dataset of this kind to the best of our knowledge. Furthermore, we apply and optimize the pix2pix I2I ML framework to this dataset. With the final model achieving an average Complex Wavelet-Structural Similarity (CW-SSIM) score of $0.76$, we prove the technique's suitability for the problem.
Authors: Nityanand Mathur, Shyam Marjit, Abhra Chaudhuri, Anjan Dutta
With the goal of understanding the visual concepts that CLIP associates with text prompts, we show that the latent space of CLIP can be visualized solely in terms of linear transformations on simple geometric primitives like circles and straight lines. Although existing approaches achieve this by sketch-synthesis-through-optimization, they do so on the space of B\'ezier curves, which exhibit a wastefully large set of structures that they can evolve into, as most of them are non-essential for generating meaningful sketches. We present CLIPDrawX, an algorithm that provides significantly better visualizations for CLIP text embeddings, using only simple primitive shapes like straight lines and circles. This constrains the set of possible outputs to linear transformations on these primitives, thereby exhibiting an inherently simpler mathematical form. The synthesis process of CLIPDrawX can be tracked end-to-end, with each visual concept being explained exclusively in terms of primitives. Implementation will be released upon acceptance. Project Page: $\href{https://clipdrawx.github.io/}{\text{https://clipdrawx.github.io/}}$.
Authors: Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark
Neural Radiance Fields have achieved remarkable results for novel view synthesis but still lack a crucial component: precise measurement of uncertainty in their predictions. Probabilistic NeRF methods have tried to address this, but their output probabilities are not typically accurately calibrated, and therefore do not capture the true confidence levels of the model. Calibration is a particularly challenging problem in the sparse-view setting, where additional held-out data is unavailable for fitting a calibrator that generalizes to the test distribution. In this paper, we introduce the first method for obtaining calibrated uncertainties from NeRF models. Our method is based on a robust and efficient metric to calculate per-pixel uncertainties from the predictive posterior distribution. We propose two techniques that eliminate the need for held-out data. The first, based on patch sampling, involves training two NeRF models for each scene. The second is a novel meta-calibrator that only requires the training of one NeRF model. Our proposed approach for obtaining calibrated uncertainties achieves state-of-the-art uncertainty in the sparse-view setting while maintaining image quality. We further demonstrate our method's effectiveness in applications such as view enhancement and next-best view selection.
Authors: Weiwei Sun, Eduard Trulls, Yang-Che Tseng, Sneha Sambandam, Gopal Sharma, Andrea Tagliasacchi, Kwang Moo Yi
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 by a significant margin.
Authors: Lennart Brocki, Neo Christopher Chung
Interpretability methods are critical components for examining and exploring deep neural networks (DNN), as well as increasing our understanding of and trust in them. Vision transformers (ViT), which can be trained to state-of-the-art performance with a self-supervised learning (SSL) training method, provide built-in attention maps (AM). While AMs can provide high-quality semantic segmentation of input images, they do not account for any signal coming from a downstream classifier. We introduce class-discriminative attention maps (CDAM), a novel post-hoc explanation method that is highly sensitive to the target class. Our method essentially scales attention scores by how relevant the corresponding tokens are for the predictions of a classifier head. Alternative to classifier outputs, CDAM can also explain a user-defined concept by targeting similarity measures in the latent space of the ViT. This allows for explanations of arbitrary concepts, defined by the user through a few sample images. We investigate the operating characteristics of CDAM in comparison with relevance propagation (RP) and token ablation maps (TAM), an alternative to pixel occlusion methods. CDAM is highly class-discriminative and semantically relevant, while providing implicit regularization of relevance scores.
PyTorch implementation: \url{https://github.com/lenbrocki/CDAM}
Web live demo: \url{https://cdam.informatism.com/}
Authors: Diedre S. Carmo, Jean Ribeiro, Alejandro P. Comellas, Joseph M. Reinhardt, Sarah E. Gerard, Letícia Rittner, Roberto A. Lotufo
The COVID-19 pandemic response highlighted the potential of deep learning methods in facilitating the diagnosis and prognosis of lung diseases through automated segmentation of normal and abnormal tissue in computed tomography (CT). Such methods not only have the potential to aid in clinical decision-making but also contribute to the comprehension of novel diseases. In light of the labor-intensive nature of manual segmentation for large chest CT cohorts, there is a pressing need for reliable automated approaches that enable efficient analysis of chest CT anatomy in vast research databases, especially in more scarcely annotated targets such as pneumonia consolidations. A limiting factor for the development of such methods is that most current models optimize a fixed annotation format per network output. To tackle this problem, polymorphic training is used to optimize a network with a fixed number of output channels to represent multiple hierarchical anatomic structures, indirectly optimizing more complex labels with simpler annotations. We combined over 6000 volumetric CT scans containing varying formats of manual and automated labels from different sources, and used polymorphic training along with multitask learning to develop MEDPSeg, an end-to-end method for the segmentation of lungs, airways, pulmonary artery, and lung lesions with separation of ground glass opacities, and parenchymal consolidations, all in a single forward prediction. We achieve state-of-the-art performance in multiple targets, particularly in the segmentation of ground glass opacities and consolidations, a challenging problem with limited manual annotation availability. In addition, we provide an open-source implementation with a graphical user interface at https://github.com/MICLab-Unicamp/medpseg.
Authors: Mohammed Baharoon, Waseem Qureshi, Jiahong Ouyang, Yanwu Xu, Kilian Phol, Abdulrhman Aljouie, Wei Peng
The integration of deep learning systems into the medical domain has been hindered by the resource-intensive process of data annotation and the inability of these systems to generalize to different data distributions. Foundation models, which are models pre-trained on large datasets, have emerged as a solution to reduce reliance on annotated data and enhance model generalizability and robustness. DINOv2, an open-source foundation model pre-trained with self-supervised learning on 142 million curated natural images, excels in extracting general-purpose visual representations, exhibiting promising capabilities across various vision tasks. Nevertheless, a critical question remains unanswered regarding DINOv2's adaptability to radiological imaging, and the clarity on whether its features are sufficiently general to benefit radiology image analysis is yet to be established. Therefore, this study comprehensively evaluates DINOv2 for radiology, conducting over 100 experiments across diverse modalities (X-ray, CT, and MRI). Tasks include disease classification and organ segmentation on both 2D and 3D images, evaluated under different settings like kNN, few-shot learning, linear-probing, end-to-end fine-tuning, and parameter-efficient fine-tuning, to measure the effectiveness and generalizability of the DINOv2 feature embeddings. Comparative analyses with established medical image analysis models, U-Net and TransUnet for segmentation, and CNN and ViT models pre-trained via supervised, weakly supervised, and self-supervised learning for classification, reveal DINOv2's superior performance in segmentation tasks and competitive results in disease classification. The findings contribute insights to potential avenues for optimizing pre-training strategies for medical imaging and enhancing the broader understanding of DINOv2's role in bridging the gap between natural and radiological image analysis.
Authors: Jamie Santos, Holly Dinkel, Julia Di, Paulo V.K. Borges, Marina Moreira, Oleg Alexandrov, Brian Coltin, Trey Smith
This work presents an algorithm for scene change detection from point clouds to enable autonomous robotic caretaking in future space habitats. Autonomous robotic systems will help maintain future deep-space habitats, such as the Gateway space station, which will be uncrewed for extended periods. Existing scene analysis software used on the International Space Station (ISS) relies on manually-labeled images for detecting changes. In contrast, the algorithm presented in this work uses raw, unlabeled point clouds as inputs. The algorithm first applies modified Expectation-Maximization Gaussian Mixture Model (GMM) clustering to two input point clouds. It then performs change detection by comparing the GMMs using the Earth Mover's Distance. The algorithm is validated quantitatively and qualitatively using a test dataset collected by an Astrobee robot in the NASA Ames Granite Lab comprising single frame depth images taken directly by Astrobee and full-scene reconstructed maps built with RGB-D and pose data from Astrobee. The runtimes of the approach are also analyzed in depth. The source code is publicly released to promote further development.
Authors: Yiqian Gan, Hao Xiao, Yizhe Zhao, Ethan Zhang, Zhe Huang, Xin Ye, Lingting Ge
Motion prediction has been an essential component of autonomous driving systems since it handles highly uncertain and complex scenarios involving moving agents of different types. In this paper, we propose a Multi-Granular TRansformer (MGTR) framework, an encoder-decoder network that exploits context features in different granularities for different kinds of traffic agents. To further enhance MGTR's capabilities, we leverage LiDAR point cloud data by incorporating LiDAR semantic features from an off-the-shelf LiDAR feature extractor. We evaluate MGTR on Waymo Open Dataset motion prediction benchmark and show that the proposed method achieved state-of-the-art performance, ranking 1st on its leaderboard (https://waymo.com/open/challenges/2023/motion-prediction/).
Authors: Rohit Kundu, Sudipta Paul, Rohit Lal, Amit K. Roy-Chowdhury
Recent advancements in computer vision predominantly rely on learning-based systems, leveraging annotations as the driving force to develop specialized models. However, annotating pixel-level information, particularly in semantic segmentation, presents a challenging and labor-intensive task, prompting the need for autonomous processes. In this work, we propose GranSAM which distinguishes itself by providing semantic segmentation at the user-defined granularity level on unlabeled data without the need for any manual supervision, offering a unique contribution in the realm of semantic mask annotation method. Specifically, we propose an approach to enable the Segment Anything Model (SAM) with semantic recognition capability to generate pixel-level annotations for images without any manual supervision. For this, we accumulate semantic information from synthetic images generated by the Stable Diffusion model or web crawled images and employ this data to learn a mapping function between SAM mask embeddings and object class labels. As a result, SAM, enabled with granularity-adjusted mask recognition, can be used for pixel-level semantic annotation purposes. We conducted experiments on the PASCAL VOC 2012 and COCO-80 datasets and observed a +17.95% and +5.17% increase in mIoU, respectively, compared to existing state-of-the-art methods when evaluated under our problem setting.
Authors: Hao Li, Curise Jia, Peng Jin, Zesen Cheng, Kehan Li, Jialu Sui, Chang Liu, Li Yuan
Image Retrieval aims to retrieve corresponding images based on a given query. In application scenarios, users intend to express their retrieval intent through various query styles. However, current retrieval tasks predominantly focus on text-query retrieval exploration, leading to limited retrieval query options and potential ambiguity or bias in user intention. In this paper, we propose the Style-Diversified Query-Based Image Retrieval task, which enables retrieval based on various query styles. To facilitate the novel setting, we propose the first Diverse-Style Retrieval dataset, encompassing diverse query styles including text, sketch, low-resolution, and art. We also propose a light-weighted style-diversified retrieval framework. For various query style inputs, we apply the Gram Matrix to extract the query's textural features and cluster them into a style space with style-specific bases. Then we employ the style-init prompt tuning module to enable the visual encoder to comprehend the texture and style information of the query. Experiments demonstrate that our model, employing the style-init prompt tuning strategy, outperforms existing retrieval models on the style-diversified retrieval task. Moreover, style-diversified queries~(sketch+text, art+text, etc) can be simultaneously retrieved in our model. The auxiliary information from other queries enhances the retrieval performance within the respective query.
Authors: Ryan Po, Guandao Yang, Kfir Aberman, Gordon Wetzstein
Customization techniques for text-to-image models have paved the way for a wide range of previously unattainable applications, enabling the generation of specific concepts across diverse contexts and styles. While existing methods facilitate high-fidelity customization for individual concepts or a limited, pre-defined set of them, they fall short of achieving scalability, where a single model can seamlessly render countless concepts. In this paper, we address a new problem called Modular Customization, with the goal of efficiently merging customized models that were fine-tuned independently for individual concepts. This allows the merged model to jointly synthesize concepts in one image without compromising fidelity or incurring any additional computational costs.
To address this problem, we introduce Orthogonal Adaptation, a method designed to encourage the customized models, which do not have access to each other during fine-tuning, to have orthogonal residual weights. This ensures that during inference time, the customized models can be summed with minimal interference.
Our proposed method is both simple and versatile, applicable to nearly all optimizable weights in the model architecture. Through an extensive set of quantitative and qualitative evaluations, our method consistently outperforms relevant baselines in terms of efficiency and identity preservation, demonstrating a significant leap toward scalable customization of diffusion models.
Authors: Fei Wei, Xinyu Zhang, Ailing Zhang, Bo Zhang, Xiangxiang Chu
With the fast-paced development of multimodal large language models (MLLMs), we can now converse with AI systems in natural languages to understand images. However, the reasoning power and world knowledge embedded in the large language models have been much less investigated and exploited for image perception tasks. In this paper, we propose Lenna, a language-enhanced reasoning detection assistant, which utilizes the robust multimodal feature representation of MLLMs, while preserving location information for detection. This is achieved by incorporating an additional <DET> token in the MLLM vocabulary that is free of explicit semantic context but serves as a prompt for the detector to identify the corresponding position. To evaluate the reasoning capability of Lenna, we construct a ReasonDet dataset to measure its performance on reasoning-based detection. Remarkably, Lenna demonstrates outstanding performance on ReasonDet and comes with significantly low training costs. It also incurs minimal transferring overhead when extended to other tasks. Our code and model will be available at https://git.io/Lenna.
Authors: Zhen Liu, Hao Zhu, Qi Zhang, Jingde Fu, Weibing Deng, Zhan Ma, Yanwen Guo, Xun Cao
Implicit Neural Representation (INR), which utilizes a neural network to map coordinate inputs to corresponding attributes, is causing a revolution in the field of signal processing. However, current INR techniques suffer from a restricted capability to tune their supported frequency set, resulting in imperfect performance when representing complex signals with multiple frequencies. We have identified that this frequency-related problem can be greatly alleviated by introducing variable-periodic activation functions, for which we propose FINER. By initializing the bias of the neural network within different ranges, sub-functions with various frequencies in the variable-periodic function are selected for activation. Consequently, the supported frequency set of FINER can be flexibly tuned, leading to improved performance in signal representation. We demonstrate the capabilities of FINER in the contexts of 2D image fitting, 3D signed distance field representation, and 5D neural radiance fields optimization, and we show that it outperforms existing INRs.
Authors: Jingmin Wei, Haoyang Shen, Ziyi Wang, Ziqian Zhang
Skin cancer, the primary type of cancer that can be identified by visual recognition, requires an automatic identification system that can accurately classify different types of lesions. This paper presents GoogLe-Dense Network (GDN), which is an image-classification model to identify two types of skin cancer, Basal Cell Carcinoma, and Melanoma. GDN uses stacking of different networks to enhance the model performance. Specifically, GDN consists of two sequential levels in its structure. The first level performs basic classification tasks accomplished by GoogLeNet and DenseNet, which are trained in parallel to enhance efficiency. To avoid low accuracy and long training time, the second level takes the output of the GoogLeNet and DenseNet as the input for a logistic regression model. We compare our method with four baseline networks including ResNet, VGGNet, DenseNet, and GoogLeNet on the dataset, in which GoogLeNet and DenseNet significantly outperform ResNet and VGGNet. In the second level, different stacking methods such as perceptron, logistic regression, SVM, decision trees and K-neighbor are studied in which Logistic Regression shows the best prediction result among all. The results prove that GDN, compared to a single network structure, has higher accuracy in optimizing skin cancer detection.
Authors: Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou
Chain-of-Thought (CoT) guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs -- a non-sequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study. Then to investigate LLMs' LoT ability in the Oogiri game, we first build a multimodal and multilingual Oogiri-GO dataset which contains over 130,000 samples from the Oogiri game, and observe the insufficient LoT ability or failures of most existing LLMs on the Oogiri game. Accordingly, we introduce a creative Leap-of-Thought (CLoT) paradigm to improve LLM's LoT ability. CLoT first formulates the Oogiri-GO dataset into LoT-oriented instruction tuning data to train pretrained LLM for achieving certain LoT humor generation and discrimination abilities. Then CLoT designs an explorative self-refinement that encourages the LLM to generate more creative LoT data via exploring parallels between seemingly unrelated concepts and selects high-quality data to train itself for self-refinement. CLoT not only excels in humor generation in the Oogiri game but also boosts creative abilities in various tasks like cloud guessing game and divergent association task. These findings advance our understanding and offer a pathway to improve LLMs' creative capacities for innovative applications across domains. The dataset, code, and models will be released online. https://github.com/sail-sg/CLoT.
Authors: Xianping Ma, Qianqian Wu, Xingyu Zhao, Xiaokang Zhang, Man-On Pun, Bo Huang
Semantic segmentation of remote sensing imagery plays a pivotal role in extracting precise information for diverse down-stream applications. Recent development of the Segment Anything Model (SAM), an advanced general-purpose segmentation model, has revolutionized this field, presenting new avenues for accurate and efficient segmentation. However, SAM is limited to generating segmentation results without class information. Consequently, the utilization of such a powerful general vision model for semantic segmentation in remote sensing images has become a focal point of research. In this paper, we present a streamlined framework aimed at leveraging the raw output of SAM by exploiting two novel concepts called SAM-Generated Object (SGO) and SAM-Generated Boundary (SGB). More specifically, we propose a novel object loss and further introduce a boundary loss as augmentative components to aid in model optimization in a general semantic segmentation framework. Taking into account the content characteristics of SGO, we introduce the concept of object consistency to leverage segmented regions lacking semantic information. By imposing constraints on the consistency of predicted values within objects, the object loss aims to enhance semantic segmentation performance. Furthermore, the boundary loss capitalizes on the distinctive features of SGB by directing the model's attention to the boundary information of the object. Experimental results on two well-known datasets, namely ISPRS Vaihingen and LoveDA Urban, demonstrate the effectiveness of our proposed method. The source code for this work will be accessible at https://github.com/sstary/SSRS.
This paper studies the fundamental learning problem of the energy-based model (EBM). Learning the EBM can be achieved using the maximum likelihood estimation (MLE), which typically involves the Markov Chain Monte Carlo (MCMC) sampling, such as the Langevin dynamics. However, the noise-initialized Langevin dynamics can be challenging in practice and hard to mix. This motivates the exploration of joint training with the generator model where the generator model serves as a complementary model to bypass MCMC sampling. However, such a method can be less accurate than the MCMC and result in biased EBM learning. While the generator can also serve as an initializer model for better MCMC sampling, its learning can be biased since it only matches the EBM and has no access to empirical training examples. Such biased generator learning may limit the potential of learning the EBM. To address this issue, we present a joint learning framework that interweaves the maximum likelihood learning algorithm for both the EBM and the complementary generator model. In particular, the generator model is learned by MLE to match both the EBM and the empirical data distribution, making it a more informative initializer for MCMC sampling of EBM. Learning generator with observed examples typically requires inference of the generator posterior. To ensure accurate and efficient inference, we adopt the MCMC posterior sampling and introduce a complementary inference model to initialize such latent MCMC sampling. We show that three separate models can be seamlessly integrated into our joint framework through two (dual-) MCMC teaching, enabling effective and efficient EBM learning.
Authors: Runpeng Yu, Xinchao Wang
In this paper, we make a bold attempt toward an ambitious task: given a pre-trained classifier, we aim to reconstruct an image generator, without relying on any data samples. From a black-box perspective, this challenge seems intractable, since it inevitably involves identifying the inverse function for a classifier, which is, by nature, an information extraction process. As such, we resort to leveraging the knowledge encapsulated within the parameters of the neural network. Grounded on the theory of Maximum-Margin Bias of gradient descent, we propose a novel learning paradigm, in which the generator is trained to ensure that the convergence conditions of the network parameters are satisfied over the generated distribution of the samples. Empirical validation from various image generation tasks substantiates the efficacy of our strategy.
Authors: Hoon-Gyu Chung, Seokjun Choi, Seung-Hwan Baek
We present differentiable point-based inverse rendering, DPIR, an analysis-by-synthesis method that processes images captured under diverse illuminations to estimate shape and spatially-varying BRDF. To this end, we adopt point-based rendering, eliminating the need for multiple samplings per ray, typical of volumetric rendering, thus significantly enhancing the speed of inverse rendering. To realize this idea, we devise a hybrid point-volumetric representation for geometry and a regularized basis-BRDF representation for reflectance. The hybrid geometric representation enables fast rendering through point-based splatting while retaining the geometric details and stability inherent to SDF-based representations. The regularized basis-BRDF mitigates the ill-posedness of inverse rendering stemming from limited light-view angular samples. We also propose an efficient shadow detection method using point-based shadow map rendering. Our extensive evaluations demonstrate that DPIR outperforms prior works in terms of reconstruction accuracy, computational efficiency, and memory footprint. Furthermore, our explicit point-based representation and rendering enables intuitive geometry and reflectance editing. The code will be publicly available.
Authors: Yansheng Li, Junwei Luo, Yongjun Zhang, Yihua Tan, Jin-Gang Yu, Song Bai
Bridge detection in remote sensing images (RSIs) plays a crucial role in various applications, but it poses unique challenges compared to the detection of other objects. In RSIs, bridges exhibit considerable variations in terms of their spatial scales and aspect ratios. Therefore, to ensure the visibility and integrity of bridges, it is essential to perform holistic bridge detection in large-size very-high-resolution (VHR) RSIs. However, the lack of datasets with large-size VHR RSIs limits the deep learning algorithms' performance on bridge detection. Due to the limitation of GPU memory in tackling large-size images, deep learning-based object detection methods commonly adopt the cropping strategy, which inevitably results in label fragmentation and discontinuous prediction. To ameliorate the scarcity of datasets, this paper proposes a large-scale dataset named GLH-Bridge comprising 6,000 VHR RSIs sampled from diverse geographic locations across the globe. These images encompass a wide range of sizes, varying from 2,048*2,048 to 16,38*16,384 pixels, and collectively feature 59,737 bridges. Furthermore, we present an efficient network for holistic bridge detection (HBD-Net) in large-size RSIs. The HBD-Net presents a separate detector-based feature fusion (SDFF) architecture and is optimized via a shape-sensitive sample re-weighting (SSRW) strategy. Based on the proposed GLH-Bridge dataset, we establish a bridge detection benchmark including the OBB and HBB tasks, and validate the effectiveness of the proposed HBD-Net. Additionally, cross-dataset generalization experiments on two publicly available datasets illustrate the strong generalization capability of the GLH-Bridge dataset.
Authors: Guozhang Li, Xinpeng Ding, De Cheng, Jie Li, Nannan Wang, Xinbo Gao
Early weakly supervised video grounding (WSVG) methods often struggle with incomplete boundary detection due to the absence of temporal boundary annotations. To bridge the gap between video-level and boundary-level annotation, explicit-supervision methods, i.e., generating pseudo-temporal boundaries for training, have achieved great success. However, data augmentations in these methods might disrupt critical temporal information, yielding poor pseudo boundaries. In this paper, we propose a new perspective that maintains the integrity of the original temporal content while introducing more valuable information for expanding the incomplete boundaries. To this end, we propose EtC (Expand then Clarify), first use the additional information to expand the initial incomplete pseudo boundaries, and subsequently refine these expanded ones to achieve precise boundaries. Motivated by video continuity, i.e., visual similarity across adjacent frames, we use powerful multimodal large language models (MLLMs) to annotate each frame within initial pseudo boundaries, yielding more comprehensive descriptions for expanded boundaries. To further clarify the noise of expanded boundaries, we combine mutual learning with a tailored proposal-level contrastive objective to use a learnable approach to harmonize a balance between incomplete yet clean (initial) and comprehensive yet noisy (expanded) boundaries for more precise ones. Experiments demonstrate the superiority of our method on two challenging WSVG datasets.
Authors: Sahil Tyagi, Martin Swany
Gradient compression alleviates expensive communication in distributed deep learning by sending fewer values and its corresponding indices, typically via Allgather (AG). Training with high compression ratio (CR) achieves high accuracy like DenseSGD, but has lower parallel scaling due to high communication cost (i.e., parallel efficiency). Using lower CRs improves parallel efficiency by lowering synchronization cost, but degrades model accuracy as well (statistical efficiency). Further, speedup attained with different models and CRs also varies with network latency, effective bandwidth and collective op used for aggregation. In many cases, collectives like Allreduce (AR) have lower cost than AG to exchange the same amount of data. In this paper, we propose an AR-compatible Topk compressor that is bandwidth-optimal and thus performs better than AG in certain network configurations. We develop a flexible communication strategy that switches between AG and AR based on which collective is optimal in the current settings, and model the pareto-relationship between parallel and statistical efficiency as a multi-objective optimization (MOO) problem to dynamically adjust CR and accelerate training while still converging to high accuracy.
Authors: Fumio Hashimoto, Kibo Ote
[Objective] This study aims to introduce a novel back projection-induced U-Net-shaped architecture, called ReconU-Net, for deep learning-based direct positron emission tomography (PET) image reconstruction. Additionally, our objective is to analyze the behavior of direct PET image reconstruction and gain deeper insights by comparing the proposed ReconU-Net architecture with other encoder-decoder architectures without skip connections. [Approach] The proposed ReconU-Net architecture uniquely integrates the physical model of the back projection operation into the skip connection. This distinctive feature facilitates the effective transfer of intrinsic spatial information from the input sinogram to the reconstructed image via an embedded physical model. The proposed ReconU-Net was trained using Monte Carlo simulation data from the Brainweb phantom and tested on both simulated and real Hoffman brain phantom data. [Main results] The proposed ReconU-Net method generated a reconstructed image with a more accurate structure compared to other deep learning-based direct reconstruction methods. Further analysis showed that the proposed ReconU-Net architecture has the ability to transfer features of multiple resolutions, especially non-abstract high-resolution information, through skip connections. Despite limited training on simulated data, the proposed ReconU-Net successfully reconstructed the real Hoffman brain phantom, unlike other deep learning-based direct reconstruction methods, which failed to produce a reconstructed image. [Significance] The proposed ReconU-Net can improve the fidelity of direct PET image reconstruction, even when dealing with small training datasets, by leveraging the synergistic relationship between data-driven modeling and the physics model of the imaging process.
Authors: Zikang Xu, Fenghe Tang, Quan Quan, Jianrui Ding, Chunping Ning, S. Kevin Zhou
With the rapid expansion of machine learning and deep learning (DL), researchers are increasingly employing learning-based algorithms to alleviate diagnostic challenges across diverse medical tasks and applications. While advancements in diagnostic precision are notable, some researchers have identified a concerning trend: their models exhibit biased performance across subgroups characterized by different sensitive attributes. This bias not only infringes upon the rights of patients but also has the potential to lead to life-altering consequences. In this paper, we inspect a series of DL segmentation models using two ultrasound datasets, aiming to assess the presence of model unfairness in these specific tasks. Our findings reveal that even state-of-the-art DL algorithms demonstrate unfair behavior in ultrasound segmentation tasks. These results serve as a crucial warning, underscoring the necessity for careful model evaluation before their deployment in real-world scenarios. Such assessments are imperative to ensure ethical considerations and mitigate the risk of adverse impacts on patient outcomes.
Authors: Yeji Song, Wonsik Shin, Junsoo Lee, Jeesoo Kim, Nojun Kwak
Driven by the upsurge progress in text-to-image (T2I) generation models, text-to-video (T2V) generation has experienced a significant advance as well. Accordingly, tasks such as modifying the object or changing the style in a video have been possible. However, previous works usually work well on trivial and consistent shapes, and easily collapse on a difficult target that has a largely different body shape from the original one. In this paper, we spot the bias problem in the existing video editing method that restricts the range of choices for the new protagonist and attempt to address this issue using the conventional image-level personalization method. We adopt motion personalization that isolates the motion from a single source video and then modifies the protagonist accordingly. To deal with the natural discrepancy between image and video, we propose a motion word with an inflated textual embedding to properly represent the motion in a source video. We also regulate the motion word to attend to proper motion-related areas by introducing a novel pseudo optical flow, efficiently computed from the pre-calculated attention maps. Finally, we decouple the motion from the appearance of the source video with an additional pseudo word. Extensive experiments demonstrate the editing capability of our method, taking a step toward more diverse and extensive video editing.
Authors: Jeongsoo Choi, Se Jin Park, Minsu Kim, Yong Man Ro
This paper proposes a novel direct Audio-Visual Speech to Audio-Visual Speech Translation (AV2AV) framework, where the input and output of the system are multimodal (i.e., audio and visual speech). With the proposed AV2AV, two key advantages can be brought: 1) We can perform real-like conversations with individuals worldwide in a virtual meeting by utilizing our own primary languages. In contrast to Speech-to-Speech Translation (A2A), which solely translates between audio modalities, the proposed AV2AV directly translates between audio-visual speech. This capability enhances the dialogue experience by presenting synchronized lip movements along with the translated speech. 2) We can improve the robustness of the spoken language translation system. By employing the complementary information of audio-visual speech, the system can effectively translate spoken language even in the presence of acoustic noise, showcasing robust performance. To mitigate the problem of the absence of a parallel AV2AV translation dataset, we propose to train our spoken language translation system with the audio-only dataset of A2A. This is done by learning unified audio-visual speech representations through self-supervised learning in advance to train the translation system. Moreover, we propose an AV-Renderer that can generate raw audio and video in parallel. It is designed with zero-shot speaker modeling, thus the speaker in source audio-visual speech can be maintained at the target translated audio-visual speech. The effectiveness of AV2AV is evaluated with extensive experiments in a many-to-many language translation setting. The demo page is available on https://choijeongsoo.github.io/av2av.
Authors: Dianmo Sheng, Dongdong Chen, Zhentao Tan, Qiankun Liu, Qi Chu, Jianmin Bao, Tao Gong, Bin Liu, Shengwei Xu, Nenghai Yu
The rapid advancement of large language models (LLMs) has accelerated the emergence of in-context learning (ICL) as a cutting-edge approach in the natural language processing domain. Recently, ICL has been employed in visual understanding tasks, such as semantic segmentation and image captioning, yielding promising results. However, existing visual ICL framework can not enable producing content across multiple modalities, which limits their potential usage scenarios. To address this issue, we present a new ICL framework for visual understanding with multi-modal output enabled. First, we quantize and embed both text and visual prompt into a unified representational space, structured as interleaved in-context sequences. Then a decoder-only sparse transformer architecture is employed to perform generative modeling on them, facilitating in-context learning. Thanks to this design, the model is capable of handling in-context vision understanding tasks with multimodal output in a unified pipeline. Experimental results demonstrate that our model achieves competitive performance compared with specialized models and previous ICL baselines. Overall, our research takes a further step toward unified multimodal in-context learning.
Authors: Haoran Tang, Xin Zhou, Jieren Deng, Zhihong Pan, Hao Tian, Pratik Chaudhari
Recent diffusion-based subject driven generative methods have enabled image generations with good fidelity for specific objects or human portraits. However, to achieve better versatility for applications, we argue that not only improved datasets and evaluations are desired, but also more careful methods to retrieve only relevant information from conditional images are anticipated. To this end, we propose an anime figures dataset RetriBooru-V1, with enhanced identity and clothing labels. We state new tasks enabled by this dataset, and introduce a new diversity metric to measure success in completing these tasks, quantifying the flexibility of image generations. We establish an RAG-inspired baseline method, designed to retrieve precise conditional information from reference images. Then, we compare with current methods on existing task to demonstrate the capability of the proposed method. Finally, we provide baseline experiment results on new tasks, and conduct ablation studies on the possible structural choices.
Authors: Xiaoqi Zhao, Youwei Pang, Zhenyu Chen, Qian Yu, Lihe Zhang, Hanqi Liu, Jiaming Zuo, Huchuan Lu
We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluate the quality of power batteries. Existing manufacturers usually rely on human eye observation to complete PBD, which makes it difficult to balance the accuracy and efficiency of detection. To address this issue and drive more attention into this meaningful task, we first elaborately collect a dataset, called X-ray PBD, which has $1,500$ diverse X-ray images selected from thousands of power batteries of $5$ manufacturers, with $7$ different visual interference. Then, we propose a novel segmentation-based solution for PBD, termed multi-dimensional collaborative network (MDCNet). With the help of line and counting predictors, the representation of the point segmentation branch can be improved at both semantic and detail aspects. Besides, we design an effective distance-adaptive mask generation strategy, which can alleviate the visual challenge caused by the inconsistent distribution density of plates to provide MDCNet with stable supervision. Without any bells and whistles, our segmentation-based MDCNet consistently outperforms various other corner detection, crowd counting and general/tiny object detection-based solutions, making it a strong baseline that can help facilitate future research in PBD. Finally, we share some potential difficulties and works for future researches. The source code and datasets will be publicly available at \href{this http URL}{X-ray PBD}.
Authors: Chen Liu, Can Han, Chengfeng Zhou, Crystal Cai, Suncheng Xiang, Hualiang Ni, Dahong Qian
Gesture recognition is a foundational task in human-machine interaction (HMI). While there has been significant progress in gesture recognition based on surface electromyography (sEMG), accurate recognition of predefined gestures only within a closed set is still inadequate in practice. It is essential to effectively discern and reject unknown gestures of disinterest in a robust system. Numerous methods based on prototype learning (PL) have been proposed to tackle this open set recognition (OSR) problem. However, they do not fully explore the inherent distinctions between known and unknown classes. In this paper, we propose a more effective PL method leveraging two novel and inherent distinctions, feature activation level and projection inconsistency. Specifically, the Feature Activation Enhancement Mechanism (FAEM) widens the gap in feature activation values between known and unknown classes. Furthermore, we introduce Orthogonal Prototype Learning (OPL) to construct multiple perspectives. OPL acts to project a sample from orthogonal directions to maximize the distinction between its two projections, where unknown samples will be projected near the clusters of different known classes while known samples still maintain intra-class similarity. Our proposed method simultaneously achieves accurate closed-set classification for predefined gestures and effective rejection for unknown gestures. Extensive experiments demonstrate its efficacy and superiority in open-set gesture recognition based on sEMG.
Authors: Hong Nguyen, Cuong V. Nguyen, Shrikanth Narayanan, Benjamin Y. Xu, Michael Pazzani
Primary open-angle glaucoma (POAG) is a chronic and progressive optic nerve condition that results in an acquired loss of optic nerve fibers and potential blindness. The gradual onset of glaucoma results in patients progressively losing their vision without being consciously aware of the changes. To diagnose POAG and determine its severity, patients must undergo a comprehensive dilated eye examination. In this work, we build a framework to rank, compare, and interpret the severity of glaucoma using fundus images. We introduce a siamese-based severity ranking using pairwise n-hidden comparisons. We additionally have a novel approach to explaining why a specific image is deemed more severe than others. Our findings indicate that the proposed severity ranking model surpasses traditional ones in terms of diagnostic accuracy and delivers improved saliency explanations.
Authors: Yuntao Shou, Wei Ai, Tao Meng
Remote sensing segmentation has a wide range of applications in environmental protection, and urban change detection, etc. Despite the success of deep learning-based remote sensing segmentation methods (e.g., CNN and Transformer), they are not flexible enough to model irregular objects. In addition, existing graph contrastive learning methods usually adopt the way of maximizing mutual information to keep the node representations consistent between different graph views, which may cause the model to learn task-independent redundant information. To tackle the above problems, this paper treats images as graph structures and introduces a simple contrastive vision GNN (SC-ViG) architecture for remote sensing segmentation. Specifically, we construct a node-masked and edge-masked graph view to obtain an optimal graph structure representation, which can adaptively learn whether to mask nodes and edges. Furthermore, this paper innovatively introduces information bottleneck theory into graph contrastive learning to maximize task-related information while minimizing task-independent redundant information. Finally, we replace the convolutional module in UNet with the SC-ViG module to complete the segmentation and classification tasks of remote sensing images. Extensive experiments on publicly available real datasets demonstrate that our method outperforms state-of-the-art remote sensing image segmentation methods.
Authors: Zhuo Huang, Chang Liu, Yinpeng Dong, Hang Su, Shibao Zheng, Tongliang Liu
Although vision models such as Contrastive Language-Image Pre-Training (CLIP) show impressive generalization performance, their zero-shot robustness is still limited under Out-of-Distribution (OOD) scenarios without fine-tuning. Instead of undesirably providing human supervision as commonly done, it is possible to take advantage of Multi-modal Large Language Models (MLLMs) that hold powerful visual understanding abilities. However, MLLMs are shown to struggle with vision problems due to the incompatibility of tasks, thus hindering their utilization. In this paper, we propose to effectively leverage MLLMs to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner. To solve the incompatibility issue, we propose a novel Denoising In-Context Learning (DICL) strategy to align vision tasks with MLLMs. Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed. Such an instruction can help any MLLMs with ICL ability to detect and rectify incorrect predictions of vision models. Through extensive experiments on ImageNet, WILDS, DomainBed, and other OOD datasets, we carefully validate the quantitative and qualitative effectiveness of our method. Our code is available at https://github.com/tmllab/Machine_Vision_Therapy.
Authors: Soroush Abbasi Koohpayegani, Anuj Singh, K L Navaneet, Hadi Jamali-Rad, Hamed Pirsiavash
Data augmentation is crucial in training deep models, preventing them from overfitting to limited data. Common data augmentation methods are effective, but recent advancements in generative AI, such as diffusion models for image generation, enable more sophisticated augmentation techniques that produce data resembling natural images. We recognize that augmented samples closer to the ideal decision boundary of a classifier are particularly effective and efficient in guiding the learning process. We introduce GeNIe which leverages a diffusion model conditioned on a text prompt to merge contrasting data points (an image from the source category and a text prompt from the target category) to generate challenging samples for the target category. Inspired by recent image editing methods, we limit the number of diffusion iterations and the amount of noise. This ensures that the generated image retains low-level and contextual features from the source image, potentially conflicting with the target category. Our extensive experiments, in few-shot and also long-tail distribution settings, demonstrate the effectiveness of our novel augmentation method, especially benefiting categories with a limited number of examples.
Authors: Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Cong-Duy Nguyen, See-Kiong Ng, Luu Anh Tuan
Temporal Language Grounding seeks to localize video moments that semantically correspond to a natural language query. Recent advances employ the attention mechanism to learn the relations between video moments and the text query. However, naive attention might not be able to appropriately capture such relations, resulting in ineffective distributions where target video moments are difficult to separate from the remaining ones. To resolve the issue, we propose an energy-based model framework to explicitly learn moment-query distributions. Moreover, we propose DemaFormer, a novel Transformer-based architecture that utilizes exponential moving average with a learnable damping factor to effectively encode moment-query inputs. Comprehensive experiments on four public temporal language grounding datasets showcase the superiority of our methods over the state-of-the-art baselines.
Authors: Jiayi Chen, Benteng Ma, Hengfei Cui, Yong Xia, Kwang-Ting Cheng
Federated learning facilitates the collaborative learning of a global model across multiple distributed medical institutions without centralizing data. Nevertheless, the expensive cost of annotation on local clients remains an obstacle to effectively utilizing local data. To mitigate this issue, federated active learning methods suggest leveraging local and global model predictions to select a relatively small amount of informative local data for annotation. However, existing methods mainly focus on all local data sampled from the same domain, making them unreliable in realistic medical scenarios with domain shifts among different clients. In this paper, we make the first attempt to assess the informativeness of local data derived from diverse domains and propose a novel methodology termed Federated Evidential Active Learning (FEAL) to calibrate the data evaluation under domain shift. Specifically, we introduce a Dirichlet prior distribution in both local and global models to treat the prediction as a distribution over the probability simplex and capture both aleatoric and epistemic uncertainties by using the Dirichlet-based evidential model. Then we employ the epistemic uncertainty to calibrate the aleatoric uncertainty. Afterward, we design a diversity relaxation strategy to reduce data redundancy and maintain data diversity. Extensive experiments and analyses are conducted to show the superiority of FEAL over the state-of-the-art active learning methods and the efficiency of FEAL under the federated active learning framework.
Authors: Jianmeng Liu, Yuyao Zhang, Zeyuan Meng, Yu-Wing Tai, Chi-Keung Tang
This paper explores promptable NeRF generation (e.g., text prompt or single image prompt) for direct conditioning and fast generation of NeRF parameters for the underlying 3D scenes, thus undoing complex intermediate steps while providing full 3D generation with conditional control. Unlike previous diffusion-CLIP-based pipelines that involve tedious per-prompt optimizations, Prompt2NeRF-PIL is capable of generating a variety of 3D objects with a single forward pass, leveraging a pre-trained implicit latent space of NeRF parameters. Furthermore, in zero-shot tasks, our experiments demonstrate that the NeRFs produced by our method serve as semantically informative initializations, significantly accelerating the inference process of existing prompt-to-NeRF methods. Specifically, we will show that our approach speeds up the text-to-NeRF model DreamFusion and the 3D reconstruction speed of the image-to-NeRF method Zero-1-to-3 by 3 to 5 times.
Authors: Ioannis Kontostathis, Evlampios Apostolidis, Vasileios Mezaris
In this work, we present an integrated system for spatiotemporal summarization of 360-degrees videos. The video summary production mainly involves the detection of salient events and their synopsis into a concise summary. The analysis relies on state-of-the-art methods for saliency detection in 360-degrees video (ATSal and SST-Sal) and video summarization (CA-SUM). It also contains a mechanism that classifies a 360-degrees video based on the use of static or moving camera during recording and decides which saliency detection method will be used, as well as a 2D video production component that is responsible to create a conventional 2D video containing the salient events in the 360-degrees video. Quantitative evaluations using two datasets for 360-degrees video saliency detection (VR-EyeTracking, Sports-360) show the accuracy and positive impact of the developed decision mechanism, and justify our choice to use two different methods for detecting the salient events. A qualitative analysis using content from these datasets, gives further insights about the functionality of the decision mechanism, shows the pros and cons of each used saliency detection method and demonstrates the advanced performance of the trained summarization method against a more conventional approach.
Authors: Tianhao Peng, Ge Gao, Heming Sun, Fan Zhang, David Bull
In recent years, end-to-end learnt video codecs have demonstrated their potential to compete with conventional coding algorithms in term of compression efficiency. However, most learning-based video compression models are associated with high computational complexity and latency, in particular at the decoder side, which limits their deployment in practical applications. In this paper, we present a novel model-agnostic pruning scheme based on gradient decay and adaptive layer-wise distillation. Gradient decay enhances parameter exploration during sparsification whilst preventing runaway sparsity and is superior to the standard Straight-Through Estimation. The adaptive layer-wise distillation regulates the sparse training in various stages based on the distortion of intermediate features. This stage-wise design efficiently updates parameters with minimal computational overhead. The proposed approach has been applied to three popular end-to-end learnt video codecs, FVC, DCVC, and DCVC-HEM. Results confirm that our method yields up to 65% reduction in MACs and 2x speed-up with less than 0.3dB drop in BD-PSNR. Supporting code and supplementary material can be downloaded from: https://jasminepp.github.io/lightweightdvc/
Authors: Florian Kofler, Hendrik Möller, Josef A. Buchner, Ezequiel de la Rosa, Ivan Ezhov, Marcel Rosier, Isra Mekki, Suprosanna Shit, Moritz Negwer, Rami Al-Maskari, Ali Ertürk, Shankeeth Vinayahalingam, Fabian Isensee, Sarthak Pati, Daniel Rueckert, Jan S. Kirschke, Stefan K. Ehrlich, Annika Reinke, Bjoern Menze, Benedikt Wiestler, Marie Piraud
This paper introduces panoptica, a versatile and performance-optimized package designed for computing instance-wise segmentation quality metrics from 2D and 3D segmentation maps. panoptica addresses the limitations of existing metrics and provides a modular framework that complements the original intersection over union-based panoptic quality with other metrics, such as the distance metric Average Symmetric Surface Distance. The package is open-source, implemented in Python, and accompanied by comprehensive documentation and tutorials. panoptica employs a three-step metrics computation process to cover diverse use cases. The efficacy of panoptica is demonstrated on various real-world biomedical datasets, where an instance-wise evaluation is instrumental for an accurate representation of the underlying clinical task. Overall, we envision panoptica as a valuable tool facilitating in-depth evaluation of segmentation methods.
Authors: Niccolò Bisagno, Nicola Garau, Antonio Luigi Stefani, Nicola Conci
Simulation is a powerful tool to easily generate annotated data, and a highly desirable feature, especially in those domains where learning models need large training datasets. Machine learning and deep learning solutions, have proven to be extremely data-hungry and sometimes, the available real-world data are not sufficient to effectively model the given task. Despite the initial skepticism of a portion of the scientific community, the potential of simulation has been largely confirmed in many application areas, and the recent developments in terms of rendering and virtualization engines, have shown a good ability also in representing complex scenes. This includes environmental factors, such as weather conditions and surface reflectance, as well as human-related events, like human actions and behaviors. We present a human crowd simulator, called UniCrowd, and its associated validation pipeline. We show how the simulator can generate annotated data, suitable for computer vision tasks, in particular for detection and segmentation, as well as the related applications, as crowd counting, human pose estimation, trajectory analysis and prediction, and anomaly detection.
Authors: Sungik Choi, Hankook Lee, Honglak Lee, Moontae Lee
Novelty detection is a fundamental task of machine learning which aims to detect abnormal ($\textit{i.e.}$ out-of-distribution (OOD)) samples. Since diffusion models have recently emerged as the de facto standard generative framework with surprising generation results, novelty detection via diffusion models has also gained much attention. Recent methods have mainly utilized the reconstruction property of in-distribution samples. However, they often suffer from detecting OOD samples that share similar background information to the in-distribution data. Based on our observation that diffusion models can \emph{project} any sample to an in-distribution sample with similar background information, we propose \emph{Projection Regret (PR)}, an efficient novelty detection method that mitigates the bias of non-semantic information. To be specific, PR computes the perceptual distance between the test image and its diffusion-based projection to detect abnormality. Since the perceptual distance often fails to capture semantic changes when the background information is dominant, we cancel out the background bias by comparing it against recursive projections. Extensive experiments demonstrate that PR outperforms the prior art of generative-model-based novelty detection methods by a significant margin.
Authors: Evlampios Apostolidis, Konstantinos Apostolidis, Vasileios Mezaris
This paper presents a web-based tool that facilitates the production of tailored summaries for online sharing on social media. Through an interactive user interface, it supports a ``one-click'' video summarization process. Based on the integrated AI models for video summarization and aspect ratio transformation, it facilitates the generation of multiple summaries of a full-length video according to the needs of target platforms with regard to the video's length and aspect ratio.
Authors: Tao Tu, Ming-Feng Li, Chieh Hubert Lin, Yen-Chi Cheng, Min Sun, Ming-Hsuan Yang
Articulated 3D reconstruction has valuable applications in various domains, yet it remains costly and demands intensive work from domain experts. Recent advancements in template-free learning methods show promising results with monocular videos. Nevertheless, these approaches necessitate a comprehensive coverage of all viewpoints of the subject in the input video, thus limiting their applicability to casually captured videos from online sources. In this work, we study articulated 3D shape reconstruction from a single and casually captured internet video, where the subject's view coverage is incomplete. We propose DreaMo that jointly performs shape reconstruction while solving the challenging low-coverage regions with view-conditioned diffusion prior and several tailored regularizations. In addition, we introduce a skeleton generation strategy to create human-interpretable skeletons from the learned neural bones and skinning weights. We conduct our study on a self-collected internet video collection characterized by incomplete view coverage. DreaMo shows promising quality in novel-view rendering, detailed articulated shape reconstruction, and skeleton generation. Extensive qualitative and quantitative studies validate the efficacy of each proposed component, and show existing methods are unable to solve correct geometry due to the incomplete view coverage.
Authors: Yichi Zhang, Xiaogang Xu
Generative models have reached an advanced stage where they can produce remarkably realistic images. However, this remarkable generative capability also introduces the risk of disseminating false or misleading information. Notably, existing image detectors for generated images encounter challenges such as low accuracy and limited generalization. This paper seeks to address this issue by seeking a representation with strong generalization capabilities to enhance the detection of generated images. Our investigation has revealed that real and generated images display distinct latent Gaussian representations when subjected to an inverse diffusion process within a pre-trained diffusion model. Exploiting this disparity, we can amplify subtle artifacts in generated images. Building upon this insight, we introduce a novel image representation known as Diffusion Noise Feature (DNF). DNF is an ensemble representation that estimates the noise generated during the inverse diffusion process. A simple classifier, e.g., ResNet, trained on DNF achieves high accuracy, robustness, and generalization capabilities for detecting generated images, even from previously unseen classes or models. We conducted experiments using a widely recognized and standard dataset, achieving state-of-the-art effects of Detection.
Authors: Camillo Quattrocchi, Antonino Furnari, Daniele Di Mauro, Mario Valerio Giuffrida, Giovanni Maria Farinella
We consider the problem of transferring a temporal action segmentation system initially designed for exocentric (fixed) cameras to an egocentric scenario, where wearable cameras capture video data. The conventional supervised approach requires the collection and labeling of a new set of egocentric videos to adapt the model, which is costly and time-consuming. Instead, we propose a novel methodology which performs the adaptation leveraging existing labeled exocentric videos and a new set of unlabeled, synchronized exocentric-egocentric video pairs, for which temporal action segmentation annotations do not need to be collected. We implement the proposed methodology with an approach based on knowledge distillation, which we investigate both at the feature and model level. To evaluate our approach, we introduce a new benchmark based on the Assembly101 dataset. Results demonstrate the feasibility and effectiveness of the proposed method against classic unsupervised domain adaptation and temporal sequence alignment approaches. Remarkably, without bells and whistles, our best model performs on par with supervised approaches trained on labeled egocentric data, without ever seeing a single egocentric label, achieving a +15.99% (28.59% vs 12.60%) improvement in the edit score on the Assembly101 dataset compared to a baseline model trained solely on exocentric data.
Authors: Hong-En Chen, Bin-Shih Wu, Sheng-Yu Huang, Yu-Chiang Frank Wang
Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization time for both training and inference, the use of GAN-based models would still be desirable for fast 3D generation. In this work, we propose Triplane Attention for text-guided 3D generation (TPA3D), an end-to-end trainable GAN-based deep learning model for fast text-to-3D generation. With only 3D shape data and their rendered 2D images observed during training, our TPA3D is designed to retrieve detailed visual descriptions for synthesizing the corresponding 3D mesh data. This is achieved by the proposed attention mechanisms on the extracted sentence and word-level text features. In our experiments, we show that TPA3D generates high-quality 3D textured shapes aligned with fine-grained descriptions, while impressive computation efficiency can be observed.
Authors: Yuxuan Yan, Chi Zhang, Rui Wang, Pei Cheng, Gang Yu, Bin Fu
This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and DreamBooth, have made strides in custom image creation, but they come with significant drawbacks. These include the need for extensive resources and time for fine-tuning, as well as the requirement for multiple reference images. To overcome these challenges, our research introduces a novel approach to identity-preserving synthesis, with a particular focus on human images. Our model leverages a direct feed-forward mechanism, circumventing the need for intensive fine-tuning, thereby facilitating quick and efficient image generation. Central to our innovation is a hybrid guidance framework, which combines stylized images, facial images, and textual prompts to guide the image generation process. This unique combination enables our model to produce a variety of applications, such as artistic portraits and identity-blended images. Our experimental results, including both qualitative and quantitative evaluations, demonstrate the superiority of our method over existing baseline models and previous works, particularly in its remarkable efficiency and ability to preserve the subject's identity with high fidelity.
Authors: Rosario Leonardi, Antonino Furnari, Francesco Ragusa, Giovanni Maria Farinella
In this study, we investigate the effectiveness of synthetic data in enhancing hand-object interaction detection within the egocentric vision domain. We introduce a simulator able to generate synthetic images of hand-object interactions automatically labeled with hand-object contact states, bounding boxes, and pixel-wise segmentation masks. Through comprehensive experiments and comparative analyses on three egocentric datasets, VISOR, EgoHOS, and ENIGMA-51, we demonstrate that the use of synthetic data and domain adaptation techniques allows for comparable performance to conventional supervised methods while requiring annotations on only a fraction of the real data. When tested with in-domain synthetic data generated from 3D models of real target environments and objects, our best models show consistent performance improvements with respect to standard fully supervised approaches based on labeled real data only. Our study also sets a new benchmark of domain adaptation for egocentric hand-object interaction detection (HOI-Synth) and provides baseline results to encourage the community to engage in this challenging task. We release the generated data, code, and the simulator at the following link: https://iplab.dmi.unict.it/HOI-Synth/.
Authors: Xiaze Zhang, Ziheng Ding, Qi Jing, Yuejie Zhang, Wenchao Ding, Rui Feng
Point clouds have shown significant potential in various domains, including Simultaneous Localization and Mapping (SLAM). However, existing approaches either rely on dense point clouds to achieve high localization accuracy or use generalized descriptors to reduce map size. Unfortunately, these two aspects seem to conflict with each other. To address this limitation, we propose a unified architecture, DeepPointMap, achieving excellent preference on both aspects. We utilize neural network to extract highly representative and sparse neural descriptors from point clouds, enabling memory-efficient map representation and accurate multi-scale localization tasks (e.g., odometry and loop-closure). Moreover, we showcase the versatility of our framework by extending it to more challenging multi-agent collaborative SLAM. The promising results obtained in these scenarios further emphasize the effectiveness and potential of our approach.
Authors: Dezhi Peng, Zhenhua Yang, Jiaxin Zhang, Chongyu Liu, Yongxin Shi, Kai Ding, Fengjun Guo, Lianwen Jin
In recent years, the optical character recognition (OCR) field has been proliferating with plentiful cutting-edge approaches for a wide spectrum of tasks. However, these approaches are task-specifically designed with divergent paradigms, architectures, and training strategies, which significantly increases the complexity of research and maintenance and hinders the fast deployment in applications. To this end, we propose UPOCR, a simple-yet-effective generalist model for Unified Pixel-level OCR interface. Specifically, the UPOCR unifies the paradigm of diverse OCR tasks as image-to-image transformation and the architecture as a vision Transformer (ViT)-based encoder-decoder. Learnable task prompts are introduced to push the general feature representations extracted by the encoder toward task-specific spaces, endowing the decoder with task awareness. Moreover, the model training is uniformly aimed at minimizing the discrepancy between the generated and ground-truth images regardless of the inhomogeneity among tasks. Experiments are conducted on three pixel-level OCR tasks including text removal, text segmentation, and tampered text detection. Without bells and whistles, the experimental results showcase that the proposed method can simultaneously achieve state-of-the-art performance on three tasks with a unified single model, which provides valuable strategies and insights for future research on generalist OCR models. Code will be publicly available.
Authors: Tero Karras, Miika Aittala, Jaakko Lehtinen, Janne Hellsten, Timo Aila, Samuli Laine
Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM diffusion model architecture, without altering its high-level structure. Observing uncontrolled magnitude changes and imbalances in both the network activations and weights over the course of training, we redesign the network layers to preserve activation, weight, and update magnitudes on expectation. We find that systematic application of this philosophy eliminates the observed drifts and imbalances, resulting in considerably better networks at equal computational complexity. Our modifications improve the previous record FID of 2.41 in ImageNet-512 synthesis to 1.81, achieved using fast deterministic sampling.
As an independent contribution, we present a method for setting the exponential moving average (EMA) parameters post-hoc, i.e., after completing the training run. This allows precise tuning of EMA length without the cost of performing several training runs, and reveals its surprising interactions with network architecture, training time, and guidance.
Authors: Muhammad Umer Ramzan, Usman Ali, Syed Haider Abbas Naqvi, Zeeshan Aslam, Tehseen, Husnain Ali, Muhammad Faheem
The auto-management of vehicle entrance and parking in any organization is a complex challenge encompassing record-keeping, efficiency, and security concerns. Manual methods for tracking vehicles and finding parking spaces are slow and a waste of time. To solve the problem of auto management of vehicle entrance and parking, we have utilized state-of-the-art deep learning models and automated the process of vehicle entrance and parking into any organization. To ensure security, our system integrated vehicle detection, license number plate verification, and face detection and recognition models to ensure that the person and vehicle are registered with the organization. We have trained multiple deep-learning models for vehicle detection, license number plate detection, face detection, and recognition, however, the YOLOv8n model outperformed all the other models. Furthermore, License plate recognition is facilitated by Google's Tesseract-OCR Engine. By integrating these technologies, the system offers efficient vehicle detection, precise identification, streamlined record keeping, and optimized parking slot allocation in buildings, thereby enhancing convenience, accuracy, and security. Future research opportunities lie in fine-tuning system performance for a wide range of real-world applications.
Authors: Xinpeng Liu, Haowen Hou, Yanchao Yang, Yong-Lu Li, Cewu Lu
Human-scene Interaction (HSI) generation is a challenging task and crucial for various downstream tasks. However, one of the major obstacles is the limited data scale. High-quality data with simultaneously captured human and 3D environments is rare, resulting in limited data diversity and complexity. In this work, we argue that interaction with a scene is essentially interacting with the space occupancy of the scene from an abstract physical perspective, leading us to a unified novel view of Human-Occupancy Interaction. By treating pure motion sequences as records of humans interacting with invisible scene occupancy, we can aggregate motion-only data into a large-scale paired human-occupancy interaction database: Motion Occupancy Base (MOB). Thus, the need for costly paired motion-scene datasets with high-quality scene scans can be substantially alleviated. With this new unified view of Human-Occupancy interaction, a single motion controller is proposed to reach the target state given the surrounding occupancy. Once trained on MOB with complex occupancy layout, the controller could handle cramped scenes and generalize well to general scenes with limited complexity. With no GT 3D scenes for training, our method can generate realistic and stable HSI motions in diverse scenarios, including both static and dynamic scenes. Our code and data would be made publicly available at https://foruck.github.io/occu-page/.
Authors: Vasileios Baltatzis, Rolandos Alexandros Potamias, Evangelos Ververas, Guanxiong Sun, Jiankang Deng, Stefanos Zafeiriou
Sign Languages (SL) serve as the predominant mode of communication for the Deaf and Hard of Hearing communities. The advent of deep learning has aided numerous methods in SL recognition and translation, achieving remarkable results. However, Sign Language Production (SLP) poses a challenge for the computer vision community as the motions generated must be realistic and have precise semantic meanings. Most SLP methods rely on 2D data, thus impeding their ability to attain a necessary level of realism. In this work, we propose a diffusion-based SLP model trained on a curated large-scale dataset of 4D signing avatars and their corresponding text transcripts. The proposed method can generate dynamic sequences of 3D avatars from an unconstrained domain of discourse using a diffusion process formed on a novel and anatomically informed graph neural network defined on the SMPL-X body skeleton. Through a series of quantitative and qualitative experiments, we show that the proposed method considerably outperforms previous methods of SLP. We believe that this work presents an important and necessary step towards realistic neural sign avatars, bridging the communication gap between Deaf and hearing communities. The code, method and generated data will be made publicly available.
Authors: Bo Ding, Zhenfeng Fan, Shuang Yang, Shihong Xia
Generating realistic talking faces is an interesting and long-standing topic in the field of computer vision. Although significant progress has been made, it is still challenging to generate high-quality dynamic faces with personalized details. This is mainly due to the inability of the general model to represent personalized details and the generalization problem to unseen controllable parameters. In this work, we propose Myportrait, a simple, general, and flexible framework for neural portrait generation. We incorporate personalized prior in a monocular video and morphable prior in 3D face morphable space for generating personalized details under novel controllable parameters. Our proposed framework supports both video-driven and audio-driven face animation given a monocular video of a single person. Distinguished by whether the test data is sent to training or not, our method provides a real-time online version and a high-quality offline version. Comprehensive experiments in various metrics demonstrate the superior performance of our method over the state-of-the-art methods. The code will be publicly available.
Authors: Jianghui Zhang, Yuanyuan Wang, Lina Guo, Jixiang Luo, Tongda Xu, Yan Wang, Zhi Wang, Hongwei Qin
JPEG is still the most widely used image compression algorithm. Most image compression algorithms only consider uncompressed original image, while ignoring a large number of already existing JPEG images. Recently, JPEG recompression approaches have been proposed to further reduce the size of JPEG files. However, those methods only consider JPEG lossless recompression, which is just a special case of the rate-distortion theorem. In this paper, we propose a unified lossly and lossless JPEG recompression framework, which consists of learned quantization table and Markovian hierarchical variational autoencoders. Experiments show that our method can achieve arbitrarily low distortion when the bitrate is close to the upper bound, namely the bitrate of the lossless compression model. To the best of our knowledge, this is the first learned method that bridges the gap between lossy and lossless recompression of JPEG images.
Authors: Wentao Qu, Yuantian Shao, Lingwu Meng, Xiaoshui Huang, Liang Xiao
Point cloud upsampling (PCU) enriches the representation of raw point clouds, significantly improving the performance in downstream tasks such as classification and reconstruction. Most of the existing point cloud upsampling methods focus on sparse point cloud feature extraction and upsampling module design. In a different way, we dive deeper into directly modelling the gradient of data distribution from dense point clouds. In this paper, we proposed a conditional denoising diffusion probability model (DDPM) for point cloud upsampling, called PUDM. Specifically, PUDM treats the sparse point cloud as a condition, and iteratively learns the transformation relationship between the dense point cloud and the noise. Simultaneously, PUDM aligns with a dual mapping paradigm to further improve the discernment of point features. In this context, PUDM enables learning complex geometry details in the ground truth through the dominant features, while avoiding an additional upsampling module design. Furthermore, to generate high-quality arbitrary-scale point clouds during inference, PUDM exploits the prior knowledge of the scale between sparse point clouds and dense point clouds during training by parameterizing a rate factor. Moreover, PUDM exhibits strong noise robustness in experimental results. In the quantitative and qualitative evaluations on PU1K and PUGAN, PUDM significantly outperformed existing methods in terms of Chamfer Distance (CD) and Hausdorff Distance (HD), achieving state of the art (SOTA) performance.
Authors: Chenhuan Li, Meihua Xiao, zehuan li, Mengxi Gao
Recently, vision transformers have performed well in various computer vision tasks, including voxel 3D reconstruction. However, the windows of the vision transformer are not multi-scale, and there is no connection between the windows, which limits the accuracy of voxel 3D reconstruction . Therefore, we propose a shifted windows attention voxel 3D reconstruction network. To the best of our knowledge, this is the first work to apply shifted window attention to voxel 3D reconstruction. Experimental results on ShapeNet verify our method achieves SOTA accuracy in single-view reconstruction.
Authors: Rui Huang (1), Binbin Jiang (1), Qingyi Zhao (1), William Wang (2), Yuxiang Zhang (1), Qing Guo (3 and 4) ((1) College of Computer Science and Technology, Civil Aviation University of China, China, (2) University of South Carolina, The USA, (3) IHPC, Agency for Science, Technology and Research, Singapore, (4) CFAR, Agency for Science, Technology and Research, Singapore)
In this work, we aim to detect the changes caused by object variations in a scene represented by the neural radiance fields (NeRFs). Given an arbitrary view and two sets of scene images captured at different timestamps, we can predict the scene changes in that view, which has significant potential applications in scene monitoring and measuring. We conducted preliminary studies and found that such an exciting task cannot be easily achieved by utilizing existing NeRFs and 2D change detection methods with many false or missing detections. The main reason is that the 2D change detection is based on the pixel appearance difference between spatial-aligned image pairs and neglects the stereo information in the NeRF. To address the limitations, we propose the C-NERF to represent scene changes as directional consistency difference-based NeRF, which mainly contains three modules. We first perform the spatial alignment of two NeRFs captured before and after changes. Then, we identify the change points based on the direction-consistent constraint; that is, real change points have similar change representations across view directions, but fake change points do not. Finally, we design the change map rendering process based on the built NeRFs and can generate the change map of an arbitrarily specified view direction. To validate the effectiveness, we build a new dataset containing ten scenes covering diverse scenarios with different changing objects. Our approach surpasses state-of-the-art 2D change detection and NeRF-based methods by a significant margin.
Authors: Hyunjik Kim, Matthias Bauer, Lucas Theis, Jonathan Richard Schwarz, Emilien Dupont
Most neural compression models are trained on large datasets of images or videos in order to generalize to unseen data. Such generalization typically requires large and expressive architectures with a high decoding complexity. Here we introduce C3, a neural compression method with strong rate-distortion (RD) performance that instead overfits a small model to each image or video separately. The resulting decoding complexity of C3 can be an order of magnitude lower than neural baselines with similar RD performance. C3 builds on COOL-CHIC (Ladune et al.) and makes several simple and effective improvements for images. We further develop new methodology to apply C3 to videos. On the CLIC2020 image benchmark, we match the RD performance of VTM, the reference implementation of the H.266 codec, with less than 3k MACs/pixel for decoding. On the UVG video benchmark, we match the RD performance of the Video Compression Transformer (Mentzer et al.), a well-established neural video codec, with less than 5k MACs/pixel for decoding.
Authors: Hao-Chun Yang, Ole Andreassen, Lars Tjelta Westlye, Andre F. Marquand, Christian F. Beckmann, Thomas Wolfers
The detection of heterogeneous mental disorders based on brain readouts remains challenging due to the complexity of symptoms and the absence of reliable biomarkers. This paper introduces CAM (Cortical Anomaly Detection through Masked Image Modeling), a novel self-supervised framework designed for the unsupervised detection of complex brain disorders using cortical surface features. We employ this framework for the detection of individuals on the psychotic spectrum and demonstrate its capabilities compared to state-ofthe-art methods, achieving an AUC of 0.696 for Schizoaffective and 0.769 for Schizophreniform, without the need for any labels. Furthermore, the analysis of atypical cortical regions includes Pars Triangularis and several frontal areas, often implicated in schizophrenia, provide further confidence in our approach. Altogether, we demonstrate a scalable approach for anomaly detection of complex brain disorders based on cortical abnormalities.
Authors: Xu Shi, Chuanchen Luo, Junran Peng, Hongwen Zhang, Yunlian Sun
Recently, significant progress has been made in text-based motion generation, enabling the generation of diverse and high-quality human motions that conform to textual descriptions. However, it remains challenging to generate fine-grained or stylized motions due to the lack of datasets annotated with detailed textual descriptions. By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for human motion generation. Specifically, we first parse previous vague textual annotation into fine-grained description of different body parts by leveraging a large language model (GPT-3.5). We then use these fine-grained descriptions to guide a transformer-based diffusion model. FG-MDM can generate fine-grained and stylized motions even outside of the distribution of the training data. Our experimental results demonstrate the superiority of FG-MDM over previous methods, especially the strong generalization capability. We will release our fine-grained textual annotations for HumanML3D and KIT.
Authors: Tianshun Han, Shengnan Gui, Yiqing Huang, Baihui Li, Lijian Liu, Benjia Zhou, Ning Jiang, Quan Lu, Ruicong Zhi, Yanyan Liang, Du Zhang, Jun Wan
Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argue that visual and textual cues are not trivial information. Therefore, we present a novel framework, namely PMMTalk, using complementary Pseudo Multi-Modal features for improving the accuracy of facial animation. The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder. Specifically, the PMMTalk encoder employs the off-the-shelf talking head generation architecture and speech recognition technology to extract visual and textual information from speech, respectively. Subsequently, the cross-modal alignment module aligns the audio-image-text features at temporal and semantic levels. Then PMMTalk decoder is employed to predict lip-syncing facial blendshape coefficients. Contrary to prior methods, PMMTalk only requires an additional random reference face image but yields more accurate results. Additionally, it is artist-friendly as it seamlessly integrates into standard animation production workflows by introducing facial blendshape coefficients. Finally, given the scarcity of 3D talking face datasets, we introduce a large-scale 3D Chinese Audio-Visual Facial Animation (3D-CAVFA) dataset. Extensive experiments and user studies show that our approach outperforms the state of the art. We recommend watching the supplementary video.
Authors: Fengyuan Shi, Jiaxi Gu, Hang Xu, Songcen Xu, Wei Zhang, Limin Wang
Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image editing, while downstream video synthesis tasks are less explored for several reasons. First, it requires huge memory and compute overhead to train a video generation foundation model. Even with video foundation models, additional costly training is still required for downstream video synthesis tasks. Second, although some works extend image diffusion models into videos in a training-free manner, temporal consistency cannot be well kept. Finally, these adaption methods are specifically designed for one task and fail to generalize to different downstream video synthesis tasks. To mitigate these issues, we propose a training-free general-purpose video synthesis framework, coined as BIVDiff, via bridging specific image diffusion models and general text-to-video foundation diffusion models. Specifically, we first use an image diffusion model (like ControlNet, Instruct Pix2Pix) for frame-wise video generation, then perform Mixed Inversion on the generated video, and finally input the inverted latents into the video diffusion model for temporal smoothing. Decoupling image and video models enables flexible image model selection for different purposes, which endows the framework with strong task generalization and high efficiency. To validate the effectiveness and general use of BIVDiff, we perform a wide range of video generation tasks, including controllable video generation video editing, video inpainting and outpainting. Our project page is available at https://bivdiff.github.io.
Authors: Donggeun Yoon, Minseok Seo, Doyi Kim, Yeji Choi, Donghyeon Cho
Weather forecasting requires not only accuracy but also the ability to perform probabilistic prediction. However, deterministic weather forecasting methods do not support probabilistic predictions, and conversely, probabilistic models tend to be less accurate. To address these challenges, in this paper, we introduce the \textbf{\textit{D}}eterministic \textbf{\textit{G}}uidance \textbf{\textit{D}}iffusion \textbf{\textit{M}}odel (DGDM) for probabilistic weather forecasting, integrating benefits of both deterministic and probabilistic approaches. During the forward process, both the deterministic and probabilistic models are trained end-to-end. In the reverse process, weather forecasting leverages the predicted result from the deterministic model, using as an intermediate starting point for the probabilistic model. By fusing deterministic models with probabilistic models in this manner, DGDM is capable of providing accurate forecasts while also offering probabilistic predictions. To evaluate DGDM, we assess it on the global weather forecasting dataset (WeatherBench) and the common video frame prediction benchmark (Moving MNIST). We also introduce and evaluate the Pacific Northwest Windstorm (PNW)-Typhoon weather satellite dataset to verify the effectiveness of DGDM in high-resolution regional forecasting. As a result of our experiments, DGDM achieves state-of-the-art results not only in global forecasting but also in regional forecasting. The code is available at: \url{https://github.com/DongGeun-Yoon/DGDM}.
Authors: Zhu Yuke, Ruan Yumeng, Yang Lei, Guo Sheng
Detecting the objects in dense and rotated scenes is a challenging task. Recent works on this topic are mostly based on Faster RCNN or Retinanet. As they are highly dependent on the pre-set dense anchors and the NMS operation, the approach is indirect and suboptimal.The end-to-end DETR-based detectors have achieved great success in horizontal object detection and many other areas like segmentation, tracking, action recognition and etc.However, the DETR-based detectors perform poorly on dense rotated target tasks and perform worse than most modern CNN-based detectors. In this paper, we find the most significant reason for the poor performance is that the original attention can not accurately focus on the oriented targets. Accordingly, we propose Rotated object detection TRansformer (RotaTR) as an extension of DETR to oriented detection. Specifically, we design Rotation Sensitive deformable (RSDeform) attention to enhance the DETR's ability to detect oriented targets. It is used to build the feature alignment module and rotation-sensitive decoder for our model. We test RotaTR on four challenging-oriented benchmarks. It shows a great advantage in detecting dense and oriented objects compared to the original DETR. It also achieves competitive results when compared to the state-of-the-art.
Authors: Lalit Pandey, Samantha M. W. Wood, Justin N. Wood
Vision transformers (ViTs) are top performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological learning because ViTs are thought to be more data hungry than brains, with ViTs requiring more training data to reach similar levels of performance. To test this assumption, we directly compared the learning abilities of ViTs and animals, by performing parallel controlled rearing experiments on ViTs and newborn chicks. We first raised chicks in impoverished visual environments containing a single object, then simulated the training data available in those environments by building virtual animal chambers in a video game engine. We recorded the first-person images acquired by agents moving through the virtual chambers and used those images to train self supervised ViTs that leverage time as a teaching signal, akin to biological visual systems. When ViTs were trained through the eyes of newborn chicks, the ViTs solved the same view invariant object recognition tasks as the chicks. Thus, ViTs were not more data hungry than newborn visual systems: both learned view invariant object representations in impoverished visual environments. The flexible and generic attention based learning mechanism in ViTs combined with the embodied data streams available to newborn animals appears sufficient to drive the development of animal-like object recognition.
For the point cloud registration task, a significant challenge arises from non-overlapping points that consume extensive computational resources while negatively affecting registration accuracy. In this paper, we introduce a dynamic approach, widely utilized to improve network efficiency in computer vision tasks, to the point cloud registration task. We employ an iterative registration process on point cloud data multiple times to identify regions where matching points cluster, ultimately enabling us to remove noisy points. Specifically, we begin with deep global sampling to perform coarse global registration. Subsequently, we employ the proposed refined node proposal module to further narrow down the registration region and perform local registration. Furthermore, we utilize a spatial consistency-based classifier to evaluate the results of each registration stage. The model terminates once it reaches sufficient confidence, avoiding unnecessary computations. Extended experiments demonstrate that our model significantly reduces time consumption compared to other methods with similar results, achieving a speed improvement of over 41% on indoor dataset (3DMatch) and 33% on outdoor datasets (KITTI) while maintaining competitive registration recall requirements.
Authors: Dongkeun Kim, Youngkil Song, Minsu Cho, Suha Kwak
Group activity detection (GAD) is the task of identifying members of each group and classifying the activity of the group at the same time in a video. While GAD has been studied recently, there is still much room for improvement in both dataset and methodology due to their limited capability to address practical GAD scenarios. To resolve these issues, we first present a new dataset, dubbed Caf\'e. Unlike existing datasets, Caf\'e is constructed primarily for GAD and presents more practical evaluation scenarios and metrics, as well as being large-scale and providing rich annotations. Along with the dataset, we propose a new GAD model that deals with an unknown number of groups and latent group members efficiently and effectively. We evaluated our model on three datasets including Caf\'e, where it outperformed previous work in terms of both accuracy and inference speed. Both our dataset and code base will be open to the public to promote future research on GAD.
Authors: Donghao Li, Yang Cao, Yuan Yao
Privacy-preserving data release algorithms have gained increasing attention for their ability to protect user privacy while enabling downstream machine learning tasks. However, the utility of current popular algorithms is not always satisfactory. Mixup of raw data provides a new way of data augmentation, which can help improve utility. However, its performance drastically deteriorates when differential privacy (DP) noise is added. To address this issue, this paper draws inspiration from the recently observed Neural Collapse (NC) phenomenon, which states that the last layer features of a neural network concentrate on the vertices of a simplex as Equiangular Tight Frame (ETF). We propose a scheme to mixup the Neural Collapse features to exploit the ETF simplex structure and release noisy mixed features to enhance the utility of the released data. By using Gaussian Differential Privacy (GDP), we obtain an asymptotic rate for the optimal mixup degree. To further enhance the utility and address the label collapse issue when the mixup degree is large, we propose a Hierarchical sampling method to stratify the mixup samples on a small number of classes. This method remarkably improves utility when the number of classes is large. Extensive experiments demonstrate the effectiveness of our proposed method in protecting against attacks and improving utility. In particular, our approach shows significantly improved utility compared to directly training classification networks with DPSGD on CIFAR100 and MiniImagenet datasets, highlighting the benefits of using privacy-preserving data release. We release reproducible code in https://github.com/Lidonghao1996/NeuroMixGDP.
Authors: Iraj Abedi, Mahsa Vali, Bentolhoda Otroshi, Maryam Zamanian, Hamidreza Bolhasani
Introduction: During the COVID-19 pandemic, computed tomography (CT) was a popular method for diagnosing COVID-19 patients. HRCT (High-Resolution Computed Tomography) is a form of computed tomography that uses advanced methods to improve image resolution. Publicly accessible COVID-19 CT image datasets are very difficult to come by due to privacy concerns, which impedes the study and development of AI-powered COVID-19 diagnostic algorithms based on CT images. Data description: To address this problem, we have introduced HRCTCov19, a new COVID-19 high-resolution chest CT scan image dataset that includes not only COVID-19 cases of Ground Glass Opacity (GGO), Crazy Paving, and Air Space Consolidation but also CT images of cases with negative COVID-19. The HRCTCov19 dataset, which includes slice-level, and patient-level labels, has the potential to aid COVID-19 research, especially for diagnosis and differentiation using artificial intelligence algorithms, machine learning, and deep learning methods. This dataset is accessible through the web at: this http URL and includes 181,106 chest HRCT images from 395 patients with four labels: GGO, Crazy Paving, Air Space Consolidation, and Negative. Keywords: COVID-19, CT scan, Computed Tomography, Chest Image, Dataset, Medical Imaging
Authors: Ming Dai, Enhui Zheng, Zhenhua Feng, Jiahao Chen, Wankou Yang
Image retrieval has emerged as a prominent solution for the self-localization task of unmanned aerial vehicles (UAVs). However, this approach involves complicated pre-processing and post-processing operations, placing significant demands on both computational and storage resources. To mitigate this issue, this paper presents an end-to-end positioning framework, namely Finding Point with Image (FPI), which aims to directly identify the corresponding location of a UAV in satellite-view images via a UAV-view image. To validate the practicality of our framework, we construct a paired dataset, namely UL14, that consists of UAV and satellite views. In addition, we establish two transformer-based baseline models, Post Fusion and Mix Fusion, for end-to-end training and inference. Through experiments, we can conclude that fusion in the backbone network can achieve better performance than later fusion. Furthermore, considering the singleness of paired images, Random Scale Crop (RSC) is proposed to enrich the diversity of the paired data. Also, the ratio and weight of positive and negative samples play a key role in model convergence. Therefore, we conducted experimental verification and proposed a Weight Balance Loss (WBL) to weigh the impact of positive and negative samples. Last, our proposed baseline based on Mix Fusion structure exhibits superior performance in time and storage efficiency, amounting to just 1/24 and 1/68, respectively, while delivering comparable or even superior performance compared to the image retrieval method. The dataset and code will be made publicly available.
Authors: Yangtao Wang (M-PSI), Xi Shen, Yuan Yuan (MIT CSAIL), Yuming Du, Maomao Li, Shell Xu Hu, James L Crowley (M-PSI), Dominique Vaufreydaz (M-PSI)
In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, where the edge between each pair of patches is labeled with a similarity score between patches using features learned by the transformer. Detection and segmentation of salient objects is then formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6%, respectively, when tested with the VOC07, VOC12, and COCO20K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets, respectively, compared to current state-of-the-art techniques. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.
Authors: Zikang Xu, Jun Li, Qingsong Yao, Han Li, S. Kevin Zhou
Machine learning-enabled medical imaging analysis has become a vital part of the automatic diagnosis system. However, machine learning, especially deep learning models have been shown to demonstrate a systematic bias towards certain subgroups of people. For instance, they yield a preferential predictive performance to males over females, which is unfair and potentially harmful especially in healthcare scenarios. In this literature survey, we give a comprehensive review of the current progress of fairness studies in medical image analysis (MedIA) and healthcare. Specifically, we first discuss the definitions of fairness, the source of unfairness and potential solutions. Then, we discuss current research on fairness for MedIA categorized by fairness evaluation and unfairness mitigation. Furthermore, we conduct extensive experiments to evaluate the fairness of different medical imaging tasks. Finally, we discuss the challenges and future directions in developing fair MedIA and healthcare applications
Authors: Sachit Kuhar, Alexey Tumanov, Judy Hoffman
Efficient inference of Deep Neural Networks (DNNs) is essential to making AI ubiquitous. Two important algorithmic techniques have shown promise for enabling efficient inference - sparsity and binarization. These techniques translate into weight sparsity and weight repetition at the hardware-software level enabling the deployment of DNNs with critically low power and latency requirements. We propose a new method called signed-binary networks to improve efficiency further (by exploiting both weight sparsity and weight repetition together) while maintaining similar accuracy. Our method achieves comparable accuracy on ImageNet and CIFAR10 datasets with binary and can lead to 69% sparsity. We observe real speedup when deploying these models on general-purpose devices and show that this high percentage of unstructured sparsity can lead to a further reduction in energy consumption on ASICs.
Authors: Bowen Lei, Dongkuan Xu, Ruqi Zhang, Shuren He, Bani K. Mallick
Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these costs, however, the sparsity constraints add difficulty to the optimization, resulting in an increase in training time and instability. In this work, we aim to overcome this problem and achieve space-time co-efficiency. To accelerate and stabilize the convergence of sparse training, we analyze the gradient changes and develop an adaptive gradient correction method. Specifically, we approximate the correlation between the current and previous gradients, which is used to balance the two gradients to obtain a corrected gradient. Our method can be used with the most popular sparse training pipelines under both standard and adversarial setups. Theoretically, we prove that our method can accelerate the convergence rate of sparse training. Extensive experiments on multiple datasets, model architectures, and sparsities demonstrate that our method outperforms leading sparse training methods by up to \textbf{5.0\%} in accuracy given the same number of training epochs, and reduces the number of training epochs by up to \textbf{52.1\%} to achieve the same accuracy. Our code is available on: \url{https://github.com/StevenBoys/AGENT}.
Authors: Sifan Zhou, Zhi Tian, Xiangxiang Chu, Xinyu Zhang, Bo Zhang, Xiaobo Lu, Chengjian Feng, Zequn Jie, Patrick Yin Chiang, Lin Ma
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolutions (known as SPConv) to speed up training and inference, which puts a hard barrier for deployment, especially for on-device applications. In this paper, to tackle the challenge of efficient 3D object detection from an industry perspective, we devise a deployment-friendly pillar-based 3D detector, termed FastPillars. First, we introduce a novel lightweight Max-and-Attention Pillar Encoding (MAPE) module specially for enhancing small 3D objects. Second, we propose a simple yet effective principle for designing a backbone in pillar-based 3D detection. We construct FastPillars based on these designs, achieving high performance and low latency without SPConv. Extensive experiments on two large-scale datasets demonstrate the effectiveness and efficiency of FastPillars for on-device 3D detection regarding both performance and speed. Specifically, FastPillars delivers state-of-the-art accuracy on Waymo Open Dataset with 1.8X speed up and 3.8 mAPH/L2 improvement over CenterPoint (SPConv-based). Our code is publicly available at: https://github.com/StiphyJay/FastPillars.
Authors: Danila Rukhovich, Anna Vorontsova, Anton Konushin
Recently, sparse 3D convolutions have changed 3D object detection. Performing on par with the voting-based approaches, 3D CNNs are memory-efficient and scale to large scenes better. However, there is still room for improvement. With a conscious, practice-oriented approach to problem-solving, we analyze the performance of such methods and localize the weaknesses. Applying modifications that resolve the found issues one by one, we end up with TR3D: a fast fully-convolutional 3D object detection model trained end-to-end, that achieves state-of-the-art results on the standard benchmarks, ScanNet v2, SUN RGB-D, and S3DIS. Moreover, to take advantage of both point cloud and RGB inputs, we introduce an early fusion of 2D and 3D features. We employ our fusion module to make conventional 3D object detection methods multimodal and demonstrate an impressive boost in performance. Our model with early feature fusion, which we refer to as TR3D+FF, outperforms existing 3D object detection approaches on the SUN RGB-D dataset. Overall, besides being accurate, both TR3D and TR3D+FF models are lightweight, memory-efficient, and fast, thereby marking another milestone on the way toward real-time 3D object detection. Code is available at https://github.com/SamsungLabs/tr3d .
Authors: Danil Galeev, Polina Popenova, Anna Vorontsova, Anton Konushin
Recent advances in interactive segmentation (IS) allow speeding up and simplifying image editing and labeling greatly. The majority of modern IS approaches accept user input in the form of clicks. However, using clicks may require too many user interactions, especially when selecting small objects, minor parts of an object, or a group of objects of the same type. In this paper, we consider such a natural form of user interaction as a loose contour, and introduce a contour-based IS method. We evaluate the proposed method on the standard segmentation benchmarks, our novel UserContours dataset, and its subset UserContours-G containing difficult segmentation cases. Through experiments, we demonstrate that a single contour provides the same accuracy as multiple clicks, thus reducing the required amount of user interactions.
Authors: Dovile Juodelyte, Amelia Jiménez-Sánchez, Veronika Cheplygina
While a key component to the success of deep learning is the availability of massive amounts of training data, medical image datasets are often limited in diversity and size. Transfer learning has the potential to bridge the gap between related yet different domains. For medical applications, however, it remains unclear whether it is more beneficial to pre-train on natural or medical images. We aim to shed light on this problem by comparing initialization on ImageNet and RadImageNet on seven medical classification tasks. Our work includes a replication study, which yields results contrary to previously published findings. In our experiments, ResNet50 models pre-trained on ImageNet tend to outperform those trained on RadImageNet. To gain further insights, we investigate the learned representations using Canonical Correlation Analysis (CCA) and compare the predictions of the different models. Our results indicate that, contrary to intuition, ImageNet and RadImageNet may converge to distinct intermediate representations, which appear to diverge further during fine-tuning. Despite these distinct representations, the predictions of the models remain similar. Our findings show that the similarity between networks before and after fine-tuning does not correlate with performance gains, suggesting that the advantages of transfer learning might not solely originate from the reuse of features in the early layers of a convolutional neural network.
Authors: Zhenmei Shi, Yifei Ming, Ying Fan, Frederic Sala, Yingyu Liang
The ability to generalize to unseen domains is crucial for machine learning systems deployed in the real world, especially when we only have data from limited training domains. In this paper, we propose a simple and effective regularization method based on the nuclear norm of the learned features for domain generalization. Intuitively, the proposed regularizer mitigates the impacts of environmental features and encourages learning domain-invariant features. Theoretically, we provide insights into why nuclear norm regularization is more effective compared to ERM and alternative regularization methods. Empirically, we conduct extensive experiments on both synthetic and real datasets. We show nuclear norm regularization achieves strong performance compared to baselines in a wide range of domain generalization tasks. Moreover, our regularizer is broadly applicable with various methods such as ERM and SWAD with consistently improved performance, e.g., 1.7% and 0.9% test accuracy improvements respectively on the DomainBed benchmark.
Authors: Zoey Guo, Yiwen Tang, Ray Zhang, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li
Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fail to weigh the relative importance of different views. In this paper, we propose ViewRefer, a multi-view framework for 3D visual grounding exploring how to grasp the view knowledge from both text and 3D modalities. For the text branch, ViewRefer leverages the diverse linguistic knowledge of large-scale language models, e.g., GPT, to expand a single grounding text to multiple geometry-consistent descriptions. Meanwhile, in the 3D modality, a transformer fusion module with inter-view attention is introduced to boost the interaction of objects across views. On top of that, we further present a set of learnable multi-view prototypes, which memorize scene-agnostic knowledge for different views, and enhance the framework from two perspectives: a view-guided attention module for more robust text features, and a view-guided scoring strategy during the final prediction. With our designed paradigm, ViewRefer achieves superior performance on three benchmarks and surpasses the second-best by +2.8%, +1.5%, and +1.35% on Sr3D, Nr3D, and ScanRefer. Code is released at https://github.com/Ivan-Tang-3D/ViewRefer3D.
Authors: Chen Xie, Francesco Daghero, Yukai Chen, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari
Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring. Previous work has shown that Deep Learning (DL) can yield superior performance on this task. However, the literature was missing an extensive comparative analysis of various efficient DL architectures for IR array-based people counting, that considers not only their accuracy, but also the cost of deploying them on memory- and energy-constrained Internet of Things (IoT) edge nodes. In this work, we address this need by comparing 6 different DL architectures on a novel dataset composed of IR images collected from a commercial 8x8 array, which we made openly available. With a wide architectural exploration of each model type, we obtain a rich set of Pareto-optimal solutions, spanning cross-validated balanced accuracy scores in the 55.70-82.70% range. When deployed on a commercial Microcontroller (MCU) by STMicroelectronics, the STM32L4A6ZG, these models occupy 0.41-9.28kB of memory, and require 1.10-7.74ms per inference, while consuming 17.18-120.43 $\mu$J of energy. Our models are significantly more accurate than a previous deterministic method (up to +39.9%), while being up to 3.53x faster and more energy efficient. Further, our models' accuracy is comparable to state-of-the-art DL solutions on similar resolution sensors, despite a much lower complexity. All our models enable continuous, real-time inference on a MCU-based IoT node, with years of autonomous operation without battery recharging.
Authors: Ali Borji
The ability of image and video generation models to create photorealistic images has reached unprecedented heights, making it difficult to distinguish between real and fake images in many cases. However, despite this progress, a gap remains between the quality of generated images and those found in the real world. To address this, we have reviewed a vast body of literature from both academic publications and social media to identify qualitative shortcomings in image generation models, which we have classified into five categories. By understanding these failures, we can identify areas where these models need improvement, as well as develop strategies for detecting deep fakes. The prevalence of deep fakes in today's society is a serious concern, and our findings can help mitigate their negative impact.
Authors: Naiyu Fang, Lemiao Qiu, Shuyou Zhang, Zili Wang, Kerui Hu
Virtual try-on is a promising computer vision topic with a high commercial value wherein a new garment is visually worn on a person with a photo-realistic effect. Previous studies conduct their shape and content inference at one stage, employing a single-scale warping mechanism and a relatively unsophisticated content inference mechanism. These approaches have led to suboptimal results in terms of garment warping and skin reservation under challenging try-on scenarios. To address these limitations, we propose a novel virtual try-on method via progressive inference paradigm (PGVTON) that leverages a top-down inference pipeline and a general garment try-on strategy. Specifically, we propose a robust try-on parsing inference method by disentangling semantic categories and introducing consistency. Exploiting the try-on parsing as the shape guidance, we implement the garment try-on via warping-mapping-composition. To facilitate adaptation to a wide range of try-on scenarios, we adopt a covering more and selecting one warping strategy and explicitly distinguish tasks based on alignment. Additionally, we regulate StyleGAN2 to implement re-naked skin inpainting, conditioned on the target skin shape and spatial-agnostic skin features. Experiments demonstrate that our method has state-of-the-art performance under two challenging scenarios. The code will be available at https://github.com/NerdFNY/PGVTON.
Authors: Corinne Stucker, Vivien Sainte Fare Garnot, Konrad Schindler
Satellite image time series in the optical and infrared spectrum suffer from frequent data gaps due to cloud cover, cloud shadows, and temporary sensor outages. It has been a long-standing problem of remote sensing research how to best reconstruct the missing pixel values and obtain complete, cloud-free image sequences. We approach that problem from the perspective of representation learning and develop U-TILISE, an efficient neural model that is able to implicitly capture spatio-temporal patterns of the spectral intensities, and that can therefore be trained to map a cloud-masked input sequence to a cloud-free output sequence. The model consists of a convolutional spatial encoder that maps each individual frame of the input sequence to a latent encoding; an attention-based temporal encoder that captures dependencies between those per-frame encodings and lets them exchange information along the time dimension; and a convolutional spatial decoder that decodes the latent embeddings back into multi-spectral images. We experimentally evaluate the proposed model on EarthNet2021, a dataset of Sentinel-2 time series acquired all over Europe, and demonstrate its superior ability to reconstruct the missing pixels. Compared to a standard interpolation baseline, it increases the PSNR by 1.8 dB at previously seen locations and by 1.3 dB at unseen locations.
Authors: Mingxiao Li, Tingyu Qu, Ruicong Yao, Wei Sun, Marie-Francine Moens
Diffusion Probabilistic Models (DPM) have shown remarkable efficacy in the synthesis of high-quality images. However, their inference process characteristically requires numerous, potentially hundreds, of iterative steps, which could exaggerate the problem of exposure bias due to the training and inference discrepancy. Previous work has attempted to mitigate this issue by perturbing inputs during training, which consequently mandates the retraining of the DPM. In this work, we conduct a systematic study of exposure bias in DPM and, intriguingly, we find that the exposure bias could be alleviated with a novel sampling method that we propose, without retraining the model. We empirically and theoretically show that, during inference, for each backward time step $t$ and corresponding state $\hat{x}_t$, there might exist another time step $t_s$ which exhibits superior coupling with $\hat{x}_t$. Based on this finding, we introduce a sampling method named Time-Shift Sampler. Our framework can be seamlessly integrated to existing sampling algorithms, such as DDPM, DDIM and other high-order solvers, inducing merely minimal additional computations. Experimental results show our method brings significant and consistent improvements in FID scores on different datasets and sampling methods. For example, integrating Time-Shift Sampler to F-PNDM yields a FID=3.88, achieving 44.49\% improvements as compared to F-PNDM, on CIFAR-10 with 10 sampling steps, which is more performant than the vanilla DDIM with 100 sampling steps. We will release the code upon acceptance.
Authors: Arian Mousakhan, Thomas Brox, Jawad Tayyub
Traditional reconstruction-based methods have struggled to achieve competitive performance in anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD), a novel denoising process for image reconstruction conditioned on a target image. This ensures a coherent restoration that closely resembles the target image. Our anomaly detection framework employs the conditioning mechanism, where the target image is set as the input image to guide the denoising process, leading to a defectless reconstruction while maintaining nominal patterns. Anomalies are then localised via a pixel-wise and feature-wise comparison of the input and reconstructed image. Finally, to enhance the effectiveness of the feature-wise comparison, we introduce a domain adaptation method that utilises nearly identical generated examples from our conditioned denoising process to fine-tune the pretrained feature extractor. The veracity of DDAD is demonstrated on various datasets including MVTec and VisA benchmarks, achieving state-of-the-art results of \(99.8 \%\) and \(98.9 \%\) image-level AUROC respectively.
Authors: Adnan Munir, Abdul Jabbar Siddiqui, Saeed Anwar
To detect unmanned aerial vehicles (UAVs) in real-time, computer vision and deep learning approaches are evolving research areas. Interest in this problem has grown due to concerns regarding the possible hazards and misuse of employing UAVs in many applications. These include potential privacy violations. To address the concerns, vision-based object detection methods have been developed for UAV detection. However, UAV detection in images with complex backgrounds and weather artifacts like rain has yet to be reasonably studied. Hence, for this purpose, we prepared two training datasets. The first dataset has the sky as its background and is called the Sky Background Dataset (SBD). The second training dataset has more complex scenes (with diverse backgrounds) and is named the Complex Background Dataset (CBD). Additionally, two test sets were prepared: one containing clear images and the other with images with three rain artifacts, named the Rainy Test Set (RTS). This work also focuses on benchmarking state-of-the-art object detection models, and to the best of our knowledge, it is the first to investigate the performance of recent and popular vision-based object detection methods for UAV detection under challenging conditions such as complex backgrounds, varying UAV sizes, and low-to-heavy rainy conditions. The findings presented in the paper shall help provide insights concerning the performance of the selected models for UAV detection under challenging conditions and pave the way to develop more robust UAV detection methods. The codes and datasets are available at: https://github.com/AdnanMunir294/UAVD-CBRA.
Authors: Yingyi Chen, Qinghua Tao, Francesco Tonin, Johan A.K. Suykens
Recently, a new line of works has emerged to understand and improve self-attention in Transformers by treating it as a kernel machine. However, existing works apply the methods for symmetric kernels to the asymmetric self-attention, resulting in a nontrivial gap between the analytical understanding and numerical implementation. In this paper, we provide a new perspective to represent and optimize self-attention through asymmetric Kernel Singular Value Decomposition (KSVD), which is also motivated by the low-rank property of self-attention normally observed in deep layers. Through asymmetric KSVD, $i$) a primal-dual representation of self-attention is formulated, where the optimization objective is cast to maximize the projection variances in the attention outputs; $ii$) a novel attention mechanism, i.e., Primal-Attention, is proposed via the primal representation of KSVD, avoiding explicit computation of the kernel matrix in the dual; $iii$) with KKT conditions, we prove that the stationary solution to the KSVD optimization in Primal-Attention yields a zero-value objective. In this manner, KSVD optimization can be implemented by simply minimizing a regularization loss, so that low-rank property is promoted without extra decomposition. Numerical experiments show state-of-the-art performance of our Primal-Attention with improved efficiency. Moreover, we demonstrate that the deployed KSVD optimization regularizes Primal-Attention with a sharper singular value decay than that of the canonical self-attention, further verifying the great potential of our method. To the best of our knowledge, this is the first work that provides a primal-dual representation for the asymmetric kernel in self-attention and successfully applies it to modeling and optimization.
Authors: Akshatha Mohan, Joshua Peeples
We present a comprehensive analysis of quantitatively evaluating explainable artificial intelligence (XAI) techniques for remote sensing image classification. Our approach leverages state-of-the-art machine learning approaches to perform remote sensing image classification across multiple modalities. We investigate the results of the models qualitatively through XAI methods. Additionally, we compare the XAI methods quantitatively through various categories of desired properties. Through our analysis, we offer insights and recommendations for selecting the most appropriate XAI method(s) to gain a deeper understanding of the models' decision-making processes. The code for this work is publicly available.
Authors: Quynh Phung, Songwei Ge, Jia-Bin Huang
Driven by the scalable diffusion models trained on large-scale datasets, text-to-image synthesis methods have shown compelling results. However, these models still fail to precisely follow the text prompt involving multiple objects, attributes, or spatial compositions. In this paper, we reveal the potential causes in the diffusion model's cross-attention and self-attention layers. We propose two novel losses to refocus attention maps according to a given spatial layout during sampling. Creating the layouts manually requires additional effort and can be tedious. Therefore, we explore using large language models (LLM) to produce these layouts for our method. We conduct extensive experiments on the DrawBench, HRS, and TIFA benchmarks to evaluate our proposed method. We show that our proposed attention refocusing effectively improves the controllability of existing approaches.
Authors: Matthew Wallingford, Vivek Ramanujan, Alex Fang, Aditya Kusupati, Roozbeh Mottaghi, Aniruddha Kembhavi, Ludwig Schmidt, Ali Farhadi
We propose Neural Priming, a technique for adapting large pretrained models to distribution shifts and downstream tasks given few or no labeled examples. Presented with class names or unlabeled test samples, Neural Priming enables the model to recall and conditions its parameters on relevant data seen throughout pretraining, thereby priming it for the test distribution. Neural Priming can be performed at test time, even for pretraining datasets as large as LAION-2B. Performing lightweight updates on the recalled data significantly improves accuracy across a variety of distribution shift and transfer learning benchmarks. Concretely, in the zero-shot setting, we see a 2.45% improvement in accuracy on ImageNet and 3.81% accuracy improvement on average across standard transfer learning benchmarks. Further, using Neural Priming at inference to adapt to distribution shift, we see a 1.41% accuracy improvement on ImageNetV2. These results demonstrate the effectiveness of Neural Priming in addressing the challenge of limited labeled data and changing distributions. Code is available at github.com/RAIVNLab/neural-priming.
Authors: Zilun Zhang, Tiancheng Zhao, Yulong Guo, Jianwei Yin
Pre-trained Vision-Language Models (VLMs) utilizing extensive image-text paired data have demonstrated unprecedented image-text association capabilities, achieving remarkable results across various downstream tasks. A critical challenge is how to make use of existing large-scale pre-trained VLMs, which are trained on common objects, to perform the domain-specific transfer for accomplishing domain-related downstream tasks. A critical challenge is how to make use of existing large-scale pre-trained VLMs, which are trained on common objects, to perform the domain-specific transfer for accomplishing domain-related downstream tasks. In this paper, we propose a new framework that includes the Domain pre-trained Vision-Language Model (DVLM), bridging the gap between the General Vision-Language Model (GVLM) and domain-specific downstream tasks. Moreover, we present an image-text paired dataset in the field of remote sensing (RS), RS5M, which has 5 million RS images with English descriptions. The dataset is obtained from filtering publicly available image-text paired datasets and captioning label-only RS datasets with pre-trained VLM. These constitute the first large-scale RS image-text paired dataset. Additionally, we fine-tuned the CLIP model and tried several Parameter-Efficient Fine-Tuning methods on RS5M to implement the DVLM. Experimental results show that our proposed dataset is highly effective for various tasks, and our model GeoRSCLIP improves upon the baseline or previous state-of-the-art model by $3\%\sim20\%$ in Zero-shot Classification (ZSC), $3\%\sim6\%$ in Remote Sensing Cross-Modal Text-Image Retrieval (RSCTIR) and $4\%\sim5\%$ in Semantic Localization (SeLo) tasks. Dataset and models have been released in: \url{https://github.com/om-ai-lab/RS5M}.
Authors: Jiahang Cao, Ziqing Wang, Hanzhong Guo, Hao Cheng, Qiang Zhang, Renjing Xu
Spiking neural networks (SNNs) have ultra-low energy consumption and high biological plausibility due to their binary and bio-driven nature compared with artificial neural networks (ANNs). While previous research has primarily focused on enhancing the performance of SNNs in classification tasks, the generative potential of SNNs remains relatively unexplored. In our paper, we put forward Spiking Denoising Diffusion Probabilistic Models (SDDPM), a new class of SNN-based generative models that achieve high sample quality. To fully exploit the energy efficiency of SNNs, we propose a purely Spiking U-Net architecture, which achieves comparable performance to its ANN counterpart using only 4 time steps, resulting in significantly reduced energy consumption. Extensive experimental results reveal that our approach achieves state-of-the-art on the generative tasks and substantially outperforms other SNN-based generative models, achieving up to 12x and 6x improvement on the CIFAR-10 and the CelebA datasets, respectively. Moreover, we propose a threshold-guided strategy that can further improve the performances by 2.69% in a training-free manner. The SDDPM symbolizes a significant advancement in the field of SNN generation, injecting new perspectives and potential avenues of exploration. Our code is available at https://github.com/AndyCao1125/SDDPM.
Authors: Yifan Zhang, Zhiyu Zhu, Junhui Hou, Dapeng Wu
The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of multi-frame 3D object detection remains largely unexplored. In this paper, we present STEMD, a novel end-to-end framework for multi-frame 3D object detection based on the DETR-like paradigm. STEMD treats multi-frame 3D object detection as a sequence-to-sequence task and effectively captures spatial-temporal dependencies at both the feature and query levels. Specifically, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network, which represents queries as nodes in a graph and enables effective modeling of object interactions within a social context. To solve the problem of missing hard cases in the proposed output of the encoder in the current frame, we incorporate the output of the previous frame to initialize the query input of the decoder. Moreover, to mitigate the issue of redundant detection results, where the model generates numerous overlapping boxes from similar queries, we consider an IoU regularization term in the loss function, which can distinguish between queries matched with the ground-truth box and queries that are similar but unmatched during the refinement process, leading to reduced redundancy and more accurate detections. Through extensive experiments, we demonstrate the effectiveness of our approach in handling challenging scenarios, while incurring only a minor additional computational overhead. The code is available at \url{https://github.com/Eaphan/STEMD}.
Authors: Qi Bi, Shaodi You, Theo Gevers
Domain-generalized urban-scene semantic segmentation (USSS) aims to learn generalized semantic predictions across diverse urban-scene styles. Unlike domain gap challenges, USSS is unique in that the semantic categories are often similar in different urban scenes, while the styles can vary significantly due to changes in urban landscapes, weather conditions, lighting, and other factors. Existing approaches typically rely on convolutional neural networks (CNNs) to learn the content of urban scenes.
In this paper, we propose a Content-enhanced Mask TransFormer (CMFormer) for domain-generalized USSS. The main idea is to enhance the focus of the fundamental component, the mask attention mechanism, in Transformer segmentation models on content information. To achieve this, we introduce a novel content-enhanced mask attention mechanism. It learns mask queries from both the image feature and its down-sampled counterpart, as lower-resolution image features usually contain more robust content information and are less sensitive to style variations. These features are fused into a Transformer decoder and integrated into a multi-resolution content-enhanced mask attention learning scheme.
Extensive experiments conducted on various domain-generalized urban-scene segmentation datasets demonstrate that the proposed CMFormer significantly outperforms existing CNN-based methods for domain-generalized semantic segmentation, achieving improvements of up to 14.00\% in terms of mIoU (mean intersection over union). The source code is publicly available at \url{https://github.com/BiQiWHU/CMFormer}.
Authors: Yun Liu, Yu-Huan Wu, Shi-Chen Zhang, Li Liu, Min Wu, Ming-Ming Cheng
Tuberculosis (TB) is a major global health threat, causing millions of deaths annually. Although early diagnosis and treatment can greatly improve the chances of survival, it remains a major challenge, especially in developing countries. Recently, computer-aided tuberculosis diagnosis (CTD) using deep learning has shown promise, but progress is hindered by limited training data. To address this, we establish a large-scale dataset, namely the Tuberculosis X-ray (TBX11K) dataset, which contains 11,200 chest X-ray (CXR) images with corresponding bounding box annotations for TB areas. This dataset enables the training of sophisticated detectors for high-quality CTD. Furthermore, we propose a strong baseline, SymFormer, for simultaneous CXR image classification and TB infection area detection. SymFormer incorporates Symmetric Search Attention (SymAttention) to tackle the bilateral symmetry property of CXR images for learning discriminative features. Since CXR images may not strictly adhere to the bilateral symmetry property, we also propose Symmetric Positional Encoding (SPE) to facilitate SymAttention through feature recalibration. To promote future research on CTD, we build a benchmark by introducing evaluation metrics, evaluating baseline models reformed from existing detectors, and running an online challenge. Experiments show that SymFormer achieves state-of-the-art performance on the TBX11K dataset. The data, code, and models will be released at https://github.com/yun-liu/Tuberculosis.
Authors: Alexander Ziller, Ayhan Can Erdur, Marwa Trigui, Alp Güvenir, Tamara T. Mueller, Philip Müller, Friederike Jungmann, Johannes Brandt, Jan Peeken, Rickmer Braren, Daniel Rueckert, Georgios Kaissis
Training Artificial Intelligence (AI) models on 3D images presents unique challenges compared to the 2D case: Firstly, the demand for computational resources is significantly higher, and secondly, the availability of large datasets for pre-training is often limited, impeding training success. This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. Our method employs attention pooling to learn to assign each slice an importance weight and, by that, obtain a weighted average of all 2D slices. These weights directly quantify the contribution of each slice to the contribution and thus make the model prediction inspectable. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods. Furthermore, we compare the in-built interpretability of our approach to HiResCam, a state-of-the-art retrospective interpretability approach.
Authors: Anatole Moureaux, Chloé Chopin, Laurent Jacques, Flavio Abreu Araujo
We present a demonstration of image classification using an echo-state network (ESN) relying on a single simulated spintronic nanostructure known as the vortex-based spin-torque oscillator (STVO) delayed in time. We employ an ultrafast data-driven simulation framework called the data-driven Thiele equation approach (DD-TEA) to simulate the STVO dynamics. This allows us to avoid the challenges associated with repeated experimental manipulation of such a nanostructured system. We showcase the versatility of our solution by successfully applying it to solve classification challenges with the MNIST, EMNIST-letters and Fashion MNIST datasets. Through our simulations, we determine that within a large ESN the results obtained using the STVO dynamics as an activation function are comparable to the ones obtained with other conventional nonlinear activation functions like the reLU and the sigmoid. While achieving state-of-the-art accuracy levels on the MNIST dataset, our model's performance on EMNIST-letters and Fashion MNIST is lower due to the relative simplicity of the system architecture and the increased complexity of the tasks. We expect that the DD-TEA framework will enable the exploration of deeper architectures, ultimately leading to improved classification accuracy.
Authors: Jilong Wang, Saihui Hou, Yan Huang, Chunshui Cao, Xu Liu, Yongzhen Huang, Tianzhu Zhang, Liang Wang
Gait recognition is to seek correct matches for query individuals by their unique walking patterns. However, current methods focus solely on extracting individual-specific features, overlooking ``interpersonal" relationships. In this paper, we propose a novel $\textbf{Relation Descriptor}$ that captures not only individual features but also relations between test gaits and pre-selected gait anchors. Specifically, we reinterpret classifier weights as gait anchors and compute similarity scores between test features and these anchors, which re-expresses individual gait features into a similarity relation distribution. In essence, the relation descriptor offers a holistic perspective that leverages the collective knowledge stored within the classifier's weights, emphasizing meaningful patterns and enhancing robustness. Despite its potential, relation descriptor poses dimensionality challenges since its dimension depends on the training set's identity count. To address this, we propose Farthest gait-Anchor Selection to identify the most discriminative gait anchors and an Orthogonal Regularization Loss to increase diversity within gait anchors. Compared to individual-specific features extracted from the backbone, our relation descriptor can boost the performance nearly without any extra costs. We evaluate the effectiveness of our method on the popular GREW, Gait3D, OU-MVLP, CASIA-B, and CCPG, showing that our method consistently outperforms the baselines and achieves state-of-the-art performance.
Authors: Rayson Laroca, Luiz A. Zanlorensi, Valter Estevam, Rodrigo Minetto, David Menotti
License Plate Recognition (LPR) plays a critical role in various applications, such as toll collection, parking management, and traffic law enforcement. Although LPR has witnessed significant advancements through the development of deep learning, there has been a noticeable lack of studies exploring the potential improvements in results by fusing the outputs from multiple recognition models. This research aims to fill this gap by investigating the combination of up to 12 different models using straightforward approaches, such as selecting the most confident prediction or employing majority vote-based strategies. Our experiments encompass a wide range of datasets, revealing substantial benefits of fusion approaches in both intra- and cross-dataset setups. Essentially, fusing multiple models reduces considerably the likelihood of obtaining subpar performance on a particular dataset/scenario. We also found that combining models based on their speed is an appealing approach. Specifically, for applications where the recognition task can tolerate some additional time, though not excessively, an effective strategy is to combine 4-6 models. These models may not be the most accurate individually, but their fusion strikes an optimal balance between speed and accuracy.
Authors: Brandon Zhao, Aviad Levis, Liam Connor, Pratul P. Srinivasan, Katherine L. Bouman
Refractive Index Tomography is the inverse problem of reconstructing the continuously-varying 3D refractive index in a scene using 2D projected image measurements. Although a purely refractive field is not directly visible, it bends light rays as they travel through space, thus providing a signal for reconstruction. The effects of such fields appear in many scientific computer vision settings, ranging from refraction due to transparent cells in microscopy to the lensing of distant galaxies caused by dark matter in astrophysics. Reconstructing these fields is particularly difficult due to the complex nonlinear effects of the refractive field on observed images. Furthermore, while standard 3D reconstruction and tomography settings typically have access to observations of the scene from many viewpoints, many refractive index tomography problem settings only have access to images observed from a single viewpoint. We introduce a method that leverages prior knowledge of light sources scattered throughout the refractive medium to help disambiguate the single-view refractive index tomography problem. We differentiably trace curved rays through a neural field representation of the refractive field, and optimize its parameters to best reproduce the observed image. We demonstrate the efficacy of our approach by reconstructing simulated refractive fields, analyze the effects of light source distribution on the recovered field, and test our method on a simulated dark matter mapping problem where we successfully recover the 3D refractive field caused by a realistic dark matter distribution.
Authors: Qihang Fan, Huaibo Huang, Mingrui Chen, Hongmin Liu, Ran He
Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity, thereby constraining the applicability of ViT. To alleviate these issues, we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP, and propose RMT, a strong vision backbone with explicit spatial prior for general purposes. Specifically, we extend the RetNet's temporal decay mechanism to the spatial domain, and propose a spatial decay matrix based on the Manhattan distance to introduce the explicit spatial prior to Self-Attention. Additionally, an attention decomposition form that adeptly adapts to explicit spatial prior is proposed, aiming to reduce the computational burden of modeling global information without disrupting the spatial decay matrix. Based on the spatial decay matrix and the attention decomposition form, we can flexibly integrate explicit spatial prior into the vision backbone with linear complexity. Extensive experiments demonstrate that RMT exhibits exceptional performance across various vision tasks. Specifically, without extra training data, RMT achieves **84.8%** and **86.1%** top-1 acc on ImageNet-1k with **27M/4.5GFLOPs** and **96M/18.2GFLOPs**. For downstream tasks, RMT achieves **54.5** box AP and **47.2** mask AP on the COCO detection task, and **52.8** mIoU on the ADE20K semantic segmentation task. Code is available at https://github.com/qhfan/RMT
Authors: Yun Zhang, Wei Li, Simiao Li, Jie Hu, Hanting Chen, Hailing Wang, Zhijun Tu, Wenjia Wang, Bingyi Jing, Yunhe Wang
Knowledge distillation (KD) emerges as a promising yet challenging technique for compressing deep neural networks, aiming to transfer extensive learning representations from proficient and computationally intensive teacher models to compact student models. However, current KD methods for super-resolution (SR) models have limited performance and restricted applications, since the characteristics of SR tasks are overlooked. In this paper, we put forth an approach from the perspective of effective data utilization, namely, the Data Upcycling Knowledge Distillation (DUKD), which facilitates the student model by the prior knowledge the teacher provided through the upcycled in-domain data derived from the input images. Besides, for the first time, we realize the label consistency regularization in KD for SR models, which is implemented by the paired invertible data augmentations. It constrains the training process of KD and leads to better generalization capability of the student model. The DUKD, due to its versatility, can be applied across a broad spectrum of teacher-student architectures (e.g., CNN and Transformer models) and SR tasks, such as single image SR, real-world SR, and SR quantization, and is in parallel with other compression techniques. Comprehensive experiments on diverse benchmarks demonstrate that the DUKD method significantly outperforms previous art.
Authors: Linqi Zhou, Aaron Lou, Samar Khanna, Stefano Ermon
Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes from a distribution that is not random noise. As such, diffusion models must rely on cumbersome methods like guidance or projected sampling to incorporate this information in the generative process. In our work, we propose Denoising Diffusion Bridge Models (DDBMs), a natural alternative to this paradigm based on diffusion bridges, a family of processes that interpolate between two paired distributions given as endpoints. Our method learns the score of the diffusion bridge from data and maps from one endpoint distribution to the other by solving a (stochastic) differential equation based on the learned score. Our method naturally unifies several classes of generative models, such as score-based diffusion models and OT-Flow-Matching, allowing us to adapt existing design and architectural choices to our more general problem. Empirically, we apply DDBMs to challenging image datasets in both pixel and latent space. On standard image translation problems, DDBMs achieve significant improvement over baseline methods, and, when we reduce the problem to image generation by setting the source distribution to random noise, DDBMs achieve comparable FID scores to state-of-the-art methods despite being built for a more general task.
Authors: Naiyu Fang, Lemiao Qiu, Shuyou Zhang, Zili Wang, Zheyuan Zhou, Kerui Hu
Depth estimation provides an alternative approach for perceiving 3D information in autonomous driving. Monocular depth estimation, whether with single-frame or multi-frame inputs, has achieved significant success by learning various types of cues and specializing in either static or dynamic scenes. Recently, these cues fusion becomes an attractive topic, aiming to enable the combined cues to perform well in both types of scenes. However, adaptive cue fusion relies on attention mechanisms, where the quadratic complexity limits the granularity of cue representation. Additionally, explicit cue fusion depends on precise segmentation, which imposes a heavy burden on mask prediction. To address these issues, we propose the GSDC Transformer, an efficient and effective component for cue fusion in monocular multi-frame depth estimation. We utilize deformable attention to learn cue relationships at a fine scale, while sparse attention reduces computational requirements when granularity increases. To compensate for the precision drop in dynamic scenes, we represent scene attributes in the form of super tokens without relying on precise shapes. Within each super token attributed to dynamic scenes, we gather its relevant cues and learn local dense relationships to enhance cue fusion. Our method achieves state-of-the-art performance on the KITTI dataset with efficient fusion speed.
Authors: Jiageng Mao, Yuxi Qian, Junjie Ye, Hang Zhao, Yue Wang
We present a simple yet effective approach that can transform the OpenAI GPT-3.5 model into a reliable motion planner for autonomous vehicles. Motion planning is a core challenge in autonomous driving, aiming to plan a driving trajectory that is safe and comfortable. Existing motion planners predominantly leverage heuristic methods to forecast driving trajectories, yet these approaches demonstrate insufficient generalization capabilities in the face of novel and unseen driving scenarios. In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capabilities and generalization potential inherent to Large Language Models (LLMs). The fundamental insight of our approach is the reformulation of motion planning as a language modeling problem, a perspective not previously explored. Specifically, we represent the planner inputs and outputs as language tokens, and leverage the LLM to generate driving trajectories through a language description of coordinate positions. Furthermore, we propose a novel prompting-reasoning-finetuning strategy to stimulate the numerical reasoning potential of the LLM. With this strategy, the LLM can describe highly precise trajectory coordinates and also its internal decision-making process in natural language. We evaluate our approach on the large-scale nuScenes dataset, and extensive experiments substantiate the effectiveness, generalization ability, and interpretability of our GPT-based motion planner. Code is now available at https://github.com/PointsCoder/GPT-Driver.
Authors: Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, Yu-Xiong Wang
While large language models (LLMs) have demonstrated impressive performance on a range of decision-making tasks, they rely on simple acting processes and fall short of broad deployment as autonomous agents. We introduce LATS (Language Agent Tree Search), a general framework that synergizes the capabilities of LLMs in planning, acting, and reasoning. Drawing inspiration from Monte Carlo tree search in model-based reinforcement learning, LATS employs LLMs as agents, value functions, and optimizers, repurposing their latent strengths for enhanced decision-making. What is crucial in this method is the use of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism that moves beyond the limitations of existing techniques. Our experimental evaluation across diverse domains, such as programming, HotPotQA, and WebShop, illustrates the applicability of LATS for both reasoning and acting. In particular, LATS achieves 94.4% for programming on HumanEval with GPT-4 and an average score of 75.9 for web browsing on WebShop with GPT-3.5, demonstrating the effectiveness and generality of our method.
Authors: Li Li, You Qin, Wei Ji, Yuxiao Zhou, Roger Zimmermann
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates). However, the presence of biased predicate annotations poses a significant challenge for PSG models, as it hinders their ability to establish a clear decision boundary among different predicates. This issue substantially impedes the practical utility and real-world applicability of PSG models. To address the intrinsic bias above, we propose a novel framework to infer potentially biased annotations by measuring the predicate prediction risks within each subject-object pair (domain), and adaptively transfer the biased annotations to consistent ones by learning invariant predicate representation embeddings. Experiments show that our method significantly improves the performance of benchmark models, achieving a new state-of-the-art performance, and shows great generalization and effectiveness on PSG dataset.
Authors: Guanlin Li, Yifei Chen, Jie Zhang, Jiwei Li, Shangwei Guo, Tianwei Zhang
AI-Generated Content (AIGC) is gaining great popularity, with many emerging commercial services and applications. These services leverage advanced generative models, such as latent diffusion models and large language models, to generate creative content (e.g., realistic images and fluent sentences) for users. The usage of such generated content needs to be highly regulated, as the service providers need to ensure the users do not violate the usage policies (e.g., abuse for commercialization, generating and distributing unsafe content). A promising solution to achieve this goal is watermarking, which adds unique and imperceptible watermarks on the content for service verification and attribution. Numerous watermarking approaches have been proposed recently. However, in this paper, we show that an adversary can easily break these watermarking mechanisms. Specifically, we consider two possible attacks. (1) Watermark removal: the adversary can easily erase the embedded watermark from the generated content and then use it freely bypassing the regulation of the service provider. (2) Watermark forging: the adversary can create illegal content with forged watermarks from another user, causing the service provider to make wrong attributions. We propose Warfare, a unified methodology to achieve both attacks in a holistic way. The key idea is to leverage a pre-trained diffusion model for content processing and a generative adversarial network for watermark removal or forging. We evaluate Warfare on different datasets and embedding setups. The results prove that it can achieve high success rates while maintaining the quality of the generated content. Compared to existing diffusion model-based attacks, Warfare is 5,050~11,000x faster.
Authors: Taoran Yi, Jiemin Fang, Junjie Wang, Guanjun Wu, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Qi Tian, Xinggang Wang
In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can help generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D object generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance or 3D avatar within 15 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time. Demos and code are available at https://taoranyi.com/gaussiandreamer/.
Authors: Yitong Jiang, Zhaoyang Zhang, Tianfan Xue, Jinwei Gu
In this paper, we aim to solve complex real-world image restoration situations, in which, one image may have a variety of unknown degradations. To this end, we propose an all-in-one image restoration framework with latent diffusion (AutoDIR), which can automatically detect and address multiple unknown degradations. Our framework first utilizes a Blind Image Quality Assessment Module (BIQA) to automatically detect and identify the unknown dominant image degradation type of the image. Then, an All-in-One Image Refinement (AIR) Module handles multiple kinds of degradation image restoration with the guidance of BIQA. Finally, a Structure Correction Module (SCM) is proposed to recover the image details distorted by AIR. Our comprehensive evaluation demonstrates that AutoDIR outperforms state-of-the-art approaches by achieving superior restoration results while supporting a wider range of tasks. Notably, AutoDIR is also the first method to automatically handle real-scenario images with multiple unknown degradations.
Authors: Shuo Wang, Issei Sato
Deep neural networks are being increasingly implemented throughout society in recent years. It is useful to identify which parameters trigger misclassification in diagnosing undesirable model behaviors. The concept of parameter saliency is proposed and used to diagnose convolutional neural networks (CNNs) by ranking convolution filters that may have caused misclassification on the basis of parameter saliency. It is also shown that fine-tuning the top ranking salient filters efficiently corrects misidentification on ImageNet. However, there is still a knowledge gap in terms of understanding why parameter saliency ranking can find the filters inducing misidentification. In this work, we attempt to bridge the gap by analyzing parameter saliency ranking from a statistical viewpoint, namely, extreme value theory. We first show that the existing work implicitly assumes that the gradient norm computed for each filter follows a normal distribution. Then, we clarify the relationship between parameter saliency and the score based on the peaks-over-threshold (POT) method, which is often used to model extreme values. Finally, we reformulate parameter saliency in terms of the POT method, where this reformulation is regarded as statistical anomaly detection and does not require the implicit assumptions of the existing parameter-saliency formulation. Our experimental results demonstrate that our reformulation can detect malicious filters as well. Furthermore, we show that the existing parameter saliency method exhibits a bias against the depth of layers in deep neural networks. In particular, this bias has the potential to inhibit the discovery of filters that cause misidentification in situations where domain shift occurs. In contrast, parameter saliency based on POT shows less of this bias.
Authors: Zhaowei Gao, Mingyang Song, Christopher Schroers, Yang Zhang
Due to old CRT display technology and limited transmission bandwidth, early film and TV broadcasts commonly used interlaced scanning. This meant each field contained only half of the information. Since modern displays require full frames, this has spurred research into deinterlacing, i.e. restoring the missing information in legacy video content. In this paper, we present a deep-learning-based method for deinterlacing animated and live-action content. Our proposed method supports bidirectional spatio-temporal information propagation across multiple scales to leverage information in both space and time. More specifically, we design a Flow-guided Refinement Block (FRB) which performs feature refinement including alignment, fusion, and rectification. Additionally, our method can process multiple fields simultaneously, reducing per-frame processing time, and potentially enabling real-time processing. Our experimental results demonstrate that our proposed method achieves superior performance compared to existing methods.
Authors: Gaoshuang Huang, Yang Zhou, Xiaofei Hu, Chenglong Zhang, Luying Zhao, Wenjian Gan, Mingbo Hou
Utilizing visual place recognition (VPR) technology to ascertain the geographical location of publicly available images is a pressing issue for real-world VPR applications. Although most current VPR methods achieve favorable results under ideal conditions, their performance in complex environments, characterized by lighting variations, seasonal changes, and occlusions caused by moving objects, is generally unsatisfactory. In this study, we utilize the DINOv2 model as the backbone network for trimming and fine-tuning to extract robust image features. We propose a novel VPR architecture called DINO-Mix, which combines a foundational vision model with feature aggregation. This architecture relies on the powerful image feature extraction capabilities of foundational vision models. We employ an MLP-Mixer-based mix module to aggregate image features, resulting in globally robust and generalizable descriptors that enable high-precision VPR. We experimentally demonstrate that the proposed DINO-Mix architecture significantly outperforms current state-of-the-art (SOTA) methods. In test sets having lighting variations, seasonal changes, and occlusions (Tokyo24/7, Nordland, SF-XL-Testv1), our proposed DINO-Mix architecture achieved Top-1 accuracy rates of 91.75%, 80.18%, and 82%, respectively. Compared with SOTA methods, our architecture exhibited an average accuracy improvement of 5.14%.
Authors: Fabiha Bushra, Muhammad E. H. Chowdhury, Rusab Sarmun, Saidul Kabir, Menatalla Said, Sohaib Bassam Zoghoul, Adam Mushtak, Israa Al-Hashimi, Abdulrahman Alqahtani, Anwarul Hasan
The increasing reliance on Computed Tomography Pulmonary Angiography for Pulmonary Embolism (PE) diagnosis presents challenges and a pressing need for improved diagnostic solutions. The primary objective of this study is to leverage deep learning techniques to enhance the Computer Assisted Diagnosis of PE. In this study, we propose a classifier-guided detection approach that effectively leverages the classifier's probabilistic inference to direct the detection predictions, marking a novel contribution in the domain of automated PE diagnosis. Our end-to-end classification framework introduces an Attention-Guided Convolutional Neural Network (AG-CNN) that leverages local context by utilizing an attention mechanism. This approach emulates the attention of a human expert by looking at both global appearances and local lesion regions before forming a conclusive decision. The classifier achieves a notable AUROC, sensitivity, specificity and F1-score of 0.927, 0.862, 0.879 and 0.805 respectively on the FUMPE dataset with Inception-v3 backbone architecture. Moreover, AG-CNN outperforms the baseline DenseNet-121 model, achieving an 8.1% AUROC gain. While prior studies have primarily focused on PE detection in main arteries, our utilization of state-of-the-art object detection models and ensembling techniques significantly enhances detection accuracy for small embolisms in the peripheral arteries. Finally, our proposed classifier-guided detection approach further refines the detection metrics contributing new state-of-the-art to the community: mAP$_{50}$, sensitivity and F1-score of 0.846, 0.901 and 0.779 respectively outperforming the former benchmark with a significant 3.7% improvement in mAP$_{50}$. Our research aims to elevate PE patient care by integrating AI solutions into clinical workflows, highlighting the potential of human-AI collaboration in medical diagnostics.
Authors: Jun Myeong Choi, Max Christman, Roni Sengupta
In this paper, we develop a personalized video relighting algorithm that produces high-quality and temporally consistent relit videos under any pose, expression, and lighting condition in real-time. Existing relighting algorithms typically rely either on publicly available synthetic data, which yields poor relighting results, or instead on light stage data which is difficult to obtain. We show that by just capturing video of a user watching YouTube videos on a monitor we can train a personalized algorithm capable of performing high-quality relighting under any condition. Our key contribution is a novel neural relighting architecture that effectively separates the intrinsic appearance features - the geometry and reflectance of the face - from the source lighting and then combines them with the target lighting to generate a relit image. This neural network architecture enables smoothing of intrinsic appearance features leading to temporally stable video relighting. Both qualitative and quantitative evaluations show that our architecture improves portrait image relighting quality and temporal consistency over state-of-the-art approaches on both casually captured `Light Stage at Your Desk' (LSYD) and light-stage-captured `One Light At a Time' (OLAT) datasets.
Authors: Wentao He, Yuchen Yan, Jianfeng Ren, Ruibin Bai, Xudong Jiang
Deep neural networks have been applied to audio spectrograms for respiratory sound classification. Existing models often treat the spectrogram as a synthetic image while overlooking its physical characteristics. In this paper, a Multi-View Spectrogram Transformer (MVST) is proposed to embed different views of time-frequency characteristics into the vision transformer. Specifically, the proposed MVST splits the mel-spectrogram into different sized patches, representing the multi-view acoustic elements of a respiratory sound. These patches and positional embeddings are then fed into transformer encoders to extract the attentional information among patches through a self-attention mechanism. Finally, a gated fusion scheme is designed to automatically weigh the multi-view features to highlight the best one in a specific scenario. Experimental results on the ICBHI dataset demonstrate that the proposed MVST significantly outperforms state-of-the-art methods for classifying respiratory sounds.
Authors: Xiaotian Han, Quanzeng You, Yongfei Liu, Wentao Chen, Huangjie Zheng, Khalil Mrini, Xudong Lin, Yiqi Wang, Bohan Zhai, Jianbo Yuan, Heng Wang, Hongxia Yang
Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. These models not only excel in traditional vision-language tasks but also demonstrate impressive performance in contemporary multi-modal benchmarks. Although many of these benchmarks attempt to holistically evaluate MLLMs, they typically concentrate on basic reasoning tasks, often yielding only simple yes/no or multi-choice responses. These methods naturally lead to confusion and difficulties in conclusively determining the reasoning capabilities of MLLMs. To mitigate this issue, we manually curate a benchmark dataset specifically designed for MLLMs, with a focus on complex reasoning tasks. Our benchmark comprises three key reasoning categories: deductive, abductive, and analogical reasoning. The queries in our dataset are intentionally constructed to engage the reasoning capabilities of MLLMs in the process of generating answers. For a fair comparison across various MLLMs, we incorporate intermediate reasoning steps into our evaluation criteria. In instances where an MLLM is unable to produce a definitive answer, its reasoning ability is evaluated by requesting intermediate reasoning steps. If these steps align with our manual annotations, appropriate scores are assigned. This evaluation scheme resembles methods commonly used in human assessments, such as exams or assignments, and represents what we consider a more effective assessment technique compared with existing benchmarks. We evaluate a selection of representative MLLMs using this rigorously developed open-ended multi-step elaborate reasoning benchmark, designed to challenge and accurately measure their reasoning capabilities. The code and data will be released at https://infimm.github.io/InfiMM-Eval/
Authors: Jaemin Lee, Minseok Seo, Sangwoo Lee, Hyobin Park, Dong-Geol Choi
In general, deep learning-based video frame interpolation (VFI) methods have predominantly focused on estimating motion vectors between two input frames and warping them to the target time. While this approach has shown impressive performance for linear motion between two input frames, it exhibits limitations when dealing with occlusions and nonlinear movements. Recently, generative models have been applied to VFI to address these issues. However, as VFI is not a task focused on generating plausible images, but rather on predicting accurate intermediate frames between two given frames, performance limitations still persist. In this paper, we propose a multi-in-single-out (MISO) based VFI method that does not rely on motion vector estimation, allowing it to effectively model occlusions and nonlinear motion. Additionally, we introduce a novel motion perceptual loss that enables MISO-VFI to better capture the spatio-temporal correlations within the video frames. Our MISO-VFI method achieves state-of-the-art results on VFI benchmarks Vimeo90K, Middlebury, and UCF101, with a significant performance gap compared to existing approaches.
Authors: Yu Huang, Yue Chen, Zhu Li
Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. Recently powered by large language models (LLMs), chat systems, such as chatGPT and PaLM, emerge and rapidly become a promising direction to achieve artificial general intelligence (AGI) in natural language processing (NLP). There comes a natural thinking that we could employ these abilities to reformulate autonomous driving. By combining LLM with foundation models, it is possible to utilize the human knowledge, commonsense and reasoning to rebuild autonomous driving systems from the current long-tailed AI dilemma. In this paper, we investigate the techniques of foundation models and LLMs applied for autonomous driving, categorized as simulation, world model, data annotation and planning or E2E solutions etc.
Authors: Zuozhuo Dai, Zhenghao Zhang, Yao Yao, Bingxue Qiu, Siyu Zhu, Long Qin, Weizhi Wang
Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and motion strength guidance, enabling precise control the movable area and its motion speed. This results in enhanced alignment between the animated visual elements and the prompting text, thereby facilitating a fine-grained and interactive animation generation process for intricate motion sequences. We validate the effectiveness of our method through rigorous experiments on an open-domain dataset, with the results showcasing its superior performance. Project page can be found at https://animationai.github.io/AnimateAnything.
Authors: Xiao Song, Jiafan Liu, Yun Li, Wenbin Lei, Ruxin Wang
Radiology Report Generation (RRG) draws attention as an interaction between vision and language fields. Previous works inherited the ideology of vision-to-language generation tasks,aiming to generate paragraphs with high consistency as reports. However, one unique characteristic of RRG, the independence between diseases, was neglected, leading to the injection of disease co-occurrence as a confounder that effects the results through backdoor path. Unfortunately, this confounder confuses the process of report generation worse because of the biased RRG data distribution. In this paper, to rethink this issue thoroughly, we reason about its causes and effects from a novel perspective of statistics and causality, where the Joint Vision Coupling and the Conditional Sentence Coherence Coupling are two aspects prone to implicitly decrease the accuracy of reports. Then, a counterfactual augmentation strategy that contains the Counterfactual Sample Synthesis and the Counterfactual Report Reconstruction sub-methods is proposed to break these two aspects of spurious effects. Experimental results and further analyses on two widely used datasets justify our reasoning and proposed methods.
Authors: Syed Talal Wasim, Kabila Haile Soboka, Abdulrahman Mahmoud, Salman Khan, David Brooks, Gu-Yeon Wei
This paper presents a novel method to enhance the reliability of image classification models during deployment in the face of transient hardware errors. By utilizing enriched text embeddings derived from GPT-3 with question prompts per class and CLIP pretrained text encoder, we investigate their impact as an initialization for the classification layer. Our approach achieves a remarkable $5.5\times$ average increase in hardware reliability (and up to $14\times$) across various architectures in the most critical layer, with minimal accuracy drop ($0.3\%$ on average) compared to baseline PyTorch models. Furthermore, our method seamlessly integrates with any image classification backbone, showcases results across various network architectures, decreases parameter and FLOPs overhead, and follows a consistent training recipe. This research offers a practical and efficient solution to bolster the robustness of image classification models against hardware failures, with potential implications for future studies in this domain. Our code and models are released at https://github.com/TalalWasim/TextGuidedResilience.
Authors: Rutuja Gurav, Het Patel, Zhuocheng Shang, Ahmed Eldawy, Jia Chen, Elia Scudiero, Evangelos Papalexakis
Climate change is increasingly disrupting worldwide agriculture, making global food production less reliable. To tackle the growing challenges in feeding the planet, cutting-edge management strategies, such as precision agriculture, empower farmers and decision-makers with rich and actionable information to increase the efficiency and sustainability of their farming practices. Crop-type maps are key information for decision-support tools but are challenging and costly to generate. We investigate the capabilities of Meta AI's Segment Anything Model (SAM) for crop-map prediction task, acknowledging its recent successes at zero-shot image segmentation. However, SAM being limited to up-to 3 channel inputs and its zero-shot usage being class-agnostic in nature pose unique challenges in using it directly for crop-type mapping. We propose using clustering consensus metrics to assess SAM's zero-shot performance in segmenting satellite imagery and producing crop-type maps. Although direct crop-type mapping is challenging using SAM in zero-shot setting, experiments reveal SAM's potential for swiftly and accurately outlining fields in satellite images, serving as a foundation for subsequent crop classification. This paper attempts to highlight a use-case of state-of-the-art image segmentation models like SAM for crop-type mapping and related specific needs of the agriculture industry, offering a potential avenue for automatic, efficient, and cost-effective data products for precision agriculture practices.
Authors: Adam Tonderski, Carl Lindström, Georg Hess, William Ljungbergh, Lennart Svensson, Christoffer Petersson
Neural radiance fields (NeRFs) have gained popularity in the autonomous driving (AD) community. Recent methods show NeRFs' potential for closed-loop simulation, enabling testing of AD systems, and as an advanced training data augmentation technique. However, existing methods often require long training times, dense semantic supervision, or lack generalizability. This, in turn, hinders the application of NeRFs for AD at scale. In this paper, we propose NeuRAD, a robust novel view synthesis method tailored to dynamic AD data. Our method features simple network design, extensive sensor modeling for both camera and lidar -- including rolling shutter, beam divergence and ray dropping -- and is applicable to multiple datasets out of the box. We verify its performance on five popular AD datasets, achieving state-of-the-art performance across the board. To encourage further development, we will openly release the NeuRAD source code. See https://github.com/georghess/NeuRAD .
Authors: Qi Fan, Xin Tao, Lei Ke, Mingqiao Ye, Yuan Zhang, Pengfei Wan, Zhongyuan Wang, Yu-Wing Tai, Chi-Keung Tang
The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities, notably imprecise bounding boxes and insufficient points. Our key finding reveals that given such low-quality prompts, SAM's mask decoder tends to activate image features that are biased towards the background or confined to specific object parts. To mitigate this issue, our key idea consists of calibrating solely SAM's mask attention by adjusting the sampling locations and amplitudes of image features, while the original SAM model architecture and weights remain unchanged. Consequently, our deformable sampling plugin (DSP) enables SAM to adaptively shift attention to the prompted target regions in a data-driven manner, facilitated by our effective robust training strategy (RTS). During inference, dynamic routing plugin (DRP) is proposed that toggles SAM between the deformable and regular grid sampling modes, conditioned on the input prompt quality. Thus, our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality, with 3) minimal learnable parameters (0.08 M) and fast adaptation (by 1 training epoch). Extensive experiments across multiple datasets validate the effectiveness and advantages of our approach, underscoring Stable-SAM as a more robust solution for segmenting anything. Codes will be released upon acceptance. https://github.com/fanq15/Stable-SAM
Authors: Zhihao Liang, Qi Zhang, Ying Feng, Ying Shan, Kui Jia
We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results. Unlike previous works that use implicit neural representations and volume rendering (e.g. NeRF), which suffer from low expressive power and high computational complexity, we extend GS, a top-performance representation for novel view synthesis, to estimate scene geometry, surface material, and environment illumination from multi-view images captured under unknown lighting conditions. There are two main problems when introducing GS to inverse rendering: 1) GS does not support producing plausible normal natively; 2) forward mapping (e.g. rasterization and splatting) cannot trace the occlusion like backward mapping (e.g. ray tracing). To address these challenges, our GS-IR proposes an efficient optimization scheme that incorporates a depth-derivation-based regularization for normal estimation and a baking-based occlusion to model indirect lighting. The flexible and expressive GS representation allows us to achieve fast and compact geometry reconstruction, photorealistic novel view synthesis, and effective physically-based rendering. We demonstrate the superiority of our method over baseline methods through qualitative and quantitative evaluations on various challenging scenes.
Authors: Jian Wang, Zhe Cao, Diogo Luvizon, Lingjie Liu, Kripasindhu Sarkar, Danhang Tang, Thabo Beeler, Christian Theobalt
In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion. This task presents significant challenges due to three factors: the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion. To address these challenges, we propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are subsequently converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction. For hand tracking, we incorporate dedicated hand detection and hand pose estimation networks for regressing 3D hand poses. Finally, we develop a diffusion-based whole-body motion prior model to refine the estimated whole-body motion while accounting for joint uncertainties. To train these networks, we collect a large synthetic dataset, EgoWholeBody, comprising 840,000 high-quality egocentric images captured across a diverse range of whole-body motion sequences. Quantitative and qualitative evaluations demonstrate the effectiveness of our method in producing high-quality whole-body motion estimates from a single egocentric camera.
Authors: Haoze Sun, Wenbo Li, Jianzhuang Liu, Haoyu Chen, Renjing Pei, Xueyi Zou, Youliang Yan, Yujiu Yang
Existing super-resolution (SR) models primarily focus on restoring local texture details, often neglecting the global semantic information within the scene. This oversight can lead to the omission of crucial semantic details or the introduction of inaccurate textures during the recovery process. In our work, we introduce the Cognitive Super-Resolution (CoSeR) framework, empowering SR models with the capacity to comprehend low-resolution images. We achieve this by marrying image appearance and language understanding to generate a cognitive embedding, which not only activates prior information from large text-to-image diffusion models but also facilitates the generation of high-quality reference images to optimize the SR process. To further improve image fidelity, we propose a novel condition injection scheme called "All-in-Attention", consolidating all conditional information into a single module. Consequently, our method successfully restores semantically correct and photorealistic details, demonstrating state-of-the-art performance across multiple benchmarks. Code: https://github.com/VINHYU/CoSeR
Authors: Lanyun Zhu, Tianrun Chen, Deyi Ji, Jieping Ye, Jun Liu
This paper proposes LLaFS, the first attempt to leverage large language models (LLMs) in few-shot segmentation. In contrast to the conventional few-shot segmentation methods that only rely on the limited and biased information from the annotated support images, LLaFS leverages the vast prior knowledge gained by LLM as an effective supplement and directly uses the LLM to segment images in a few-shot manner. To enable the text-based LLM to handle image-related tasks, we carefully design an input instruction that allows the LLM to produce segmentation results represented as polygons, and propose a region-attribute table to simulate the human visual mechanism and provide multi-modal guidance. We also synthesize pseudo samples and use curriculum learning for pretraining to augment data and achieve better optimization. LLaFS achieves state-of-the-art results on multiple datasets, showing the potential of using LLMs for few-shot computer vision tasks. Code will be available at https://github.com/lanyunzhu99/LLaFS.
Authors: Siyuan Huang, Yifan Zhou, Ram Prabhakar Kathirvel, Rama Chellappa, Chun Pong Lau
Interactive Segmentation Models (ISMs) like the Segment Anything Model have significantly improved various computer vision tasks, yet their application to Person Re-identification (ReID) remains limited. On the other hand, existing semantic pre-training models for ReID often have limitations like predefined parsing ranges or coarse semantics. Additionally, ReID and Clothes-Changing ReID (CC-ReID) are usually treated separately due to their different domains. This paper investigates whether utilizing precise human-centric semantic representation can boost the ReID performance and improve the generalization among various ReID tasks. We propose SemReID, a self-supervised ReID model that leverages ISMs for adaptive part-based semantic extraction, contributing to the improvement of ReID performance. SemReID additionally refines its semantic representation through techniques such as image masking and KoLeo regularization. Evaluation across three types of ReID datasets -- standard ReID, CC-ReID, and unconstrained ReID -- demonstrates superior performance compared to state-of-the-art methods. In addition, recognizing the scarcity of large person datasets with fine-grained semantics, we introduce the novel LUPerson-Part dataset to assist ReID methods in acquiring the fine-grained part semantics for robust performance.
Authors: Tianwei Yin, Michaël Gharbi, Richard Zhang, Eli Shechtman, Fredo Durand, William T. Freeman, Taesung Park
Diffusion models generate high-quality images but require dozens of forward passes. We introduce Distribution Matching Distillation (DMD), a procedure to transform a diffusion model into a one-step image generator with minimal impact on image quality. We enforce the one-step image generator match the diffusion model at distribution level, by minimizing an approximate KL divergence whose gradient can be expressed as the difference between 2 score functions, one of the target distribution and the other of the synthetic distribution being produced by our one-step generator. The score functions are parameterized as two diffusion models trained separately on each distribution. Combined with a simple regression loss matching the large-scale structure of the multi-step diffusion outputs, our method outperforms all published few-step diffusion approaches, reaching 2.62 FID on ImageNet 64x64 and 11.49 FID on zero-shot COCO-30k, comparable to Stable Diffusion but orders of magnitude faster. Utilizing FP16 inference, our model generates images at 20 FPS on modern hardware.
Authors: Aman Bhatta, Domingo Mery, Haiyu Wu, Kevin W. Bowyer
The first layer of a deep CNN backbone applies filters to an image to extract the basic features available to later layers. During training, some filters may go inactive, mean ing all weights in the filter approach zero. An inactive fil ter in the final model represents a missed opportunity to extract a useful feature. This phenomenon is especially prevalent in specialized CNNs such as for face recogni tion (as opposed to, e.g., ImageNet). For example, in one the most widely face recognition model (ArcFace), about half of the convolution filters in the first layer are inactive. We propose a novel approach designed and tested specif ically for face recognition networks, known as "CRAFT: Contextual Re-Activation of Filters for Face Recognition Training". CRAFT identifies inactive filters during training and reinitializes them based on the context of strong filters at that stage in training. We show that CRAFT reduces fraction of inactive filters from 44% to 32% on average and discovers filter patterns not found by standard training. Compared to standard training without reactivation, CRAFT demonstrates enhanced model accuracy on standard face-recognition benchmark datasets including AgeDB-30, CPLFW, LFW, CALFW, and CFP-FP, as well as on more challenging datasets like IJBB and IJBC.
Authors: Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne
Vision-language foundation models have shown remarkable performance in various zero-shot settings such as image retrieval, classification, or captioning. But so far, those models seem to fall behind when it comes to zero-shot localization of referential expressions and objects in images. As a result, they need to be fine-tuned for this task. In this paper, we show that pretrained vision-language (VL) models allow for zero-shot open-vocabulary object localization without any fine-tuning. To leverage those capabilities, we propose a Grounding Everything Module (GEM) that generalizes the idea of value-value attention introduced by CLIPSurgery to a self-self attention path. We show that the concept of self-self attention corresponds to clustering, thus enforcing groups of tokens arising from the same object to be similar while preserving the alignment with the language space. To further guide the group formation, we propose a set of regularizations that allows the model to finally generalize across datasets and backbones. We evaluate the proposed GEM framework on various benchmark tasks and datasets for semantic segmentation. It shows that GEM not only outperforms other training-free open-vocabulary localization methods, but also achieves state-of-the-art results on the recently proposed OpenImagesV7 large-scale segmentation benchmark.
Authors: Jaewoo Jung, Jisang Han, Jiwon Kang, Seongchan Kim, Min-Seop Kwak, Seungryong Kim
Recently, neural radiance field (NeRF) has shown remarkable performance in novel view synthesis and 3D reconstruction. However, it still requires abundant high-quality images, limiting its applicability in real-world scenarios. To overcome this limitation, recent works have focused on training NeRF only with sparse viewpoints by giving additional regularizations, often called few-shot NeRF. We observe that due to the under-constrained nature of the task, solely using additional regularization is not enough to prevent the model from overfitting to sparse viewpoints. In this paper, we propose a novel framework, dubbed Self-Evolving Neural Radiance Fields (SE-NeRF), that applies a self-training framework to NeRF to address these problems. We formulate few-shot NeRF into a teacher-student framework to guide the network to learn a more robust representation of the scene by training the student with additional pseudo labels generated from the teacher. By distilling ray-level pseudo labels using distinct distillation schemes for reliable and unreliable rays obtained with our novel reliability estimation method, we enable NeRF to learn a more accurate and robust geometry of the 3D scene. We show and evaluate that applying our self-training framework to existing models improves the quality of the rendered images and achieves state-of-the-art performance in multiple settings.
Authors: Mahmoud Khalil, Ahmad Khalil, Alioune Ngom
Image Classification is a fundamental task in the field of computer vision that frequently serves as a benchmark for gauging advancements in Computer Vision. Over the past few years, significant progress has been made in image classification due to the emergence of deep learning. However, challenges still exist, such as modeling fine-grained visual information, high computation costs, the parallelism of the model, and inconsistent evaluation protocols across datasets. In this paper, we conduct a comprehensive survey of existing papers on Vision Transformers for image classification. We first introduce the popular image classification datasets that influenced the design of models. Then, we present Vision Transformers models in chronological order, starting with early attempts at adapting attention mechanism to vision tasks followed by the adoption of vision transformers, as they have demonstrated success in capturing intricate patterns and long-range dependencies within images. Finally, we discuss open problems and shed light on opportunities for image classification to facilitate new research ideas.
Authors: Raghavv Goel, Cecilia Morales, Manpreet Singh, Artur Dubrawski, John Galeotti, Howie Choset
Segmenting a moving needle in ultrasound images is challenging due to the presence of artifacts, noise, and needle occlusion. This task becomes even more demanding in scenarios where data availability is limited. Convolutional Neural Networks (CNNs) have been successful in many computer vision applications, but struggle to accurately segment needles without considering their motion. In this paper, we present a novel approach for needle segmentation that combines classical Kalman Filter (KF) techniques with data-driven learning, incorporating both needle features and needle motion. Our method offers two key contributions. First, we propose a compatible framework that seamlessly integrates into commonly used encoder-decoder style architectures. Second, we demonstrate superior performance compared to recent state-of-the-art needle segmentation models using our novel convolutional neural network (CNN) based KF-inspired block, achieving a 15\% reduction in pixel-wise needle tip error and an 8\% reduction in length error. Third, to our knowledge we are the first to implement a learnable filter to incorporate non-linear needle motion for improving needle segmentation.
Authors: Che Liu, Cheng Ouyang, Yinda Chen, Cesar César Quilodrán-Casas, Lei Ma, Jie Fu, Yike Guo, Anand Shah, Wenjia Bai, Rossella Arcucci
Expert annotation of 3D medical image for downstream analysis is resource-intensive, posing challenges in clinical applications. Visual self-supervised learning (vSSL), though effective for learning visual invariance, neglects the incorporation of domain knowledge from medicine. To incorporate medical knowledge into visual representation learning, vision-language pre-training (VLP) has shown promising results in 2D image. However, existing VLP approaches become generally impractical when applied to high-resolution 3D medical images due to GPU hardware constraints and the potential loss of critical details caused by downsampling, which is the intuitive solution to hardware constraints. To address the above limitations, we introduce T3D, the first VLP framework designed for high-resolution 3D medical images. T3D incorporates two text-informed pretext tasks: (\lowerromannumeral{1}) text-informed contrastive learning; (\lowerromannumeral{2}) text-informed image restoration. These tasks focus on learning 3D visual representations from high-resolution 3D medical images and integrating clinical knowledge from radiology reports, without distorting information through forced alignment of downsampled volumes with detailed anatomical text. Trained on a newly curated large-scale dataset of 3D medical images and radiology reports, T3D significantly outperforms current vSSL methods in tasks like organ and tumor segmentation, as well as disease classification. This underlines T3D's potential in representation learning for 3D medical image analysis. All data and code will be available upon acceptance.
Authors: Yilin Ye, Qian Zhu, Shishi Xiao, Kang Zhang, Wei Zeng
Image search is an essential and user-friendly method to explore vast galleries of digital images. However, existing image search methods heavily rely on proximity measurements like tag matching or image similarity, requiring precise user inputs for satisfactory results. To meet the growing demand for a contemporary image search engine that enables accurate comprehension of users' search intentions, we introduce an innovative user intent expansion framework. Our framework leverages visual-language models to parse and compose multi-modal user inputs to provide more accurate and satisfying results. It comprises two-stage processes: 1) a parsing stage that incorporates a language parsing module with large language models to enhance the comprehension of textual inputs, along with a visual parsing module that integrates an interactive segmentation module to swiftly identify detailed visual elements within images; and 2) a logic composition stage that combines multiple user search intents into a unified logic expression for more sophisticated operations in complex searching scenarios. Moreover, the intent expansion framework enables users to perform flexible contextualized interactions with the search results to further specify or adjust their detailed search intents iteratively. We implemented the framework into an image search system for NFT (non-fungible token) search and conducted a user study to evaluate its usability and novel properties. The results indicate that the proposed framework significantly improves users' image search experience. Particularly the parsing and contextualized interactions prove useful in allowing users to express their search intents more accurately and engage in a more enjoyable iterative search experience.
Authors: Xin Lin, Chao Ren, Kelvin C.K. Chan, Lu Qi, Jinshan Pan, Ming-Hsuan Yang
Multi-task image restoration has gained significant interest due to its inherent versatility and efficiency compared to its single-task counterpart. Despite its potential, performance degradation is observed with an increase in the number of tasks, primarily attributed to the distinct nature of each restoration task. Addressing this challenge, we introduce \mbox{\textbf{DINO-IR}}, a novel multi-task image restoration approach leveraging robust features extracted from DINOv2. Our empirical analysis shows that while shallow features of DINOv2 capture rich low-level image characteristics, the deep features ensure a robust semantic representation insensitive to degradations while preserving high-frequency contour details. Building on these features, we devise specialized components, including multi-layer semantic fusion module, DINO-Restore adaption and fusion module, and DINO perception contrastive loss, to integrate DINOv2 features into the restoration paradigm. Equipped with the aforementioned components, our DINO-IR performs favorably against existing multi-task image restoration approaches in various tasks by a large margin, indicating the superiority and necessity of reinforcing the robust features for multi-task image restoration.
Authors: Yizhou Wang, Yixuan Wu, Shixiang Tang, Weizhen He, Xun Guo, Feng Zhu, Lei Bai, Rui Zhao, Jian Wu, Tong He, Wanli Ouyang
Human-centric perception tasks, e.g., human mesh recovery, 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, most of them only excel in 2D vision tasks or require extensive fine-tuning for practical deployment in real-world scenarios. These limitations severely restrict their usability across various downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing most of the mainstream tasks simultaneously without task-specific finetuning, covering 2D vision, 3D vision, skeleton-based, and vision-language tasks. 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 human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. To validate the effectiveness of our proposed method, we conduct comprehensive experiments on 11 benchmarks across 8 human-centric tasks. Experimental results surpass previous methods substantially, demonstrating the superiority of our proposed method. The code will be available on https://github.com/OpenGVLab/HumanBench.
Authors: Yuchao Gu, Yipin Zhou, Bichen Wu, Licheng Yu, Jia-Wei Liu, Rui Zhao, Jay Zhangjie Wu, David Junhao Zhang, Mike Zheng Shou, Kevin Tang
Current diffusion-based video editing primarily focuses on structure-preserved editing by utilizing various dense correspondences to ensure temporal consistency and motion alignment. However, these approaches are often ineffective when the target edit involves a shape change. To embark on video editing with shape change, we explore customized video subject swapping in this work, where we aim to replace the main subject in a source video with a target subject having a distinct identity and potentially different shape. In contrast to previous methods that rely on dense correspondences, we introduce the VideoSwap framework that exploits semantic point correspondences, inspired by our observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape. We also introduce various user-point interactions (\eg, removing points and dragging points) to address various semantic point correspondence. Extensive experiments demonstrate state-of-the-art video subject swapping results across a variety of real-world videos.
Authors: Lucas Farndale, Robert Insall, Ke Yuan
Computational pathology models rarely utilise data that will not be available for inference. This means most models cannot learn from highly informative data such as additional immunohistochemical (IHC) stains and spatial transcriptomics. We present TriDeNT, a novel self-supervised method for utilising privileged data that is not available during inference to improve performance. We demonstrate the efficacy of this method for a range of different paired data including immunohistochemistry, spatial transcriptomics and expert nuclei annotations. In all settings, TriDeNT outperforms other state-of-the-art methods in downstream tasks, with observed improvements of up to 101%. Furthermore, we provide qualitative and quantitative measurements of the features learned by these models and how they differ from baselines. TriDeNT offers a novel method to distil knowledge from scarce or costly data during training, to create significantly better models for routine inputs.