Authors: Tingqin Lai, Xiaolin Liang, Yi Zhu, Xinyi Wu, Lianye Liao, Xuelin Yuan, Ping Su, Shihai Sun
Recently, there has been increased attention towards 3D imaging using single-pixel single-photon detection (also known as temporal data) due to its potential advantages in terms of cost and power efficiency. However, to eliminate the symmetry blur in the reconstructed images, a fixed background is required. This paper proposes a fusion-data-based 3D imaging method that utilizes a single-pixel single-photon detector and a millimeter-wave radar to capture temporal histograms of a scene from multiple perspectives. Subsequently, the 3D information can be reconstructed from the one-dimensional fusion temporal data by using Artificial Neural Network (ANN). Both the simulation and experimental results demonstrate that our fusion method effectively eliminates symmetry blur and improves the quality of the reconstructed images.
Authors: Neetu Sigger, Tuan Thanh Nguyen, Gianluca Tozzi, Quoc-Tuan Vien, Sinh Van Nguyen
Hyperspectral images (HSI) have become popular for analysing remotely sensed images in multiple domain like agriculture, medical. However, existing models struggle with complex relationships and characteristics of spectral-spatial data due to the multi-band nature and data redundancy of hyperspectral data. To address this limitation, we propose a new network called DiffSpectralNet, which combines diffusion and transformer techniques. Our approach involves a two-step process. First, we use an unsupervised learning framework based on the diffusion model to extract both high-level and low-level spectral-spatial features. The diffusion method is capable of extracting diverse and meaningful spectral-spatial features, leading to improvement in HSI classification. Then, we employ a pretrained denoising U-Net to extract intermediate hierarchical features for classification. Finally, we use a supervised transformer-based classifier to perform the HSI classification. Through comprehensive experiments on HSI datasets, we evaluate the classification performance of DiffSpectralNet. The results demonstrate that our framework significantly outperforms existing approaches, achieving state-of-the-art performance.
Authors: Thiago Santos, Harish Kamath, Christopher R. McAdams, Mary S. Newell, Marina Mosunjac, Gabriela Oprea-Ilies, Geoffrey Smith, Constance Lehman, Judy Gichoya, Imon Banerjee, Hari Trivedi
Automated classification of cancer pathology reports can extract information from unstructured reports and categorize each report into structured diagnosis and severity categories. Thus, such system can reduce the burden for populating tumor registries, help registration for clinical trial as well as developing large dataset for deep learning model development using true pathologic ground truth. However, the content of breast pathology reports can be difficult for categorize due to the high linguistic variability in content and wide variety of potential diagnoses >50. Existing NLP models are primarily focused on developing classifier for primary breast cancer types (e.g. IDC, DCIS, ILC) and tumor characteristics, and ignore the rare diagnosis of cancer subtypes. We then developed a hierarchical hybrid transformer-based pipeline (59 labels) - Hierarchical Classification System for Breast Cancer Specimen Report (HCSBC), which utilizes the potential of the transformer context-preserving NLP technique and compared our model to several state of the art ML and DL models. We trained the model on the EUH data and evaluated our model's performance on two external datasets - MGH and Mayo Clinic. We publicly release the code and a live application under Huggingface spaces repository
Authors: Kaylee Burns, Zach Witzel, Jubayer Ibn Hamid, Tianhe Yu, Chelsea Finn, Karol Hausman
Inspired by the success of transfer learning in computer vision, roboticists have investigated visual pre-training as a means to improve the learning efficiency and generalization ability of policies learned from pixels. To that end, past work has favored large object interaction datasets, such as first-person videos of humans completing diverse tasks, in pursuit of manipulation-relevant features. Although this approach improves the efficiency of policy learning, it remains unclear how reliable these representations are in the presence of distribution shifts that arise commonly in robotic applications. Surprisingly, we find that visual representations designed for manipulation and control tasks do not necessarily generalize under subtle changes in lighting and scene texture or the introduction of distractor objects. To understand what properties do lead to robust representations, we compare the performance of 15 pre-trained vision models under different visual appearances. We find that emergent segmentation ability is a strong predictor of out-of-distribution generalization among ViT models. The rank order induced by this metric is more predictive than metrics that have previously guided generalization research within computer vision and machine learning, such as downstream ImageNet accuracy, in-domain accuracy, or shape-bias as evaluated by cue-conflict performance. We test this finding extensively on a suite of distribution shifts in ten tasks across two simulated manipulation environments. On the ALOHA setup, segmentation score predicts real-world performance after offline training with 50 demonstrations.
Authors: Ahmed Bourouis, Judith Ellen Fan, Yulia Gryaditskaya
We study the underexplored but fundamental vision problem of machine understanding of abstract freehand scene sketches. We introduce a sketch encoder that results in semantically-aware feature space, which we evaluate by testing its performance on a semantic sketch segmentation task. To train our model we rely only on the availability of bitmap sketches with their brief captions and do not require any pixel-level annotations. To obtain generalization to a large set of sketches and categories, we build on a vision transformer encoder pretrained with the CLIP model. We freeze the text encoder and perform visual-prompt tuning of the visual encoder branch while introducing a set of critical modifications. Firstly, we augment the classical key-query (k-q) self-attention blocks with value-value (v-v) self-attention blocks. Central to our model is a two-level hierarchical network design that enables efficient semantic disentanglement: The first level ensures holistic scene sketch encoding, and the second level focuses on individual categories. We, then, in the second level of the hierarchy, introduce a cross-attention between textual and visual branches. Our method outperforms zero-shot CLIP pixel accuracy of segmentation results by 37 points, reaching an accuracy of $85.5\%$ on the FS-COCO sketch dataset. Finally, we conduct a user study that allows us to identify further improvements needed over our method to reconcile machine and human understanding of scene sketches.
Authors: Haoyu Ma, Shahin Mahdizadehaghdam, Bichen Wu, Zhipeng Fan, Yuchao Gu, Wenliang Zhao, Lior Shapira, Xiaohui Xie
Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.
Authors: Sihan Liu, Yiwei Ma, Xiaoqing Zhang, Haowei Wang, Jiayi Ji, Xiaoshuai Sun, Rongrong Ji
Referring Remote Sensing Image Segmentation (RRSIS) is a new challenge that combines computer vision and natural language processing, delineating specific regions in aerial images as described by textual queries. Traditional Referring Image Segmentation (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery, leading to suboptimal segmentation results. To address these challenges, we introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS. RMSIN incorporates an Intra-scale Interaction Module (IIM) to effectively address the fine-grained detail required at multiple scales and a Cross-scale Interaction Module (CIM) for integrating these details coherently across the network. Furthermore, RMSIN employs an Adaptive Rotated Convolution (ARC) to account for the diverse orientations of objects, a novel contribution that significantly enhances segmentation accuracy. To assess the efficacy of RMSIN, we have curated an expansive dataset comprising 17,402 image-caption-mask triplets, which is unparalleled in terms of scale and variety. This dataset not only presents the model with a wide range of spatial and rotational scenarios but also establishes a stringent benchmark for the RRSIS task, ensuring a rigorous evaluation of performance. Our experimental evaluations demonstrate the exceptional performance of RMSIN, surpassing existing state-of-the-art models by a significant margin. All datasets and code are made available at https://github.com/Lsan2401/RMSIN.
Authors: Fan Zhang, Shaodi You, Yu Li, Ying Fu
Monocular depth estimation has experienced significant progress on terrestrial images in recent years, largely due to deep learning advancements. However, it remains inadequate for underwater scenes, primarily because of data scarcity. Given the inherent challenges of light attenuation and backscattering in water, acquiring clear underwater images or precise depth information is notably difficult and costly. Consequently, learning-based approaches often rely on synthetic data or turn to unsupervised or self-supervised methods to mitigate this lack of data. Nonetheless, the performance of these methods is often constrained by the domain gap and looser constraints. In this paper, we propose a novel pipeline for generating photorealistic underwater images using accurate terrestrial depth data. This approach facilitates the training of supervised models for underwater depth estimation, effectively reducing the performance disparity between terrestrial and underwater environments. Contrary to prior synthetic datasets that merely apply style transfer to terrestrial images without altering the scene content, our approach uniquely creates vibrant, non-existent underwater scenes by leveraging terrestrial depth data through the innovative Stable Diffusion model. Specifically, we introduce a unique Depth2Underwater ControlNet, trained on specially prepared \{Underwater, Depth, Text\} data triplets, for this generation task. Our newly developed dataset enables terrestrial depth estimation models to achieve considerable improvements, both quantitatively and qualitatively, on unseen underwater images, surpassing their terrestrial pre-trained counterparts. Moreover, the enhanced depth accuracy for underwater scenes also aids underwater image restoration techniques that rely on depth maps, further demonstrating our dataset's utility. The dataset will be available at https://github.com/zkawfanx/Atlantis.
Authors: Kaipeng Fang, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Zhi-Qi Cheng, Xiyao Li, Heng Tao Shen
The goal of Universal Cross-Domain Retrieval (UCDR) is to achieve robust performance in generalized test scenarios, wherein data may belong to strictly unknown domains and categories during training. Recently, pre-trained models with prompt tuning have shown strong generalization capabilities and attained noteworthy achievements in various downstream tasks, such as few-shot learning and video-text retrieval. However, applying them directly to UCDR may not sufficiently to handle both domain shift (i.e., adapting to unfamiliar domains) and semantic shift (i.e., transferring to unknown categories). To this end, we propose Prompting-to-Simulate (ProS), the first method to apply prompt tuning for UCDR. ProS employs a two-step process to simulate Content-aware Dynamic Prompts (CaDP) which can impact models to produce generalized features for UCDR. Concretely, in Prompt Units Learning stage, we introduce two Prompt Units to individually capture domain and semantic knowledge in a mask-and-align way. Then, in Context-aware Simulator Learning stage, we train a Content-aware Prompt Simulator under a simulated test scenarios to produce the corresponding CaDP. Extensive experiments conducted on three benchmark datasets show that our method achieves new state-of-the-art performance without bringing excessive parameters. Our method is publicly available at https://anonymous.4open.science/r/ProS
Authors: Fei Pan, Sangryul Jeon, Brian Wang, Frank Mckenna, Stella X. Yu
Existing building recognition methods, exemplified by BRAILS, utilize supervised learning to extract information from satellite and street-view images for classification and segmentation. However, each task module requires human-annotated data, hindering the scalability and robustness to regional variations and annotation imbalances. In response, we propose a new zero-shot workflow for building attribute extraction that utilizes large-scale vision and language models to mitigate reliance on external annotations. The proposed workflow contains two key components: image-level captioning and segment-level captioning for the building images based on the vocabularies pertinent to structural and civil engineering. These two components generate descriptive captions by computing feature representations of the image and the vocabularies, and facilitating a semantic match between the visual and textual representations. Consequently, our framework offers a promising avenue to enhance AI-driven captioning for building attribute extraction in the structural and civil engineering domains, ultimately reducing reliance on human annotations while bolstering performance and adaptability.
Authors: Jiaming Liu, Ran Xu, Senqiao Yang, Renrui Zhang, Qizhe Zhang, Zehui Chen, Yandong Guo, Shanghang Zhang
Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions, addressing real-world dynamism. Existing CTTA methods mainly rely on entropy minimization or teacher-student pseudo-labeling schemes for knowledge extraction in unlabeled target domains. However, dynamic data distributions cause miscalibrated predictions and noisy pseudo-labels in existing self-supervised learning methods, hindering the effective mitigation of error accumulation and catastrophic forgetting problems during the continual adaptation process. To tackle these issues, we propose a continual self-supervised method, Adaptive Distribution Masked Autoencoders (ADMA), which enhances the extraction of target domain knowledge while mitigating the accumulation of distribution shifts. Specifically, we propose a Distribution-aware Masking (DaM) mechanism to adaptively sample masked positions, followed by establishing consistency constraints between the masked target samples and the original target samples. Additionally, for masked tokens, we utilize an efficient decoder to reconstruct a hand-crafted feature descriptor (e.g., Histograms of Oriented Gradients), leveraging its invariant properties to boost task-relevant representations. Through conducting extensive experiments on four widely recognized benchmarks, our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks.
Authors: Demircan Tas, Rohit Priyadarshi Sanatani
There has been a growing adoption of computer vision tools and technologies in architectural design workflows over the past decade. Notable use cases include point cloud generation, visual content analysis, and spatial awareness for robotic fabrication. Multiple image classification, object detection, and semantic pixel segmentation models have become popular for the extraction of high-level symbolic descriptions and semantic content from two-dimensional images and videos. However, a major challenge in this regard has been the extraction of high-level architectural structures (walls, floors, ceilings windows etc.) from diverse imagery where parts of these elements are occluded by furniture, people, or other non-architectural elements. This project aims to tackle this problem by proposing models that are capable of extracting architecturally meaningful semantic descriptions from two-dimensional scenes of populated interior spaces. 1000 virtual classrooms are parametrically generated, randomized along key spatial parameters such as length, width, height, and door/window positions. The positions of cameras, and non-architectural visual obstructions (furniture/objects) are also randomized. A Generative Adversarial Network (GAN) for image-to-image translation (Pix2Pix) is trained on synthetically generated rendered images of these enclosures, along with corresponding image abstractions representing high-level architectural structure. The model is then tested on unseen synthetic imagery of new enclosures, and outputs are compared to ground truth using pixel-wise comparison for evaluation. A similar model evaluation is also carried out on photographs of existing indoor enclosures, to measure its performance in real-world settings.
Authors: Ziyu Lin, Enzo Tartaglione, Van-Tam Nguyen
On-device training is an emerging approach in machine learning where models are trained on edge devices, aiming to enhance privacy protection and real-time performance. However, edge devices typically possess restricted computational power and resources, making it challenging to perform computationally intensive model training tasks. Consequently, reducing resource consumption during training has become a pressing concern in this field. To this end, we propose SCoTTi (Save Computation at Training Time), an adaptive framework that addresses the aforementioned challenge. It leverages an optimizable threshold parameter to effectively reduce the number of neuron updates during training which corresponds to a decrease in memory and computation footprint. Our proposed approach demonstrates superior performance compared to the state-of-the-art methods regarding computational resource savings on various commonly employed benchmarks and popular architectures, including ResNets, MobileNet, and Swin-T.
Authors: Divya Mereddy
With advanced AI, while every industry is growing at rocket speed, the smart home industry has not reached the next generation. There is still a huge leap of innovation that needs to happen before we call a home a Smart home. A Smart home should predict residents' needs and fulfill them in a timely manner. One of the important tasks of maintaining a home is timely grocery tracking and supply maintenance. Grocery tracking models are very famous in the retail industry but they are nonexistent in the common household. Groceries detection in household refrigerators or storage closets is very complicated compared to retail shelving data. In this paper, home grocery tracking problem is resolved by combining retail shelving data and fruits dataset with real-time 360 view data points collected from home groceries storage. By integrating this vision-based object detection system along with supply chain and user food interest prediction systems, complete automation of groceries ordering can be achieved.
Authors: HyeongGwon Hong, Yooshin Cho, Hanbyel Cho, Jaesung Ahn, Junmo Kim
Gradient inversion attacks can leak data privacy when clients share weight updates with the server in federated learning (FL). Existing studies mainly use L2 or cosine distance as the loss function for gradient matching in the attack. Our empirical investigation shows that the vulnerability ranking varies with the loss function used. Gradient norm, which is commonly used as a vulnerability proxy for gradient inversion attack, cannot explain this as it remains constant regardless of the loss function for gradient matching. In this paper, we propose a loss-aware vulnerability proxy (LAVP) for the first time. LAVP refers to either the maximum or minimum eigenvalue of the Hessian with respect to gradient matching loss at ground truth. This suggestion is based on our theoretical findings regarding the local optimization of the gradient inversion in proximity to the ground truth, which corresponds to the worst case attack scenario. We demonstrate the effectiveness of LAVP on various architectures and datasets, showing its consistent superiority over the gradient norm in capturing sample vulnerabilities. The performance of each proxy is measured in terms of Spearman's rank correlation with respect to several similarity scores. This work will contribute to enhancing FL security against any potential loss functions beyond L2 or cosine distance in the future.
Authors: Hangjie Yuan, Shiwei Zhang, Xiang Wang, Yujie Wei, Tao Feng, Yining Pan, Yingya Zhang, Ziwei Liu, Samuel Albanie, Dong Ni
Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle this problem, we propose InstructVideo to instruct text-to-video diffusion models with human feedback by reward fine-tuning. InstructVideo has two key ingredients: 1) To ameliorate the cost of reward fine-tuning induced by generating through the full DDIM sampling chain, we recast reward fine-tuning as editing. By leveraging the diffusion process to corrupt a sampled video, InstructVideo requires only partial inference of the DDIM sampling chain, reducing fine-tuning cost while improving fine-tuning efficiency. 2) To mitigate the absence of a dedicated video reward model for human preferences, we repurpose established image reward models, e.g., HPSv2. To this end, we propose Segmental Video Reward, a mechanism to provide reward signals based on segmental sparse sampling, and Temporally Attenuated Reward, a method that mitigates temporal modeling degradation during fine-tuning. Extensive experiments, both qualitative and quantitative, validate the practicality and efficacy of using image reward models in InstructVideo, significantly enhancing the visual quality of generated videos without compromising generalization capabilities. Code and models will be made publicly available.
Authors: Akio Kodaira, Chenfeng Xu, Toshiki Hazama, Takanori Yoshimoto, Kohei Ohno, Shogo Mitsuhori, Soichi Sugano, Hanying Cho, Zhijian Liu, Kurt Keutzer
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limitation becomes particularly evident in scenarios involving continuous input, such as Metaverse, live video streaming, and broadcasting, where high throughput is imperative. To address this, we present a novel approach that transforms the original sequential denoising into the batching denoising process. Stream Batch eliminates the conventional wait-and-interact approach and enables fluid and high throughput streams. To handle the frequency disparity between data input and model throughput, we design a novel input-output queue for parallelizing the streaming process. Moreover, the existing diffusion pipeline uses classifier-free guidance(CFG), which requires additional U-Net computation. To mitigate the redundant computations, we propose a novel residual classifier-free guidance (RCFG) algorithm that reduces the number of negative conditional denoising steps to only one or even zero. Besides, we introduce a stochastic similarity filter(SSF) to optimize power consumption. Our Stream Batch achieves around 1.5x speedup compared to the sequential denoising method at different denoising levels. The proposed RCFG leads to speeds up to 2.05x higher than the conventional CFG. Combining the proposed strategies and existing mature acceleration tools makes the image-to-image generation achieve up-to 91.07fps on one RTX4090, improving the throughputs of AutoPipline developed by Diffusers over 59.56x. Furthermore, our proposed StreamDiffusion also significantly reduces the energy consumption by 2.39x on one RTX3060 and 1.99x on one RTX4090, respectively.
Authors: Benedikt Kolbeinsson, Krystian Mikolajczyk
Accurate depth and semantic segmentation are crucial for various computer vision tasks. However, the scarcity of annotated real-world aerial datasets poses a significant challenge for training and evaluating robust models. Additionally, the detection and segmentation of thin objects, such as wires, cables, and fences, present a critical concern for ensuring the safe operation of drones. To address these limitations, we present a novel synthetic dataset specifically designed for depth and semantic segmentation tasks in aerial views. Leveraging photo-realistic rendering techniques, our dataset provides a valuable resource for training models using a synthetic-supervision training scheme while introducing new drone-specific metrics for depth accuracy.
Authors: Barak Meiri, Dvir Samuel, Nir Darshan, Gal Chechik, Shai Avidan, Rami Ben-Ari
Text-guided diffusion models offer powerful new ways to generate and manipulate images. Several applications of these models, including image editing interpolation, and semantic augmentation, require diffusion inversion. This is the process of finding a noise seed that can be used to generate a given image. Current techniques for inverting a given image can be slow or inaccurate. The technical challenge for inverting the diffusion process arises from an implicit equation over the latent that cannot be solved in closed form. Previous approaches proposed to solve this issue by approximation or various learning schemes. Here, we formulate the problem as a fixed-point equation problem and solve it using fixed-point iterations, a well-studied approach in numerical analysis. We further identify a source of inconsistency that significantly hurts the inversion of real images encoded to the latent space. We show how to correct it by applying a prompt-aware adjustment of the encoding. Our solution, Fixed-point inversion, is much faster than previous techniques like EDICT and Null-text, with similar inversion quality. It can be combined with any pretrained diffusion model and requires no model training, prompt tuning, or additional parameters. In a series of experiments, we find that Fixed-point inversion shows improved results in several downstream tasks: image editing, image interpolation, and generation of rare objects.
Authors: Heming Yao, Jérôme Lüscher, Benjamin Gutierrez Becker, Josep Arús-Pous, Tommaso Biancalani, Amelie Bigorgne, David Richmond
Colonoscopy plays a crucial role in the diagnosis and prognosis of various gastrointestinal diseases. Due to the challenges of collecting large-scale high-quality ground truth annotations for colonoscopy images, and more generally medical images, we explore using self-supervised features from vision transformers in three challenging tasks for colonoscopy images. Our results indicate that image-level features learned from DINO models achieve image classification performance comparable to fully supervised models, and patch-level features contain rich semantic information for object detection. Furthermore, we demonstrate that self-supervised features combined with unsupervised segmentation can be used to discover multiple clinically relevant structures in a fully unsupervised manner, demonstrating the tremendous potential of applying these methods in medical image analysis.
Authors: Li Ding, Lee Spector
One potential drawback of using aggregated performance measurement in machine learning is that models may learn to accept higher errors on some training cases as compromises for lower errors on others, with the lower errors actually being instances of overfitting. This can lead to both stagnation at local optima and poor generalization. Lexicase selection is an uncompromising method developed in evolutionary computation, which selects models on the basis of sequences of individual training case errors instead of using aggregated metrics such as loss and accuracy. In this paper, we investigate how lexicase selection, in its general form, can be integrated into the context of deep learning to enhance generalization. We propose Gradient Lexicase Selection, an optimization framework that combines gradient descent and lexicase selection in an evolutionary fashion. Our experimental results demonstrate that the proposed method improves the generalization performance of various widely-used deep neural network architectures across three image classification benchmarks. Additionally, qualitative analysis suggests that our method assists networks in learning more diverse representations. Our source code is available on GitHub: https://github.com/ld-ing/gradient-lexicase.
Authors: Clément Grisi, Geert Litjens, Jeroen van der Laak
Vision Transformers (ViTs) have ushered in a new era in computer vision, showcasing unparalleled performance in many challenging tasks. However, their practical deployment in computational pathology has largely been constrained by the sheer size of whole slide images (WSIs), which result in lengthy input sequences. Transformers faced a similar limitation when applied to long documents, and Hierarchical Transformers were introduced to circumvent it. Given the analogous challenge with WSIs and their inherent hierarchical structure, Hierarchical Vision Transformers (H-ViTs) emerge as a promising solution in computational pathology. This work delves into the capabilities of H-ViTs, evaluating their efficiency for prostate cancer grading in WSIs. Our results show that they achieve competitive performance against existing state-of-the-art solutions.
Authors: Payam Jome Yazdian, Eric Liu, Li Cheng, Angelica Lim
This paper proposes MotionScript, a motion-to-text conversion algorithm and natural language representation for human body motions. MotionScript aims to describe movements in greater detail and with more accuracy than previous natural language approaches. Many motion datasets describe relatively objective and simple actions with little variation on the way they are expressed (e.g. sitting, walking, dribbling a ball). But for expressive actions that contain a diversity of movements in the class (e.g. being sad, dancing), or for actions outside the domain of standard motion capture datasets (e.g. stylistic walking, sign-language), more specific and granular natural language descriptions are needed. Our proposed MotionScript descriptions differ from existing natural language representations in that it provides direct descriptions in natural language instead of simple action labels or high-level human captions. To the best of our knowledge, this is the first attempt at translating 3D motions to natural language descriptions without requiring training data. Our experiments show that when MotionScript representations are used in a text-to-motion neural task, body movements are more accurately reconstructed, and large language models can be used to generate unseen complex motions.
Authors: Shutong Jin, Ruiyu Wang, Florian T. Pokorny
Although large-scale text-to-image generative models have shown promising performance in synthesizing high-quality images, directly applying these models to image editing remains a significant challenge. This challenge is further amplified in video editing due to the additional dimension of time. Especially for editing real videos as it necessitates maintaining a stable semantic layout across the frames while executing localized edits precisely without disrupting the existing backgrounds. In this paper, we propose \textit{RealCraft}, an attention-control-based method for zero-shot editing in real videos. By employing the object-centric manipulation of cross-attention between prompts and frames and spatial-temporal attention within the frames, we achieve precise shape-wise editing along with enhanced consistency. Our model can be used directly with Stable Diffusion and operates without the need for additional localized information. We showcase our zero-shot attention-control-based method across a range of videos, demonstrating localized, high-fidelity, shape-precise and time-consistent editing in videos of various lengths, up to 64 frames.
Authors: Hang Xu, Alessandro Perelli
In this work, we present a novel self-supervised method for Low Dose Computed Tomography (LDCT) reconstruction. Reducing the radiation dose to patients during a CT scan is a crucial challenge since the quality of the reconstruction highly degrades because of low photons or limited measurements. Supervised deep learning methods have shown the ability to remove noise in images but require accurate ground truth which can be obtained only by performing additional high-radiation CT scans. Therefore, we propose a novel self-supervised framework for LDCT, in which ground truth is not required for training the convolutional neural network (CNN). Based on the Noise2Inverse (N2I) method, we enforce in the training loss the equivariant property of rotation transformation, which is induced by the CT imaging system, to improve the quality of the CT image in a lower dose. Numerical and experimental results show that the reconstruction accuracy of N2I with sparse views is degrading while the proposed rotational augmented Noise2Inverse (RAN2I) method keeps better image quality over a different range of sampling angles. Finally, the quantitative results demonstrate that RAN2I achieves higher image quality compared to N2I, and experimental results of RAN2I on real projection data show comparable performance to supervised learning.
Authors: Hongyi He, Longjun Liu, Haonan Zhang, Nanning Zheng
Among existing Neural Architecture Search methods, DARTS is known for its efficiency and simplicity. This approach applies continuous relaxation of network representation to construct a weight-sharing supernet and enables the identification of excellent subnets in just a few GPU days. However, performance collapse in DARTS results in deteriorating architectures filled with parameter-free operations and remains a great challenge to the robustness. To resolve this problem, we reveal that the fundamental reason is the biased estimation of the candidate importance in the search space through theoretical and experimental analysis, and more precisely select operations via information-based measurements. Furthermore, we demonstrate that the excessive concern over the supernet and inefficient utilization of data in bi-level optimization also account for suboptimal results. We adopt a more realistic objective focusing on the performance of subnets and simplify it with the help of the information-based measurements. Finally, we explain theoretically why progressively shrinking the width of the supernet is necessary and reduce the approximation error of optimal weights in DARTS. Our proposed method, named IS-DARTS, comprehensively improves DARTS and resolves the aforementioned problems. Extensive experiments on NAS-Bench-201 and DARTS-based search space demonstrate the effectiveness of IS-DARTS.
Authors: Fahim Ahmed Zaman, Mathews Jacob, Amanda Chang, Kan Liu, Milan Sonka, Xiaodong Wu
Diffusion models have shown impressive performance for image generation, often times outperforming other generative models. Since their introduction, researchers have extended the powerful noise-to-image denoising pipeline to discriminative tasks, including image segmentation. In this work we propose a conditional score-based generative modeling framework for medical image segmentation which relies on a parametric surface representation for the segmentation masks. The surface re-parameterization allows the direct application of standard diffusion theory, as opposed to when the mask is represented as a binary mask. Moreover, we adapted an extended variant of the diffusion technique known as the "cold-diffusion" where the diffusion model can be constructed with deterministic perturbations instead of Gaussian noise, which facilitates significantly faster convergence in the reverse diffusion. We evaluated our method on the segmentation of the left ventricle from 65 transthoracic echocardiogram videos (2230 echo image frames) and compared its performance to the most popular and widely used image segmentation models. Our proposed model not only outperformed the compared methods in terms of segmentation accuracy, but also showed potential in estimating segmentation uncertainties for further downstream analyses due to its inherent generative nature.
Authors: Fahim Ahmed Zaman, Wahidul Alam, Tarun Kanti Roy, Amanda Chang, Kan Liu, Xiaodong Wu
Researchers have shown significant correlations among segmented objects in various medical imaging modalities and disease related pathologies. Several studies showed that using hand crafted features for disease prediction neglects the immense possibility to use latent features from deep learning (DL) models which may reduce the overall accuracy of differential diagnosis. However, directly using classification or segmentation models on medical to learn latent features opt out robust feature selection and may lead to overfitting. To fill this gap, we propose a novel feature selection technique using the latent space of a segmentation model that can aid diagnosis. We evaluated our method in differentiating a rare cardiac disease: Takotsubo Syndrome (TTS) from the ST elevation myocardial infarction (STEMI) using echocardiogram videos (echo). TTS can mimic clinical features of STEMI in echo and extremely hard to distinguish. Our approach shows promising results in differential diagnosis of TTS with 82% diagnosis accuracy beating the previous state-of-the-art (SOTA) approach. Moreover, the robust feature selection technique using LASSO algorithm shows great potential in reducing the redundant features and creates a robust pipeline for short- and long-term disease prognoses in the downstream analysis.
Authors: Bumsoo Kim, Jinhyung Kim, Yeonsik Jo, Seung Hwan Kim
Recent advances in vision language pretraining (VLP) have been largely attributed to the large-scale data collected from the web. However, uncurated dataset contains weakly correlated image-text pairs, causing data inefficiency. To address the issue, knowledge distillation have been explored at the expense of extra image and text momentum encoders to generate teaching signals for misaligned image-text pairs. In this paper, our goal is to resolve the misalignment problem with an efficient distillation framework. To this end, we propose ECLIPSE: Expediting Contrastive Language-Image Pretraining with Self-distilled Encoders. ECLIPSE features a distinctive distillation architecture wherein a shared text encoder is utilized between an online image encoder and a momentum image encoder. This strategic design choice enables the distillation to operate within a unified projected space of text embedding, resulting in better performance. Based on the unified text embedding space, ECLIPSE compensates for the additional computational cost of the momentum image encoder by expediting the online image encoder. Through our extensive experiments, we validate that there is a sweet spot between expedition and distillation where the partial view from the expedited online image encoder interacts complementarily with the momentum teacher. As a result, ECLIPSE outperforms its counterparts while achieving substantial acceleration in inference speed.
Authors: Bumsoo Kim, Yeonsik Jo, Jinhyung Kim, Seung Hwan Kim
Contrastive Language-Image Pretraining has emerged as a prominent approach for training vision and text encoders with uncurated image-text pairs from the web. To enhance data-efficiency, recent efforts have introduced additional supervision terms that involve random-augmented views of the image. However, since the image augmentation process is unaware of its text counterpart, this procedure could cause various degrees of image-text misalignments during training. Prior methods either disregarded this discrepancy or introduced external models to mitigate the impact of misalignments during training. In contrast, we propose a novel metric learning approach that capitalizes on these misalignments as an additional training source, which we term "Misalign, Contrast then Distill (MCD)". Unlike previous methods that treat augmented images and their text counterparts as simple positive pairs, MCD predicts the continuous scales of misalignment caused by the augmentation. Our extensive experimental results show that our proposed MCD achieves state-of-the-art transferability in multiple classification and retrieval downstream datasets.
Authors: Bumsoo Kim, Taeho Choi, Jaewoo Kang, Hyunwoo J. Kim
Recent advances in deep neural networks have achieved significant progress in detecting individual objects from an image. However, object detection is not sufficient to fully understand a visual scene. Towards a deeper visual understanding, the interactions between objects, especially humans and objects are essential. Most prior works have obtained this information with a bottom-up approach, where the objects are first detected and the interactions are predicted sequentially by pairing the objects. This is a major bottleneck in HOI detection inference time. To tackle this problem, we propose UnionDet, a one-stage meta-architecture for HOI detection powered by a novel union-level detector that eliminates this additional inference stage by directly capturing the region of interaction. Our one-stage detector for human-object interaction shows a significant reduction in interaction prediction time 4x~14x while outperforming state-of-the-art methods on two public datasets: V-COCO and HICO-DET.
Authors: Andreas Papachristodoulou, Christos Kyrkou, Stelios Timotheou, Theocharis Theocharides
The Forward-Forward (FF) Algorithm has been recently proposed to alleviate the issues of backpropagation (BP) commonly used to train deep neural networks. However, its current formulation exhibits limitations such as the generation of negative data, slower convergence, and inadequate performance on complex tasks. In this paper, we take the main ideas of FF and improve them by leveraging channel-wise competitive learning in the context of convolutional neural networks for image classification tasks. A layer-wise loss function is introduced that promotes competitive learning and eliminates the need for negative data construction. To enhance both the learning of compositional features and feature space partitioning, a channel-wise feature separator and extractor block is proposed that complements the competitive learning process. Our method outperforms recent FF-based models on image classification tasks, achieving testing errors of 0.58%, 7.69%, 21.89%, and 48.77% on MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 respectively. Our approach bridges the performance gap between FF learning and BP methods, indicating the potential of our proposed approach to learn useful representations in a layer-wise modular fashion, enabling more efficient and flexible learning.
Authors: Abdulkadhem A. Abdulkadhem
In this paper, we introduce an innovative approach for extracting trajectories from a camera sensor in GPS-denied environments, leveraging visual odometry. The system takes video footage captured by a forward-facing camera mounted on a vehicle as input, with the output being a chain code representing the camera's trajectory. The proposed methodology involves several key steps. Firstly, we employ phase correlation between consecutive frames of the video to extract essential information. Subsequently, we introduce a novel chain code method termed "dynamic chain code," which is based on the x-shift values derived from the phase correlation. The third step involves determining directional changes (forward, left, right) by establishing thresholds and extracting the corresponding chain code. This extracted code is then stored in a buffer for further processing. Notably, our system outperforms traditional methods reliant on spatial features, exhibiting greater speed and robustness in noisy environments. Importantly, our approach operates without external camera calibration information. Moreover, by incorporating visual odometry, our system enhances its accuracy in estimating camera motion, providing a more comprehensive understanding of trajectory dynamics. Finally, the system culminates in the visualization of the normalized camera motion trajectory.
Authors: Shichong Peng, Alireza Moazeni, Ke Li
Deep generative models, such as diffusion models, GANs, and IMLE, have shown impressive capability in tackling inverse problems. However, the validity of model-generated solutions w.r.t. the forward problem and the reliability of associated uncertainty estimates remain understudied. This study evaluates recent diffusion-based, GAN-based, and IMLE-based methods on three inverse problems, i.e., $16\times$ super-resolution, colourization, and image decompression. We assess the validity of these models' outputs as solutions to the inverse problems and conduct a thorough analysis of the reliability of the models' estimates of uncertainty over the solution. Overall, we find that the IMLE-based CHIMLE method outperforms other methods in terms of producing valid solutions and reliable uncertainty estimates.
Authors: Yunye Gong, Robik Shrestha, Jared Claypoole, Michael Cogswell, Arijit Ray, Christopher Kanan, Ajay Divakaran
We propose a novel VQA dataset, based on picture stories designed for educating young children, that aims to facilitate comprehensive evaluation and characterization of vision-language models on comprehension tasks. Unlike current VQA datasets that often focus on fact-based memorization and simple reasoning tasks without principled scientific grounding, we collect data containing tasks reflecting different levels of comprehension and underlying cognitive processes, as laid out in Bloom's Taxonomy, a classic framework widely adopted in education research. The proposed BloomVQA dataset can be mapped to a hierarchical graph-based representation of visual stories, enabling automatic data augmentation and novel measures characterizing model consistency across the underlying taxonomy. We demonstrate graded evaluation and reliability analysis based on our proposed consistency metrics on state-of-the-art vision-language models. Our results suggest that, while current models achieve the most gain on low-level comprehension tasks, they generally fall short on high-level tasks requiring more advanced comprehension and cognitive skills, as 38.0% drop in VQA accuracy is observed comparing lowest and highest level tasks. Furthermore, current models show consistency patterns misaligned with human comprehension in various scenarios, suggesting emergent structures of model behaviors.
Authors: Guangtao Zheng, Mengdi Huai, Aidong Zhang
Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard augmentations, such as translate, or invert, has not been fully exploited in SDG; practically, these augmentations are used as a part of a data preprocessing procedure. Although it is intuitive to use many such augmentations to boost the robustness of a model to out-of-distribution domain shifts, we lack a principled approach to harvest the benefit brought from multiple these augmentations. Here, we conceptualize standard data augmentations with learnable parameters as semantics transformations that can manipulate certain semantics of a sample, such as the geometry or color of an image. Then, we propose Adversarial learning with Semantics Transformations (AdvST) that augments the source domain data with semantics transformations and learns a robust model with the augmented data. We theoretically show that AdvST essentially optimizes a distributionally robust optimization objective defined on a set of semantics distributions induced by the parameters of semantics transformations. We demonstrate that AdvST can produce samples that expand the coverage on target domain data. Compared with the state-of-the-art methods, AdvST, despite being a simple method, is surprisingly competitive and achieves the best average SDG performance on the Digits, PACS, and DomainNet datasets. Our code is available at https://github.com/gtzheng/AdvST.
Authors: Chengxiang Yin, Zhengping Che, Kun Wu, Zhiyuan Xu, Qinru Qiu, Jian Tang
Video Question Answering (VideoQA) is a very attractive and challenging research direction aiming to understand complex semantics of heterogeneous data from two domains, i.e., the spatio-temporal video content and the word sequence in question. Although various attention mechanisms have been utilized to manage contextualized representations by modeling intra- and inter-modal relationships of the two modalities, one limitation of the predominant VideoQA methods is the lack of reasoning with event correlation, that is, sensing and analyzing relationships among abundant and informative events contained in the video. In this paper, we introduce the dense caption modality as a new auxiliary and distill event-correlated information from it to infer the correct answer. To this end, we propose a novel end-to-end trainable model, Event-Correlated Graph Neural Networks (EC-GNNs), to perform cross-modal reasoning over information from the three modalities (i.e., caption, video, and question). Besides the exploitation of a brand new modality, we employ cross-modal reasoning modules for explicitly modeling inter-modal relationships and aggregating relevant information across different modalities, and we propose a question-guided self-adaptive multi-modal fusion module to collect the question-oriented and event-correlated evidence through multi-step reasoning. We evaluate our model on two widely-used benchmark datasets and conduct an ablation study to justify the effectiveness of each proposed component.
Authors: Jiang-Tian Zhai, Xialei Liu, Lu Yu, Ming-Ming Cheng
Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques can only be applied to current task data. Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration. The conventional knowledge distillation-based methods place too strict constraints on the network parameters and features to prevent forgetting, which limits the training of new tasks. To loose this constraint, we proposed a novel fine-grained selective patch-level distillation to adaptively balance plasticity and stability. Some task-agnostic patches can be used to preserve the decision boundary of the old task. While some patches containing the important foreground are favorable for learning the new task.
Moreover, we employ a task-agnostic mechanism to generate more realistic prototypes of old tasks with the current task sample for reducing classifier bias for fine-grained knowledge restoration. Extensive experiments on CIFAR100, TinyImageNet and ImageNet-Subset demonstrate the effectiveness of our method. Code is available at https://github.com/scok30/vit-cil.
Authors: Chengxiang Yin, Zhengping Che, Kun Wu, Zhiyuan Xu, Jian Tang
Visual Question Answering (VQA) has emerged as one of the most challenging tasks in artificial intelligence due to its multi-modal nature. However, most existing VQA methods are incapable of handling Knowledge-based Visual Question Answering (KB-VQA), which requires external knowledge beyond visible contents to answer questions about a given image. To address this issue, we propose a novel framework that endows the model with capabilities of answering more general questions, and achieves a better exploitation of external knowledge through generating Multiple Clues for Reasoning with Memory Neural Networks (MCR-MemNN). Specifically, a well-defined detector is adopted to predict image-question related relation phrases, each of which delivers two complementary clues to retrieve the supporting facts from external knowledge base (KB), which are further encoded into a continuous embedding space using a content-addressable memory. Afterwards, mutual interactions between visual-semantic representation and the supporting facts stored in memory are captured to distill the most relevant information in three modalities (i.e., image, question, and KB). Finally, the optimal answer is predicted by choosing the supporting fact with the highest score. We conduct extensive experiments on two widely-used benchmarks. The experimental results well justify the effectiveness of MCR-MemNN, as well as its superiority over other KB-VQA methods.
Authors: Qihang Fang, Yafei Song, Keqiang Li, Liefeng Bo
Neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by the photometric loss in an end-to-end training manner, NeRF inherently suffers from the shape-radiance ambiguity problem, i.e., it can perfectly fit training views but does not guarantee decoupling the two fields correctly. To deal with this issue, existing works have incorporated prior knowledge to provide an independent supervision signal for the density field, including total variation loss, sparsity loss, distortion loss, etc. These losses are based on general assumptions about the density field, e.g., it should be smooth, sparse, or compact, which are not adaptive to a specific scene. In this paper, we propose a more adaptive method to reduce the shape-radiance ambiguity. The key is a rendering method that is only based on the density field. Specifically, we first estimate the color field based on the density field and posed images in a closed form. Then NeRF's rendering process can proceed. We address the problems in estimating the color field, including occlusion and non-uniformly distributed views. Afterward, it is applied to regularize NeRF's density field. As our regularization is guided by photometric loss, it is more adaptive compared to existing ones. Experimental results show that our method improves the density field of NeRF both qualitatively and quantitatively. Our code is available at https://github.com/qihangGH/Closed-form-color-field.
Authors: Haoxing Chen, Yaohui Li, Zhangxuan Gu, Zhuoer Xu, Jun Lan, Huaxiong Li
Image harmonization is a crucial technique in image composition that aims to seamlessly match the background by adjusting the foreground of composite images. Current methods adopt either global-level or pixel-level feature matching. Global-level feature matching ignores the proximity prior, treating foreground and background as separate entities. On the other hand, pixel-level feature matching loses contextual information. Therefore, it is necessary to use the information from semantic maps that describe different objects to guide harmonization. In this paper, we propose Semantic-guided Region-aware Instance Normalization (SRIN) that can utilize the semantic segmentation maps output by a pre-trained Segment Anything Model (SAM) to guide the visual consistency learning of foreground and background features. Abundant experiments demonstrate the superiority of our method for image harmonization over state-of-the-art methods.
Authors: Julio Silva-Rodriguez, Sina Hajimiri, Ismail Ben Ayed, Jose Dolz
Efficient transfer learning (ETL) is receiving increasing attention to adapt large pre-trained language-vision models on downstream tasks with a few labeled samples. While significant progress has been made, we reveal that state-of-the-art ETL approaches exhibit strong performance only in narrowly-defined experimental setups, and with a careful adjustment of hyperparameters based on a large corpus of labeled samples. In particular, we make two interesting, and surprising empirical observations. First, to outperform a simple Linear Probing baseline, these methods require to optimize their hyper-parameters on each target task. And second, they typically underperform -- sometimes dramatically -- standard zero-shot predictions in the presence of distributional drifts. Motivated by the unrealistic assumptions made in the existing literature, i.e., access to a large validation set and case-specific grid-search for optimal hyperparameters, we propose a novel approach that meets the requirements of real-world scenarios. More concretely, we introduce a CLass-Adaptive linear Probe (CLAP) objective, whose balancing term is optimized via an adaptation of the general Augmented Lagrangian method tailored to this context. We comprehensively evaluate CLAP on a broad span of datasets and scenarios, demonstrating that it consistently outperforms SoTA approaches, while yet being a much more efficient alternative.
Authors: Libo Wang, Sijun Dong, Ying Chen, Xiaoliang Meng, Shenghui Fang
Semantic segmentation of remote sensing images plays a vital role in a wide range of Earth Observation (EO) applications, such as land use land cover mapping, environment monitoring, and sustainable development. Driven by rapid developments in Artificial Intelligence (AI), deep learning (DL) has emerged as the mainstream tool for semantic segmentation and achieved many breakthroughs in the field of remote sensing. However, the existing DL-based methods mainly focus on unimodal visual data while ignoring the rich multimodal information involved in the real world, usually demonstrating weak reliability and generlization. Inspired by the success of Vision Transformers and large language models, we propose a novel metadata-collaborative multimodal segmentation network (MetaSegNet) that applies vision-language representation learning for semantic segmentation of remote sensing images. Unlike the common model structure that only uses unimodal visual data, we extract the key characteristic (i.e. the climate zone) from freely available remote sensing image metadata and transfer it into knowledge-based text prompts via the generic ChatGPT. Then, we construct an image encoder, a text encoder and a crossmodal attention fusion subnetwork to extract the image and text feature and apply image-text interaction. Benefiting from such a design, the proposed MetaSegNet demonstrates superior generalization and achieves competitive accuracy with state-of-the-art semantic segmentation methods on the large-scale OpenEarthMap dataset (68.6% mIoU) and Potsdam dataset (93.3% mean F1 score) as well as LoveDA dataset (52.2% mIoU).
Authors: Zhaoyang Zhang, Wenqi Shao, Yixiao Ge, Xiaogang Wang, Jinwei Gu, Ping Luo
This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classification, object detection, and instance segmentation. Furthermore, our approach surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.
Authors: Lipeng Gu, Xuefeng Yan, Liangliang Nan, Dingkun Zhu, Honghua Chen, Weiming Wang, Mingqiang Wei
Current methodologies in point cloud analysis predominantly explore 3D geometries, often achieved through the introduction of intricate learnable geometric extractors in the encoder or by deepening networks with repeated blocks. However, these approaches inevitably lead to a significant number of learnable parameters, resulting in substantial computational costs and imposing memory burdens on CPU/GPU. Additionally, the existing strategies are primarily tailored for object-level point cloud classification and segmentation tasks, with limited extensions to crucial scene-level applications, such as autonomous driving. In response to these limitations, we introduce PointeNet, an efficient network designed specifically for point cloud analysis. PointeNet distinguishes itself with its lightweight architecture, low training cost, and plug-and-play capability, effectively capturing representative features. The network consists of a Multivariate Geometric Encoding (MGE) module and an optional Distance-aware Semantic Enhancement (DSE) module. The MGE module employs operations of sampling, grouping, and multivariate geometric aggregation to lightweightly capture and adaptively aggregate multivariate geometric features, providing a comprehensive depiction of 3D geometries. The DSE module, designed for real-world autonomous driving scenarios, enhances the semantic perception of point clouds, particularly for distant points. Our method demonstrates flexibility by seamlessly integrating with a classification/segmentation head or embedding into off-the-shelf 3D object detection networks, achieving notable performance improvements at a minimal cost. Extensive experiments on object-level datasets, including ModelNet40, ScanObjectNN, ShapeNetPart, and the scene-level dataset KITTI, demonstrate the superior performance of PointeNet over state-of-the-art methods in point cloud analysis.
Authors: Wenhao Xu, Rongtao Xu, Changwei Wang, Shibiao Xu, Li Guo, Man Zhang, Xiaopeng Zhang
Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes. Code is available at:https://github.com/clearxu/SPT.
Authors: Beibei Jing, Youjia Zhang, Zikai Song, Junqing Yu, Wei Yang
Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant progress in human motion synthesis.However, existing methods struggle to handle text inputs that describe complex or long motions.In this paper, we propose the Adaptable Motion Diffusion (AMD) model, which leverages a Large Language Model (LLM) to parse the input text into a sequence of concise and interpretable anatomical scripts that correspond to the target motion.This process exploits the LLM's ability to provide anatomical guidance for complex motion synthesis.We then devise a two-branch fusion scheme that balances the influence of the input text and the anatomical scripts on the inverse diffusion process, which adaptively ensures the semantic fidelity and diversity of the synthesized motion.Our method can effectively handle texts with complex or long motion descriptions, where existing methods often fail. Experiments on datasets with relatively more complex motions, such as CLCD1 and CLCD2, demonstrate that our AMD significantly outperforms existing state-of-the-art models.
Authors: Jingwen Ye, Ruonan Yu, Songhua Liu, Xinchao Wang
Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are frequently treated as a black box, consequently mitigating the vulnerability to such attacks. Thus, enhancing the transferability of the adversarial samples has become a crucial area of research, which heavily relies on selecting appropriate surrogate models. To address this challenge, we propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach is accomplished by leveraging the pre-trained CLIP model. Firstly, we conduct a visual attack on the clean image that causes semantic perturbations on the aligned embedding space with the other textual modality. Then, we apply the corresponding defense on the textual modality by updating the prompts, which forces the re-matching on the perturbed embedding space. Finally, to enhance the attack transferability, we utilize the iterative training strategy on the visual attack and the textual defense, where the two processes optimize from each other. We evaluate our approach on several benchmark datasets and demonstrate that our mutual-modal attack strategy can effectively produce high-transferable attacks, which are stable regardless of the target networks. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
Authors: Carol Anderson, Phil Crone (Ancestry.com)
Text segmentation, the task of dividing a document into sections, is often a prerequisite for performing additional natural language processing tasks. Existing text segmentation methods have typically been developed and tested using clean, narrative-style text with segments containing distinct topics. Here we consider a challenging text segmentation task: dividing newspaper marriage announcement lists into units of one announcement each. In many cases the information is not structured into sentences, and adjacent segments are not topically distinct from each other. In addition, the text of the announcements, which is derived from images of historical newspapers via optical character recognition, contains many typographical errors. As a result, these announcements are not amenable to segmentation with existing techniques. We present a novel deep learning-based model for segmenting such text and show that it significantly outperforms an existing state-of-the-art method on our task.
Authors: Bo Yang, Hong Peng, Chenggang Guo, Xiaohui Luo, Jun Wang, Xianzhong Long
Prompt treatment for melanoma is crucial. To assist physicians in identifying lesion areas precisely in a quick manner, we propose a novel skin lesion segmentation technique namely SLP-Net, an ultra-lightweight segmentation network based on the spiking neural P(SNP) systems type mechanism. Most existing convolutional neural networks achieve high segmentation accuracy while neglecting the high hardware cost. SLP-Net, on the contrary, has a very small number of parameters and a high computation speed. We design a lightweight multi-scale feature extractor without the usual encoder-decoder structure. Rather than a decoder, a feature adaptation module is designed to replace it and implement multi-scale information decoding. Experiments at the ISIC2018 challenge demonstrate that the proposed model has the highest Acc and DSC among the state-of-the-art methods, while experiments on the PH2 dataset also demonstrate a favorable generalization ability. Finally, we compare the computational complexity as well as the computational speed of the models in experiments, where SLP-Net has the highest overall superiority
Authors: Bo Yang, Hong Peng, Xiaohui Luo, Jun Wang, Xianzhong Long
Breast cancer(BC) is a prevalent type of malignant tumor in women. Early diagnosis and treatment are vital for enhancing the patients' survival rate. Downsampling in deep networks may lead to loss of information, so for compensating the detail and edge information and allowing convolutional neural networks to pay more attention to seek the lesion region, we propose a multi-stages attention architecture based on NSNP neurons with autapses. First, unlike the single-scale attention acquisition methods of existing methods, we set up spatial attention acquisition at each feature map scale of the convolutional network to obtain an fusion global information on attention guidance. Then we introduce a new type of NSNP variants called NSNP neurons with autapses. Specifically, NSNP systems are modularized as feature encoders, recoding the features extracted from convolutional neural network as well as the fusion of attention information and preserve the key characteristic elements in feature maps. This ensures the retention of valuable data while gradually transforming high-dimensional complicated info into low-dimensional ones. The proposed method is evaluated on the public dataset BreakHis at various magnifications and classification tasks. It achieves a classification accuracy of 96.32% at all magnification cases, outperforming state-of-the-art methods. Ablation studies are also performed, verifying the proposed model's efficacy. The source code is available at XhuBobYoung/Breast-cancer-Classification.
Authors: Seunghoo Hong, Juhun Lee, Simon S. Woo
Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content, which allows the model to directly generate them. Given that retraining these large models on individual concept deletion requests is infeasible, fine-tuning algorithms have been developed to tackle concept erasing in diffusion models. While these algorithms yield good concept erasure, they all present one of the following issues: 1) the corrupted feature space yields synthesis of disintegrated objects, 2) the initially synthesized content undergoes a divergence in both spatial structure and semantics in the generated images, and 3) sub-optimal training updates heighten the model's susceptibility to utility harm. These issues severely degrade the original utility of generative models. In this work, we present a new approach that solves all of these challenges. We take inspiration from the concept of classifier guidance and propose a surgical update on the classifier guidance term while constraining the drift of the unconditional score term. Furthermore, our algorithm empowers the user to select an alternative to the erasing concept, allowing for more controllability. Our experimental results show that our algorithm not only erases the target concept effectively but also preserves the model's generation capability.
Authors: Luke Yoffe, Aditya Sharma, Tobias Höllerer
One key challenge in augmented reality is the placement of virtual content in natural locations. Existing automated techniques are only able to work with a closed-vocabulary, fixed set of objects. In this paper, we introduce a new open-vocabulary method for object placement. Our eight-stage pipeline leverages recent advances in segmentation models, vision-language models, and LLMs to place any virtual object in any AR camera frame or scene. In a preliminary user study, we show that our method performs at least as well as human experts 57% of the time.
Authors: Zhangbin Li, Dan Guo, Jinxing Zhou, Jing Zhang, Meng Wang
This paper focuses on the Audio-Visual Question Answering (AVQA) task that aims to answer questions derived from untrimmed audible videos. To generate accurate answers, an AVQA model is expected to find the most informative audio-visual clues relevant to the given questions. In this paper, we propose to explicitly consider fine-grained visual objects in video frames (object-level clues) and explore the multi-modal relations(i.e., the object, audio, and question) in terms of feature interaction and model optimization. For the former, we present an end-to-end object-oriented network that adopts a question-conditioned clue discovery module to concentrate audio/visual modalities on respective keywords of the question and designs a modality-conditioned clue collection module to highlight closely associated audio segments or visual objects. For model optimization, we propose an object-aware adaptive-positivity learning strategy that selects the highly semantic-matched multi-modal pair as positivity. Specifically, we design two object-aware contrastive loss functions to identify the highly relevant question-object pairs and audio-object pairs, respectively. These selected pairs are constrained to have larger similarity values than the mismatched pairs. The positivity-selecting process is adaptive as the positivity pairs selected in each video frame may be different. These two object-aware objectives help the model understand which objects are exactly relevant to the question and which are making sounds. Extensive experiments on the MUSIC-AVQA dataset demonstrate the proposed method is effective in finding favorable audio-visual clues and also achieves new state-of-the-art question-answering performance.
Authors: Yuan Zhang, Yaolei Qi, Xiaoming Qi, Lotfi Senhadji, Yongyue Wei, Feng Chen, Guanyu Yang
Federated learning (FL) for histopathology image segmentation involving multiple medical sites plays a crucial role in advancing the field of accurate disease diagnosis and treatment. However, it is still a task of great challenges due to the sample imbalance across clients and large data heterogeneity from disparate organs, variable segmentation tasks, and diverse distribution. Thus, we propose a novel FL approach for histopathology nuclei and tissue segmentation, FedSODA, via synthetic-driven cross-assessment operation (SO) and dynamic stratified-layer aggregation (DA). Our SO constructs a cross-assessment strategy to connect clients and mitigate the representation bias under sample imbalance. Our DA utilizes layer-wise interaction and dynamic aggregation to diminish heterogeneity and enhance generalization. The effectiveness of our FedSODA has been evaluated on the most extensive histopathology image segmentation dataset from 7 independent datasets. The code is available at https://github.com/yuanzhang7/FedSODA.
Authors: Yuhui Wu, Guoqing Wang, Zhiwen Wang, Yang Yang, Tianyu Li, Peng Wang, Chongyi Li, Heng Tao Shen
Low-light image enhancement (LLIE) has achieved promising performance by employing conditional diffusion models. In this study, we propose ReCo-Diff, a novel approach that incorporates Retinex-based prior as an additional pre-processing condition to regulate the generating capabilities of the diffusion model. ReCo-Diff first leverages a pre-trained decomposition network to produce initial reflectance and illumination maps of the low-light image. Then, an adjustment network is introduced to suppress the noise in the reflectance map and brighten the illumination map, thus forming the learned Retinex-based condition. The condition is integrated into a refinement network, implementing Retinex-based conditional modules that offer sufficient guidance at both feature- and image-levels. By treating Retinex theory as a condition, ReCo-Diff presents a unique perspective for establishing an LLIE-specific diffusion model. Extensive experiments validate the rationality and superiority of our ReCo-Diff approach. The code will be made publicly available.
Authors: Yuqi Lin, Minghao Chen, Kaipeng Zhang, Hengjia Li, Mingming Li, Zheng Yang, Dongqin Lv, Binbin Lin, Haifeng Liu, Deng Cai
Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text descriptions supervised by contrastive loss, making it highly effective for single-label classification. However, it shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class and the contrastive nature of softmax operation aggravates it. In this study, we observe that the multi-label classification results heavily rely on discriminative local features but are overlooked by CLIP. As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags. It comprises three steps: (1) patch-level classification to obtain coarse scores; (2) dual-masking attention refinement (DMAR) module to refine the coarse scores; (3) class-wise reidentification (CWR) module to remedy predictions from a global perspective. This framework is solely based on frozen CLIP and significantly enhances its multi-label classification performance on various benchmarks without dataset-specific training. Besides, to comprehensively assess the quality and practicality of generated tags, we extend their application to the downstream task, i.e., weakly supervised semantic segmentation (WSSS) with generated tags as image-level pseudo labels. Experiments demonstrate that this classify-then-segment paradigm dramatically outperforms other annotation-free segmentation methods and validates the effectiveness of generated tags. Our code is available at https://github.com/linyq2117/TagCLIP.
Authors: Hongyuan Wang, Lizhi Wang, Jiang Xu, Chang Chen, Xue Hu, Fenglong Song, Youliang Yan
Spectral super-resolution from the easily obtainable RGB image to hyperspectral image (HSI) has drawn increasing interest in the field of computational photography. The crucial aspect of spectral super-resolution lies in exploiting the correlation within HSIs. However, two types of bottlenecks in existing Transformers limit performance improvement and practical applications. First, existing Transformers often separately emphasize either spatial-wise or spectral-wise correlation, disrupting the 3D features of HSI and hindering the exploitation of unified spatial-spectral correlation. Second, the existing self-attention mechanism learns the correlation between pairs of tokens and captures the full-rank correlation matrix, leading to its inability to establish mutual linear dependence among multiple tokens. To address these issues, we propose a novel Exhaustive Correlation Transformer (ECT) for spectral super-resolution. First, we propose a Spectral-wise Discontinuous 3D (SD3D) splitting strategy, which models unified spatial-spectral correlation by simultaneously utilizing spatial-wise continuous splitting and spectral-wise discontinuous splitting. Second, we propose a Dynamic Low-Rank Mapping (DLRM) model, which captures mutual linear dependence among multiple tokens through a dynamically calculated low-rank dependence map. By integrating unified spatial-spectral attention with mutual linear dependence, our ECT can establish exhaustive correlation within HSI. The experimental results on both simulated and real data indicate that our method achieves state-of-the-art performance. Codes and pretrained models will be available later.
Authors: Nannan Wu, Zhaobin Sun, Zengqiang Yan, Li Yu
Federated learning (FL) has emerged as a promising paradigm for training segmentation models on decentralized medical data, owing to its privacy-preserving property. However, existing research overlooks the prevalent annotation noise encountered in real-world medical datasets, which limits the performance ceilings of FL. In this paper, we, for the first time, identify and tackle this problem. For problem formulation, we propose a contour evolution for modeling non-independent and identically distributed (Non-IID) noise across pixels within each client and then extend it to the case of multi-source data to form a heterogeneous noise model (\textit{i.e.}, Non-IID annotation noise across clients). For robust learning from annotations with such two-level Non-IID noise, we emphasize the importance of data quality in model aggregation, allowing high-quality clients to have a greater impact on FL. To achieve this, we propose \textbf{Fed}erated learning with \textbf{A}nnotation qu\textbf{A}lity-aware \textbf{A}ggregat\textbf{I}on, named \textbf{FedA$^3$I}, by introducing a quality factor based on client-wise noise estimation. Specifically, noise estimation at each client is accomplished through the Gaussian mixture model and then incorporated into model aggregation in a layer-wise manner to up-weight high-quality clients. Extensive experiments on two real-world medical image segmentation datasets demonstrate the superior performance of FedA$^3$I against the state-of-the-art approaches in dealing with cross-client annotation noise. The code is available at \color{blue}{https://github.com/wnn2000/FedAAAI}.
Authors: Shahrokh Heidari, Michael J. Dinneen, Patrice Delmas
Computer Vision (CV) labelling algorithms play a pivotal role in the domain of low-level vision. For decades, it has been known that these problems can be elegantly formulated as discrete energy minimization problems derived from probabilistic graphical models (such as Markov Random Fields). Despite recent advances in inference algorithms (such as graph-cut and message-passing algorithms), the resulting energy minimization problems are generally viewed as intractable. The emergence of quantum computations, which offer the potential for faster solutions to certain problems than classical methods, has led to an increased interest in utilizing quantum properties to overcome intractable problems. Recently, there has also been a growing interest in Quantum Computer Vision (QCV), with the hope of providing a credible alternative or assistant to deep learning solutions in the field. This study investigates a new Quantum Annealing based inference algorithm for CV discrete energy minimization problems. Our contribution is focused on Stereo Matching as a significant CV labeling problem. As a proof of concept, we also use a hybrid quantum-classical solver provided by D-Wave System to compare our results with the best classical inference algorithms in the literature.
Authors: Zhecheng Wang, Rajanie Prabha, Tianyuan Huang, Jiajun Wu, Ram Rajagopal
Remote sensing imagery, despite its broad applications in helping achieve Sustainable Development Goals and tackle climate change, has not yet benefited from the recent advancements of versatile, task-agnostic vision language models (VLMs). A key reason is that the large-scale, semantically diverse image-text dataset required for developing VLMs is still absent for remote sensing images. Unlike natural images, remote sensing images and their associated text descriptions cannot be efficiently collected from the public Internet at scale. In this work, we bridge this gap by using geo-coordinates to automatically connect open, unlabeled remote sensing images with rich semantics covered in OpenStreetMap, and thus construct SkyScript, a comprehensive vision-language dataset for remote sensing images, comprising 2.6 million image-text pairs covering 29K distinct semantic tags. With continual pre-training on this dataset, we obtain a VLM that surpasses baseline models with a 6.2% average accuracy gain in zero-shot scene classification across seven benchmark datasets. It also demonstrates the ability of zero-shot transfer for fine-grained object attribute classification and cross-modal retrieval. We hope this dataset can support the advancement of VLMs for various multi-modal tasks in remote sensing, such as open-vocabulary classification, retrieval, captioning, and text-to-image synthesis.
Authors: Fernando Pérez-García, Sam Bond-Taylor, Pedro P. Sanchez, Boris van Breugel, Daniel C. Castro, Harshita Sharma, Valentina Salvatelli, Maria T. A. Wetscherek, Hannah Richardson, Matthew P. Lungren, Aditya Nori, Javier Alvarez-Valle, Ozan Oktay, Maximilian Ilse
Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing. This work proposes using generative image editing to simulate dataset shifts and diagnose failure modes of biomedical vision models; this can be used in advance of deployment to assess readiness, potentially reducing cost and patient harm. Existing editing methods can produce undesirable changes, with spurious correlations learned due to the co-occurrence of disease and treatment interventions, limiting practical applicability. To address this, we train a text-to-image diffusion model on multiple chest X-ray datasets and introduce a new editing method RadEdit that uses multiple masks, if present, to constrain changes and ensure consistency in the edited images. We consider three types of dataset shifts: acquisition shift, manifestation shift, and population shift, and demonstrate that our approach can diagnose failures and quantify model robustness without additional data collection, complementing more qualitative tools for explainable AI.
Authors: Wenqi Jia, Miao Liu, Hao Jiang, Ishwarya Ananthabhotla, James M. Rehg, Vamsi Krishna Ithapu, Ruohan Gao
In recent years, the thriving development of research related to egocentric videos has provided a unique perspective for the study of conversational interactions, where both visual and audio signals play a crucial role. While most prior work focus on learning about behaviors that directly involve the camera wearer, we introduce the Ego-Exocentric Conversational Graph Prediction problem, marking the first attempt to infer exocentric conversational interactions from egocentric videos. We propose a unified multi-modal, multi-task framework -- Audio-Visual Conversational Attention (Av-CONV), for the joint prediction of conversation behaviors -- speaking and listening -- for both the camera wearer as well as all other social partners present in the egocentric video. Specifically, we customize the self-attention mechanism to model the representations across-time, across-subjects, and across-modalities. To validate our method, we conduct experiments on a challenging egocentric video dataset that includes first-person perspective, multi-speaker, and multi-conversation scenarios. Our results demonstrate the superior performance of our method compared to a series of baselines. We also present detailed ablation studies to assess the contribution of each component in our model. Project page: https://vjwq.github.io/AV-CONV/.
Authors: Bo Liu, Liqiang Yu, Chang Che, Qunwei Lin, Hao Hu, Xinyu Zhao
This paper focuses on the analysis of the application effectiveness of the integration of deep learning and computer vision technologies. Deep learning achieves a historic breakthrough by constructing hierarchical neural networks, enabling end-to-end feature learning and semantic understanding of images. The successful experiences in the field of computer vision provide strong support for training deep learning algorithms. The tight integration of these two fields has given rise to a new generation of advanced computer vision systems, significantly surpassing traditional methods in tasks such as machine vision image classification and object detection. In this paper, typical image classification cases are combined to analyze the superior performance of deep neural network models while also pointing out their limitations in generalization and interpretability, proposing directions for future improvements. Overall, the efficient integration and development trend of deep learning with massive visual data will continue to drive technological breakthroughs and application expansion in the field of computer vision, making it possible to build truly intelligent machine vision systems. This deepening fusion paradigm will powerfully promote unprecedented tasks and functions in computer vision, providing stronger development momentum for related disciplines and industries.
Authors: Vida Esmaeili, Mahmood Mohassel Feghhi, Seyed Omid Shahdi
The contagious and pandemic COVID-19 disease is currently considered as the main health concern and posed widespread panic across human-beings. It affects the human respiratory tract and lungs intensely. So that it has imposed significant threats for premature death. Although, its early diagnosis can play a vital role in revival phase, the radiography tests with the manual intervention are a time-consuming process. Time is also limited for such manual inspecting of numerous patients in the hospitals. Thus, the necessity of automatic diagnosis on the chest X-ray or the CT images with a high efficient performance is urgent. Toward this end, we propose a novel method, named as the ULGFBP-ResNet51 to tackle with the COVID-19 diagnosis in the images. In fact, this method includes Uniform Local Binary Pattern (ULBP), Gabor Filter (GF), and ResNet51. According to our results, this method could offer superior performance in comparison with the other methods, and attain maximum accuracy.
Authors: Wenbin Lin, Chengwei Zheng, Jun-Hai Yong, Feng Xu
Lightweight creation of 3D digital avatars is a highly desirable but challenging task. With only sparse videos of a person under unknown illumination, we propose a method to create relightable and animatable neural avatars, which can be used to synthesize photorealistic images of humans under novel viewpoints, body poses, and lighting. The key challenge here is to disentangle the geometry, material of the clothed body, and lighting, which becomes more difficult due to the complex geometry and shadow changes caused by body motions. To solve this ill-posed problem, we propose novel techniques to better model the geometry and shadow changes. For geometry change modeling, we propose an invertible deformation field, which helps to solve the inverse skinning problem and leads to better geometry quality. To model the spatial and temporal varying shading cues, we propose a pose-aware part-wise light visibility network to estimate light occlusion. Extensive experiments on synthetic and real datasets show that our approach reconstructs high-quality geometry and generates realistic shadows under different body poses. Code and data are available at \url{https://wenbin-lin.github.io/RelightableAvatar-page/}.
Authors: José Guilherme de Almeida, Nuno M. Rodrigues, Sara Silva, Nickolas Papanikolaou
Deep learning models trained with large amounts of data have become a recent and effective approach to predictive problem solving -- these have become known as "foundation models" as they can be used as fundamental tools for other applications. While the paramount examples of image classification (earlier) and large language models (more recently) led the way, the Segment Anything Model (SAM) was recently proposed and stands as the first foundation model for image segmentation, trained on over 10 million images and with recourse to over 1 billion masks. However, the question remains -- what are the limits of this foundation? Given that magnetic resonance imaging (MRI) stands as an important method of diagnosis, we sought to understand whether SAM could be used for a few tasks of zero-shot segmentation using MRI data. Particularly, we wanted to know if selecting masks from the pool of SAM predictions could lead to good segmentations.
Here, we provide a critical assessment of the performance of SAM on magnetic resonance imaging data. We show that, while acceptable in a very limited set of cases, the overall trend implies that these models are insufficient for MRI segmentation across the whole volume, but can provide good segmentations in a few, specific slices. More importantly, we note that while foundation models trained on natural images are set to become key aspects of predictive modelling, they may prove ineffective when used on other imaging modalities.
Authors: Pau Torras, Sanket Biswas, Alicia Fornés
The quality of Optical Music Recognition (OMR) systems is a rather difficult magnitude to measure. There is no lingua franca shared among OMR datasets that allows to compare systems' performance on equal grounds, since most of them are specialised on certain approaches. As a result, most state-of-the-art works currently report metrics that cannot be compared directly. In this paper we identify the need of a common music representation language and propose the Music Tree Notation (MTN) format, thanks to which the definition of standard metrics is possible. This format represents music as a set of primitives that group together into higher-abstraction nodes, a compromise between the expression of fully graph-based and sequential notation formats. We have also developed a specific set of OMR metrics and a typeset score dataset as a proof of concept of this idea.
Authors: Shuyuan Wang, Qi Li, Huiyuan Luo, Chengkan Lv, Zhengtao Zhang
Visual anomaly detection aims at classifying and locating the regions that deviate from the normal appearance. Embedding-based methods and reconstruction-based methods are two main approaches for this task. However, they are either not efficient or not precise enough for the industrial detection. To deal with this problem, we derive POUTA (Produce Once Utilize Twice for Anomaly detection), which improves both the accuracy and efficiency by reusing the discriminant information potential in the reconstructive network. We observe that the encoder and decoder representations of the reconstructive network are able to stand for the features of the original and reconstructed image respectively. And the discrepancies between the symmetric reconstructive representations provides roughly accurate anomaly information. To refine this information, a coarse-to-fine process is proposed in POUTA, which calibrates the semantics of each discriminative layer by the high-level representations and supervision loss. Equipped with the above modules, POUTA is endowed with the ability to provide a more precise anomaly location than the prior arts. Besides, the representation reusage also enables to exclude the feature extraction process in the discriminative network, which reduces the parameters and improves the efficiency. Extensive experiments show that, POUTA is superior or comparable to the prior methods with even less cost. Furthermore, POUTA also achieves better performance than the state-of-the-art few-shot anomaly detection methods without any special design, showing that POUTA has strong ability to learn representations inherent in the training data.
Authors: Pan Xie, Taiyi Peng, Yao Du, Qipeng Zhang
Sign Language Production (SLP) is the tough task of turning sign language into sign videos. The main goal of SLP is to create these videos using a sign gloss. In this research, we've developed a new method to make high-quality sign videos without using human poses as a middle step. Our model works in two main parts: first, it learns from a generator and the video's hidden features, and next, it uses another model to understand the order of these hidden features. To make this method even better for sign videos, we make several significant improvements. (i) In the first stage, we take an improved 3D VQ-GAN to learn downsampled latent representations. (ii) In the second stage, we introduce sequence-to-sequence attention to better leverage conditional information. (iii) The separated two-stage training discards the realistic visual semantic of the latent codes in the second stage. To endow the latent sequences semantic information, we extend the token-level autoregressive latent codes learning with perceptual loss and reconstruction loss for the prior model with visual perception. Compared with previous state-of-the-art approaches, our model performs consistently better on two word-level sign language datasets, i.e., WLASL and NMFs-CSL.
Authors: Eerik Alamikkotervo, Risto Ojala, Alvari Seppänen, Kari Tammi
Detection of the drivable area in all conditions is crucial for autonomous driving and advanced driver assistance systems. However, the amount of labeled data in adverse driving conditions is limited, especially in winter, and supervised methods generalize poorly to conditions outside the training distribution. For easy adaption to all conditions, the need for human annotation should be removed from the learning process. In this paper, Trajectory-Aided Drivable area Auto-labeling with Pre-trained self-supervised features (TADAP) is presented for automated annotation of the drivable area in winter driving conditions. A sample of the drivable area is extracted based on the trajectory estimate from the global navigation satellite system. Similarity with the sample area is determined based on pre-trained self-supervised visual features. Image areas similar to the sample area are considered to be drivable. These TADAP labels were evaluated with a novel winter-driving dataset, collected in varying driving scenes. A prediction model trained with the TADAP labels achieved a +9.6 improvement in intersection over union compared to the previous state-of-the-art of self-supervised drivable area detection.
Authors: Thibaud Ehret, Roger Marí, Dawa Derksen, Nicolas Gasnier, Gabriele Facciolo
Radiance fields have been a major breakthrough in the field of inverse rendering, novel view synthesis and 3D modeling of complex scenes from multi-view image collections. Since their introduction, it was shown that they could be extended to other modalities such as LiDAR, radio frequencies, X-ray or ultrasound. In this paper, we show that, despite the important difference between optical and synthetic aperture radar (SAR) image formation models, it is possible to extend radiance fields to radar images thus presenting the first "radar fields". This allows us to learn surface models using only collections of radar images, similar to how regular radiance fields are learned and with the same computational complexity on average. Thanks to similarities in how both fields are defined, this work also shows a potential for hybrid methods combining both optical and SAR images.
Authors: Junjie Gao, Pengfei Wang, Qiujie Dong, Qiong Zeng, Shiqing Xin, Caiming Zhang
Establishing accurate and representative matches is a crucial step in addressing the point cloud registration problem. A commonly employed approach involves detecting keypoints with salient geometric features and subsequently mapping these keypoints from one frame of the point cloud to another. However, methods within this category are hampered by the repeatability of the sampled keypoints. In this paper, we introduce a saliency-guided trans\textbf{former}, referred to as \textit{D3Former}, which entails the joint learning of repeatable \textbf{D}ense \textbf{D}etectors and feature-enhanced \textbf{D}escriptors. The model comprises a Feature Enhancement Descriptor Learning (FEDL) module and a Repetitive Keypoints Detector Learning (RKDL) module. The FEDL module utilizes a region attention mechanism to enhance feature distinctiveness, while the RKDL module focuses on detecting repeatable keypoints to enhance matching capabilities. Extensive experimental results on challenging indoor and outdoor benchmarks demonstrate that our proposed method consistently outperforms state-of-the-art point cloud matching methods. Notably, tests on 3DLoMatch, even with a low overlap ratio, show that our method consistently outperforms recently published approaches such as RoReg and RoITr. For instance, with the number of extracted keypoints reduced to 250, the registration recall scores for RoReg, RoITr, and our method are 64.3\%, 73.6\%, and 76.5\%, respectively.
Authors: Maximilian Ernst Tschuchnig, Julia Coste-Marin, Philipp Steininger, Michael Gadermayr
Semantic segmentation is a crucial task in medical image processing, essential for segmenting organs or lesions such as tumors. In this study we aim to improve automated segmentation in CBCTs through multi-task learning. To evaluate effects on different volume qualities, a CBCT dataset is synthesised from the CT Liver Tumor Segmentation Benchmark (LiTS) dataset. To improve segmentation, two approaches are investigated. First, we perform multi-task learning to add morphology based regularization through a volume reconstruction task. Second, we use this reconstruction task to reconstruct the best quality CBCT (most similar to the original CT), facilitating denoising effects. We explore both holistic and patch-based approaches. Our findings reveal that, especially using a patch-based approach, multi-task learning improves segmentation in most cases and that these results can further be improved by our denoising approach.
Authors: Bruno Arcanjo, Bruno Ferrarini, Maria Fasli, Michael Milford, Klaus D. McDonald-Maier, Shoaib Ehsan
Visual place recognition (VPR) enables autonomous systems to localize themselves within an environment using image information. While VPR techniques built upon a Convolutional Neural Network (CNN) backbone dominate state-of-the-art VPR performance, their high computational requirements make them unsuitable for platforms equipped with low-end hardware. Recently, a lightweight VPR system based on multiple bio-inspired classifiers, dubbed DrosoNets, has been proposed, achieving great computational efficiency at the cost of reduced absolute place retrieval performance. In this work, we propose a novel multi-DrosoNet localization system, dubbed RegionDrosoNet, with significantly improved VPR performance, while preserving a low-computational profile. Our approach relies on specializing distinct groups of DrosoNets on differently sliced partitions of the original image, increasing extrinsic model differentiation. Furthermore, we introduce a novel voting module to combine the outputs of all DrosoNets into the final place prediction which considers multiple top refence candidates from each DrosoNet. RegionDrosoNet outperforms other lightweight VPR techniques when dealing with both appearance changes and viewpoint variations. Moreover, it competes with computationally expensive methods on some benchmark datasets at a small fraction of their online inference time.
Authors: Ishan Rajendrakumar Dave, Simon Jenni, Mubarak Shah
Self-supervised approaches for video have shown impressive results in video understanding tasks. However, unlike early works that leverage temporal self-supervision, current state-of-the-art methods primarily rely on tasks from the image domain (e.g., contrastive learning) that do not explicitly promote the learning of temporal features. We identify two factors that limit existing temporal self-supervision: 1) tasks are too simple, resulting in saturated training performance, and 2) we uncover shortcuts based on local appearance statistics that hinder the learning of high-level features. To address these issues, we propose 1) a more challenging reformulation of temporal self-supervision as frame-level (rather than clip-level) recognition tasks and 2) an effective augmentation strategy to mitigate shortcuts. Our model extends a representation of single video frames, pre-trained through contrastive learning, with a transformer that we train through temporal self-supervision. We demonstrate experimentally that our more challenging frame-level task formulations and the removal of shortcuts drastically improve the quality of features learned through temporal self-supervision. The generalization capability of our self-supervised video method is evidenced by its state-of-the-art performance in a wide range of high-level semantic tasks, including video retrieval, action classification, and video attribute recognition (such as object and scene identification), as well as low-level temporal correspondence tasks like video object segmentation and pose tracking. Additionally, we show that the video representations learned through our method exhibit increased robustness to the input perturbations.
Authors: Yuming Gu, Hongyi Xu, You Xie, Guoxian Song, Yichun Shi, Di Chang, Jing Yang, Lingjie Luo
We present DiffPortrait3D, a conditional diffusion model that is capable of synthesizing 3D-consistent photo-realistic novel views from as few as a single in-the-wild portrait. Specifically, given a single RGB input, we aim to synthesize plausible but consistent facial details rendered from novel camera views with retained both identity and facial expression. In lieu of time-consuming optimization and fine-tuning, our zero-shot method generalizes well to arbitrary face portraits with unposed camera views, extreme facial expressions, and diverse artistic depictions. At its core, we leverage the generative prior of 2D diffusion models pre-trained on large-scale image datasets as our rendering backbone, while the denoising is guided with disentangled attentive control of appearance and camera pose. To achieve this, we first inject the appearance context from the reference image into the self-attention layers of the frozen UNets. The rendering view is then manipulated with a novel conditional control module that interprets the camera pose by watching a condition image of a crossed subject from the same view. Furthermore, we insert a trainable cross-view attention module to enhance view consistency, which is further strengthened with a novel 3D-aware noise generation process during inference. We demonstrate state-of-the-art results both qualitatively and quantitatively on our challenging in-the-wild and multi-view benchmarks.
Authors: Byung Hyun Lee, Min-hwan Oh, Se Young Chun
Task-free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire data from the past, present as well as future is considered as the gold standard, naive approaches in TF-CL with the current samples may be conflicted with learning with samples in the future, leading to catastrophic forgetting and poor plasticity. Thus, a proactive consideration of an unseen future sample in TF-CL becomes imperative. Motivated by this intuition, we propose a novel TF-CL framework considering future samples and show that injecting adversarial perturbations on both input data and decision-making is effective. Then, we propose a novel method named Doubly Perturbed Continual Learning (DPCL) to efficiently implement these input and decision-making perturbations. Specifically, for input perturbation, we propose an approximate perturbation method that injects noise into the input data as well as the feature vector and then interpolates the two perturbed samples. For decision-making process perturbation, we devise multiple stochastic classifiers. We also investigate a memory management scheme and learning rate scheduling reflecting our proposed double perturbations. We demonstrate that our proposed method outperforms the state-of-the-art baseline methods by large margins on various TF-CL benchmarks.
Authors: Jordan Vice, Naveed Akhtar, Richard Hartley, Ajmal Mian
Bias in text-to-image (T2I) models can propagate unfair social representations and may be used to aggressively market ideas or push controversial agendas. Existing T2I model bias evaluation methods only focus on social biases. We look beyond that and instead propose an evaluation methodology to quantify general biases in T2I generative models, without any preconceived notions. We assess four state-of-the-art T2I models and compare their baseline bias characteristics to their respective variants (two for each), where certain biases have been intentionally induced. We propose three evaluation metrics to assess model biases including: (i) Distribution bias, (ii) Jaccard hallucination and (iii) Generative miss-rate. We conduct two evaluation studies, modelling biases under general, and task-oriented conditions, using a marketing scenario as the domain for the latter. We also quantify social biases to compare our findings to related works. Finally, our methodology is transferred to evaluate captioned-image datasets and measure their bias. Our approach is objective, domain-agnostic and consistently measures different forms of T2I model biases. We have developed a web application and practical implementation of what has been proposed in this work, which is at https://huggingface.co/spaces/JVice/try-before-you-bias. A video series with demonstrations is available at https://www.youtube.com/channel/UCk-0xyUyT0MSd_hkp4jQt1Q
Authors: Yue-Jiang Dong, Yuan-Chen Guo, Ying-Tian Liu, Fang-Lue Zhang, Song-Hai Zhang
Self-supervised monocular depth estimation is of significant importance with applications spanning across autonomous driving and robotics. However, the reliance on self-supervision introduces a strong static-scene assumption, thereby posing challenges in achieving optimal performance in dynamic scenes, which are prevalent in most real-world situations. To address these issues, we propose PPEA-Depth, a Progressive Parameter-Efficient Adaptation approach to transfer a pre-trained image model for self-supervised depth estimation. The training comprises two sequential stages: an initial phase trained on a dataset primarily composed of static scenes, succeeded by an expansion to more intricate datasets involving dynamic scenes. To facilitate this process, we design compact encoder and decoder adapters to enable parameter-efficient tuning, allowing the network to adapt effectively. They not only uphold generalized patterns from pre-trained image models but also retain knowledge gained from the preceding phase into the subsequent one. Extensive experiments demonstrate that PPEA-Depth achieves state-of-the-art performance on KITTI, CityScapes and DDAD datasets.
Authors: Xingyilang Yin, Xi Yang, Liangchen Liu, Nannan Wang, Xinbo Gao
Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we propose Point Deformable Network (PDNet), a concise MLP-based network that can capture long-range relations with strong representation ability. Specifically, we put forward Point Deformable Aggregation Module (PDAM) to improve representation capability in both long-range dependency and adaptive aggregation among points. For each query point, PDAM aggregates information from deformable reference points rather than points in limited local areas. The deformable reference points are generated data-dependent, and we initialize them according to the input point positions. Additional offsets and modulation scalars are learned on the whole point features, which shift the deformable reference points to the regions of interest. We also suggest estimating the normal vector for point clouds and applying Enhanced Normal Embedding (ENE) to the geometric extractors to improve the representation ability of single-point. Extensive experiments and ablation studies on various benchmarks demonstrate the effectiveness and superiority of our PDNet.
Authors: Sushil Sharma, Arindam Das, Ganesh Sistu, Mark Halton, Ciarán Eising
Trajectory prediction is, naturally, a key task for vehicle autonomy. While the number of traffic rules is limited, the combinations and uncertainties associated with each agent's behaviour in real-world scenarios are nearly impossible to encode. Consequently, there is a growing interest in learning-based trajectory prediction. The proposed method in this paper predicts trajectories by considering perception and trajectory prediction as a unified system. In considering them as unified tasks, we show that there is the potential to improve the performance of perception. To achieve these goals, we present BEVSeg2TP - a surround-view camera bird's-eye-view-based joint vehicle segmentation and ego vehicle trajectory prediction system for autonomous vehicles. The proposed system uses a network trained on multiple camera views. The images are transformed using several deep learning techniques to perform semantic segmentation of objects, including other vehicles, in the scene. The segmentation outputs are fused across the camera views to obtain a comprehensive representation of the surrounding vehicles from the bird's-eye-view perspective. The system further predicts the future trajectory of the ego vehicle using a spatiotemporal probabilistic network (STPN) to optimize trajectory prediction. This network leverages information from encoder-decoder transformers and joint vehicle segmentation.
Authors: Joseph Heyward, João Carreira, Dima Damen, Andrew Zisserman, Viorica Pătrăucean
The First Perception Test challenge was held as a half-day workshop alongside the IEEE/CVF International Conference on Computer Vision (ICCV) 2023, with the goal of benchmarking state-of-the-art video models on the recently proposed Perception Test benchmark. The challenge had six tracks covering low-level and high-level tasks, with both a language and non-language interface, across video, audio, and text modalities, and covering: object tracking, point tracking, temporal action localisation, temporal sound localisation, multiple-choice video question-answering, and grounded video question-answering. We summarise in this report the task descriptions, metrics, baselines, and results.
Authors: Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-Andre Carbonneau
Reconstructing an avatar from a portrait image has many applications in multimedia, but remains a challenging research problem. Extracting reflectance maps and geometry from one image is ill-posed: recovering geometry is a one-to-many mapping problem and reflectance and light are difficult to disentangle. Accurate geometry and reflectance can be captured under the controlled conditions of a light stage, but it is costly to acquire large datasets in this fashion. Moreover, training solely with this type of data leads to poor generalization with in-the-wild images. This motivates the introduction of MoSAR, a method for 3D avatar generation from monocular images. We propose a semi-supervised training scheme that improves generalization by learning from both light stage and in-the-wild datasets. This is achieved using a novel differentiable shading formulation. We show that our approach effectively disentangles the intrinsic face parameters, producing relightable avatars. As a result, MoSAR estimates a richer set of skin reflectance maps, and generates more realistic avatars than existing state-of-the-art methods. We also introduce a new dataset, named FFHQ-UV-Intrinsics, the first public dataset providing intrisic face attributes at scale (diffuse, specular, ambient occlusion and translucency maps) for a total of 10k subjects. The project website and the dataset are available on the following link: https://ubisoftlaforge.github.io/character/mosar
Authors: William Heyden, Habib Ullah, M. Salman Siddiqui, Fadi Al Machot
Generalized Zero-Shot Learning (GZSL) recognizes unseen classes by transferring knowledge from the seen classes, depending on the inherent interactions between visual and semantic data. However, the discrepancy between well-prepared training data and unpredictable real-world test scenarios remains a significant challenge. This paper introduces a dual strategy to address the generalization gap. Firstly, we incorporate semantic information through an innovative encoder. This encoder effectively integrates class-specific semantic information by targeting the performance disparity, enhancing the produced features to enrich the semantic space for class-specific attributes. Secondly, we refine our generative capabilities using a novel compositional loss function. This approach generates discriminative classes, effectively classifying both seen and unseen classes. In addition, we extend the exploitation of the learned latent space by utilizing controlled semantic inputs, ensuring the robustness of the model in varying environments. This approach yields a model that outperforms the state-of-the-art models in terms of both generalization and diverse settings, notably without requiring hyperparameter tuning or domain-specific adaptations. We also propose a set of novel evaluation metrics to provide a more detailed assessment of the reliability and reproducibility of the results. The complete code is made available on https://github.com/william-heyden/SEER-ZeroShotLearning/.
Authors: Li Ma, Vasu Agrawal, Haithem Turki, Changil Kim, Chen Gao, Pedro Sander, Michael Zollhöfer, Christian Richardt
Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.
Authors: Jinge Wu, Yunsoo Kim, Eva C. Keller, Jamie Chow, Adam P. Levine, Nikolas Pontikos, Zina Ibrahim, Paul Taylor, Michelle C. Williams, Honghan Wu
This paper proposes one of the first clinical applications of multimodal large language models (LLMs) as an assistant for radiologists to check errors in their reports. We created an evaluation dataset from two real-world radiology datasets (MIMIC-CXR and IU-Xray), with 1,000 subsampled reports each. A subset of original reports was modified to contain synthetic errors by introducing various type of mistakes. The evaluation contained two difficulty levels: SIMPLE for binary error-checking and COMPLEX for identifying error types. LLaVA (Large Language and Visual Assistant) variant models, including our instruction-tuned model, were used for the evaluation. Additionally, a domain expert evaluation was conducted on a small test set. At the SIMPLE level, the LLaVA v1.5 model outperformed other publicly available models. Instruction tuning significantly enhanced performance by 47.4% and 25.4% on MIMIC-CXR and IU-Xray data, respectively. The model also surpassed the domain experts accuracy in the MIMIC-CXR dataset by 1.67%. Notably, among the subsets (N=21) of the test set where a clinician did not achieve the correct conclusion, the LLaVA ensemble mode correctly identified 71.4% of these cases. This study marks a promising step toward utilizing multi-modal LLMs to enhance diagnostic accuracy in radiology. The ensemble model demonstrated comparable performance to clinicians, even capturing errors overlooked by humans. Nevertheless, future work is needed to improve the model ability to identify the types of inconsistency.
Authors: Sushil Sharma, Aryan Singh, Ganesh Sistu, Mark Halton, Ciarán Eising
Predicting the trajectory of an ego vehicle is a critical component of autonomous driving systems. Current state-of-the-art methods typically rely on Deep Neural Networks (DNNs) and sequential models to process front-view images for future trajectory prediction. However, these approaches often struggle with perspective issues affecting object features in the scene. To address this, we advocate for the use of Bird's Eye View (BEV) perspectives, which offer unique advantages in capturing spatial relationships and object homogeneity. In our work, we leverage Graph Neural Networks (GNNs) and positional encoding to represent objects in a BEV, achieving competitive performance compared to traditional DNN-based methods. While the BEV-based approach loses some detailed information inherent to front-view images, we balance this by enriching the BEV data by representing it as a graph where relationships between the objects in a scene are captured effectively.
Authors: Difei Gao, Lei Ji, Zechen Bai, Mingyu Ouyang, Peiran Li, Dongxing Mao, Qinchen Wu, Weichen Zhang, Peiyi Wang, Xiangwu Guo, Hengxu Wang, Luowei Zhou, Mike Zheng Shou
Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown capabilities in automating tasks on Android and Web platforms. However, these tasks are primarily aimed at simple device usage and entertainment operations. This paper presents a novel benchmark, AssistGUI, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We carefully collected a set of 100 tasks from nine widely-used software applications, such as, After Effects and MS Word, each accompanied by the necessary project files for better evaluation. Moreover, we propose an advanced Actor-Critic Embodied Agent framework, which incorporates a sophisticated GUI parser driven by an LLM-agent and an enhanced reasoning mechanism adept at handling lengthy procedural tasks. Our experimental results reveal that our GUI Parser and Reasoning mechanism outshine existing methods in performance. Nevertheless, the potential remains substantial, with the best model attaining only a 46% success rate on our benchmark. We conclude with a thorough analysis of the current methods' limitations, setting the stage for future breakthroughs in this domain.
Authors: Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
Color constancy and color illusion perception are two phenomena occurring in the human visual system, which can help us reveal unknown mechanisms of human perception. For decades computer vision scientists have developed numerous color constancy methods, which estimate the reflectance of the surface by discounting the illuminant. However, color illusions have not been analyzed in detail in the field of computational color constancy, which we find surprising since the relationship they share is significant and may let us design more robust systems. We argue that any model that can reproduce our sensation on color illusions should also be able to provide pixel-wise estimates of the light source. In other words, we suggest that the analysis of color illusions helps us to improve the performance of the existing global color constancy methods, and enable them to provide pixel-wise estimates for scenes illuminated by multiple light sources. In this study, we share the outcomes of our investigation in which we take several color constancy methods and modify them to reproduce the behavior of the human visual system on color illusions. Also, we show that parameters purely extracted from illusions are able to improve the performance of color constancy methods. A noteworthy outcome is that our strategy based on the investigation of color illusions outperforms the state-of-the-art methods that are specifically designed to transform global color constancy algorithms into multi-illuminant algorithms.
Authors: Haili Ye, Xiaoqing Zhang, Yan Hu, Huazhu Fu, Jiang Liu
The morphologies of vessel-like structures, such as blood vessels and nerve fibres, play significant roles in disease diagnosis, e.g., Parkinson's disease. Deep network-based refinement segmentation methods have recently achieved promising vessel-like structure segmentation results. There are still two challenges: (1) existing methods have limitations in rehabilitating subsection ruptures in segmented vessel-like structures; (2) they are often overconfident in predicted segmentation results. To tackle these two challenges, this paper attempts to leverage the potential of spatial interconnection relationships among subsection ruptures from the structure rehabilitation perspective. Based on this, we propose a novel Vessel-like Structure Rehabilitation Network (VSR-Net) to rehabilitate subsection ruptures and improve the model calibration based on coarse vessel-like structure segmentation results. VSR-Net first constructs subsection rupture clusters with Curvilinear Clustering Module (CCM). Then, the well-designed Curvilinear Merging Module (CMM) is applied to rehabilitate the subsection ruptures to obtain the refined vessel-like structures. Extensive experiments on five 2D/3D medical image datasets show that VSR-Net significantly outperforms state-of-the-art (SOTA) refinement segmentation methods with lower calibration error. Additionally, we provide quantitative analysis to explain the morphological difference between the rehabilitation results of VSR-Net and ground truth (GT), which is smaller than SOTA methods and GT, demonstrating that our method better rehabilitates vessel-like structures by restoring subsection ruptures.
Authors: Li Wang, Xiaohua Zhang, Longfei Li, Hongyun Meng, Xianghai Cao
Spectral unmixing is a significant challenge in hyperspectral image processing. Existing unmixing methods utilize prior knowledge about the abundance distribution to solve the regularization optimization problem, where the difficulty lies in choosing appropriate prior knowledge and solving the complex regularization optimization problem. To solve these problems, we propose a hyperspectral conditional generative adversarial network (HyperGAN) method as a generic unmixing framework, based on the following assumption: the unmixing process from pixel to abundance can be regarded as a transformation of two modalities with an internal specific relationship. The proposed HyperGAN is composed of a generator and discriminator, the former completes the modal conversion from mixed hyperspectral pixel patch to the abundance of corresponding endmember of the central pixel and the latter is used to distinguish whether the distribution and structure of generated abundance are the same as the true ones. We propose hyperspectral image (HSI) Patch Transformer as the main component of the generator, which utilize adaptive attention score to capture the internal pixels correlation of the HSI patch and leverage the spatial-spectral information in a fine-grained way to achieve optimization of the unmixing process. Experiments on synthetic data and real hyperspectral data achieve impressive results compared to state-of-the-art competitors.
Authors: Hongtao Wu, Ya Jing, Chilam Cheang, Guangzeng Chen, Jiafeng Xu, Xinghang Li, Minghuan Liu, Hang Li, Tao Kong
Generative pre-trained models have demonstrated remarkable effectiveness in language and vision domains by learning useful representations. In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation can significantly benefit from large-scale video generative pre-training. We introduce GR-1, a straightforward GPT-style model designed for multi-task language-conditioned visual robot manipulation. GR-1 takes as inputs a language instruction, a sequence of observation images, and a sequence of robot states. It predicts robot actions as well as future images in an end-to-end manner. Thanks to a flexible design, GR-1 can be seamlessly finetuned on robot data after pre-trained on a large-scale video dataset. We perform extensive experiments on the challenging CALVIN benchmark and a real robot. On CALVIN benchmark, our method outperforms state-of-the-art baseline methods and improves the success rate from 88.9% to 94.9%. In the setting of zero-shot unseen scene generalization, GR-1 improves the success rate from 53.3% to 85.4%. In real robot experiments, GR-1 also outperforms baseline methods and shows strong potentials in generalization to unseen scenes and objects. We provide inaugural evidence that a unified GPT-style transformer, augmented with large-scale video generative pre-training, exhibits remarkable generalization to multi-task visual robot manipulation. Project page: https://GR1-Manipulation.github.io
Authors: Stanislaw Szymanowicz, Christian Rupprecht, Andrea Vedaldi
We introduce the Splatter Image, an ultra-fast approach for monocular 3D object reconstruction which operates at 38 FPS. Splatter Image is based on Gaussian Splatting, which has recently brought real-time rendering, fast training, and excellent scaling to multi-view reconstruction. For the first time, we apply Gaussian Splatting in a monocular reconstruction setting. Our approach is learning-based, and, at test time, reconstruction only requires the feed-forward evaluation of a neural network. The main innovation of Splatter Image is the surprisingly straightforward design: it uses a 2D image-to-image network to map the input image to one 3D Gaussian per pixel. The resulting Gaussians thus have the form of an image, the Splatter Image. We further extend the method to incorporate more than one image as input, which we do by adding cross-view attention. Owning to the speed of the renderer (588 FPS), we can use a single GPU for training while generating entire images at each iteration in order to optimize perceptual metrics like LPIPS. On standard benchmarks, we demonstrate not only fast reconstruction but also better results than recent and much more expensive baselines in terms of PSNR, LPIPS, and other metrics.
Authors: Habib Boloorchi Tabrizi, Christopher Crick
In this study, we address the critical challenge of balancing speed and accuracy while maintaining interpretablity in visual odometry (VO) systems, a pivotal aspect in the field of autonomous navigation and robotics. Traditional VO systems often face a trade-off between computational speed and the precision of pose estimation. To tackle this issue, we introduce an innovative system that synergistically combines traditional VO methods with a specifically tailored fully connected network (FCN). Our system is unique in its approach to handle each degree of freedom independently within the FCN, placing a strong emphasis on causal inference to enhance interpretability. This allows for a detailed and accurate assessment of relative pose error (RPE) across various degrees of freedom, providing a more comprehensive understanding of parameter variations and movement dynamics in different environments. Notably, our system demonstrates a remarkable improvement in processing speed without compromising accuracy. In certain scenarios, it achieves up to a 5% reduction in Root Mean Square Error (RMSE), showcasing its ability to effectively bridge the gap between speed and accuracy that has long been a limitation in VO research. This advancement represents a significant step forward in developing more efficient and reliable VO systems, with wide-ranging applications in real-time navigation and robotic systems.
Authors: Octave Mariotti, Oisin Mac Aodha, Hakan Bilen
Recent progress in self-supervised representation learning has resulted in models that are capable of extracting image features that are not only effective at encoding image level, but also pixel-level, semantics. These features have been shown to be effective for dense visual semantic correspondence estimation, even outperforming fully-supervised methods. Nevertheless, current self-supervised approaches still fail in the presence of challenging image characteristics such as symmetries and repeated parts. To address these limitations, we propose a new approach for semantic correspondence estimation that supplements discriminative self-supervised features with 3D understanding via a weak geometric spherical prior. Compared to more involved 3D pipelines, our model only requires weak viewpoint information, and the simplicity of our spherical representation enables us to inject informative geometric priors into the model during training. We propose a new evaluation metric that better accounts for repeated part and symmetry-induced mistakes. We present results on the challenging SPair-71k dataset, where we show that our approach demonstrates is capable of distinguishing between symmetric views and repeated parts across many object categories, and also demonstrate that we can generalize to unseen classes on the AwA dataset.
Authors: Weiwei Gu, Anant Sah, Nakul Gopalan
We present a framework for robots to learn novel visual concepts and tasks via in-situ linguistic interactions with human users. Previous approaches have either used large pre-trained visual models to infer novel objects zero-shot, or added novel concepts along with their attributes and representations to a concept hierarchy. We extend the approaches that focus on learning visual concept hierarchies by enabling them to learn novel concepts and solve unseen robotics tasks with them. To enable a visual concept learner to solve robotics tasks one-shot, we developed two distinct techniques. Firstly, we propose a novel approach, Hi-Viscont(HIerarchical VISual CONcept learner for Task), which augments information of a novel concept to its parent nodes within a concept hierarchy. This information propagation allows all concepts in a hierarchy to update as novel concepts are taught in a continual learning setting. Secondly, we represent a visual task as a scene graph with language annotations, allowing us to create novel permutations of a demonstrated task zero-shot in-situ. We present two sets of results. Firstly, we compare Hi-Viscont with the baseline model (FALCON) on visual question answering(VQA) in three domains. While being comparable to the baseline model on leaf level concepts, Hi-Viscont achieves an improvement of over 9% on non-leaf concepts on average. We compare our model's performance against the baseline FALCON model. Our framework achieves 33% improvements in success rate metric, and 19% improvements in the object level accuracy compared to the baseline model. With both of these results we demonstrate the ability of our model to learn tasks and concepts in a continual learning setting on the robot.
Authors: Xiaoli Liu, Jianqin Yin, Di Guo, Huaping Liu
Early action prediction (EAP) aims to recognize human actions from a part of action execution in ongoing videos, which is an important task for many practical applications. Most prior works treat partial or full videos as a whole, ignoring rich action knowledge hidden in videos, i.e., semantic consistencies among different partial videos. In contrast, we partition original partial or full videos to form a new series of partial videos and mine the Action-Semantic Consistent Knowledge (ASCK) among these new partial videos evolving in arbitrary progress levels. Moreover, a novel Rich Action-semantic Consistent Knowledge network (RACK) under the teacher-student framework is proposed for EAP. Firstly, we use a two-stream pre-trained model to extract features of videos. Secondly, we treat the RGB or flow features of the partial videos as nodes and their action semantic consistencies as edges. Next, we build a bi-directional semantic graph for the teacher network and a single-directional semantic graph for the student network to model rich ASCK among partial videos. The MSE and MMD losses are incorporated as our distillation loss to enrich the ASCK of partial videos from the teacher to the student network. Finally, we obtain the final prediction by summering the logits of different subnetworks and applying a softmax layer. Extensive experiments and ablative studies have been conducted, demonstrating the effectiveness of modeling rich ASCK for EAP. With the proposed RACK, we have achieved state-of-the-art performance on three benchmarks. The code is available at https://github.com/lily2lab/RACK.git.
Authors: Xinzhu Ma, Wanli Ouyang, Andrea Simonelli, Elisa Ricci
3D object detection from images, one of the fundamental and challenging problems in autonomous driving, has received increasing attention from both industry and academia in recent years. Benefiting from the rapid development of deep learning technologies, image-based 3D detection has achieved remarkable progress. Particularly, more than 200 works have studied this problem from 2015 to 2021, encompassing a broad spectrum of theories, algorithms, and applications. However, to date no recent survey exists to collect and organize this knowledge. In this paper, we fill this gap in the literature and provide the first comprehensive survey of this novel and continuously growing research field, summarizing the most commonly used pipelines for image-based 3D detection and deeply analyzing each of their components. Additionally, we also propose two new taxonomies to organize the state-of-the-art methods into different categories, with the intent of providing a more systematic review of existing methods and facilitating fair comparisons with future works. In retrospect of what has been achieved so far, we also analyze the current challenges in the field and discuss future directions for image-based 3D detection research.
Authors: Hammad A. Ayyubi, Christopher Thomas, Lovish Chum, Rahul Lokesh, Long Chen, Yulei Niu, Xudong Lin, Xuande Feng, Jaywon Koo, Sounak Ray, Shih-Fu Chang
Events describe happenings in our world that are of importance. Naturally, understanding events mentioned in multimedia content and how they are related forms an important way of comprehending our world. Existing literature can infer if events across textual and visual (video) domains are identical (via grounding) and thus, on the same semantic level. However, grounding fails to capture the intricate cross-event relations that exist due to the same events being referred to on many semantic levels. For example, in Figure 1, the abstract event of "war" manifests at a lower semantic level through subevents "tanks firing" (in video) and airplane "shot" (in text), leading to a hierarchical, multimodal relationship between the events.
In this paper, we propose the task of extracting event hierarchies from multimodal (video and text) data to capture how the same event manifests itself in different modalities at different semantic levels. This reveals the structure of events and is critical to understanding them. To support research on this task, we introduce the Multimodal Hierarchical Events (MultiHiEve) dataset. Unlike prior video-language datasets, MultiHiEve is composed of news video-article pairs, which makes it rich in event hierarchies. We densely annotate a part of the dataset to construct the test benchmark. We show the limitations of state-of-the-art unimodal and multimodal baselines on this task. Further, we address these limitations via a new weakly supervised model, leveraging only unannotated video-article pairs from MultiHiEve. We perform a thorough evaluation of our proposed method which demonstrates improved performance on this task and highlight opportunities for future research.
Authors: Georg Bökman, Axel Flinth, Fredrik Kahl
Equivariance of linear neural network layers is well studied. In this work, we relax the equivariance condition to only be true in a projective sense. We propose a way to construct a projectively equivariant neural network through building a standard equivariant network where the linear group representations acting on each intermediate feature space are "multiplicatively modified lifts" of projective group representations. By theoretically studying the relation of projectively and linearly equivariant linear layers, we show that our approach is the most general possible when building a network out of linear layers. The theory is showcased in two simple experiments.
Authors: Jacob Krantz, Shurjo Banerjee, Wang Zhu, Jason Corso, Peter Anderson, Stefan Lee, Jesse Thomason
We present Iterative Vision-and-Language Navigation (IVLN), a paradigm for evaluating language-guided agents navigating in a persistent environment over time. Existing Vision-and-Language Navigation (VLN) benchmarks erase the agent's memory at the beginning of every episode, testing the ability to perform cold-start navigation with no prior information. However, deployed robots occupy the same environment for long periods of time. The IVLN paradigm addresses this disparity by training and evaluating VLN agents that maintain memory across tours of scenes that consist of up to 100 ordered instruction-following Room-to-Room (R2R) episodes, each defined by an individual language instruction and a target path. We present discrete and continuous Iterative Room-to-Room (IR2R) benchmarks comprising about 400 tours each in 80 indoor scenes. We find that extending the implicit memory of high-performing transformer VLN agents is not sufficient for IVLN, but agents that build maps can benefit from environment persistence, motivating a renewed focus on map-building agents in VLN.
Authors: Xuanjun Chen, Haibin Wu, Chung-Che Wang, Hung-yi Lee, Jyh-Shing Roger Jang
Audio-visual synchronization aims to determine whether the mouth movements and speech in the video are synchronized. VocaLiST reaches state-of-the-art performance by incorporating multimodal Transformers to model audio-visual interact information. However, it requires high computing resources, making it impractical for real-world applications. This paper proposed an MTDVocaLiST model, which is trained by our proposed multimodal Transformer distillation (MTD) loss. MTD loss enables MTDVocaLiST model to deeply mimic the cross-attention distribution and value-relation in the Transformer of VocaLiST. Additionally, we harness uncertainty weighting to fully exploit the interaction information across all layers. Our proposed method is effective in two aspects: From the distillation method perspective, MTD loss outperforms other strong distillation baselines. From the distilled model's performance perspective: 1) MTDVocaLiST outperforms similar-size SOTA models, SyncNet, and Perfect Match models by 15.65% and 3.35%; 2) MTDVocaLiST reduces the model size of VocaLiST by 83.52%, yet still maintaining similar performance.
Authors: Aditya Murali, Deepak Alapatt, Pietro Mascagni, Armine Vardazaryan, Alain Garcia, Nariaki Okamoto, Didier Mutter, Nicolas Padoy
Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality of their exposure. Prior works have approached this task by including semantic segmentation as an intermediate step, using predicted segmentation masks to then predict the CVS. While these methods are effective, they rely on extremely expensive ground-truth segmentation annotations and tend to fail when the predicted segmentation is incorrect, limiting generalization. In this work, we propose a method for CVS prediction wherein we first represent a surgical image using a disentangled latent scene graph, then process this representation using a graph neural network. Our graph representations explicitly encode semantic information - object location, class information, geometric relations - to improve anatomy-driven reasoning, as well as visual features to retain differentiability and thereby provide robustness to semantic errors. Finally, to address annotation cost, we propose to train our method using only bounding box annotations, incorporating an auxiliary image reconstruction objective to learn fine-grained object boundaries. We show that our method not only outperforms several baseline methods when trained with bounding box annotations, but also scales effectively when trained with segmentation masks, maintaining state-of-the-art performance.
Authors: Navid Mohammadi Foumani, Lynn Miller, Chang Wei Tan, Geoffrey I. Webb, Germain Forestier, Mahsa Salehi
Time Series Classification and Extrinsic Regression are important and challenging machine learning tasks. Deep learning has revolutionized natural language processing and computer vision and holds great promise in other fields such as time series analysis where the relevant features must often be abstracted from the raw data but are not known a priori. This paper surveys the current state of the art in the fast-moving field of deep learning for time series classification and extrinsic regression. We review different network architectures and training methods used for these tasks and discuss the challenges and opportunities when applying deep learning to time series data. We also summarize two critical applications of time series classification and extrinsic regression, human activity recognition and satellite earth observation.
Authors: Ning Liao, Xiaopeng Zhang, Min Cao, Junchi Yan, Qi Tian
In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i.e., not seen during training), they always predict them as one of the training classes. The exhibited label bias causes difficulty in open set recognition (OSR), in which an image should be correctly predicted as one of the known classes or the unknown one. To achieve this goal, we propose a vision-language prompt tuning method with mitigated label bias (M-Tuning). It introduces open words from the WordNet to extend the range of words forming the prompt texts from only closed-set label words to more, and thus prompts are tuned in a simulated open-set scenario. Besides, inspired by the observation that classifying directly on large datasets causes a much higher false positive rate than on small datasets, we propose a Combinatorial Tuning and Testing (CTT) strategy for improving performance. CTT decomposes M-Tuning on large datasets as multiple independent group-wise tuning on fewer classes, then makes accurate and comprehensive predictions by selecting the optimal sub-prompt. Finally, given the lack of VL-based OSR baselines in the literature, especially for prompt methods, we contribute new baselines for fair comparisons. Our method achieves the best performance on datasets with various scales, and extensive ablation studies also validate its effectiveness.
Authors: Wenhan Yang, Jingdong Gao, Baharan Mirzasoleiman
Contrastive vision-language representation learning has achieved state-of-the-art performance for zero-shot classification, by learning from millions of image-caption pairs crawled from the internet. However, the massive data that powers large multimodal models such as CLIP, makes them extremely vulnerable to various types of targeted data poisoning and backdoor attacks. Despite this vulnerability, robust contrastive vision-language pre-training against such attacks has remained unaddressed. In this work, we propose ROCLIP, the first effective method for robust pre-training multimodal vision-language models against targeted data poisoning and backdoor attacks. ROCLIP effectively breaks the association between poisoned image-caption pairs by considering a relatively large and varying pool of random captions, and matching every image with the text that is most similar to it in the pool instead of its own caption, every few epochs.It also leverages image and text augmentations to further strengthen the defense and improve the performance of the model. Our extensive experiments show that ROCLIP renders state-of-the-art targeted data poisoning and backdoor attacks ineffective during pre-training CLIP models. In particular, ROCLIP decreases the success rate for targeted data poisoning attacks from 93.75% to 12.5% and that of backdoor attacks down to 0%, while improving the model's linear probe performance by 10% and maintains a similar zero shot performance compared to CLIP. By increasing the frequency of matching, ROCLIP is able to defend strong attacks, which add up to 1% poisoned examples to the data, and successfully maintain a low attack success rate of 12.5%, while trading off the performance on some tasks.
Authors: Matan Levy, Rami Ben-Ari, Nir Darshan, Dani Lischinski
The task of Composed Image Retrieval (CoIR) involves queries that combine image and text modalities, allowing users to express their intent more effectively. However, current CoIR datasets are orders of magnitude smaller compared to other vision and language (V&L) datasets. Additionally, some of these datasets have noticeable issues, such as queries containing redundant modalities. To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones. Pre-training on our LaSCo, shows a noteworthy improvement in performance, even in zero-shot. Furthermore, we propose a new approach for analyzing CoIR datasets and methods, which detects modality redundancy or necessity, in queries. We also introduce a new CoIR baseline, the Cross-Attention driven Shift Encoder (CASE). This baseline allows for early fusion of modalities using a cross-attention module and employs an additional auxiliary task during training. Our experiments demonstrate that this new baseline outperforms the current state-of-the-art methods on established benchmarks like FashionIQ and CIRR.
Authors: Changsheng Lv, Mengshi Qi, Xia Li, Zhengyuan Yang, Huadong Ma
In this paper, we propose a novel model called SGFormer, Semantic Graph TransFormer for point cloud-based 3D scene graph generation. The task aims to parse a point cloud-based scene into a semantic structural graph, with the core challenge of modeling the complex global structure. Existing methods based on graph convolutional networks (GCNs) suffer from the over-smoothing dilemma and can only propagate information from limited neighboring nodes. In contrast, SGFormer uses Transformer layers as the base building block to allow global information passing, with two types of newly-designed layers tailored for the 3D scene graph generation task. Specifically, we introduce the graph embedding layer to best utilize the global information in graph edges while maintaining comparable computation costs. Furthermore, we propose the semantic injection layer to leverage linguistic knowledge from large-scale language model (i.e., ChatGPT), to enhance objects' visual features. We benchmark our SGFormer on the established 3DSSG dataset and achieve a 40.94% absolute improvement in relationship prediction's R@50 and an 88.36% boost on the subset with complex scenes over the state-of-the-art. Our analyses further show SGFormer's superiority in the long-tail and zero-shot scenarios. Our source code is available at https://github.com/Andy20178/SGFormer.
Authors: Yu-Jhe Li, Tao Xu, Ji Hou, Bichen Wu, Xiaoliang Dai, Albert Pumarola, Peizhao Zhang, Peter Vajda, Kris Kitani
We tackle the task of text-to-3D creation with pre-trained latent-based NeRFs (NeRFs that generate 3D objects given input latent code). Recent works such as DreamFusion and Magic3D have shown great success in generating 3D content using NeRFs and text prompts, but the current approach of optimizing a NeRF for every text prompt is 1) extremely time-consuming and 2) often leads to low-resolution outputs. To address these challenges, we propose a novel method named 3D-CLFusion which leverages the pre-trained latent-based NeRFs and performs fast 3D content creation in less than a minute. In particular, we introduce a latent diffusion prior network for learning the w latent from the input CLIP text/image embeddings. This pipeline allows us to produce the w latent without further optimization during inference and the pre-trained NeRF is able to perform multi-view high-resolution 3D synthesis based on the latent. We note that the novelty of our model lies in that we introduce contrastive learning during training the diffusion prior which enables the generation of the valid view-invariant latent code. We demonstrate through experiments the effectiveness of our proposed view-invariant diffusion process for fast text-to-3D creation, e.g., 100 times faster than DreamFusion. We note that our model is able to serve as the role of a plug-and-play tool for text-to-3D with pre-trained NeRFs.
Authors: Wulian Yun, Mengshi Qi, Chuanming Wang, Huadong Ma
Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision. Pseudo label generation is a promising strategy to solve the challenging problem, but the current methods ignore the natural temporal structure of the video that can provide rich information to assist such a generation process. In this paper, we propose a novel weakly-supervised temporal action localization method by inferring salient snippet-feature. First, we design a saliency inference module that exploits the variation relationship between temporal neighbor snippets to discover salient snippet-features, which can reflect the significant dynamic change in the video. Secondly, we introduce a boundary refinement module that enhances salient snippet-features through the information interaction unit. Then, a discrimination enhancement module is introduced to enhance the discriminative nature of snippet-features. Finally, we adopt the refined snippet-features to produce high-fidelity pseudo labels, which could be used to supervise the training of the action localization network. Extensive experiments on two publicly available datasets, i.e., THUMOS14 and ActivityNet v1.3, demonstrate our proposed method achieves significant improvements compared to the state-of-the-art methods.
Authors: Cheng Jin, Zhengrui Guo, Yi Lin, Luyang Luo, Hao Chen
Deep learning has seen rapid growth in recent years and achieved state-of-the-art performance in a wide range of applications. However, training models typically requires expensive and time-consuming collection of large quantities of labeled data. This is particularly true within the scope of medical imaging analysis (MIA), where data are limited and labels are expensive to be acquired. Thus, label-efficient deep learning methods are developed to make comprehensive use of the labeled data as well as the abundance of unlabeled and weak-labeled data. In this survey, we extensively investigated over 300 recent papers to provide a comprehensive overview of recent progress on label-efficient learning strategies in MIA. We first present the background of label-efficient learning and categorize the approaches into different schemes. Next, we examine the current state-of-the-art methods in detail through each scheme. Specifically, we provide an in-depth investigation, covering not only canonical semi-supervised, self-supervised, and multi-instance learning schemes, but also recently emerged active and annotation-efficient learning strategies. Moreover, as a comprehensive contribution to the field, this survey not only elucidates the commonalities and unique features of the surveyed methods but also presents a detailed analysis of the current challenges in the field and suggests potential avenues for future research.
Authors: Susung Hong, Donghoon Ahn, Seungryong Kim
Existing score-distilling text-to-3D generation techniques, despite their considerable promise, often encounter the view inconsistency problem. One of the most notable issues is the Janus problem, where the most canonical view of an object (\textit{e.g}., face or head) appears in other views. In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem -- the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation. Our first approach, called score debiasing, involves cutting off the score estimated by 2D diffusion models and gradually increasing the truncation value throughout the optimization process. Our second approach, called prompt debiasing, identifies conflicting words between user prompts and view prompts using a language model, and adjusts the discrepancy between view prompts and the viewing direction of an object. Our experimental results show that our methods improve the realism of the generated 3D objects by significantly reducing artifacts and achieve a good trade-off between faithfulness to the 2D diffusion models and 3D consistency with little overhead. Our project page is available at~\url{https://susunghong.github.io/Debiased-Score-Distillation-Sampling/}.
Authors: Mischa Dombrowski, Hadrien Reynaud, Johanna P. Müller, Matthew Baugh, Bernhard Kainz
Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets. Notably, this method has been readily employed for medical applications, such as X-ray image synthesis, leveraging the plethora of associated radiology reports. Yet, a prevailing concern is the lack of assurance on whether these models genuinely comprehend their generated content. With the evolution of text-conditional image generation, these models have grown potent enough to facilitate object localization scrutiny. Our research underscores this advancement in the critical realm of medical imaging, emphasizing the crucial role of interpretability. We further unravel a consequential trade-off between image fidelity as gauged by conventional metrics and model interpretability in generative diffusion models. Specifically, the adoption of learnable text encoders when fine-tuning results in diminished interpretability. Our in-depth exploration uncovers the underlying factors responsible for this divergence. Consequently, we present a set of design principles for the development of truly interpretable generative models. Code is available at https://github.com/MischaD/chest-distillation.
Authors: Nathaniel Chodosh, Deva Ramanan, Simon Lucey
Popular benchmarks for self-supervised LiDAR scene flow (stereoKITTI, and FlyingThings3D) have unrealistic rates of dynamic motion, unrealistic correspondences, and unrealistic sampling patterns. As a result, progress on these benchmarks is misleading and may cause researchers to focus on the wrong problems. We evaluate a suite of top methods on a suite of real-world datasets (Argoverse 2.0, Waymo, and NuScenes) and report several conclusions. First, we find that performance on stereoKITTI is negatively correlated with performance on real-world data. Second, we find that one of this task's key components -- removing the dominant ego-motion -- is better solved by classic ICP than any tested method. Finally, we show that despite the emphasis placed on learning, most performance gains are caused by pre- and post-processing steps: piecewise-rigid refinement and ground removal. We demonstrate this through a baseline method that combines these processing steps with a learning-free test-time flow optimization. This baseline outperforms every evaluated method.
Authors: Berk Iskender, Marc L. Klasky, Yoram Bresler
Dynamic imaging addresses the recovery of a time-varying 2D or 3D object at each time instant using its undersampled measurements. In particular, in the case of dynamic tomography, only a single projection at a single view angle may be available at a time, making the problem severely ill-posed. In this work, we propose an approach, RED-PSM, which combines for the first time two powerful techniques to address this challenging imaging problem. The first, are partially separable models, which have been used to efficiently introduce a low-rank prior for the spatio-temporal object. The second is the recent \textit{Regularization by Denoising (RED)}, which provides a flexible framework to exploit the impressive performance of state-of-the-art image denoising algorithms, for various inverse problems. We propose a partially separable objective with RED and a computationally efficient and scalable optimization scheme with variable splitting and ADMM. Theoretical analysis proves the convergence of our objective to a value corresponding to a stationary point satisfying the first-order optimality conditions. Convergence is accelerated by a particular projection-domain-based initialization. We demonstrate the performance and computational improvements of our proposed RED-PSM with a learned image denoiser by comparing it to a recent deep-prior-based method known as TD-DIP. Although the main focus is on dynamic tomography, we also show performance advantages of RED-PSM in a cardiac dynamic MRI setting.
Authors: Yusuke Hirota, Yuta Nakashima, Noa Garcia
Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing models to focus on people to reduce gender misclassification, it conversely generates gender-stereotypical words at the expense of predicting the correct gender. From this observation, we hypothesize that there are two types of gender bias affecting image captioning models: 1) bias that exploits context to predict gender, and 2) bias in the probability of generating certain (often stereotypical) words because of gender. To mitigate both types of gender biases, we propose a framework, called LIBRA, that learns from synthetically biased samples to decrease both types of biases, correcting gender misclassification and changing gender-stereotypical words to more neutral ones. Code is available at https://github.com/rebnej/LIBRA.
Authors: Wenhao Wang, Yifan Sun, Wei Li, Yi Yang
This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task. Different from prior HIC methods, our hierarchical prompting is the first to explicitly inject ancestor-class information as a tokenized hint that benefits the descendant-class discrimination. We think it well imitates human visual recognition, i.e., humans may use the ancestor class as a prompt to draw focus on the subtle differences among descendant classes. We model this prompting mechanism into a Transformer with Hierarchical Prompting (TransHP). TransHP consists of three steps: 1) learning a set of prompt tokens to represent the coarse (ancestor) classes, 2) on-the-fly predicting the coarse class of the input image at an intermediate block, and 3) injecting the prompt token of the predicted coarse class into the intermediate feature. Though the parameters of TransHP maintain the same for all input images, the injected coarse-class prompt conditions (modifies) the subsequent feature extraction and encourages a dynamic focus on relatively subtle differences among the descendant classes. Extensive experiments show that TransHP improves image classification on accuracy (e.g., improving ViT-B/16 by +2.83% ImageNet classification accuracy), training data efficiency (e.g., +12.69% improvement under 10% ImageNet training data), and model explainability. Moreover, TransHP also performs favorably against prior HIC methods, showing that TransHP well exploits the hierarchical information. The code is available at: https://github.com/WangWenhao0716/TransHP.
Authors: Yihao Huang, Felix Juefei-Xu, Qing Guo, Jie Zhang, Yutong Wu, Ming Hu, Tianlin Li, Geguang Pu, Yang Liu
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible backdoor attacks. This paper investigates a critical and unexplored aspect of text-to-image (T2I) diffusion models - their potential vulnerability to backdoor attacks via personalization. Our study focuses on a zero-day backdoor vulnerability prevalent in two families of personalization methods, epitomized by Textual Inversion and DreamBooth.Compared to traditional backdoor attacks, our proposed method can facilitate more precise, efficient, and easily accessible attacks with a lower barrier to entry. We provide a comprehensive review of personalization in T2I diffusion models, highlighting the operation and exploitation potential of this backdoor vulnerability. To be specific, by studying the prompt processing of Textual Inversion and DreamBooth, we have devised dedicated backdoor attacks according to the different ways of dealing with unseen tokens and analyzed the influence of triggers and concept images on the attack effect. Through comprehensive empirical study, we endorse the utilization of the nouveau-token backdoor attack due to its impressive effectiveness, stealthiness, and integrity, markedly outperforming the legacy-token backdoor attack.
Authors: Jiarui Sun, Girish Chowdhary
Stochastic Human Motion Prediction (HMP) aims to predict multiple possible upcoming pose sequences based on past human motion trajectories. Although previous approaches have shown impressive performance, they face several issues, including complex training processes and a tendency to generate predictions that are often inconsistent with the provided history, and sometimes even becoming entirely unreasonable. To overcome these issues, we propose DiffMotion, an end-to-end diffusion-based stochastic HMP framework. DiffMotion's motion predictor is composed of two modules, including (1) a Transformer-based network for initial motion reconstruction from corrupted motion, and (2) a Graph Convolutional Network (GCN) to refine the generated motion considering past observations. Our method, facilitated by this novel Transformer-GCN module design and a proposed variance scheduler, excels in predicting accurate, realistic, and consistent motions, while maintaining an appropriate level of diversity. Our results on benchmark datasets show that DiffMotion significantly outperforms previous methods in terms of both accuracy and fidelity, while demonstrating superior robustness.
Authors: Marco Bellagente, Manuel Brack, Hannah Teufel, Felix Friedrich, Björn Deiseroth, Constantin Eichenberg, Andrew Dai, Robert Baldock, Souradeep Nanda, Koen Oostermeijer, Andres Felipe Cruz-Salinas, Patrick Schramowski, Kristian Kersting, Samuel Weinbach
The recent popularity of text-to-image diffusion models (DM) can largely be attributed to the intuitive interface they provide to users. The intended generation can be expressed in natural language, with the model producing faithful interpretations of text prompts. However, expressing complex or nuanced ideas in text alone can be difficult. To ease image generation, we propose MultiFusion that allows one to express complex and nuanced concepts with arbitrarily interleaved inputs of multiple modalities and languages. MutliFusion leverages pre-trained models and aligns them for integration into a cohesive system, thereby avoiding the need for extensive training from scratch. Our experimental results demonstrate the efficient transfer of capabilities from individual modules to the downstream model. Specifically, the fusion of all independent components allows the image generation module to utilize multilingual, interleaved multimodal inputs despite being trained solely on monomodal data in a single language.
Authors: Xiaomeng Yang, Zhi Qiao, Jin Wei, Dongbao Yang, Yu Zhou
Scene Text Recognition (STR) is difficult because of the variations in text styles, shapes, and backgrounds. Though the integration of linguistic information enhances models' performance, existing methods based on either permuted language modeling (PLM) or masked language modeling (MLM) have their pitfalls. PLM's autoregressive decoding lacks foresight into subsequent characters, while MLM overlooks inter-character dependencies. Addressing these problems, we propose a masked and permuted implicit context learning network for STR, which unifies PLM and MLM within a single decoder, inheriting the advantages of both approaches. We utilize the training procedure of PLM, and to integrate MLM, we incorporate word length information into the decoding process and replace the undetermined characters with mask tokens. Besides, perturbation training is employed to train a more robust model against potential length prediction errors. Our empirical evaluations demonstrate the performance of our model. It not only achieves superior performance on the common benchmarks but also achieves a substantial improvement of $9.1\%$ on the more challenging Union14M-Benchmark.
Authors: Tao Lei, Rui Sun, Xuan Wang, Yingbo Wang, Xi He, Asoke Nandi
The hybrid architecture of convolutional neural networks (CNNs) and Transformer are very popular for medical image segmentation. However, it suffers from two challenges. First, although a CNNs branch can capture the local image features using vanilla convolution, it cannot achieve adaptive feature learning. Second, although a Transformer branch can capture the global features, it ignores the channel and cross-dimensional self-attention, resulting in a low segmentation accuracy on complex-content images. To address these challenges, we propose a novel hybrid architecture of convolutional neural networks hand in hand with vision Transformers (CiT-Net) for medical image segmentation. Our network has two advantages. First, we design a dynamic deformable convolution and apply it to the CNNs branch, which overcomes the weak feature extraction ability due to fixed-size convolution kernels and the stiff design of sharing kernel parameters among different inputs. Second, we design a shifted-window adaptive complementary attention module and a compact convolutional projection. We apply them to the Transformer branch to learn the cross-dimensional long-term dependency for medical images. Experimental results show that our CiT-Net provides better medical image segmentation results than popular SOTA methods. Besides, our CiT-Net requires lower parameters and less computational costs and does not rely on pre-training. The code is publicly available at https://github.com/SR0920/CiT-Net.
Authors: Rui Sun, Tao Lei, Weichuan Zhang, Yong Wan, Yong Xia, Asoke K. Nandi
The hybrid architecture of convolution neural networks (CNN) and Transformer has been the most popular method for medical image segmentation. However, the existing networks based on the hybrid architecture suffer from two problems. First, although the CNN branch can capture image local features by using convolution operation, the vanilla convolution is unable to achieve adaptive extraction of image features. Second, although the Transformer branch can model the global information of images, the conventional self-attention only focuses on the spatial self-attention of images and ignores the channel and cross-dimensional self-attention leading to low segmentation accuracy for medical images with complex backgrounds. To solve these problems, we propose vision Transformer embrace convolutional neural networks for medical image segmentation (TEC-Net). Our network has two advantages. First, dynamic deformable convolution (DDConv) is designed in the CNN branch, which not only overcomes the difficulty of adaptive feature extraction using fixed-size convolution kernels, but also solves the defect that different inputs share the same convolution kernel parameters, effectively improving the feature expression ability of CNN branch. Second, in the Transformer branch, a (shifted)-window adaptive complementary attention module ((S)W-ACAM) and compact convolutional projection are designed to enable the network to fully learn the cross-dimensional long-range dependency of medical images with few parameters and calculations. Experimental results show that the proposed TEC-Net provides better medical image segmentation results than SOTA methods including CNN and Transformer networks. In addition, our TEC-Net requires fewer parameters and computational costs and does not rely on pre-training. The code is publicly available at https://github.com/SR0920/TEC-Net.
Authors: Gehua Ma, Runhao Jiang, Rui Yan, Huajin Tang
Developing computational models of neural response is crucial for understanding sensory processing and neural computations. Current state-of-the-art neural network methods use temporal filters to handle temporal dependencies, resulting in an unrealistic and inflexible processing paradigm. Meanwhile, these methods target trial-averaged firing rates and fail to capture important features in spike trains. This work presents the temporal conditioning spiking latent variable models (TeCoS-LVM) to simulate the neural response to natural visual stimuli. We use spiking neurons to produce spike outputs that directly match the recorded trains. This approach helps to avoid losing information embedded in the original spike trains. We exclude the temporal dimension from the model parameter space and introduce a temporal conditioning operation to allow the model to adaptively explore and exploit temporal dependencies in stimuli sequences in a {\it natural paradigm}. We show that TeCoS-LVM models can produce more realistic spike activities and accurately fit spike statistics than powerful alternatives. Additionally, learned TeCoS-LVM models can generalize well to longer time scales. Overall, while remaining computationally tractable, our model effectively captures key features of neural coding systems. It thus provides a useful tool for building accurate predictive computational accounts for various sensory perception circuits.
Authors: Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Recently, the performance of neural image compression (NIC) has steadily improved thanks to the last line of study, reaching or outperforming state-of-the-art conventional codecs. Despite significant progress, current NIC methods still rely on ConvNet-based entropy coding, limited in modeling long-range dependencies due to their local connectivity and the increasing number of architectural biases and priors, resulting in complex underperforming models with high decoding latency. Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT). Through the proposed ICT, we can capture both global and local contexts from the latent representations and better parameterize the distribution of the quantized latents. Further, we leverage a learnable scaling module with a sandwich ConvNeXt-based pre-/post-processor to accurately extract more compact latent codes while reconstructing higher-quality images. Extensive experimental results on benchmark datasets showed that the proposed framework significantly improves the trade-off between coding efficiency and decoder complexity over the versatile video coding (VVC) reference encoder (VTM-18.0) and the neural codec SwinT-ChARM. Moreover, we provide model scaling studies to verify the computational efficiency of our approach and conduct several objective and subjective analyses to bring to the fore the performance gap between the adaptive image compression transformer (AICT) and the neural codec SwinT-ChARM.
Authors: Yiren Jian, Chongyang Gao, Soroush Vosoughi
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current paradigm uses visual features as prompts to guide language models, with a focus on determining the most relevant visual features for corresponding text. Our approach diverges by concentrating on the language component, specifically identifying the optimal prompts to align with visual features. We introduce the Prompt-Transformer (P-Former), a model that predicts these ideal prompts, which is trained exclusively on linguistic data, bypassing the need for image-text pairings. This strategy subtly bifurcates the end-to-end VL training process into an additional, separate stage. Our experiments reveal that our framework significantly enhances the performance of a robust image-to-text baseline (BLIP-2), and effectively narrows the performance gap between models trained with either 4M or 129M image-text pairs. Importantly, our framework is modality-agnostic and flexible in terms of architectural design, as validated by its successful application in a video learning task using varied base modules. The code will be made available at https://github.com/yiren-jian/BLIText.
Authors: Ganping Li, Yoshito Otake, Mazen Soufi, Masashi Taniguchi, Masahide Yagi, Noriaki Ichihashi, Keisuke Uemura, Masaki Takao, Nobuhiko Sugano, Yoshinobu Sato
Purpose: Manual annotations for training deep learning (DL) models in auto-segmentation are time-intensive. This study introduces a hybrid representation-enhanced sampling strategy that integrates both density and diversity criteria within an uncertainty-based Bayesian active learning (BAL) framework to reduce annotation efforts by selecting the most informative training samples. Methods: The experiments are performed on two lower extremity (LE) datasets of MRI and CT images, focusing on the segmentation of the femur, pelvis, sacrum, quadriceps femoris, hamstrings, adductors, sartorius, and iliopsoas, utilizing a U-net-based BAL framework. Our method selects uncertain samples with high density and diversity for manual revision, optimizing for maximal similarity to unlabeled instances and minimal similarity to existing training data. We assess the accuracy and efficiency using Dice and a proposed metric called reduced annotation cost (RAC), respectively. We further evaluate the impact of various acquisition rules on BAL performance and design an ablation study for effectiveness estimation. Results: In MRI and CT datasets, our method was superior or comparable to existing ones, achieving a 0.8\% Dice and 1.0\% RAC increase in CT (statistically significant), and a 0.8\% Dice and 1.1\% RAC increase in MRI (not statistically significant) in volume-wise acquisition. Our ablation study indicates that combining density and diversity criteria enhances the efficiency of BAL in musculoskeletal segmentation compared to using either criterion alone. Conclusion: Our sampling method is proven efficient in reducing annotation costs in image segmentation tasks. The combination of the proposed method and our BAL framework provides a semi-automatic way for efficient annotation of medical image datasets.
Authors: Kai Liu, Sheng Jin, Zhihang Fu, Ze Chen, Rongxin Jiang, Jieping Ye
Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem arises. The frame-by-frame accumulated uncertainty prevents trackers from learning the consistent feature embedding against time variation. To avoid this uncertainty problem, recent self-supervised techniques are adopted, whereas they failed to capture temporal relations. The interframe uncertainty still exists. In fact, this paper argues that though the uncertainty problem is inevitable, it is possible to leverage the uncertainty itself to improve the learned consistency in turn. Specifically, an uncertainty-based metric is developed to verify and rectify the risky associations. The resulting accurate pseudo-tracklets boost learning the feature consistency. And accurate tracklets can incorporate temporal information into spatial transformation. This paper proposes a tracklet-guided augmentation strategy to simulate tracklets' motion, which adopts a hierarchical uncertainty-based sampling mechanism for hard sample mining. The ultimate unsupervised MOT framework, namely U2MOT, is proven effective on MOT-Challenges and VisDrone-MOT benchmark. U2MOT achieves a SOTA performance among the published supervised and unsupervised trackers.
Authors: Amira Guesmi, Muhammad Abdullah Hanif, Bassem Ouni, Muhammad Shafique
In this paper, we investigate the vulnerability of MDE to adversarial patches. We propose a novel \underline{S}tealthy \underline{A}dversarial \underline{A}ttacks on \underline{M}DE (SAAM) that compromises MDE by either corrupting the estimated distance or causing an object to seamlessly blend into its surroundings. Our experiments, demonstrate that the designed stealthy patch successfully causes a DNN-based MDE to misestimate the depth of objects. In fact, our proposed adversarial patch achieves a significant 60\% depth error with 99\% ratio of the affected region. Importantly, despite its adversarial nature, the patch maintains a naturalistic appearance, making it inconspicuous to human observers. We believe that this work sheds light on the threat of adversarial attacks in the context of MDE on edge devices. We hope it raises awareness within the community about the potential real-life harm of such attacks and encourages further research into developing more robust and adaptive defense mechanisms.
Authors: Zirong Li, Yanyang Wang, Jianjia Zhang, Weiwen Wu, Hengyong Yu
Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are crucial technologies in the field of medical imaging. Score-based models have proven to be effective in addressing different inverse problems encountered in CT and MRI, such as sparse-view CT and fast MRI reconstruction. However, these models face challenges in achieving accurate three dimensional (3D) volumetric reconstruction. The existing score-based models primarily focus on reconstructing two dimensional (2D) data distribution, leading to inconsistencies between adjacent slices in the reconstructed 3D volumetric images. To overcome this limitation, we propose a novel two-and-a-half order score-based model (TOSM). During the training phase, our TOSM learns data distributions in 2D space, which reduces the complexity of training compared to directly working on 3D volumes. However, in the reconstruction phase, the TOSM updates the data distribution in 3D space, utilizing complementary scores along three directions (sagittal, coronal, and transaxial) to achieve a more precise reconstruction. The development of TOSM is built on robust theoretical principles, ensuring its reliability and efficacy. Through extensive experimentation on large-scale sparse-view CT and fast MRI datasets, our method demonstrates remarkable advancements and attains state-of-the-art results in solving 3D ill-posed inverse problems. Notably, the proposed TOSM effectively addresses the inter-slice inconsistency issue, resulting in high-quality 3D volumetric reconstruction.
Authors: Arindam Kumar Paul
Human Facial Expressions plays an important role in identifying human actions or intention. Facial expressions can represent any specific action of any person and the pattern of violent behavior of any person strongly depends on the geographic region. Here we have designed an automated system by using a Convolutional Neural Network which can detect whether a person has any intention to commit any crime or not. Here we proposed a new method that can identify criminal intentions or violent behavior of any person before executing crimes more efficiently by using very little data on facial expressions before executing a crime or any violent tasks. Instead of using image features which is a time-consuming and faulty method we used an automated feature selector Convolutional Neural Network model which can capture exact facial expressions for training and then can predict that target facial expressions more accurately. Here we used only the facial data of a specific geographic region which can represent the violent and before-crime before-crime facial patterns of the people of the whole region.
Authors: Ernie Chu, Tzuhsuan Huang, Shuo-Yen Lin, Jun-Cheng Chen
This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position information, such as a normal G-buffer, or perform text-guided editing on videos captured in real-world scenarios. We employ explicit optical flows to construct a practical coding that enforces physical constraints on generated frames and mediates independent frame-wise scores. By leveraging this coding, maintaining temporal consistency in the generated videos can be framed as an optimization problem with a closed-form solution. To ensure compatibility with Stable Diffusion, we also suggest a workaround for modifying observation-space scores in latent Diffusion Models. Notably, MeDM does not require fine-tuning or test-time optimization of the Diffusion Models. Through extensive qualitative, quantitative, and subjective experiments on various benchmarks, the study demonstrates the effectiveness and superiority of the proposed approach. Our project page can be found at https://medm2023.github.io
Authors: Alexis Goujon, Sebastian Neumayer, Michael Unser
We propose to learn non-convex regularizers with a prescribed upper bound on their weak-convexity modulus. Such regularizers give rise to variational denoisers that minimize a convex energy. They rely on few parameters (less than 15,000) and offer a signal-processing interpretation as they mimic handcrafted sparsity-promoting regularizers. Through numerical experiments, we show that such denoisers outperform convex-regularization methods as well as the popular BM3D denoiser. Additionally, the learned regularizer can be deployed to solve inverse problems with iterative schemes that provably converge. For both CT and MRI reconstruction, the regularizer generalizes well and offers an excellent tradeoff between performance, number of parameters, guarantees, and interpretability when compared to other data-driven approaches.
Authors: Ao Luo, Linxin Song, Keisuke Nonaka, Kyohei Unno, Heming Sun, Masayuki Goto, Jiro Katto
In recent years, the task of learned point cloud compression has gained prominence. An important type of point cloud, the spinning LiDAR point cloud, is generated by spinning LiDAR on vehicles. This process results in numerous circular shapes and azimuthal angle invariance features within the point clouds. However, these two features have been largely overlooked by previous methodologies. In this paper, we introduce a model-agnostic method called Spherical-Coordinate-based learned Point cloud compression (SCP), designed to leverage the aforementioned features fully. Additionally, we propose a multi-level Octree for SCP to mitigate the reconstruction error for distant areas within the Spherical-coordinate-based Octree. SCP exhibits excellent universality, making it applicable to various learned point cloud compression techniques. Experimental results demonstrate that SCP surpasses previous state-of-the-art methods by up to 29.14% in point-to-point PSNR BD-Rate.
Authors: Shenghong Luo, Xuhang Chen, Weiwen Chen, Zinuo Li, Shuqiang Wang, Chi-Man Pun
Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in the ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present Vigset, a pioneering dataset for vignetting removal. Vigset includes 983 pairs of both vignetting and vignetting-free high-resolution ($5340\times3697$) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we propose the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods. The code, models, and dataset are available at \url{https://github.com/CXH-Research/DeVigNet}.
Authors: Zi-Xin Zou, Weihao Cheng, Yan-Pei Cao, Shi-Sheng Huang, Ying Shan, Song-Hai Zhang
Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained diffusion priors into 3D representations using score distillation sampling (SDS), these methods often struggle to simultaneously achieve high-quality, consistent, and detailed results for both novel-view synthesis (NVS) and geometry. In this work, we present Sparse3D, a novel 3D reconstruction method tailored for sparse view inputs. Our approach distills robust priors from a multiview-consistent diffusion model to refine a neural radiance field. Specifically, we employ a controller that harnesses epipolar features from input views, guiding a pre-trained diffusion model, such as Stable Diffusion, to produce novel-view images that maintain 3D consistency with the input. By tapping into 2D priors from powerful image diffusion models, our integrated model consistently delivers high-quality results, even when faced with open-world objects. To address the blurriness introduced by conventional SDS, we introduce the category-score distillation sampling (C-SDS) to enhance detail. We conduct experiments on CO3DV2 which is a multi-view dataset of real-world objects. Both quantitative and qualitative evaluations demonstrate that our approach outperforms previous state-of-the-art works on the metrics regarding NVS and geometry reconstruction.
Authors: Avinash Paliwal, Brandon Nguyen, Andrii Tsarov, Nima Khademi Kalantari
In recent years, novel view synthesis from a single image has seen significant progress thanks to the rapid advancements in 3D scene representation and image inpainting techniques. While the current approaches are able to synthesize geometrically consistent novel views, they often do not handle the view-dependent effects properly. Specifically, the highlights in their synthesized images usually appear to be glued to the surfaces, making the novel views unrealistic. To address this major problem, we make a key observation that the process of synthesizing novel views requires changing the shading of the pixels based on the novel camera, and moving them to appropriate locations. Therefore, we propose to split the view synthesis process into two independent tasks of pixel reshading and relocation. During the reshading process, we take the single image as the input and adjust its shading based on the novel camera. This reshaded image is then used as the input to an existing view synthesis method to relocate the pixels and produce the final novel view image. We propose to use a neural network to perform reshading and generate a large set of synthetic input-reshaded pairs to train our network. We demonstrate that our approach produces plausible novel view images with realistic moving highlights on a variety of real world scenes.
Authors: Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin, Ekaterina Shumitskaya, Sergey Lavrushkin, Dmitriy Vatolin
Nowadays neural-network-based image- and video-quality metrics show better performance compared to traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving visual quality. The existing benchmarks of quality metrics compare their performance in terms of correlation with subjective quality and calculation time. However, the adversarial robustness of image-quality metrics is also an area worth researching. In this paper, we analyse modern metrics' robustness to different adversarial attacks. We adopted adversarial attacks from computer vision tasks and compared attacks' efficiency against 15 no-reference image/video-quality metrics. Some metrics showed high resistance to adversarial attacks which makes their usage in benchmarks safer than vulnerable metrics. The benchmark accepts new metrics submissions for researchers who want to make their metrics more robust to attacks or to find such metrics for their needs. Try our benchmark using pip install robustness-benchmark.
Authors: Xiaohui Liu, Zhilu Zhang, Xiaohe Wu, Chaoyu Feng, Xiaotao Wang, LEI LEI, Wangmeng Zuo
Real-world image de-weathering aims at removing various undesirable weather-related artifacts. Owing to the impossibility of capturing image pairs concurrently, existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images, resulting in imperfect supervision. Such non-ideal supervision negatively affects the training process of learning-based de-weathering methods. In this work, we attempt to address the problem with a unified solution for various inconsistencies. Specifically, inspired by information bottleneck theory, we first develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image while removing most weather-related degradations. In particular, multiple adjacent frames of the current input are also fed into CLC to enhance the pseudo-label. Then we combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy (IAS). During testing, only the de-weathering model is used for inference. Experiments on two real-world de-weathering datasets show that our method helps existing de-weathering models achieve better performance. Codes are available at https://github.com/1180300419/imperfect-deweathering.
Authors: Fahim Ahmed Zaman, Xiaodong Wu, Weiyu Xu, Milan Sonka, Raghuraman Mudumbai
We describe a method for verifying the output of a deep neural network for medical image segmentation that is robust to several classes of random as well as worst-case perturbations i.e. adversarial attacks. This method is based on a general approach recently developed by the authors called "Trust, but Verify" wherein an auxiliary verification network produces predictions about certain masked features in the input image using the segmentation as an input. A well-designed auxiliary network will produce high-quality predictions when the input segmentations are accurate, but will produce low-quality predictions when the segmentations are incorrect. Checking the predictions of such a network with the original image allows us to detect bad segmentations. However, to ensure the verification method is truly robust, we need a method for checking the quality of the predictions that does not itself rely on a black-box neural network. Indeed, we show that previous methods for segmentation evaluation that do use deep neural regression networks are vulnerable to false negatives i.e. can inaccurately label bad segmentations as good. We describe the design of a verification network that avoids such vulnerability and present results to demonstrate its robustness compared to previous methods.
Authors: Lucas R. Schwengber, Lucas Resende, Paulo Orenstein, Roberto I. Oliveira
Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques. Such algorithms typically learn continuous embeddings of the data. To avoid a subsequent costly binarization step, a common solution is to employ loss functions that combine a similarity learning term (to ensure similar images are grouped to nearby embeddings) and a quantization penalty term (to ensure that the embedding entries are close to binarized entries, e.g., -1 or 1). Still, the interaction between these two terms can make learning harder and the embeddings worse. We propose an alternative quantization strategy that decomposes the learning problem in two stages: first, perform similarity learning over the embedding space with no quantization; second, find an optimal orthogonal transformation of the embeddings so each coordinate of the embedding is close to its sign, and then quantize the transformed embedding through the sign function. In the second step, we parametrize orthogonal transformations using Householder matrices to efficiently leverage stochastic gradient descent. Since similarity measures are usually invariant under orthogonal transformations, this quantization strategy comes at no cost in terms of performance. The resulting algorithm is unsupervised, fast, hyperparameter-free and can be run on top of any existing deep hashing or metric learning algorithm. We provide extensive experimental results showing that this approach leads to state-of-the-art performance on widely used image datasets, and, unlike other quantization strategies, brings consistent improvements in performance to existing deep hashing algorithms.
Authors: Yuheng Fan, Hanxi Liao, Shiqi Huang, Yimin Luo, Huazhu Fu, Haikun Qi
Diffusion probabilistic models (DPMs) which employ explicit likelihood characterization and a gradual sampling process to synthesize data, have gained increasing research interest. Despite their huge computational burdens due to the large number of steps involved during sampling, DPMs are widely appreciated in various medical imaging tasks for their high-quality and diversity of generation. Magnetic resonance imaging (MRI) is an important medical imaging modality with excellent soft tissue contrast and superb spatial resolution, which possesses unique opportunities for DPMs. Although there is a recent surge of studies exploring DPMs in MRI, a survey paper of DPMs specifically designed for MRI applications is still lacking. This review article aims to help researchers in the MRI community to grasp the advances of DPMs in different applications. We first introduce the theory of two dominant kinds of DPMs, categorized according to whether the diffusion time step is discrete or continuous, and then provide a comprehensive review of emerging DPMs in MRI, including reconstruction, image generation, image translation, segmentation, anomaly detection, and further research topics. Finally, we discuss the general limitations as well as limitations specific to the MRI tasks of DPMs and point out potential areas that are worth further exploration.
Authors: Vladimir Arkhipkin, Zein Shaheen, Viacheslav Vasilev, Elizaveta Dakhova, Andrey Kuznetsov, Denis Dimitrov
Multimedia generation approaches occupy a prominent place in artificial intelligence research. Text-to-image models achieved high-quality results over the last few years. However, video synthesis methods recently started to develop. This paper presents a new two-stage latent diffusion text-to-video generation architecture based on the text-to-image diffusion model. The first stage concerns keyframes synthesis to figure the storyline of a video, while the second one is devoted to interpolation frames generation to make movements of the scene and objects smooth. We compare several temporal conditioning approaches for keyframes generation. The results show the advantage of using separate temporal blocks over temporal layers in terms of metrics reflecting video generation quality aspects and human preference. The design of our interpolation model significantly reduces computational costs compared to other masked frame interpolation approaches. Furthermore, we evaluate different configurations of MoVQ-based video decoding scheme to improve consistency and achieve higher PSNR, SSIM, MSE, and LPIPS scores. Finally, we compare our pipeline with existing solutions and achieve top-2 scores overall and top-1 among open-source solutions: CLIPSIM = 0.2976 and FVD = 433.054. Project page: https://ai-forever.github.io/kandinsky-video/
Authors: Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin
3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation. GaussianEditor enhances precision and control in editing through our proposed Gaussian semantic tracing, which traces the editing target throughout the training process. Additionally, we propose Hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, efficacy, and rapid performance, marking a significant advancement in 3D editing. Project Page: https://buaacyw.github.io/gaussian-editor/
Authors: Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Roldão, Dzmitry Tsishkou, Cyrille Migniot, Pascal Vasseur, Cédric Demonceaux
In rapidly-evolving domains such as autonomous driving, the use of multiple sensors with different modalities is crucial to ensure high operational precision and stability. To correctly exploit the provided information by each sensor in a single common frame, it is essential for these sensors to be accurately calibrated. In this paper, we leverage the ability of Neural Radiance Fields (NeRF) to represent different sensors modalities in a common volumetric representation to achieve robust and accurate spatio-temporal sensor calibration. By designing a partitioning approach based on the visible part of the scene for each sensor, we formulate the calibration problem using only the overlapping areas. This strategy results in a more robust and accurate calibration that is less prone to failure. We demonstrate that our approach works on outdoor urban scenes by validating it on multiple established driving datasets. Results show that our method is able to get better accuracy and robustness compared to existing methods.
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.
Authors: Jacopo Bonato, Francesco Pelosin, Luigi Sabetta, Alessandro Nicolosi
The recent surge of pervasive devices that generate dynamic data streams has underscored the necessity for learning systems to adapt continually to data distributional shifts. To tackle this challenge, the research community has put forth a spectrum of methodologies, including the demanding pursuit of class-incremental learning without replay data. In this study, we present MIND, a parameter isolation method that aims to significantly enhance the performance of replay-free solutions and achieve state-of-the-art results on several widely studied datasets. Our approach introduces two main contributions: two alternative distillation procedures that significantly improve the efficiency of MIND increasing the accumulated knowledge of each sub-network, and the optimization of the BachNorm layers across tasks inside the sub-networks. Overall, MIND outperforms all the state-of-the-art methods for rehearsal-free Class-Incremental learning (with an increment in classification accuracy of approx. +6% on CIFAR-100/10 and +10% on TinyImageNet/10) reaching up to approx. +40% accuracy in Domain-Incremental scenarios. Moreover, we ablated each contribution to demonstrate its impact on performance improvement. Our results showcase the superior performance of MIND indicating its potential for addressing the challenges posed by Class-incremental and Domain-Incremental learning in resource-constrained environments.
Authors: Xinzhou Wang, Yikai Wang, Junliang Ye, Zhengyi Wang, Fuchun Sun, Pengkun Liu, Ling Wang, Kai Sun, Xintong Wang, Bin He
Text-to-3D model adaptations have advanced static 3D model quality, but sequential 3D model generation, particularly for animatable objects with large motions, is still scarce. Our work proposes AnimatableDreamer, a text-to-4D generation framework capable of generating diverse categories of non-rigid objects while adhering to the object motions extracted from a monocular video. At its core, AnimatableDreamer is equipped with our novel optimization design dubbed Canonical Score Distillation (CSD), which simplifies the generation dimension from 4D to 3D by denoising over different frames in the time-varying camera spaces while conducting the distillation process in a unique canonical space shared per video. Concretely, CSD ensures that score gradients back-propagate to the canonical space through differentiable warping, hence guaranteeing the time-consistent generation and maintaining morphological plausibility across different poses. By lifting the 3D generator to 4D with warping functions, AnimatableDreamer offers a novel perspective on non-rigid 3D model generation and reconstruction. Besides, with inductive knowledge from a multi-view consistent diffusion model, CSD regularizes reconstruction from novel views, thus cyclically enhancing the generation process. Extensive experiments demonstrate the capability of our method in generating high-flexibility text-guided 3D models from the monocular video, while also showing improved reconstruction performance over typical non-rigid reconstruction methods. Project page https://AnimatableDreamer.github.io.
Authors: Yue Jiang, Yueming Lyu, Tianxiang Ma, Bo Peng, Jing Dong
Recent text-conditioned image generation models have demonstrated an exceptional capacity to produce diverse and creative imagery with high visual quality. However, when pre-trained on billion-sized datasets randomly collected from the Internet, where potential biased human preferences exist, these models tend to produce images with common and recurring stereotypes, particularly for certain racial groups. In this paper, we conduct an initial analysis of the publicly available Stable Diffusion model and its derivatives, highlighting the presence of racial stereotypes. These models often generate distorted or biased images for certain racial groups, emphasizing stereotypical characteristics. To address these issues, we propose a framework called "RS-Corrector", designed to establish an anti-stereotypical preference in the latent space and update the latent code for refined generated results. The correction process occurs during the inference stage without requiring fine-tuning of the original model. Extensive empirical evaluations demonstrate that the introduced \themodel effectively corrects the racial stereotypes of the well-trained Stable Diffusion model while leaving the original model unchanged.
Authors: Zhen Wang, Qiangeng Xu, Feitong Tan, Menglei Chai, Shichen Liu, Rohit Pandey, Sean Fanello, Achuta Kadambi, Yinda Zhang
Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents complex 3D shapes in a 2D data format that is easy to denoise. We pair this representation with a diffusion model, MVDD, that is capable of generating high-quality dense point clouds with 20K+ points with fine-grained details. To enforce 3D consistency in multi-view depth, we introduce an epipolar line segment attention that conditions the denoising step for a view on its neighboring views. Additionally, a depth fusion module is incorporated into diffusion steps to further ensure the alignment of depth maps. When augmented with surface reconstruction, MVDD can also produce high-quality 3D meshes. Furthermore, MVDD stands out in other tasks such as depth completion, and can serve as a 3D prior, significantly boosting many downstream tasks, such as GAN inversion. State-of-the-art results from extensive experiments demonstrate MVDD's excellent ability in 3D shape generation, depth completion, and its potential as a 3D prior for downstream tasks.
Authors: Prithvijit Chattopadhyay, Bharat Goyal, Boglarka Ecsedi, Viraj Prabhu, Judy Hoffman
Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world applications can be challenging due to appearance disparities. A commonly employed solution to counter this SIM2REAL gap is unsupervised domain adaptation, where models are trained using labeled SIM data and unlabeled REAL data. Mispredictions made by such SIM2REAL adapted models are often associated with miscalibration - stemming from overconfident predictions on real data. In this paper, we introduce AUGCAL, a simple training-time patch for unsupervised adaptation that improves SIM2REAL adapted models by - (1) reducing overall miscalibration, (2) reducing overconfidence in incorrect predictions and (3) improving confidence score reliability by better guiding misclassification detection - all while retaining or improving SIM2REAL performance. Given a base SIM2REAL adaptation algorithm, at training time, AUGCAL involves replacing vanilla SIM images with strongly augmented views (AUG intervention) and additionally optimizing for a training time calibration loss on augmented SIM predictions (CAL intervention). We motivate AUGCAL using a brief analytical justification of how to reduce miscalibration on unlabeled REAL data. Through our experiments, we empirically show the efficacy of AUGCAL across multiple adaptation methods, backbones, tasks and shifts.
Authors: Soham Bafana
Understanding object recognition patterns in mice is crucial for advancing behavioral neuroscience and has significant implications for human health, particularly in the realm of Alzheimer's research. This study is centered on the development, application, and evaluation of a state-of-the-art computational pipeline designed to analyze such behaviors, specifically focusing on Novel Object Recognition (NOR) and Spontaneous Location Recognition (SLR) tasks. The pipeline integrates three advanced computational models: Any-Maze for initial data collection, DeepLabCut for detailed pose estimation, and Convolutional Neural Networks (CNNs) for nuanced behavioral classification. Employed across four distinct mouse groups, this pipeline demonstrated high levels of accuracy and robustness. Despite certain challenges like video quality limitations and the need for manual calculations, the results affirm the pipeline's efficacy and potential for scalability. The study serves as a proof of concept for a multidimensional computational approach to behavioral neuroscience, emphasizing the pipeline's versatility and readiness for future, more complex analyses.
Authors: Zhenduo Zhang, Bo-Wen Zhang, Guang Liu
Current text-to-image editing models often encounter challenges with smoothly manipulating multiple attributes using a single instruction. Taking inspiration from the Chain-of-Thought prompting technique utilized in language models, we present an innovative concept known as Chain-of-Instruct Editing (CoIE), which enhances the capabilities of these models through step-by-step editing using a series of instructions. In particular, in the context of face manipulation, we leverage the contextual learning abilities of a pretrained Large Language Model (LLM), such as GPT-4, to generate a sequence of instructions from the original input, utilizing a purpose-designed 1-shot template. To further improve the precision of each editing step, we conduct fine-tuning on the editing models using our self-constructed instruction-guided face editing dataset, Instruct-CelebA. And additionally, we incorporate a super-resolution module to mitigate the adverse effects of editability and quality degradation. Experimental results across various challenging cases confirm the significant boost in multi-attribute facial image manipulation using chain-of-instruct editing. This is evident in enhanced editing success rates, measured by CLIPSim and Coverage metrics, improved by 17.86% and 85.45% respectively, and heightened controllability indicated by Preserve L1 and Quality metrics, improved by 11.58% and 4.93% respectively.
Authors: Wenqian Zhang, Molin Huang, Yuxuan Zhou, Juze Zhang, Jingyi Yu, Jingya Wang, Lan Xu
The recently emerging text-to-motion advances have spired numerous attempts for convenient and interactive human motion generation. Yet, existing methods are largely limited to generating body motions only without considering the rich two-hand motions, let alone handling various conditions like body dynamics or texts. To break the data bottleneck, we propose BOTH57M, a novel multi-modal dataset for two-hand motion generation. Our dataset includes accurate motion tracking for the human body and hands and provides pair-wised finger-level hand annotations and body descriptions. We further provide a strong baseline method, BOTH2Hands, for the novel task: generating vivid two-hand motions from both implicit body dynamics and explicit text prompts. We first warm up two parallel body-to-hand and text-to-hand diffusion models and then utilize the cross-attention transformer for motion blending. Extensive experiments and cross-validations demonstrate the effectiveness of our approach and dataset for generating convincing two-hand motions from the hybrid body-and-textual conditions. Our dataset and code will be disseminated to the community for future research.
Authors: Piyush Arora, Pratik Mazumder
Deep learning models are known to suffer from the problem of bias, and researchers have been exploring methods to address this issue. However, most of these methods require prior knowledge of the bias and are not always practical. In this paper, we focus on a more practical setting with no prior information about the bias. Generally, in this setting, there are a large number of bias-aligned samples that cause the model to produce biased predictions and a few bias-conflicting samples that do not conform to the bias. If the training data is limited, the influence of the bias-aligned samples may become even stronger on the model predictions, and we experimentally demonstrate that existing debiasing techniques suffer severely in such cases. In this paper, we examine the effects of unknown bias in small dataset regimes and present a novel approach to mitigate this issue. The proposed approach directly addresses the issue of the extremely low occurrence of bias-conflicting samples in limited data settings through the synthesis of hybrid samples that can be used to reduce the effect of bias. We perform extensive experiments on several benchmark datasets and experimentally demonstrate the effectiveness of our proposed approach in addressing any unknown bias in the presence of limited data. Specifically, our approach outperforms the vanilla, LfF, LDD, and DebiAN debiasing methods by absolute margins of 10.39%, 9.08%, 8.07%, and 9.67% when only 10% of the Corrupted CIFAR-10 Type 1 dataset is available with a bias-conflicting sample ratio of 0.05.
Authors: Joshua Wang
We propose a PnP algorithm for a camera constrained to two-dimensional movement (applicable, for instance, to many wheeled robotics platforms). Leveraging this assumption allows performance improvements over 3D PnP algorithms due to the reduction in search space dimensionality. It also reduces the incidence of ambiguous pose estimates (as, in most cases, the spurious solutions fall outside the plane of movement). Our algorithm finds an approximate solution using geometric criteria and refines its prediction iteratively. We compare this algorithm to existing 3D PnP algorithms in terms of accuracy, performance, and robustness to noise.
Authors: Hao Shao, Quansheng Zeng, Qibin Hou, Jufeng Yang
Efficiently capturing multi-scale information and building long-range dependencies among pixels are essential for medical image segmentation because of the various sizes and shapes of the lesion regions or organs. In this paper, we present Multi-scale Cross-axis Attention (MCA) to solve the above challenging issues based on the efficient axial attention. Instead of simply connecting axial attention along the horizontal and vertical directions sequentially, we propose to calculate dual cross attentions between two parallel axial attentions to capture global information better. To process the significant variations of lesion regions or organs in individual sizes and shapes, we also use multiple convolutions of strip-shape kernels with different kernel sizes in each axial attention path to improve the efficiency of the proposed MCA in encoding spatial information. We build the proposed MCA upon the MSCAN backbone, yielding our network, termed MCANet. Our MCANet with only 4M+ parameters performs even better than most previous works with heavy backbones (e.g., Swin Transformer) on four challenging tasks, including skin lesion segmentation, nuclei segmentation, abdominal multi-organ segmentation, and polyp segmentation. Code is available at https://github.com/haoshao-nku/medical_seg.
Authors: Chuangchuang Tan, Huan Liu, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei
Recently, the proliferation of highly realistic synthetic images, facilitated through a variety of GANs and Diffusions, has significantly heightened the susceptibility to misuse. While the primary focus of deepfake detection has traditionally centered on the design of detection algorithms, an investigative inquiry into the generator architectures has remained conspicuously absent in recent years. This paper contributes to this lacuna by rethinking the architectures of CNN-based generators, thereby establishing a generalized representation of synthetic artifacts. Our findings illuminate that the up-sampling operator can, beyond frequency-based artifacts, produce generalized forgery artifacts. In particular, the local interdependence among image pixels caused by upsampling operators is significantly demonstrated in synthetic images generated by GAN or diffusion. Building upon this observation, we introduce the concept of Neighboring Pixel Relationships(NPR) as a means to capture and characterize the generalized structural artifacts stemming from up-sampling operations. A comprehensive analysis is conducted on an open-world dataset, comprising samples generated by \tft{28 distinct generative models}. This analysis culminates in the establishment of a novel state-of-the-art performance, showcasing a remarkable \tft{11.6\%} improvement over existing methods. The code is available at https://github.com/chuangchuangtan/NPR-DeepfakeDetection.
Authors: Jiachen Zhou, Peizhuo Lv, Yibing Lan, Guozhu Meng, Kai Chen, Hualong Ma
Dataset sanitization is a widely adopted proactive defense against poisoning-based backdoor attacks, aimed at filtering out and removing poisoned samples from training datasets. However, existing methods have shown limited efficacy in countering the ever-evolving trigger functions, and often leading to considerable degradation of benign accuracy. In this paper, we propose DataElixir, a novel sanitization approach tailored to purify poisoned datasets. We leverage diffusion models to eliminate trigger features and restore benign features, thereby turning the poisoned samples into benign ones. Specifically, with multiple iterations of the forward and reverse process, we extract intermediary images and their predicted labels for each sample in the original dataset. Then, we identify anomalous samples in terms of the presence of label transition of the intermediary images, detect the target label by quantifying distribution discrepancy, select their purified images considering pixel and feature distance, and determine their ground-truth labels by training a benign model. Experiments conducted on 9 popular attacks demonstrates that DataElixir effectively mitigates various complex attacks while exerting minimal impact on benign accuracy, surpassing the performance of baseline defense methods.
Authors: Jiankai Sun, Chuanyang Zheng, Enze Xie, Zhengying Liu, Ruihang Chu, Jianing Qiu, Jiaqi Xu, Mingyu Ding, Hongyang Li, Mengzhe Geng, Yue Wu, Wenhai Wang, Junsong Chen, Zhangyue Yin, Xiaozhe Ren, Jie Fu, Junxian He, Wu Yuan, Qi Liu, Xihui Liu, Yu Li, Hao Dong, Yu Cheng, Ming Zhang, Pheng Ann Heng, Jifeng Dai, Ping Luo, Jingdong Wang, Ji-Rong Wen, Xipeng Qiu, Yike Guo, Hui Xiong, Qun Liu, Zhenguo Li
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation. It serves as a fundamental methodology in the field of Artificial General Intelligence (AGI). With the ongoing development of foundation models, there is a growing interest in exploring their abilities in reasoning tasks. In this paper, we introduce seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks. We then delve into the potential future directions behind the emergence of reasoning abilities within foundation models. We also discuss the relevance of multimodal learning, autonomous agents, and super alignment in the context of reasoning. By discussing these future research directions, we hope to inspire researchers in their exploration of this field, stimulate further advancements in reasoning with foundation models, and contribute to the development of AGI.
Authors: Chaojian Li, Bichen Wu, Peter Vajda, Yingyan (Celine)Lin
Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Nevertheless, achieving real-time NeRF rendering in large-scale scenes has presented challenges, often leading to the adoption of either intricate baked mesh representations with a substantial number of triangles or resource-intensive ray marching in baked representations. We challenge these conventions, observing that high-quality geometry, represented by meshes with substantial triangles, is not necessary for achieving photorealistic rendering quality. Consequently, we propose MixRT, a novel NeRF representation that includes a low-quality mesh, a view-dependent displacement map, and a compressed NeRF model. This design effectively harnesses the capabilities of existing graphics hardware, thus enabling real-time NeRF rendering on edge devices. Leveraging a highly-optimized WebGL-based rendering framework, our proposed MixRT attains real-time rendering speeds on edge devices (over 30 FPS at a resolution of 1280 x 720 on a MacBook M1 Pro laptop), better rendering quality (0.2 PSNR higher in indoor scenes of the Unbounded-360 datasets), and a smaller storage size (less than 80% compared to state-of-the-art methods).
Authors: Chunjie Luo, Fei Luo, Yusen Wang, Enxu Zhao, Chunxia Xiao
Reconstructing a dynamic human with loose clothing is an important but difficult task. To address this challenge, we propose a method named DLCA-Recon to create human avatars from monocular videos. The distance from loose clothing to the underlying body rapidly changes in every frame when the human freely moves and acts. Previous methods lack effective geometric initialization and constraints for guiding the optimization of deformation to explain this dramatic change, resulting in the discontinuous and incomplete reconstruction surface. To model the deformation more accurately, we propose to initialize an estimated 3D clothed human in the canonical space, as it is easier for deformation fields to learn from the clothed human than from SMPL. With both representations of explicit mesh and implicit SDF, we utilize the physical connection information between consecutive frames and propose a dynamic deformation field (DDF) to optimize deformation fields. DDF accounts for contributive forces on loose clothing to enhance the interpretability of deformations and effectively capture the free movement of loose clothing. Moreover, we propagate SMPL skinning weights to each individual and refine pose and skinning weights during the optimization to improve skinning transformation. Based on more reasonable initialization and DDF, we can simulate real-world physics more accurately. Extensive experiments on public and our own datasets validate that our method can produce superior results for humans with loose clothing compared to the SOTA methods.
Authors: Akshat Kishore Shrivastava, Tapan Kumar Gandhi
In this paper, we propose an novel methodology aimed at simulating the learning phenomenon of nystagmus through the application of differential blurring on datasets. Nystagmus is a biological phenomenon that influences human vision throughout life, notably by diminishing head shake from infancy to adulthood. Leveraging this concept, we address the issue of waste classification, a pressing global concern. The proposed framework comprises two modules, with the second module closely resembling the original Vision Transformer, a state-of-the-art model model in classification tasks. The primary motivation behind our approach is to enhance the model's precision and adaptability, mirroring the real-world conditions that the human visual system undergoes. This novel methodology surpasses the standard Vision Transformer model in waste classification tasks, exhibiting an improvement with a margin of 2%. This improvement underscores the potential of our methodology in improving model precision by drawing inspiration from human vision perception. Further research in the proposed methodology could yield greater performance results, and can be extrapolated to other global issues.
Authors: Jichang Li, Guanbin Li, Hui Cheng, Zicheng Liao, Yizhou Yu
Federated learning with noisy labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning by aggregating multiple client models trained with local noisy or clean samples. On the basis of a federated learning framework, recent advances primarily adopt label noise filtering to separate clean samples from noisy ones on each client, thereby mitigating the negative impact of label noise. However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability. In this paper, we present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter for effectively identifying samples with noisy labels on every client, thereby raising stability during local training sessions. Without sacrificing data privacy, this is achieved by modeling the global distribution of label noise across all clients. Then, in an effort to make the global model achieve higher performance, we introduce a Predictive Consistency based Sampler to identify more credible local data for local model training, thus preventing noise memorization and further boosting the training stability. Extensive experiments on CIFAR-10, CIFAR-100, and Clothing1M demonstrate that \texttt{FedDiv} achieves superior performance over state-of-the-art F-LNL methods under different label noise settings for both IID and non-IID data partitions. Source code is publicly available at https://github.com/lijichang/FLNL-FedDiv.
Authors: Ruiyuan Zhang, Jiaxiang Liu, Zexi Li, Hao Dong, Jie Fu, Chao Wu
Geometric fracture assembly presents a challenging practical task in archaeology and 3D computer vision. Previous methods have focused solely on assembling fragments based on semantic information, which has limited the quantity of objects that can be effectively assembled. Therefore, there is a need to develop a scalable framework for geometric fracture assembly without relying on semantic information. To improve the effectiveness of assembling geometric fractures without semantic information, we propose a co-creation space comprising several assemblers capable of gradually and unambiguously assembling fractures. Additionally, we introduce a novel loss function, i.e., the geometric-based collision loss, to address collision issues during the fracture assembly process and enhance the results. Our framework exhibits better performance on both PartNet and Breaking Bad datasets compared to existing state-of-the-art frameworks. Extensive experiments and quantitative comparisons demonstrate the effectiveness of our proposed framework, which features linear computational complexity, enhanced abstraction, and improved generalization. Our code is publicly available at https://github.com/Ruiyuan-Zhang/CCS.
Authors: Chaoyou Fu, Renrui Zhang, Zihan Wang, Yubo Huang, Zhengye Zhang, Longtian Qiu, Gaoxiang Ye, Yunhang Shen, Mengdan Zhang, Peixian Chen, Sirui Zhao, Shaohui Lin, Deqiang Jiang, Di Yin, Peng Gao, Ke Li, Hongsheng Li, Xing Sun
The surge of interest towards Multi-modal Large Language Models (MLLMs), e.g., GPT-4V(ision) from OpenAI, has marked a significant trend in both academia and industry. They endow Large Language Models (LLMs) with powerful capabilities in visual understanding, enabling them to tackle diverse multi-modal tasks. Very recently, Google released Gemini, its newest and most capable MLLM built from the ground up for multi-modality. In light of the superior reasoning capabilities, can Gemini challenge GPT-4V's leading position in multi-modal learning? In this paper, we present a preliminary exploration of Gemini Pro's visual understanding proficiency, which comprehensively covers four domains: fundamental perception, advanced cognition, challenging vision tasks, and various expert capacities. We compare Gemini Pro with the state-of-the-art GPT-4V to evaluate its upper limits, along with the latest open-sourced MLLM, Sphinx, which reveals the gap between manual efforts and black-box systems. The qualitative samples indicate that, while GPT-4V and Gemini showcase different answering styles and preferences, they can exhibit comparable visual reasoning capabilities, and Sphinx still trails behind them concerning domain generalizability. Specifically, GPT-4V tends to elaborate detailed explanations and intermediate steps, and Gemini prefers to output a direct and concise answer. The quantitative evaluation on the popular MME benchmark also demonstrates the potential of Gemini to be a strong challenger to GPT-4V. Our early investigation of Gemini also observes some common issues of MLLMs, indicating that there still remains a considerable distance towards artificial general intelligence. Our project for tracking the progress of MLLM is released at https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models.