Authors: Xing-Yu Ma, Shaogang Hao
As the feature size of integrated circuits continues to decrease, optical proximity correction (OPC) has emerged as a crucial resolution enhancement technology for ensuring high printability in the lithography process. Recently, level set-based inverse lithography technology (ILT) has drawn considerable attention as a promising OPC solution, showcasing its powerful pattern fidelity, especially in advanced process. However, massive computational time consumption of ILT limits its applicability to mainly correcting partial layers and hotspot regions. Deep learning (DL) methods have shown great potential in accelerating ILT. However, lack of domain knowledge of inverse lithography limits the ability of DL-based algorithms in process window (PW) enhancement and etc. In this paper, we propose an inverse lithography physics-informed deep neural level set (ILDLS) approach for mask optimization. This approach utilizes level set based-ILT as a layer within the DL framework and iteratively conducts mask prediction and correction to significantly enhance printability and PW in comparison with results from pure DL and ILT. With this approach, computation time is reduced by a few orders of magnitude versus ILT. By gearing up DL with knowledge of inverse lithography physics, ILDLS provides a new and efficient mask optimization solution.
Authors: Thomas Ruegg, Pietro Bonazzi, Andrea Ronco
Gaze estimation is a valuable technology with numerous applications in fields such as human-computer interaction, virtual reality, and medicine. This report presents the implementation of a gaze estimation system using the Sony Spresense microcontroller board and explores its performance in latency, MAC/cycle, and power consumption. The report also provides insights into the system's architecture, including the gaze estimation model used. Additionally, a demonstration of the system is presented, showcasing its functionality and performance. Our lightweight model TinyTrackerS is a mere 169Kb in size, using 85.8k parameters and runs on the Spresense platform at 3 FPS.
Authors: Hongwei Yao, Zheng Li, Kunzhe Huang, Jian Lou, Zhan Qin, Kui Ren
With the performance of deep neural networks (DNNs) remarkably improving, DNNs have been widely used in many areas. Consequently, the DNN model has become a valuable asset, and its intellectual property is safeguarded by ownership verification techniques (e.g., DNN fingerprinting). However, the feasibility of the DNN fingerprint removal attack and its potential influence remains an open problem. In this paper, we perform the first comprehensive investigation of DNN fingerprint removal attacks. Generally, the knowledge contained in a DNN model can be categorized into general semantic and fingerprint-specific knowledge. To this end, we propose a min-max bilevel optimization-based DNN fingerprint removal attack named RemovalNet, to evade model ownership verification. The lower-level optimization is designed to remove fingerprint-specific knowledge. While in the upper-level optimization, we distill the victim model's general semantic knowledge to maintain the surrogate model's performance. We conduct extensive experiments to evaluate the fidelity, effectiveness, and efficiency of the RemovalNet against four advanced defense methods on six metrics. The empirical results demonstrate that (1) the RemovalNet is effective. After our DNN fingerprint removal attack, the model distance between the target and surrogate models is x100 times higher than that of the baseline attacks, (2) the RemovalNet is efficient. It uses only 0.2% (400 samples) of the substitute dataset and 1,000 iterations to conduct our attack. Besides, compared with advanced model stealing attacks, the RemovalNet saves nearly 85% of computational resources at most, (3) the RemovalNet achieves high fidelity that the created surrogate model maintains high accuracy after the DNN fingerprint removal process. Our code is available at: https://github.com/grasses/RemovalNet.
Authors: Xiaoyu Dong, Naoto Yokoya
Understanding dark scenes based on multi-modal image data is challenging, as both the visible and auxiliary modalities provide limited semantic information for the task. Previous methods focus on fusing the two modalities but neglect the correlations among semantic classes when minimizing losses to align pixels with labels, resulting in inaccurate class predictions. To address these issues, we introduce a supervised multi-modal contrastive learning approach to increase the semantic discriminability of the learned multi-modal feature spaces by jointly performing cross-modal and intra-modal contrast under the supervision of the class correlations. The cross-modal contrast encourages same-class embeddings from across the two modalities to be closer and pushes different-class ones apart. The intra-modal contrast forces same-class or different-class embeddings within each modality to be together or apart. We validate our approach on a variety of tasks that cover diverse light conditions and image modalities. Experiments show that our approach can effectively enhance dark scene understanding based on multi-modal images with limited semantics by shaping semantic-discriminative feature spaces. Comparisons with previous methods demonstrate our state-of-the-art performance. Code and pretrained models are available at https://github.com/palmdong/SMMCL.
Authors: Duo Peng, Ping Hu, Qiuhong Ke, Jun Liu
Translating images from a source domain to a target domain for learning target models is one of the most common strategies in domain adaptive semantic segmentation (DASS). However, existing methods still struggle to preserve semantically-consistent local details between the original and translated images. In this work, we present an innovative approach that addresses this challenge by using source-domain labels as explicit guidance during image translation. Concretely, we formulate cross-domain image translation as a denoising diffusion process and utilize a novel Semantic Gradient Guidance (SGG) method to constrain the translation process, conditioning it on the pixel-wise source labels. Additionally, a Progressive Translation Learning (PTL) strategy is devised to enable the SGG method to work reliably across domains with large gaps. Extensive experiments demonstrate the superiority of our approach over state-of-the-art methods.
Authors: Usman Muhammad, Mourad Oussalah, Md Ziaul Hoque, Jorma Laaksonen
Due to the growing availability of face anti-spoofing databases, researchers are increasingly focusing on video-based methods that use hundreds to thousands of images to assess their impact on performance. However, there is no clear consensus on the exact number of frames in a video required to improve the performance of face anti-spoofing tasks. Inspired by the visual saliency theory, we present a video summarization method for face anti-spoofing tasks that aims to enhance the performance and efficiency of deep learning models by leveraging visual saliency. In particular, saliency information is extracted from the differences between the Laplacian and Wiener filter outputs of the source images, enabling identification of the most visually salient regions within each frame. Subsequently, the source images are decomposed into base and detail layers, enhancing representation of important information. The weighting maps are then computed based on the saliency information, indicating the importance of each pixel in the image. By linearly combining the base and detail layers using the weighting maps, the method fuses the source images to create a single representative image that summarizes the entire video. The key contribution of our proposed method lies in demonstrating how visual saliency can be used as a data-centric approach to improve the performance and efficiency of face presentation attack detection models. By focusing on the most salient images or regions within the images, a more representative and diverse training set can be created, potentially leading to more effective models. To validate the method's effectiveness, a simple deep learning architecture (CNN-RNN) was used, and the experimental results showcased state-of-the-art performance on five challenging face anti-spoofing datasets.
Authors: Wenxuan Zhang, Paul Janson, Kai Yi, Ivan Skorokhodov, Mohamed Elhoseiny
Learning novel concepts, remembering previous knowledge, and adapting it to future tasks occur simultaneously throughout a human's lifetime. To model such comprehensive abilities, continual zero-shot learning (CZSL) has recently been introduced. However, most existing methods overused unseen semantic information that may not be continually accessible in realistic settings. In this paper, we address the challenge of continual zero-shot learning where unseen information is not provided during training, by leveraging generative modeling. The heart of the generative-based methods is to learn quality representations from seen classes to improve the generative understanding of the unseen visual space. Motivated by this, we introduce generalization-bound tools and provide the first theoretical explanation for the benefits of generative modeling to CZSL tasks. Guided by the theoretical analysis, we then propose our learning algorithm that employs a novel semantically guided Generative Random Walk (GRW) loss. The GRW loss augments the training by continually encouraging the model to generate realistic and characterized samples to represent the unseen space. Our algorithm achieves state-of-the-art performance on AWA1, AWA2, CUB, and SUN datasets, surpassing existing CZSL methods by 3-7\%. The code has been made available here \url{https://github.com/wx-zhang/IGCZSL}
Authors: Sanjoy Chowdhury, Sreyan Ghosh, Subhrajyoti Dasgupta, Anton Ratnarajah, Utkarsh Tyagi, Dinesh Manocha
We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates the complementary visual modality to perform audio dereverberation. Given an image of the environment where the reverberated sound signal has been recorded, AdVerb employs a novel geometry-aware cross-modal transformer architecture that captures scene geometry and audio-visual cross-modal relationship to generate a complex ideal ratio mask, which, when applied to the reverberant audio predicts the clean sound. The effectiveness of our method is demonstrated through extensive quantitative and qualitative evaluations. Our approach significantly outperforms traditional audio-only and audio-visual baselines on three downstream tasks: speech enhancement, speech recognition, and speaker verification, with relative improvements in the range of 18% - 82% on the LibriSpeech test-clean set. We also achieve highly satisfactory RT60 error scores on the AVSpeech dataset.
Authors: Rafael Henrique Vareto, Manuel Günther, William Robson Schwartz
Open-set face recognition refers to a scenario in which biometric systems have incomplete knowledge of all existing subjects. Therefore, they are expected to prevent face samples of unregistered subjects from being identified as previously enrolled identities. This watchlist context adds an arduous requirement that calls for the dismissal of irrelevant faces by focusing mainly on subjects of interest. As a response, this work introduces a novel method that associates an ensemble of compact neural networks with a margin-based cost function that explores additional samples. Supplementary negative samples can be obtained from external databases or synthetically built at the representation level in training time with a new mix-up feature augmentation approach. Deep neural networks pre-trained on large face datasets serve as the preliminary feature extraction module. We carry out experiments on well-known LFW and IJB-C datasets where results show that the approach is able to boost closed and open-set identification rates.
Authors: Deblina Bhattacharjee, Sabine Süsstrunk, Mathieu Salzmann
We introduce the first multitasking vision transformer adapters that learn generalizable task affinities which can be applied to novel tasks and domains. Integrated into an off-the-shelf vision transformer backbone, our adapters can simultaneously solve multiple dense vision tasks in a parameter-efficient manner, unlike existing multitasking transformers that are parametrically expensive. In contrast to concurrent methods, we do not require retraining or fine-tuning whenever a new task or domain is added. We introduce a task-adapted attention mechanism within our adapter framework that combines gradient-based task similarities with attention-based ones. The learned task affinities generalize to the following settings: zero-shot task transfer, unsupervised domain adaptation, and generalization without fine-tuning to novel domains. We demonstrate that our approach outperforms not only the existing convolutional neural network-based multitasking methods but also the vision transformer-based ones. Our project page is at \url{https://ivrl.github.io/VTAGML}.
Authors: Yufeng Yin, Di Chang, Guoxian Song, Shen Sang, Tiancheng Zhi, Jing Liu, Linjie Luo, Mohammad Soleymani
Automatic detection of facial Action Units (AUs) allows for objective facial expression analysis. Due to the high cost of AU labeling and the limited size of existing benchmarks, previous AU detection methods tend to overfit the dataset, resulting in a significant performance loss when evaluated across corpora. To address this problem, we propose FG-Net for generalizable facial action unit detection. Specifically, FG-Net extracts feature maps from a StyleGAN2 model pre-trained on a large and diverse face image dataset. Then, these features are used to detect AUs with a Pyramid CNN Interpreter, making the training efficient and capturing essential local features. The proposed FG-Net achieves a strong generalization ability for heatmap-based AU detection thanks to the generalizable and semantic-rich features extracted from the pre-trained generative model. Extensive experiments are conducted to evaluate within- and cross-corpus AU detection with the widely-used DISFA and BP4D datasets. Compared with the state-of-the-art, the proposed method achieves superior cross-domain performance while maintaining competitive within-domain performance. In addition, FG-Net is data-efficient and achieves competitive performance even when trained on 1000 samples. Our code will be released at \url{https://github.com/ihp-lab/FG-Net}
Authors: Manuele Barraco, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
Image captioning, like many tasks involving vision and language, currently relies on Transformer-based architectures for extracting the semantics in an image and translating it into linguistically coherent descriptions. Although successful, the attention operator only considers a weighted summation of projections of the current input sample, therefore ignoring the relevant semantic information which can come from the joint observation of other samples. In this paper, we devise a network which can perform attention over activations obtained while processing other training samples, through a prototypical memory model. Our memory models the distribution of past keys and values through the definition of prototype vectors which are both discriminative and compact. Experimentally, we assess the performance of the proposed model on the COCO dataset, in comparison with carefully designed baselines and state-of-the-art approaches, and by investigating the role of each of the proposed components. We demonstrate that our proposal can increase the performance of an encoder-decoder Transformer by 3.7 CIDEr points both when training in cross-entropy only and when fine-tuning with self-critical sequence training. Source code and trained models are available at: https://github.com/aimagelab/PMA-Net.
Authors: Roy Hirsch, Mathilde Caron, Regev Cohen, Amir Livne, Ron Shapiro, Tomer Golany, Roman Goldenberg, Daniel Freedman, Ehud Rivlin
Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly specialized expertise. Yet, there are many healthcare domains for which SSL has not been extensively explored. One such domain is endoscopy, minimally invasive procedures which are commonly used to detect and treat infections, chronic inflammatory diseases or cancer. In this work, we study the use of a leading SSL framework, namely Masked Siamese Networks (MSNs), for endoscopic video analysis such as colonoscopy and laparoscopy. To fully exploit the power of SSL, we create sizable unlabeled endoscopic video datasets for training MSNs. These strong image representations serve as a foundation for secondary training with limited annotated datasets, resulting in state-of-the-art performance in endoscopic benchmarks like surgical phase recognition during laparoscopy and colonoscopic polyp characterization. Additionally, we achieve a 50% reduction in annotated data size without sacrificing performance. Thus, our work provides evidence that SSL can dramatically reduce the need of annotated data in endoscopy.
Authors: Matthew Martel, Jackson Wagner
Generating realistic audio effects for movies and other media is a challenging task that is accomplished today primarily through physical techniques known as Foley art. Foley artists create sounds with common objects (e.g., boxing gloves, broken glass) in time with video as it is playing to generate captivating audio tracks. In this work, we aim to develop a deep-learning based framework that does much the same - observes video in it's natural sequence and generates realistic audio to accompany it. Notably, we have reason to believe this is achievable due to advancements in realistic audio generation techniques conditioned on other inputs (e.g., Wavenet conditioned on text). We explore several different model architectures to accomplish this task that process both previously-generated audio and video context. These include deep-fusion CNN, dilated Wavenet CNN with visual context, and transformer-based architectures. We find that the transformer-based architecture yields the most promising results, matching low-frequencies to visual patterns effectively, but failing to generate more nuanced waveforms.
Authors: Neha Gianchandani, Mahsa Dibaji, Mariana Bento, Ethan MacDonald, Roberto Souza
Deep learning models have achieved state-of-the-art results in estimating brain age, which is an important brain health biomarker, from magnetic resonance (MR) images. However, most of these models only provide a global age prediction, and rely on techniques, such as saliency maps to interpret their results. These saliency maps highlight regions in the input image that were significant for the model's predictions, but they are hard to be interpreted, and saliency map values are not directly comparable across different samples. In this work, we reframe the age prediction problem from MR images to an image-to-image regression problem where we estimate the brain age for each brain voxel in MR images. We compare voxel-wise age prediction models against global age prediction models and their corresponding saliency maps. The results indicate that voxel-wise age prediction models are more interpretable, since they provide spatial information about the brain aging process, and they benefit from being quantitative.
Authors: Bowen Shi
Sign language, which conveys meaning through gestures, is the chief means of communication among deaf people. Recognizing sign language in natural settings presents significant challenges due to factors such as lighting, background clutter, and variations in signer characteristics. In this thesis, I study automatic sign language processing in the wild, using signing videos collected from the Internet. This thesis contributes new datasets, tasks, and methods. Most chapters of this thesis address tasks related to fingerspelling, an important component of sign language and yet has not been studied widely by prior work. I present three new large-scale ASL datasets in the wild: ChicagoFSWild, ChicagoFSWild+, and OpenASL. Using ChicagoFSWild and ChicagoFSWild+, I address fingerspelling recognition, which consists of transcribing fingerspelling sequences into text. I propose an end-to-end approach based on iterative attention that allows recognition from a raw video without explicit hand detection. I further show that using a Conformer-based network jointly modeling handshape and mouthing can bring performance close to that of humans. Next, I propose two tasks for building real-world fingerspelling-based applications: fingerspelling detection and search. For fingerspelling detection, I introduce a suite of evaluation metrics and a new detection model via multi-task training. To address the problem of searching for fingerspelled keywords in raw sign language videos, we propose a novel method that jointly localizes and matches fingerspelling segments to text. Finally, I will describe a benchmark for large-vocabulary open-domain sign language translation based on OpenASL. To address the challenges of sign language translation in realistic settings, we propose a set of techniques including sign search as a pretext task for pre-training and fusion of mouthing and handshape features.
Authors: Xiao Li, Pan He, Aotian Wu, Sanjay Ranka, Anand Rangarajan
We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introduce drastically stronger augmentation by establishing spatiotemporal correspondences across multiple frames. We dovetail clustering and pseudo-label learning in this work. Essentially, we alternate between clustering points into semantic groups and optimizing models using point-wise pseudo-spatiotemporal labels with a simple learning objective. Therefore, our method can learn discriminative features in an unsupervised learning fashion. We show promising segmentation performance on Semantic-KITTI, SemanticPOSS, and FLORIDA benchmark datasets covering scenarios in autonomous vehicle and intersection infrastructure, which is competitive when compared against many existing fully supervised learning methods. This general framework can lead to a unified representation learning approach for LiDAR point clouds incorporating domain knowledge.
Authors: Sushrut Thorat, Adrien Doerig, Tim C. Kietzmann
Recurrent neural networks (RNNs) have yielded promising results for both recognizing objects in challenging conditions and modeling aspects of primate vision. However, the representational dynamics of recurrent computations remain poorly understood, especially in large-scale visual models. Here, we studied such dynamics in RNNs trained for object classification on MiniEcoset, a novel subset of ecoset. We report two main insights. First, upon inference, representations continued to evolve after correct classification, suggesting a lack of the notion of being ``done with classification''. Second, focusing on ``readout zones'' as a way to characterize the activation trajectories, we observe that misclassified representations exhibit activation patterns with lower L2 norm, and are positioned more peripherally in the readout zones. Such arrangements help the misclassified representations move into the correct zones as time progresses. Our findings generalize to networks with lateral and top-down connections, and include both additive and multiplicative interactions with the bottom-up sweep. The results therefore contribute to a general understanding of RNN dynamics in naturalistic tasks. We hope that the analysis framework will aid future investigations of other types of RNNs, including understanding of representational dynamics in primate vision.
Authors: Tinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal
We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that operate independently of how the model was generated. The proposed defense is built upon a novel reverse engineering approach that can directly extract backdoor functionality of a given backdoored model to a backdoor expert model. The approach is straightforward -- finetuning the backdoored model over a small set of intentionally mislabeled clean samples, such that it unlearns the normal functionality while still preserving the backdoor functionality, and thus resulting in a model (dubbed a backdoor expert model) that can only recognize backdoor inputs. Based on the extracted backdoor expert model, we show the feasibility of devising highly accurate backdoor input detectors that filter out the backdoor inputs during model inference. Further augmented by an ensemble strategy with a finetuned auxiliary model, our defense, BaDExpert (Backdoor Input Detection with Backdoor Expert), effectively mitigates 16 SOTA backdoor attacks while minimally impacting clean utility. The effectiveness of BaDExpert has been verified on multiple datasets (CIFAR10, GTSRB and ImageNet) across various model architectures (ResNet, VGG, MobileNetV2 and Vision Transformer).
Convolutional neural networks (CNNs) have been widely used to build deep learning models for medical image registration, but manually designed network architectures are not necessarily optimal. This paper presents a hierarchical NAS framework (HNAS-Reg), consisting of both convolutional operation search and network topology search, to identify the optimal network architecture for deformable medical image registration. To mitigate the computational overhead and memory constraints, a partial channel strategy is utilized without losing optimization quality. Experiments on three datasets, consisting of 636 T1-weighted magnetic resonance images (MRIs), have demonstrated that the proposal method can build a deep learning model with improved image registration accuracy and reduced model size, compared with state-of-the-art image registration approaches, including one representative traditional approach and two unsupervised learning-based approaches.
Authors: Xueqi Guo, Luyao Shi, Xiongchao Chen, Bo Zhou, Qiong Liu, Huidong Xie, Yi-Hwa Liu, Richard Palyo, Edward J. Miller, Albert J. Sinusas, Bruce Spottiswoode, Chi Liu, Nicha C. Dvornek
The rapid tracer kinetics of rubidium-82 ($^{82}$Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the early frames where conventional intensity-based image registration techniques are not applicable. Alternatively, a promising approach utilizes generative methods to handle the tracer distribution changes to assist existing registration methods. To improve frame-wise registration and parametric quantification, we propose a Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) to transform the early frames into the late reference frame using an all-to-one mapping. Specifically, a feature-wise linear modulation layer encodes channel-wise parameters generated from temporal tracer kinetics information, and rough cardiac segmentations with local shifts serve as the anatomical information. We validated our proposed method on a clinical $^{82}$Rb PET dataset and found that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, motion estimation accuracy and clinical myocardial blood flow (MBF) quantification were improved compared to using the original frames. Our code is published at https://github.com/gxq1998/TAI-GAN.
Authors: Mona Ahmadian, Frank Guerin, Andrew Gilbert
Self-supervised learning (SSL) techniques have recently produced outstanding results in learning visual representations from unlabeled videos. Despite the importance of motion in supervised learning techniques for action recognition, SSL methods often do not explicitly consider motion information in videos. To address this issue, we propose MOFO (MOtion FOcused), a novel SSL method for focusing representation learning on the motion area of a video, for action recognition. MOFO automatically detects motion areas in videos and uses these to guide the self-supervision task. We use a masked autoencoder which randomly masks out a high proportion of the input sequence; we force a specified percentage of the inside of the motion area to be masked and the remainder from outside. We further incorporate motion information into the finetuning step to emphasise motion in the downstream task. We demonstrate that our motion-focused innovations can significantly boost the performance of the currently leading SSL method (VideoMAE) for action recognition. Our method improves the recent self-supervised Vision Transformer (ViT), VideoMAE, by achieving +2.6%, +2.1%, +1.3% accuracy on Epic-Kitchens verb, noun and action classification, respectively, and +4.7% accuracy on Something-Something V2 action classification. Our proposed approach significantly improves the performance of the current SSL method for action recognition, indicating the importance of explicitly encoding motion in SSL.
Authors: Wenzhao Li, Tianhao Wu, Fangcheng Zhong, Cengiz Oztireli
The radiance fields style transfer is an emerging field that has recently gained popularity as a means of 3D scene stylization, thanks to the outstanding performance of neural radiance fields in 3D reconstruction and view synthesis. We highlight a research gap in radiance fields style transfer, the lack of sufficient perceptual controllability, motivated by the existing concept in the 2D image style transfer. In this paper, we present ARF-Plus, a 3D neural style transfer framework offering manageable control over perceptual factors, to systematically explore the perceptual controllability in 3D scene stylization. Four distinct types of controls - color preservation control, (style pattern) scale control, spatial (selective stylization area) control, and depth enhancement control - are proposed and integrated into this framework. Results from real-world datasets, both quantitative and qualitative, show that the four types of controls in our ARF-Plus framework successfully accomplish their corresponding perceptual controls when stylizing 3D scenes. These techniques work well for individual style inputs as well as for the simultaneous application of multiple styles within a scene. This unlocks a realm of limitless possibilities, allowing customized modifications of stylization effects and flexible merging of the strengths of different styles, ultimately enabling the creation of novel and eye-catching stylistic effects on 3D scenes.
Authors: Luke W. Sagers, James A. Diao, Luke Melas-Kyriazi, Matthew Groh, Pranav Rajpurkar, Adewole S. Adamson, Veronica Rotemberg, Roxana Daneshjou, Arjun K. Manrai
While hundreds of artificial intelligence (AI) algorithms are now approved or cleared by the US Food and Drugs Administration (FDA), many studies have shown inconsistent generalization or latent bias, particularly for underrepresented populations. Some have proposed that generative AI could reduce the need for real data, but its utility in model development remains unclear. Skin disease serves as a useful case study in synthetic image generation due to the diversity of disease appearance, particularly across the protected attribute of skin tone. Here we show that latent diffusion models can scalably generate images of skin disease and that augmenting model training with these data improves performance in data-limited settings. These performance gains saturate at synthetic-to-real image ratios above 10:1 and are substantially smaller than the gains obtained from adding real images. As part of our analysis, we generate and analyze a new dataset of 458,920 synthetic images produced using several generation strategies. Our results suggest that synthetic data could serve as a force-multiplier for model development, but the collection of diverse real-world data remains the most important step to improve medical AI algorithms.
Authors: Wenxuan Zhang, Paul Janson, Rahaf Aljundi, Mohamed Elhoseiny
Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies in updating foundation models to accommodate novel information while retaining their original ability. In this paper, we present a novel approach to achieving continual model updates by effecting localized modifications to a small subset of parameters. Guided by insights gleaned from prior analyses of foundational models, we first localize a specific layer for model refinement and then introduce an importance scoring mechanism designed to update only the most crucial weights. Our method is exhaustively evaluated on foundational vision-language models, measuring its efficacy in both learning new information and preserving pre-established knowledge across a diverse spectrum of continual learning tasks, including Aircraft, Birdsnap CIFAR-100, CUB, Cars, and GTSRB. The results show that our method improves the existing continual learning methods by 0.5\% - 10\% on average, and reduces the loss of pre-trained knowledge from around 5\% to 0.97\%. Comprehensive ablation studies substantiate our method design, shedding light on the contributions of each component to controllably learning new knowledge and mitigating the forgetting of pre-trained knowledge.
Authors: Jueqi Wang, Jacob Levman, Walter Hugo Lopez Pinaya, Petru-Daniel Tudosiu, M. Jorge Cardoso, Razvan Marinescu
High-resolution (HR) MRI scans obtained from research-grade medical centers provide precise information about imaged tissues. However, routine clinical MRI scans are typically in low-resolution (LR) and vary greatly in contrast and spatial resolution due to the adjustments of the scanning parameters to the local needs of the medical center. End-to-end deep learning methods for MRI super-resolution (SR) have been proposed, but they require re-training each time there is a shift in the input distribution. To address this issue, we propose a novel approach that leverages a state-of-the-art 3D brain generative model, the latent diffusion model (LDM) trained on UK BioBank, to increase the resolution of clinical MRI scans. The LDM acts as a generative prior, which has the ability to capture the prior distribution of 3D T1-weighted brain MRI. Based on the architecture of the brain LDM, we find that different methods are suitable for different settings of MRI SR, and thus propose two novel strategies: 1) for SR with more sparsity, we invert through both the decoder of the LDM and also through a deterministic Denoising Diffusion Implicit Models (DDIM), an approach we will call InverseSR(LDM); 2) for SR with less sparsity, we invert only through the LDM decoder, an approach we will call InverseSR(Decoder). These two approaches search different latent spaces in the LDM model to find the optimal latent code to map the given LR MRI into HR. The training process of the generative model is independent of the MRI under-sampling process, ensuring the generalization of our method to many MRI SR problems with different input measurements. We validate our method on over 100 brain T1w MRIs from the IXI dataset. Our method can demonstrate that powerful priors given by LDM can be used for MRI reconstruction.
Authors: Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, Mar Gonzalez-Franco
Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers. Specifically, we introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. The proposed method does not require any training or language dependency to extract quality segmentation for any images. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU.
Authors: Melissa Dell, Jacob Carlson, Tom Bryan, Emily Silcock, Abhishek Arora, Zejiang Shen, Luca D'Amico-Wong, Quan Le, Pablo Querubin, Leander Heldring
Existing full text datasets of U.S. public domain newspapers do not recognize the often complex layouts of newspaper scans, and as a result the digitized content scrambles texts from articles, headlines, captions, advertisements, and other layout regions. OCR quality can also be low. This study develops a novel, deep learning pipeline for extracting full article texts from newspaper images and applies it to the nearly 20 million scans in Library of Congress's public domain Chronicling America collection. The pipeline includes layout detection, legibility classification, custom OCR, and association of article texts spanning multiple bounding boxes. To achieve high scalability, it is built with efficient architectures designed for mobile phones. The resulting American Stories dataset provides high quality data that could be used for pre-training a large language model to achieve better understanding of historical English and historical world knowledge. The dataset could also be added to the external database of a retrieval-augmented language model to make historical information - ranging from interpretations of political events to minutiae about the lives of people's ancestors - more widely accessible. Furthermore, structured article texts facilitate using transformer-based methods for popular social science applications like topic classification, detection of reproduced content, and news story clustering. Finally, American Stories provides a massive silver quality dataset for innovating multimodal layout analysis models and other multimodal applications.
Authors: Xiangyu Chen, Ruiwen Zhen, Shuai Li, Xiaotian Li, Guanghui Wang
Image restoration aims to restore high-quality images from degraded counterparts and has seen significant advancements through deep learning techniques. The technique has been widely applied to mobile devices for tasks such as mobile photography. Given the resource limitations on mobile devices, such as memory constraints and runtime requirements, the efficiency of models during deployment becomes paramount. Nevertheless, most previous works have primarily concentrated on analyzing the efficiency of single modules and improving them individually. This paper examines the efficiency across different layers. We propose a roadmap that can be applied to further accelerate image restoration models prior to deployment while simultaneously increasing PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index). The roadmap first increases the model capacity by adding more parameters to partial convolutions on FLOPs non-sensitive layers. Then, it applies partial depthwise convolution coupled with decoupling upsampling/downsampling layers to accelerate the model speed. Extensive experiments demonstrate that our approach decreases runtime by up to 13% and reduces the number of parameters by up to 23%, while increasing PSNR and SSIM on several image restoration datasets. Source Code of our method is available at \href{https://github.com/xiangyu8/MOFA}{https://github.com/xiangyu8/MOFA}.
Authors: Yuqi Fang, Jinjian Wu, Qianqian Wang, Shijun Qiu, Andrea Bozoki, Huaicheng Yan, Mingxia Liu
Resting-state functional MRI (rs-fMRI) is increasingly employed in multi-site research to aid neurological disorder analysis. Existing studies usually suffer from significant cross-site/domain data heterogeneity caused by site effects such as differences in scanners/protocols. Many methods have been proposed to reduce fMRI heterogeneity between source and target domains, heavily relying on the availability of source data. But acquiring source data is challenging due to privacy concerns and/or data storage burdens in multi-site studies. To this end, we design a source-free collaborative domain adaptation (SCDA) framework for fMRI analysis, where only a pretrained source model and unlabeled target data are accessible. Specifically, a multi-perspective feature enrichment method (MFE) is developed for target fMRI analysis, consisting of multiple collaborative branches to dynamically capture fMRI features of unlabeled target data from multiple views. Each branch has a data-feeding module, a spatiotemporal feature encoder, and a class predictor. A mutual-consistency constraint is designed to encourage pair-wise consistency of latent features of the same input generated from these branches for robust representation learning. To facilitate efficient cross-domain knowledge transfer without source data, we initialize MFE using parameters of a pretrained source model. We also introduce an unsupervised pretraining strategy using 3,806 unlabeled fMRIs from three large-scale auxiliary databases, aiming to obtain a general feature encoder. Experimental results on three public datasets and one private dataset demonstrate the efficacy of our method in cross-scanner and cross-study prediction tasks. The model pretrained on large-scale rs-fMRI data has been released to the public.
Authors: Chang Li, Qian Huang, Yingchi Mao
Graph Convolutional Networks (GCNs) have been widely used in skeleton-based human action recognition. In GCN-based methods, the spatio-temporal graph is fundamental for capturing motion patterns. However, existing approaches ignore the physical dependency and synchronized spatio-temporal correlations between joints, which limits the representation capability of GCNs. To solve these problems, we construct the directed diffusion graph for action modeling and introduce the activity partition strategy to optimize the weight sharing mechanism of graph convolution kernels. In addition, we present the spatio-temporal synchronization encoder to embed synchronized spatio-temporal semantics. Finally, we propose Directed Diffusion Graph Convolutional Network (DD-GCN) for action recognition, and the experiments on three public datasets: NTU-RGB+D, NTU-RGB+D 120, and NW-UCLA, demonstrate the state-of-the-art performance of our method.
Authors: Chenyue Jiao, Chongke Bi, Lu Yang
Large-scale numerical simulations are capable of generating data up to terabytes or even petabytes. As a promising method of data reduction, super-resolution (SR) has been widely studied in the scientific visualization community. However, most of them are based on deep convolutional neural networks (CNNs) or generative adversarial networks (GANs) and the scale factor needs to be determined before constructing the network. As a result, a single training session only supports a fixed factor and has poor generalization ability. To address these problems, this paper proposes a Feature-Enhanced Implicit Neural Representation (FFEINR) for spatio-temporal super-resolution of flow field data. It can take full advantage of the implicit neural representation in terms of model structure and sampling resolution. The neural representation is based on a fully connected network with periodic activation functions, which enables us to obtain lightweight models. The learned continuous representation can decode the low-resolution flow field input data to arbitrary spatial and temporal resolutions, allowing for flexible upsampling. The training process of FFEINR is facilitated by introducing feature enhancements for the input layer, which complements the contextual information of the flow field.To demonstrate the effectiveness of the proposed method, a series of experiments are conducted on different datasets by setting different hyperparameters. The results show that FFEINR achieves significantly better results than the trilinear interpolation method.
Authors: Yuan Yuan, Yang Zhan, Zhitong Xiong
Vision-and-language pre-training (VLP) models have experienced a surge in popularity recently. By fine-tuning them on specific datasets, significant performance improvements have been observed in various tasks. However, full fine-tuning of VLP models not only consumes a significant amount of computational resources but also has a significant environmental impact. Moreover, as remote sensing (RS) data is constantly being updated, full fine-tuning may not be practical for real-world applications. To address this issue, in this work, we investigate the parameter-efficient transfer learning (PETL) method to effectively and efficiently transfer visual-language knowledge from the natural domain to the RS domain on the image-text retrieval task. To this end, we make the following contributions. 1) We construct a novel and sophisticated PETL framework for the RS image-text retrieval (RSITR) task, which includes the pretrained CLIP model, a multimodal remote sensing adapter, and a hybrid multi-modal contrastive (HMMC) learning objective; 2) To deal with the problem of high intra-modal similarity in RS data, we design a simple yet effective HMMC loss; 3) We provide comprehensive empirical studies for PETL-based RS image-text retrieval. Our results demonstrate that the proposed method is promising and of great potential for practical applications. 4) We benchmark extensive state-of-the-art PETL methods on the RSITR task. Our proposed model only contains 0.16M training parameters, which can achieve a parameter reduction of 98.9% compared to full fine-tuning, resulting in substantial savings in training costs. Our retrieval performance exceeds traditional methods by 7-13% and achieves comparable or better performance than full fine-tuning. This work can provide new ideas and useful insights for RS vision-language tasks.
Authors: Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov, Ke Li, Ming-Ming Cheng
Class Incremental Learning (CIL) aims to sequentially learn new classes while avoiding catastrophic forgetting of previous knowledge. We propose to use Masked Autoencoders (MAEs) as efficient learners for CIL. MAEs were originally designed to learn useful representations through reconstructive unsupervised learning, and they can be easily integrated with a supervised loss for classification. Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL. We also propose a bilateral MAE framework to learn from image-level and embedding-level fusion, which produces better-quality reconstructed images and more stable representations. Our experiments confirm that our approach performs better than the state-of-the-art on CIFAR-100, ImageNet-Subset, and ImageNet-Full. The code is available at https://github.com/scok30/MAE-CIL .
Authors: Wenqi Liang, Gan Sun, Chenxi Liu, Jiahua Dong, Kangru Wang
3D object detection has achieved significant performance in many fields, e.g., robotics system, autonomous driving, and augmented reality. However, most existing methods could cause catastrophic forgetting of old classes when performing on the class-incremental scenarios. Meanwhile, the current class-incremental 3D object detection methods neglect the relationships between the object localization information and category semantic information and assume all the knowledge of old model is reliable. To address the above challenge, we present a novel Incremental 3D Object Detection framework with the guidance of prompting, i.e., I3DOD. Specifically, we propose a task-shared prompts mechanism to learn the matching relationships between the object localization information and category semantic information. After training on the current task, these prompts will be stored in our prompt pool, and perform the relationship of old classes in the next task. Moreover, we design a reliable distillation strategy to transfer knowledge from two aspects: a reliable dynamic distillation is developed to filter out the negative knowledge and transfer the reliable 3D knowledge to new detection model; the relation feature is proposed to capture the responses relation in feature space and protect plasticity of the model when learning novel 3D classes. To the end, we conduct comprehensive experiments on two benchmark datasets and our method outperforms the state-of-the-art object detection methods by 0.6% - 2.7% in terms of mAP@0.25.
Authors: Siming Fu, Xiaoxuan He, Xinpeng Ding, Yuchen Cao, Hualiang Wang
Recently, large-scale pre-trained vision-language models have presented benefits for alleviating class imbalance in long-tailed recognition. However, the long-tailed data distribution can corrupt the representation space, where the distance between head and tail categories is much larger than the distance between two tail categories. This uneven feature space distribution causes the model to exhibit unclear and inseparable decision boundaries on the uniformly distributed test set, which lowers its performance. To address these challenges, we propose the uniformly category prototype-guided vision-language framework to effectively mitigate feature space bias caused by data imbalance. Especially, we generate a set of category prototypes uniformly distributed on a hypersphere. Category prototype-guided mechanism for image-text matching makes the features of different classes converge to these distinct and uniformly distributed category prototypes, which maintain a uniform distribution in the feature space, and improve class boundaries. Additionally, our proposed irrelevant text filtering and attribute enhancement module allows the model to ignore irrelevant noisy text and focus more on key attribute information, thereby enhancing the robustness of our framework. In the image recognition fine-tuning stage, to address the positive bias problem of the learnable classifier, we design the class feature prototype-guided classifier, which compensates for the performance of tail classes while maintaining the performance of head classes. Our method outperforms previous vision-language methods for long-tailed learning work by a large margin and achieves state-of-the-art performance.
Authors: Shengchao Yuan, Yishun Dou, Rui Shi, Bingbing Ni, Zhong Zheng
Meshes are widely used in 3D computer vision and graphics, but their irregular topology poses challenges in applying them to existing neural network architectures. Recent advances in mesh neural networks turn to remeshing and push the boundary of pioneer methods that solely take the raw meshes as input. Although the remeshing offers a regular topology that significantly facilitates the design of mesh network architectures, features extracted from such remeshed proxies may struggle to retain the underlying geometry faithfully, limiting the subsequent neural network's capacity. To address this issue, we propose SieveNet, a novel paradigm that takes into account both the regular topology and the exact geometry. Specifically, this method utilizes structured mesh topology from remeshing and accurate geometric information from distortion-aware point sampling on the surface of the original mesh. Furthermore, our method eliminates the need for hand-crafted feature engineering and can leverage off-the-shelf network architectures such as the vision transformer. Comprehensive experimental results on classification and segmentation tasks well demonstrate the effectiveness and superiority of our method.
Authors: Gihun Lee, Minchan Jeong, Sangmook Kim, Jaehoon Oh, Se-Young Yun
Federated Learning (FL) aggregates locally trained models from individual clients to construct a global model. While FL enables learning a model with data privacy, it often suffers from significant performance degradation when client data distributions are heterogeneous. Many previous FL algorithms have addressed this issue by introducing various proximal restrictions. These restrictions aim to encourage global alignment by constraining the deviation of local learning from the global objective. However, they inherently limit local learning by interfering with the original local objectives. Recently, an alternative approach has emerged to improve local learning generality. By obtaining local models within a smooth loss landscape, this approach mitigates conflicts among different local objectives of the clients. Yet, it does not ensure stable global alignment, as local learning does not take the global objective into account. In this study, we propose Federated Stability on Learning (FedSoL), which combines both the concepts of global alignment and local generality. In FedSoL, the local learning seeks a parameter region robust against proximal perturbations. This strategy introduces an implicit proximal restriction effect in local learning while maintaining the original local objective for parameter update. Our experiments show that FedSoL consistently achieves state-of-the-art performance on various setups.
Authors: Zikun Zhou, Shukun Wu, Guoqing Zhu, Hongpeng Wang, Zhenyu He
RGB-Thermal (RGB-T) semantic segmentation has shown great potential in handling low-light conditions where RGB-based segmentation is hindered by poor RGB imaging quality. The key to RGB-T semantic segmentation is to effectively leverage the complementarity nature of RGB and thermal images. Most existing algorithms fuse RGB and thermal information in feature space via concatenation, element-wise summation, or attention operations in either unidirectional enhancement or bidirectional aggregation manners. However, they usually overlook the modality gap between RGB and thermal images during feature fusion, resulting in modality-specific information from one modality contaminating the other. In this paper, we propose a Channel and Spatial Relation-Propagation Network (CSRPNet) for RGB-T semantic segmentation, which propagates only modality-shared information across different modalities and alleviates the modality-specific information contamination issue. Our CSRPNet first performs relation-propagation in channel and spatial dimensions to capture the modality-shared features from the RGB and thermal features. CSRPNet then aggregates the modality-shared features captured from one modality with the input feature from the other modality to enhance the input feature without the contamination issue. While being fused together, the enhanced RGB and thermal features will be also fed into the subsequent RGB or thermal feature extraction layers for interactive feature fusion, respectively. We also introduce a dual-path cascaded feature refinement module that aggregates multi-layer features to produce two refined features for semantic and boundary prediction. Extensive experimental results demonstrate that CSRPNet performs favorably against state-of-the-art algorithms.
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: Zichao Dong, Weikun Zhang, Xufeng Huang, Hang Ji, Xin Zhan, Junbo Chen
Human robot interaction is an exciting task, which aimed to guide robots following instructions from human. Since huge gap lies between human natural language and machine codes, end to end human robot interaction models is fair challenging. Further, visual information receiving from sensors of robot is also a hard language for robot to perceive. In this work, HuBo-VLM is proposed to tackle perception tasks associated with human robot interaction including object detection and visual grounding by a unified transformer based vision language model. Extensive experiments on the Talk2Car benchmark demonstrate the effectiveness of our approach. Code would be publicly available in https://github.com/dzcgaara/HuBo-VLM.
Authors: Yuanshen Guan, Ruikang Xu, Mingde Yao, Lizhi Wang, Zhiwei Xiong
Image fusion aims to generate a high-quality image from multiple images captured under varying conditions. The key problem of this task is to preserve complementary information while filtering out irrelevant information for the fused result. However, existing methods address this problem by leveraging static convolutional neural networks (CNNs), suffering two inherent limitations during feature extraction, i.e., being unable to handle spatial-variant contents and lacking guidance from multiple inputs. In this paper, we propose a novel mutual-guided dynamic network (MGDN) for image fusion, which allows for effective information utilization across different locations and inputs. Specifically, we design a mutual-guided dynamic filter (MGDF) for adaptive feature extraction, composed of a mutual-guided cross-attention (MGCA) module and a dynamic filter predictor, where the former incorporates additional guidance from different inputs and the latter generates spatial-variant kernels for different locations. In addition, we introduce a parallel feature fusion (PFF) module to effectively fuse local and global information of the extracted features. To further reduce the redundancy among the extracted features while simultaneously preserving their shared structural information, we devise a novel loss function that combines the minimization of normalized mutual information (NMI) with an estimated gradient mask. Experimental results on five benchmark datasets demonstrate that our proposed method outperforms existing methods on four image fusion tasks. The code and model are publicly available at: https://github.com/Guanys-dar/MGDN.
Authors: Rafael Zimmer, Marcos Sobral, Helio Azevedo
This paper focuses on the use of emotion recognition techniques to assist psychologists in performing children's therapy through remotely robot operated sessions. In the field of psychology, the use of agent-mediated therapy is growing increasingly given recent advances in robotics and computer science. Specifically, the use of Embodied Conversational Agents (ECA) as an intermediary tool can help professionals connect with children who face social challenges such as Attention Deficit Hyperactivity Disorder (ADHD), Autism Spectrum Disorder (ASD) or even who are physically unavailable due to being in regions of armed conflict, natural disasters, or other circumstances. In this context, emotion recognition represents an important feedback for the psychotherapist. In this article, we initially present the result of a bibliographical research associated with emotion recognition in children. This research revealed an initial overview on algorithms and datasets widely used by the community. Then, based on the analysis carried out on the results of the bibliographical research, we used the technique of dense optical flow features to improve the ability of identifying emotions in children in uncontrolled environments. From the output of a hybrid model of Convolutional Neural Network, two intermediary features are fused before being processed by a final classifier. The proposed architecture was called HybridCNNFusion. Finally, we present the initial results achieved in the recognition of children's emotions using a dataset of Brazilian children.
Authors: Teli Ma, Mengmeng Wang, Jimin Xiao, Huifeng Wu, Yong Liu
Siamese network has been a de facto benchmark framework for 3D LiDAR object tracking with a shared-parametric encoder extracting features from template and search region, respectively. This paradigm relies heavily on an additional matching network to model the cross-correlation/similarity of the template and search region. In this paper, we forsake the conventional Siamese paradigm and propose a novel single-branch framework, SyncTrack, synchronizing the feature extracting and matching to avoid forwarding encoder twice for template and search region as well as introducing extra parameters of matching network. The synchronization mechanism is based on the dynamic affinity of the Transformer, and an in-depth analysis of the relevance is provided theoretically. Moreover, based on the synchronization, we introduce a novel Attentive Points-Sampling strategy into the Transformer layers (APST), replacing the random/Farthest Points Sampling (FPS) method with sampling under the supervision of attentive relations between the template and search region. It implies connecting point-wise sampling with the feature learning, beneficial to aggregating more distinctive and geometric features for tracking with sparse points. Extensive experiments on two benchmark datasets (KITTI and NuScenes) show that SyncTrack achieves state-of-the-art performance in real-time tracking.
Authors: Jie Hong, Zeeshan Hayder, Junlin Han, Pengfei Fang, Mehrtash Harandi, Lars Petersson
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training. An analysis of the audio-visual data reveals a large degree of hyperbolicity, indicating the potential benefit of using a hyperbolic transformation to achieve curvature-aware geometric learning, with the aim of exploring more complex hierarchical data structures for this task. The proposed approach employs a novel loss function that incorporates cross-modality alignment between video and audio features in the hyperbolic space. Additionally, we explore the use of multiple adaptive curvatures for hyperbolic projections. The experimental results on this very challenging task demonstrate that our proposed hyperbolic approach for zero-shot learning outperforms the SOTA method on three datasets: VGGSound-GZSL, UCF-GZSL, and ActivityNet-GZSL achieving a harmonic mean (HM) improvement of around 3.0%, 7.0%, and 5.3%, respectively.
Authors: Dakshit Agrawal, Jiajie Xu, Siva Karthik Mustikovela, Ioannis Gkioulekas, Ashish Shrivastava, Yuning Chai
We propose a novel-view augmentation (NOVA) strategy to train NeRFs for photo-realistic 3D composition of dynamic objects in a static scene. Compared to prior work, our framework significantly reduces blending artifacts when inserting multiple dynamic objects into a 3D scene at novel views and times; achieves comparable PSNR without the need for additional ground truth modalities like optical flow; and overall provides ease, flexibility, and scalability in neural composition. Our codebase is on GitHub.
Authors: Tianyuan Yuan, Yicheng Liu, Yue Wang, Yilun Wang, Hang Zhao
High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on single-frame input. This approach limits their stability and performance in complex scenarios such as occlusions, largely due to the absence of temporal information. Moreover, their performance diminishes when applied to broader perception ranges. In this paper, we present StreamMapNet, a novel online mapping pipeline adept at long-sequence temporal modeling of videos. StreamMapNet employs multi-point attention and temporal information which empowers the construction of large-range local HD maps with high stability and further addresses the limitations of existing methods. Furthermore, we critically examine widely used online HD Map construction benchmark and datasets, Argoverse2 and nuScenes, revealing significant bias in the existing evaluation protocols. We propose to resplit the benchmarks according to geographical spans, promoting fair and precise evaluations. Experimental results validate that StreamMapNet significantly outperforms existing methods across all settings while maintaining an online inference speed of $14.2$ FPS.
Authors: Shuai Lyu, Dongmei Mo, Waikeung Wong
Existing K-nearest neighbor (KNN) retrieval-based methods usually conduct industrial anomaly detection in two stages: obtain feature representations with a pre-trained CNN model and perform distance measures for defect detection. However, the features are not fully exploited as they ignore domain bias and the difference of local density in feature space, which limits the detection performance. In this paper, we propose Reducing Biases (REB) in representation by considering the domain bias of the pre-trained model and building a self-supervised learning task for better domain adaption with a defect generation strategy (DefectMaker) imitating the natural defects. Additionally, we propose a local density KNN (LDKNN) to reduce the local density bias and obtain effective anomaly detection. We achieve a promising result of 99.5\% AUROC on the widely used MVTec AD benchmark. We also achieve 88.0\% AUROC on the challenging MVTec LOCO AD dataset and bring an improvement of 4.7\% AUROC to the state-of-the-art result. All results are obtained with smaller backbone networks such as Vgg11 and Resnet18, which indicates the effectiveness and efficiency of REB for practical industrial applications.
Authors: Tobias Koch, Christian Riess, Thomas Köhler
Handling entirely unknown data is a challenge for any deployed classifier. Classification models are typically trained on a static pre-defined dataset and are kept in the dark for the open unassigned feature space. As a result, they struggle to deal with out-of-distribution data during inference. Addressing this task on the class-level is termed open-set recognition (OSR). However, most OSR methods are inherently limited, as they train closed-set classifiers and only adapt the downstream predictions to OSR. This work presents LORD, a framework to Leverage Open-set Recognition by exploiting unknown Data. LORD explicitly models open space during classifier training and provides a systematic evaluation for such approaches. We identify three model-agnostic training strategies that exploit background data and applied them to well-established classifiers. Due to LORD's extensive evaluation protocol, we consistently demonstrate improved recognition of unknown data. The benchmarks facilitate in-depth analysis across various requirement levels. To mitigate dependency on extensive and costly background datasets, we explore mixup as an off-the-shelf data generation technique. Our experiments highlight mixup's effectiveness as a substitute for background datasets. Lightweight constraints on mixup synthesis further improve OSR performance.
Authors: Yibo Cui, Liang Xie, Yakun Zhang, Meishan Zhang, Ye Yan, Erwei Yin
Cross-modal alignment is one key challenge for Vision-and-Language Navigation (VLN). Most existing studies concentrate on mapping the global instruction or single sub-instruction to the corresponding trajectory. However, another critical problem of achieving fine-grained alignment at the entity level is seldom considered. To address this problem, we propose a novel Grounded Entity-Landmark Adaptive (GELA) pre-training paradigm for VLN tasks. To achieve the adaptive pre-training paradigm, we first introduce grounded entity-landmark human annotations into the Room-to-Room (R2R) dataset, named GEL-R2R. Additionally, we adopt three grounded entity-landmark adaptive pre-training objectives: 1) entity phrase prediction, 2) landmark bounding box prediction, and 3) entity-landmark semantic alignment, which explicitly supervise the learning of fine-grained cross-modal alignment between entity phrases and environment landmarks. Finally, we validate our model on two downstream benchmarks: VLN with descriptive instructions (R2R) and dialogue instructions (CVDN). The comprehensive experiments show that our GELA model achieves state-of-the-art results on both tasks, demonstrating its effectiveness and generalizability.
Authors: Baowen Zhang, Jiahe Li, Xiaoming Deng, Yinda Zhang, Cuixia Ma, Hongan Wang
Learning 3D shape representation with dense correspondence for deformable objects is a fundamental problem in computer vision. Existing approaches often need additional annotations of specific semantic domain, e.g., skeleton poses for human bodies or animals, which require extra annotation effort and suffer from error accumulation, and they are limited to specific domain. In this paper, we propose a novel self-supervised approach to learn neural implicit shape representation for deformable objects, which can represent shapes with a template shape and dense correspondence in 3D. Our method does not require the priors of skeleton and skinning weight, and only requires a collection of shapes represented in signed distance fields. To handle the large deformation, we constrain the learned template shape in the same latent space with the training shapes, design a new formulation of local rigid constraint that enforces rigid transformation in local region and addresses local reflection issue, and present a new hierarchical rigid constraint to reduce the ambiguity due to the joint learning of template shape and correspondences. Extensive experiments show that our model can represent shapes with large deformations. We also show that our shape representation can support two typical applications, such as texture transfer and shape editing, with competitive performance. The code and models are available at https://iscas3dv.github.io/deformshape
Authors: Chen Liang, Wenguan Wang, Jiaxu Miao, Yi Yang
Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.
Authors: Rishit Javia, Falak Shah, Shivam Dave
Pose based video sychronization can have applications in multiple domains such as gameplay performance evaluation, choreography or guiding athletes. The subject's actions could be compared and evaluated against those performed by professionals side by side. In this paper, we propose an end to end pipeline for synchronizing videos based on pose. The first step crops the region where the person present in the image followed by pose detection on the cropped image. This is followed by application of Dynamic Time Warping(DTW) on angle/ distance measures between the pose keypoints leading to a scale and shift invariant pose matching pipeline.
Authors: Haibo Jin, Haoxuan Che, Yi Lin, Hao Chen
Automatic medical report generation (MRG) is of great research value as it has the potential to relieve radiologists from the heavy burden of report writing. Despite recent advancements, accurate MRG remains challenging due to the need for precise clinical understanding and the identification of clinical findings. Moreover, the imbalanced distribution of diseases makes the challenge even more pronounced, as rare diseases are underrepresented in training data, making their diagnostic performance unreliable. To address these challenges, we propose diagnosis-driven prompts for medical report generation (PromptMRG), a novel framework that aims to improve the diagnostic accuracy of MRG with the guidance of diagnosis-aware prompts. Specifically, PromptMRG is based on encoder-decoder architecture with an extra disease classification branch. When generating reports, the diagnostic results from the classification branch are converted into token prompts to explicitly guide the generation process. To further improve the diagnostic accuracy, we design cross-modal feature enhancement, which retrieves similar reports from the database to assist the diagnosis of a query image by leveraging the knowledge from a pre-trained CLIP. Moreover, the disease imbalanced issue is addressed by applying an adaptive logit-adjusted loss to the classification branch based on the individual learning status of each disease, which overcomes the barrier of text decoder's inability to manipulate disease distributions. Experiments on two MRG benchmarks show the effectiveness of the proposed method, where it obtains state-of-the-art clinical efficacy performance on both datasets.
Authors: Yupu Yao, Shangqi Deng, Zihan Cao, Harry Zhang, Liang-Jian Deng
Diffusion models have exhibited promising progress in video generation. However, they often struggle to retain consistent details within local regions across frames. One underlying cause is that traditional diffusion models approximate Gaussian noise distribution by utilizing predictive noise, without fully accounting for the impact of inherent information within the input itself. Additionally, these models emphasize the distinction between predictions and references, neglecting information intrinsic to the videos. To address this limitation, inspired by the self-attention mechanism, we propose a novel text-to-video (T2V) generation network structure based on diffusion models, dubbed Additional Perturbation for Latent noise with Adversarial training (APLA). Our approach only necessitates a single video as input and builds upon pre-trained stable diffusion networks. Notably, we introduce an additional compact network, known as the Video Generation Transformer (VGT). This auxiliary component is designed to extract perturbations from the inherent information contained within the input, thereby refining inconsistent pixels during temporal predictions. We leverage a hybrid architecture of transformers and convolutions to compensate for temporal intricacies, enhancing consistency between different frames within the video. Experiments demonstrate a noticeable improvement in the consistency of the generated videos both qualitatively and quantitatively.
Authors: Huaxin Zhang, Xiang Wang, Xiaohao Xu, Zhiwu Qing, Changxin Gao, Nong Sang
Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully supervised methods. Code will be available at https://github.com/pipixin321/HR-Pro.
Authors: Songchun Zhang, Chunhui Zhao
Weakly supervised temporal action localization (WSTAL) aims to localize actions in untrimmed videos using video-level labels. Despite recent advances, existing approaches mainly follow a localization-by-classification pipeline, generally processing each segment individually, thereby exploiting only limited contextual information. As a result, the model will lack a comprehensive understanding (e.g. appearance and temporal structure) of various action patterns, leading to ambiguity in classification learning and temporal localization. Our work addresses this from a novel perspective, by exploring and exploiting the cross-video contextual knowledge within the dataset to recover the dataset-level semantic structure of action instances via weak labels only, thereby indirectly improving the holistic understanding of fine-grained action patterns and alleviating the aforementioned ambiguities. Specifically, an end-to-end framework is proposed, including a Robust Memory-Guided Contrastive Learning (RMGCL) module and a Global Knowledge Summarization and Aggregation (GKSA) module. First, the RMGCL module explores the contrast and consistency of cross-video action features, assisting in learning more structured and compact embedding space, thus reducing ambiguity in classification learning. Further, the GKSA module is used to efficiently summarize and propagate the cross-video representative action knowledge in a learnable manner to promote holistic action patterns understanding, which in turn allows the generation of high-confidence pseudo-labels for self-learning, thus alleviating ambiguity in temporal localization. Extensive experiments on THUMOS14, ActivityNet1.3, and FineAction demonstrate that our method outperforms the state-of-the-art methods, and can be easily plugged into other WSTAL methods.
Authors: Josef Cersovsky, Sadegh Mohammadi, Dagmar Kainmueller, Johannes Hoehne
The classification of gigapixel histopathology images with deep multiple instance learning models has become a critical task in digital pathology and precision medicine. In this work, we propose a Transformer-based multiple instance learning approach that replaces the traditional learned attention mechanism with a regional, Vision Transformer inspired self-attention mechanism. We present a method that fuses regional patch information to derive slide-level predictions and show how this regional aggregation can be stacked to hierarchically process features on different distance levels. To increase predictive accuracy, especially for datasets with small, local morphological features, we introduce a method to focus the image processing on high attention regions during inference. Our approach is able to significantly improve performance over the baseline on two histopathology datasets and points towards promising directions for further research.
Authors: An Ngo, Daniel Phelps, Derrick Lai, Thanyared Wong, Lucas Mathias, Anish Shivamurthy, Mustafa Ajmal, Minghao Liu, James Davis
Currently, digital avatars can be created manually using human images as reference. Systems such as Bitmoji are excellent producers of detailed avatar designs, with hundreds of choices for customization. A supervised learning model could be trained to generate avatars automatically, but the hundreds of possible options create difficulty in securing non-noisy data to train a model. As a solution, we train a model to produce avatars from human images using tag-based annotations. This method provides better annotator agreement, leading to less noisy data and higher quality model predictions. Our contribution is an application of tag-based annotation to train a model for avatar face creation. We design tags for 3 different facial facial features offered by Bitmoji, and train a model using tag-based annotation to predict the nose.
Authors: Po-Yung Chou, Yu-Chun Lo, Bo-Zheng Xie, Cheng-Hung Lin, Yu-Yung Kao
The CoachAI Badminton 2023 Track1 initiative aim to automatically detect events within badminton match videos. Detecting small objects, especially the shuttlecock, is of quite importance and demands high precision within the challenge. Such detection is crucial for tasks like hit count, hitting time, and hitting location. However, even after revising the well-regarded shuttlecock detecting model, TrackNet, our object detection models still fall short of the desired accuracy. To address this issue, we've implemented various deep learning methods to tackle the problems arising from noisy detectied data, leveraging diverse data types to improve precision. In this report, we detail the detection model modifications we've made and our approach to the 11 tasks. Notably, our system garnered a score of 0.78 out of 1.0 in the challenge.
Authors: Paul Gavrikov, Janis Keuper
Assessing the robustness of deep neural networks against out-of-distribution inputs is crucial, especially in safety-critical domains like autonomous driving, but also in safety systems where malicious actors can digitally alter inputs to circumvent safety guards. However, designing effective out-of-distribution tests that encompass all possible scenarios while preserving accurate label information is a challenging task. Existing methodologies often entail a compromise between variety and constraint levels for attacks and sometimes even both. In a first step towards a more holistic robustness evaluation of image classification models, we introduce an attack method based on image solarization that is conceptually straightforward yet avoids jeopardizing the global structure of natural images independent of the intensity. Through comprehensive evaluations of multiple ImageNet models, we demonstrate the attack's capacity to degrade accuracy significantly, provided it is not integrated into the training augmentations. Interestingly, even then, no full immunity to accuracy deterioration is achieved. In other settings, the attack can often be simplified into a black-box attack with model-independent parameters. Defenses against other corruptions do not consistently extend to be effective against our specific attack.
Project website: https://github.com/paulgavrikov/adversarial_solarization
Authors: Dimitrios Daskalakis, Nikolaos Gkalelis, Vasileios Mezaris
In this paper, we introduce Masked Feature Modelling (MFM), a novel approach for the unsupervised pre-training of a Graph Attention Network (GAT) block. MFM utilizes a pretrained Visual Tokenizer to reconstruct masked features of objects within a video, leveraging the MiniKinetics dataset. We then incorporate the pre-trained GAT block into a state-of-the-art bottom-up supervised video-event recognition architecture, ViGAT, to improve the model's starting point and overall accuracy. Experimental evaluations on the YLI-MED dataset demonstrate the effectiveness of MFM in improving event recognition performance.
Authors: Ario Sadafi, Matthias Hehr, Nassir Navab, Carsten Marr
Accurate classification of Acute Myeloid Leukemia (AML) subtypes is crucial for clinical decision-making and patient care. In this study, we investigate the potential presence of age and sex bias in AML subtype classification using Multiple Instance Learning (MIL) architectures. To that end, we train multiple MIL models using different levels of sex imbalance in the training set and excluding certain age groups. To assess the sex bias, we evaluate the performance of the models on male and female test sets. For age bias, models are tested against underrepresented age groups in the training data. We find a significant effect of sex and age bias on the performance of the model for AML subtype classification. Specifically, we observe that females are more likely to be affected by sex imbalance dataset and certain age groups, such as patients with 72 to 86 years of age with the RUNX1::RUNX1T1 genetic subtype, are significantly affected by an age bias present in the training data. Ensuring inclusivity in the training data is thus essential for generating reliable and equitable outcomes in AML genetic subtype classification, ultimately benefiting diverse patient populations.
Authors: Ario Sadafi, Raheleh Salehi, Armin Gruber, Sayedali Shetab Boushehri, Pascal Giehr, Nassir Navab, Carsten Marr
Accurate classification of white blood cells in peripheral blood is essential for diagnosing hematological diseases. Due to constantly evolving clinical settings, data sources, and disease classifications, it is necessary to update machine learning classification models regularly for practical real-world use. Such models significantly benefit from sequentially learning from incoming data streams without forgetting previously acquired knowledge. However, models can suffer from catastrophic forgetting, causing a drop in performance on previous tasks when fine-tuned on new data. Here, we propose a rehearsal-based continual learning approach for class incremental and domain incremental scenarios in white blood cell classification. To choose representative samples from previous tasks, we employ exemplar set selection based on the model's predictions. This involves selecting the most confident samples and the most challenging samples identified through uncertainty estimation of the model. We thoroughly evaluated our proposed approach on three white blood cell classification datasets that differ in color, resolution, and class composition, including scenarios where new domains or new classes are introduced to the model with every task. We also test a long class incremental experiment with both new domains and new classes. Our results demonstrate that our approach outperforms established baselines in continual learning, including existing iCaRL and EWC methods for classifying white blood cells in cross-domain environments.
Authors: Jiawei Lin, Jiaqi Guo, Shizhao Sun, Weijiang Xu, Ting Liu, Jian-Guang Lou, Dongmei Zhang
Creating layouts is a fundamental step in graphic design. In this work, we propose to use text as the guidance to create graphic layouts, i.e., Text-to-Layout, aiming to lower the design barriers. Text-to-Layout is a challenging task, because it needs to consider the implicit, combined, and incomplete layout constraints from text, each of which has not been studied in previous work. To address this, we present a two-stage approach, named parse-then-place. The approach introduces an intermediate representation (IR) between text and layout to represent diverse layout constraints. With IR, Text-to-Layout is decomposed into a parse stage and a place stage. The parse stage takes a textual description as input and generates an IR, in which the implicit constraints from the text are transformed into explicit ones. The place stage generates layouts based on the IR. To model combined and incomplete constraints, we use a Transformer-based layout generation model and carefully design a way to represent constraints and layouts as sequences. Besides, we adopt the pretrain-then-finetune strategy to boost the performance of the layout generation model with large-scale unlabeled layouts. To evaluate our approach, we construct two Text-to-Layout datasets and conduct experiments on them. Quantitative results, qualitative analysis, and user studies demonstrate the effectiveness of our approach.
Authors: Shizhou Zhang, Qingchun Yang, De Cheng, Yinghui Xing, Guoqiang Liang, Peng Wang, Yanning Zhang
In this work, we construct a large-scale dataset for Ground-to-Aerial Person Search, named G2APS, which contains 31,770 images of 260,559 annotated bounding boxes for 2,644 identities appearing in both of the UAVs and ground surveillance cameras. To our knowledge, this is the first dataset for cross-platform intelligent surveillance applications, where the UAVs could work as a powerful complement for the ground surveillance cameras. To more realistically simulate the actual cross-platform Ground-to-Aerial surveillance scenarios, the surveillance cameras are fixed about 2 meters above the ground, while the UAVs capture videos of persons at different location, with a variety of view-angles, flight attitudes and flight modes. Therefore, the dataset has the following unique characteristics: 1) drastic view-angle changes between query and gallery person images from cross-platform cameras; 2) diverse resolutions, poses and views of the person images under 9 rich real-world scenarios. On basis of the G2APS benchmark dataset, we demonstrate detailed analysis about current two-step and end-to-end person search methods, and further propose a simple yet effective knowledge distillation scheme on the head of the ReID network, which achieves state-of-the-art performances on both of the G2APS and the previous two public person search datasets, i.e., PRW and CUHK-SYSU. The dataset and source code available on \url{https://github.com/yqc123456/HKD_for_person_search}.
Authors: Bin Wang, Fan Wu, Xiao Han, Jiahui Peng, Huaping Zhong, Pan Zhang, Xiaoyi Dong, Weijia Li, Wei Li, Jiaqi Wang, Conghui He
The integration of visual encoders and large language models (LLMs) has driven recent progress in multimodal large language models (MLLMs). However, the scarcity of high-quality instruction-tuning data for vision-language tasks remains a challenge. The current leading paradigm, such as LLaVA, relies on language-only GPT-4 to generate data, which requires pre-annotated image captions and detection bounding boxes, suffering from understanding image details. A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks. However, it's worth noting that the currently accessible MLLMs are not as powerful as their LLM counterparts, as they tend to produce inadequate responses and generate false information. As a solution for addressing the current issue, this paper proposes the Visual Instruction Generation and Correction (VIGC) framework that enables multimodal large language models to generate instruction-tuning data and progressively enhance its quality on-the-fly. Specifically, Visual Instruction Generation (VIG) guides the vision-language model to generate diverse instruction-tuning data. To ensure generation quality, Visual Instruction Correction (VIC) adopts an iterative update mechanism to correct any inaccuracies in data produced by VIG, effectively reducing the risk of hallucination. Leveraging the diverse, high-quality data generated by VIGC, we finetune mainstream models and validate data quality based on various evaluations. Experimental results demonstrate that VIGC not only compensates for the shortcomings of language-only data generation methods, but also effectively enhances the benchmark performance. The models, datasets, and code will be made publicly available.
Authors: Razan Dibo, Andrey Galichin, Pavel Astashev, Dmitry V. Dylov, Oleg Y. Rogov
In recent years, computer-aided diagnosis systems have shown great potential in assisting radiologists with accurate and efficient medical image analysis. This paper presents a novel approach for bone pathology localization and classification in wrist X-ray images using a combination of YOLO (You Only Look Once) and the Shifted Window Transformer (Swin) with a newly proposed block. The proposed methodology addresses two critical challenges in wrist X-ray analysis: accurate localization of bone pathologies and precise classification of abnormalities. The YOLO framework is employed to detect and localize bone pathologies, leveraging its real-time object detection capabilities. Additionally, the Swin, a transformer-based module, is utilized to extract contextual information from the localized regions of interest (ROIs) for accurate classification.
Authors: Santiago Estrada, David Kügler, Emad Bahrami, Peng Xu, Dilshad Mousa, Monique M.B. Breteler, N. Ahmad Aziz, Martin Reuter
The hypothalamus plays a crucial role in the regulation of a broad range of physiological, behavioural, and cognitive functions. However, despite its importance, only a few small-scale neuroimaging studies have investigated its substructures, likely due to the lack of fully automated segmentation tools to address scalability and reproducibility issues of manual segmentation. While the only previous attempt to automatically sub-segment the hypothalamus with a neural network showed promise for 1.0 mm isotropic T1-weighted (T1w) MRI, there is a need for an automated tool to sub-segment also high-resolutional (HiRes) MR scans, as they are becoming widely available, and include structural detail also from multi-modal MRI. We, therefore, introduce a novel, fast, and fully automated deep learning method named HypVINN for sub-segmentation of the hypothalamus and adjacent structures on 0.8 mm isotropic T1w and T2w brain MR images that is robust to missing modalities. We extensively validate our model with respect to segmentation accuracy, generalizability, in-session test-retest reliability, and sensitivity to replicate hypothalamic volume effects (e.g. sex-differences). The proposed method exhibits high segmentation performance both for standalone T1w images as well as for T1w/T2w image pairs. Even with the additional capability to accept flexible inputs, our model matches or exceeds the performance of state-of-the-art methods with fixed inputs. We, further, demonstrate the generalizability of our method in experiments with 1.0 mm MR scans from both the Rhineland Study and the UK Biobank. Finally, HypVINN can perform the segmentation in less than a minute (GPU) and will be available in the open source FastSurfer neuroimaging software suite, offering a validated, efficient, and scalable solution for evaluating imaging-derived phenotypes of the hypothalamus.
Authors: Ziqi Yang, Zhongyu Li, Chen Liu, Xiangde Luo, Xingguang Wang, Dou Xu, Chaoqun Li, Xiaoying Qin, Meng Yang, Long Jin
Convolutional neural networks excel in histopathological image classification, yet their pixel-level focus hampers explainability. Conversely, emerging graph convolutional networks spotlight cell-level features and medical implications. However, limited by their shallowness and suboptimal use of high-dimensional pixel data, GCNs underperform in multi-class histopathological image classification. To make full use of pixel-level and cell-level features dynamically, we propose an asymmetric co-training framework combining a deep graph convolutional network and a convolutional neural network for multi-class histopathological image classification. To improve the explainability of the entire framework by embedding morphological and topological distribution of cells, we build a 14-layer deep graph convolutional network to handle cell graph data. For the further utilization and dynamic interactions between pixel-level and cell-level information, we also design a co-training strategy to integrate the two asymmetric branches. Notably, we collect a private clinically acquired dataset termed LUAD7C, including seven subtypes of lung adenocarcinoma, which is rare and more challenging. We evaluated our approach on the private LUAD7C and public colorectal cancer datasets, showcasing its superior performance, explainability, and generalizability in multi-class histopathological image classification.
Authors: Chenping Fu, Xin Fan, Jiewen Xiao, Wanqi Yuan, Risheng Liu, Zhongxuan Luo
Underwater object detection suffers from low detection performance because the distance and wavelength dependent imaging process yield evident image quality degradations such as haze-like effects, low visibility, and color distortions. Therefore, we commit to resolving the issue of underwater object detection with compounded environmental degradations. Typical approaches attempt to develop sophisticated deep architecture to generate high-quality images or features. However, these methods are only work for limited ranges because imaging factors are either unstable, too sensitive, or compounded. Unlike these approaches catering for high-quality images or features, this paper seeks transferable prior knowledge from detector-friendly images. The prior guides detectors removing degradations that interfere with detection. It is based on statistical observations that, the heavily degraded regions of detector-friendly (DFUI) and underwater images have evident feature distribution gaps while the lightly degraded regions of them overlap each other. Therefore, we propose a residual feature transference module (RFTM) to learn a mapping between deep representations of the heavily degraded patches of DFUI- and underwater- images, and make the mapping as a heavily degraded prior (HDP) for underwater detection. Since the statistical properties are independent to image content, HDP can be learned without the supervision of semantic labels and plugged into popular CNNbased feature extraction networks to improve their performance on underwater object detection. Without bells and whistles, evaluations on URPC2020 and UODD show that our methods outperform CNN-based detectors by a large margin. Our method with higher speeds and less parameters still performs better than transformer-based detectors. Our code and DFUI dataset can be found in https://github.com/xiaoDetection/Learning-Heavily-Degraed-Prior.
Authors: Mengya Han, Heliang Zheng, Chaoyue Wang, Yong Luo, Han Hu, Jing Zhang, Yonggang Wen
In this work, we address the task of few-shot part segmentation, which aims to segment the different parts of an unseen object using very few labeled examples. It is found that leveraging the textual space of a powerful pre-trained image-language model (such as CLIP) can be beneficial in learning visual features. Therefore, we develop a novel method termed PartSeg for few-shot part segmentation based on multimodal learning. Specifically, we design a part-aware prompt learning method to generate part-specific prompts that enable the CLIP model to better understand the concept of ``part'' and fully utilize its textual space. Furthermore, since the concept of the same part under different object categories is general, we establish relationships between these parts during the prompt learning process. We conduct extensive experiments on the PartImageNet and Pascal$\_$Part datasets, and the experimental results demonstrated that our proposed method achieves state-of-the-art performance.
Authors: Nyothiri Aung, Tahar Kechadi, Liming Chen, Sahraoui Dhelim
CNNs have been widely applied for medical image analysis. However, limited memory capacity is one of the most common drawbacks of processing high-resolution 3D volumetric data. 3D volumes are usually cropped or downsized first before processing, which can result in a loss of resolution, increase class imbalance, and affect the performance of the segmentation algorithms. In this paper, we propose an end-to-end deep learning approach called IP-UNet. IP-UNet is a UNet-based model that performs multi-class segmentation on Intensity Projection (IP) of 3D volumetric data instead of the memory-consuming 3D volumes. IP-UNet uses limited memory capability for training without losing the original 3D image resolution. We compare the performance of three models in terms of segmentation accuracy and computational cost: 1) Slice-by-slice 2D segmentation of the CT scan images using a conventional 2D UNet model. 2) IP-UNet that operates on data obtained by merging the extracted Maximum Intensity Projection (MIP), Closest Vessel Projection (CVP), and Average Intensity Projection (AvgIP) representations of the source 3D volumes, then applying the UNet model on the output IP images. 3) 3D-UNet model directly reads the 3D volumes constructed from a series of CT scan images and outputs the 3D volume of the predicted segmentation. We test the performance of these methods on 3D volumetric images for automatic breast calcification detection. Experimental results show that IP-Unet can achieve similar segmentation accuracy with 3D-Unet but with much better performance. It reduces the training time by 70\% and memory consumption by 92\%.
Authors: Changxu Cheng, Peng Wang, Cheng Da, Qi Zheng, Cong Yao
The diversity in length constitutes a significant characteristic of text. Due to the long-tail distribution of text lengths, most existing methods for scene text recognition (STR) only work well on short or seen-length text, lacking the capability of recognizing longer text or performing length extrapolation. This is a crucial issue, since the lengths of the text to be recognized are usually not given in advance in real-world applications, but it has not been adequately investigated in previous works. Therefore, we propose in this paper a method called Length-Insensitive Scene TExt Recognizer (LISTER), which remedies the limitation regarding the robustness to various text lengths. Specifically, a Neighbor Decoder is proposed to obtain accurate character attention maps with the assistance of a novel neighbor matrix regardless of the text lengths. Besides, a Feature Enhancement Module is devised to model the long-range dependency with low computation cost, which is able to perform iterations with the neighbor decoder to enhance the feature map progressively. To the best of our knowledge, we are the first to achieve effective length-insensitive scene text recognition. Extensive experiments demonstrate that the proposed LISTER algorithm exhibits obvious superiority on long text recognition and the ability for length extrapolation, while comparing favourably with the previous state-of-the-art methods on standard benchmarks for STR (mainly short text).
Authors: Tim Schreier, Katrin Renz, Andreas Geiger, Kashyap Chitta
Prior work in 3D object detection evaluates models using offline metrics like average precision since closed-loop online evaluation on the downstream driving task is costly. However, it is unclear how indicative offline results are of driving performance. In this work, we perform the first empirical evaluation measuring how predictive different detection metrics are of driving performance when detectors are integrated into a full self-driving stack. We conduct extensive experiments on urban driving in the CARLA simulator using 16 object detection models. We find that the nuScenes Detection Score has a higher correlation to driving performance than the widely used average precision metric. In addition, our results call for caution on the exclusive reliance on the emerging class of `planner-centric' metrics.
Authors: Zongyu Li, Ian Reyes, Homa Alemzadeh
Surgical context inference has recently garnered significant attention in robot-assisted surgery as it can facilitate workflow analysis, skill assessment, and error detection. However, runtime context inference is challenging since it requires timely and accurate detection of the interactions among the tools and objects in the surgical scene based on the segmentation of video data. On the other hand, existing state-of-the-art video segmentation methods are often biased against infrequent classes and fail to provide temporal consistency for segmented masks. This can negatively impact the context inference and accurate detection of critical states. In this study, we propose a solution to these challenges using a Space Time Correspondence Network (STCN). STCN is a memory network that performs binary segmentation and minimizes the effects of class imbalance. The use of a memory bank in STCN allows for the utilization of past image and segmentation information, thereby ensuring consistency of the masks. Our experiments using the publicly available JIGSAWS dataset demonstrate that STCN achieves superior segmentation performance for objects that are difficult to segment, such as needle and thread, and improves context inference compared to the state-of-the-art. We also demonstrate that segmentation and context inference can be performed at runtime without compromising performance.
Authors: Yu-Xiang Zeng, Jun-Wei Hsieh, Xin Li, Ming-Ching Chang
Detecting small scene text instances in the wild is particularly challenging, where the influence of irregular positions and nonideal lighting often leads to detection errors. We present MixNet, a hybrid architecture that combines the strengths of CNNs and Transformers, capable of accurately detecting small text from challenging natural scenes, regardless of the orientations, styles, and lighting conditions. MixNet incorporates two key modules: (1) the Feature Shuffle Network (FSNet) to serve as the backbone and (2) the Central Transformer Block (CTBlock) to exploit the 1D manifold constraint of the scene text. We first introduce a novel feature shuffling strategy in FSNet to facilitate the exchange of features across multiple scales, generating high-resolution features superior to popular ResNet and HRNet. The FSNet backbone has achieved significant improvements over many existing text detection methods, including PAN, DB, and FAST. Then we design a complementary CTBlock to leverage center line based features similar to the medial axis of text regions and show that it can outperform contour-based approaches in challenging cases when small scene texts appear closely. Extensive experimental results show that MixNet, which mixes FSNet with CTBlock, achieves state-of-the-art results on multiple scene text detection datasets.
Authors: Zitao Wang, Qiguang Miao, Yue Xi
The portrait matting task aims to extract an alpha matte with complete semantics and finely-detailed contours. In comparison to CNN-based approaches, transformers with self-attention allow a larger receptive field, enabling it to better capture long-range dependencies and low-frequency semantic information of a portrait. However, the recent research shows that self-attention mechanism struggle with modeling high-frequency information and capturing fine contour details, which can lead to bias while predicting the portrait's contours. To address the problem, we propose EFormer to enhance the model's attention towards semantic and contour features. Especially the latter, which is surrounded by a large amount of high-frequency details. We build a semantic and contour detector (SCD) to accurately capture the distribution of semantic and contour features. And we further design contour-edge extraction branch and semantic extraction branch for refining contour features and complete semantic information. Finally, we fuse the two kinds of features and leverage the segmentation head to generate the predicted portrait matte. Remarkably, EFormer is an end-to-end trimap-free method and boasts a simple structure. Experiments conducted on VideoMatte240K-JPEGSD and AIM datasets demonstrate that EFormer outperforms previous portrait matte methods.
Authors: Mohamed R. Ibrahim, Terry Lyons
Through our respiratory system, many viruses and diseases frequently spread and pass from one person to another. Covid-19 served as an example of how crucial it is to track down and cut back on contacts to stop its spread. There is a clear gap in finding automatic methods that can detect hand-to-face contact in complex urban scenes or indoors. In this paper, we introduce a computer vision framework, called FaceTouch, based on deep learning. It comprises deep sub-models to detect humans and analyse their actions. FaceTouch seeks to detect hand-to-face touches in the wild, such as through video chats, bus footage, or CCTV feeds. Despite partial occlusion of faces, the introduced system learns to detect face touches from the RGB representation of a given scene by utilising the representation of the body gestures such as arm movement. This has been demonstrated to be useful in complex urban scenarios beyond simply identifying hand movement and its closeness to faces. Relying on Supervised Contrastive Learning, the introduced model is trained on our collected dataset, given the absence of other benchmark datasets. The framework shows a strong validation in unseen datasets which opens the door for potential deployment.
Authors: Wei Xie, Haobo Jiang, Shuo Gu, Jin Xie
Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks.Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance techniques still suffer from unsatisfactory robustness. To mitigate it, in this paper, we propose a novel implicit obstacle map-driven indoor navigation framework for robust obstacle avoidance, where an implicit obstacle map is learned based on the historical trial-and-error experience rather than the visual image. In order to further improve the navigation efficiency, a non-local target memory aggregation module is designed to leverage a non-local network to model the intrinsic relationship between the target semantic and the target orientation clues during the navigation process so as to mine the most target-correlated object clues for the navigation decision. Extensive experimental results on AI2-Thor and RoboTHOR benchmarks verify the excellent obstacle avoidance and navigation efficiency of our proposed method. The core source code is available at https://github.com/xwaiyy123/object-navigation.
Authors: Yash Deo, Rodrigo Bonazzola, Haoran Dou, Yan Xia, Tianyou Wei, Nishant Ravikumar, Alejandro F. Frangi, Toni Lassila
Magnetic resonance angiography (MRA) is an imaging modality for visualising blood vessels. It is useful for several diagnostic applications and for assessing the risk of adverse events such as haemorrhagic stroke (resulting from the rupture of aneurysms in blood vessels). However, MRAs are not acquired routinely, hence, an approach to synthesise blood vessel segmentations from more routinely acquired MR contrasts such as T1 and T2, would be useful. We present an encoder-decoder model for synthesising segmentations of the main cerebral arteries in the circle of Willis (CoW) from only T2 MRI. We propose a two-phase multi-objective learning approach, which captures both global and local features. It uses learned local attention maps generated by dilating the segmentation labels, which forces the network to only extract information from the T2 MRI relevant to synthesising the CoW. Our synthetic vessel segmentations generated from only T2 MRI achieved a mean Dice score of $0.79 \pm 0.03$ in testing, compared to state-of-the-art segmentation networks such as transformer U-Net ($0.71 \pm 0.04$) and nnU-net($0.68 \pm 0.05$), while using only a fraction of the parameters. The main qualitative difference between our synthetic vessel segmentations and the comparative models was in the sharper resolution of the CoW vessel segments, especially in the posterior circulation.
Authors: Xinyu Zhang, Yan Gong, Zhiwei Li, Xin Gao, Dafeng Jin, Jun Li, Huaping Liu
Multi-modal fusion is increasingly being used for autonomous driving tasks, as images from different modalities provide unique information for feature extraction. However, the existing two-stream networks are only fused at a specific network layer, which requires a lot of manual attempts to set up. As the CNN goes deeper, the two modal features become more and more advanced and abstract, and the fusion occurs at the feature level with a large gap, which can easily hurt the performance. In this study, we propose a novel fusion architecture called skip-cross networks (SkipcrossNets), which combines adaptively LiDAR point clouds and camera images without being bound to a certain fusion epoch. Specifically, skip-cross connects each layer to each layer in a feed-forward manner, and for each layer, the feature maps of all previous layers are used as input and its own feature maps are used as input to all subsequent layers for the other modality, enhancing feature propagation and multi-modal features fusion. This strategy facilitates selection of the most similar feature layers from two data pipelines, providing a complementary effect for sparse point cloud features during fusion processes. The network is also divided into several blocks to reduce the complexity of feature fusion and the number of model parameters. The advantages of skip-cross fusion were demonstrated through application to the KITTI and A2D2 datasets, achieving a MaxF score of 96.85% on KITTI and an F1 score of 84.84% on A2D2. The model parameters required only 2.33 MB of memory at a speed of 68.24 FPS, which could be viable for mobile terminals and embedded devices.
Authors: Yuan Gong, Yong Zhang, Xiaodong Cun, Fei Yin, Yanbo Fan, Xuan Wang, Baoyuan Wu, Yujiu Yang
We target cross-domain face reenactment in this paper, i.e., driving a cartoon image with the video of a real person and vice versa. Recently, many works have focused on one-shot talking face generation to drive a portrait with a real video, i.e., within-domain reenactment. Straightforwardly applying those methods to cross-domain animation will cause inaccurate expression transfer, blur effects, and even apparent artifacts due to the domain shift between cartoon and real faces. Only a few works attempt to settle cross-domain face reenactment. The most related work AnimeCeleb requires constructing a dataset with pose vector and cartoon image pairs by animating 3D characters, which makes it inapplicable anymore if no paired data is available. In this paper, we propose a novel method for cross-domain reenactment without paired data. Specifically, we propose a transformer-based framework to align the motions from different domains into a common latent space where motion transfer is conducted via latent code addition. Two domain-specific motion encoders and two learnable motion base memories are used to capture domain properties. A source query transformer and a driving one are exploited to project domain-specific motion to the canonical space. The edited motion is projected back to the domain of the source with a transformer. Moreover, since no paired data is provided, we propose a novel cross-domain training scheme using data from two domains with the designed analogy constraint. Besides, we contribute a cartoon dataset in Disney style. Extensive evaluations demonstrate the superiority of our method over competing methods.
Authors: Gengxuan Tian, Junqiao Zhao, Yingfeng Cai, Fenglin Zhang, Wenjie Mu, Chen Ye
LiDAR-based place recognition plays a crucial role in Simultaneous Localization and Mapping (SLAM) and LiDAR localization.
Despite the emergence of various deep learning-based and hand-crafting-based methods, rotation-induced place recognition failure remains a critical challenge.
Existing studies address this limitation through specific training strategies or network structures.
However, the former does not produce satisfactory results, while the latter focuses mainly on the reduced problem of SO(2) rotation invariance. Methods targeting SO(3) rotation invariance suffer from limitations in discrimination capability.
In this paper, we propose a new method that employs Vector Neurons Network (VNN) to achieve SO(3) rotation invariance.
We first extract rotation-equivariant features from neighboring points and map low-dimensional features to a high-dimensional space through VNN.
Afterwards, we calculate the Euclidean and Cosine distance in the rotation-equivariant feature space as rotation-invariant feature descriptors.
Finally, we aggregate the features using GeM pooling to obtain global descriptors.
To address the significant information loss when formulating rotation-invariant descriptors, we propose computing distances between features at different layers within the Euclidean space neighborhood.
This greatly improves the discriminability of the point cloud descriptors while ensuring computational efficiency.
Experimental results on public datasets show that our approach significantly outperforms other baseline methods implementing rotation invariance, while achieving comparable results with current state-of-the-art place recognition methods that do not consider rotation issues.
Authors: Qiuyu Zhu, Xuewen Zu, Chengfei Liu
For the convolutional neural network (CNN) used for pattern classification, the training loss function is usually applied to the final output of the network, except for some regularization constraints on the network parameters. However, with the increasing of the number of network layers, the influence of the loss function on the network front layers gradually decreases, and the network parameters tend to fall into local optimization. At the same time, it is found that the trained network has significant information redundancy at all stages of features, which reduces the effectiveness of feature mapping at all stages and is not conducive to the change of the subsequent parameters of the network in the direction of optimality. Therefore, it is possible to obtain a more optimized solution of the network and further improve the classification accuracy of the network by designing a loss function for restraining the front stage features and eliminating the information redundancy of the front stage features .For CNN, this article proposes a multi-stage feature decorrelation loss (MFD Loss), which refines effective features and eliminates information redundancy by constraining the correlation of features at all stages. Considering that there are many layers in CNN, through experimental comparison and analysis, MFD Loss acts on multiple front layers of CNN, constrains the output features of each layer and each channel, and performs supervision training jointly with classification loss function during network training. Compared with the single Softmax Loss supervised learning, the experiments on several commonly used datasets on several typical CNNs prove that the classification performance of Softmax Loss+MFD Loss is significantly better. Meanwhile, the comparison experiments before and after the combination of MFD Loss and some other typical loss functions verify its good universality.
Authors: Yuhe Liu, Chuanjian Liu, Kai Han, Quan Tang, Zengchang Qin
Semantic segmentation is a computer vision task that associates a label with each pixel in an image. Modern approaches tend to introduce class embeddings into semantic segmentation for deeply utilizing category semantics, and regard supervised class masks as final predictions. In this paper, we explore the mechanism of class embeddings and have an insight that more explicit and meaningful class embeddings can be generated based on class masks purposely. Following this observation, we propose ECENet, a new segmentation paradigm, in which class embeddings are obtained and enhanced explicitly during interacting with multi-stage image features. Based on this, we revisit the traditional decoding process and explore inverted information flow between segmentation masks and class embeddings. Furthermore, to ensure the discriminability and informativity of features from backbone, we propose a Feature Reconstruction module, which combines intrinsic and diverse branches together to ensure the concurrence of diversity and redundancy in features. Experiments show that our ECENet outperforms its counterparts on the ADE20K dataset with much less computational cost and achieves new state-of-the-art results on PASCAL-Context dataset. The code will be released at https://gitee.com/mindspore/models and https://github.com/Carol-lyh/ECENet.
Authors: Jordy Van Landeghem, Sanket Biswas, Matthew B. Blaschko, Marie-Francine Moens
This paper highlights the need to bring document classification benchmarking closer to real-world applications, both in the nature of data tested ($X$: multi-channel, multi-paged, multi-industry; $Y$: class distributions and label set variety) and in classification tasks considered ($f$: multi-page document, page stream, and document bundle classification, ...). We identify the lack of public multi-page document classification datasets, formalize different classification tasks arising in application scenarios, and motivate the value of targeting efficient multi-page document representations. An experimental study on proposed multi-page document classification datasets demonstrates that current benchmarks have become irrelevant and need to be updated to evaluate complete documents, as they naturally occur in practice. This reality check also calls for more mature evaluation methodologies, covering calibration evaluation, inference complexity (time-memory), and a range of realistic distribution shifts (e.g., born-digital vs. scanning noise, shifting page order). Our study ends on a hopeful note by recommending concrete avenues for future improvements.}
Authors: Fei Wang, Liang Ding, Jun Rao, Ye Liu, Li Shen, Changxing Ding
The multimedia community has shown a significant interest in perceiving and representing the physical world with multimodal pretrained neural network models, and among them, the visual-language pertaining (VLP) is, currently, the most captivating topic. However, there have been few endeavors dedicated to the exploration of 1) whether essential linguistic knowledge (e.g., semantics and syntax) can be extracted during VLP, and 2) how such linguistic knowledge impact or enhance the multimodal alignment. In response, here we aim to elucidate the impact of comprehensive linguistic knowledge, including semantic expression and syntactic structure, on multimodal alignment. Specifically, we design and release the SNARE, the first large-scale multimodal alignment probing benchmark, to detect the vital linguistic components, e.g., lexical, semantic, and syntax knowledge, containing four tasks: Semantic structure, Negation logic, Attribute ownership, and Relationship composition. Based on our proposed probing benchmarks, our holistic analyses of five advanced VLP models illustrate that the VLP model: i) shows insensitivity towards complex syntax structures and relies on content words for sentence comprehension; ii) demonstrates limited comprehension of combinations between sentences and negations; iii) faces challenges in determining the presence of actions or spatial relationships within visual information and struggles with verifying the correctness of triple combinations. We make our benchmark and code available at \url{https://github.com/WangFei-2019/SNARE/}.
Authors: Hossein Shakibania, Sina Raoufi, Hassan Khotanlou
Low-light images, characterized by inadequate illumination, pose challenges of diminished clarity, muted colors, and reduced details. Low-light image enhancement, an essential task in computer vision, aims to rectify these issues by improving brightness, contrast, and overall perceptual quality, thereby facilitating accurate analysis and interpretation. This paper introduces the Convolutional Dense Attention-guided Network (CDAN), a novel solution for enhancing low-light images. CDAN integrates an autoencoder-based architecture with convolutional and dense blocks, complemented by an attention mechanism and skip connections. This architecture ensures efficient information propagation and feature learning. Furthermore, a dedicated post-processing phase refines color balance and contrast. Our approach demonstrates notable progress compared to state-of-the-art results in low-light image enhancement, showcasing its robustness across a wide range of challenging scenarios. Our model performs remarkably on benchmark datasets, effectively mitigating under-exposure and proficiently restoring textures and colors in diverse low-light scenarios. This achievement underscores CDAN's potential for diverse computer vision tasks, notably enabling robust object detection and recognition in challenging low-light conditions.
Authors: Ziyan Yang, Kushal Kafle, Zhe Lin, Scott Cohen, Zhihong Ding, Vicente Ordonez
We propose Subject-Conditional Relation Detection SCoRD, where conditioned on an input subject, the goal is to predict all its relations to other objects in a scene along with their locations. Based on the Open Images dataset, we propose a challenging OIv6-SCoRD benchmark such that the training and testing splits have a distribution shift in terms of the occurrence statistics of $\langle$subject, relation, object$\rangle$ triplets. To solve this problem, we propose an auto-regressive model that given a subject, it predicts its relations, objects, and object locations by casting this output as a sequence of tokens. First, we show that previous scene-graph prediction methods fail to produce as exhaustive an enumeration of relation-object pairs when conditioned on a subject on this benchmark. Particularly, we obtain a recall@3 of 83.8% for our relation-object predictions compared to the 49.75% obtained by a recent scene graph detector. Then, we show improved generalization on both relation-object and object-box predictions by leveraging during training relation-object pairs obtained automatically from textual captions and for which no object-box annotations are available. Particularly, for $\langle$subject, relation, object$\rangle$ triplets for which no object locations are available during training, we are able to obtain a recall@3 of 42.59% for relation-object pairs and 32.27% for their box locations.
Authors: Alessandro Simoni, Francesco Marchetti, Guido Borghi, Federico Becattini, Lorenzo Seidenari, Roberto Vezzani, Alberto Del Bimbo
In recent years, the effective and safe collaboration between humans and machines has gained significant importance, particularly in the Industry 4.0 scenario. A critical prerequisite for realizing this collaborative paradigm is precisely understanding the robot's 3D pose within its environment. Therefore, in this paper, we introduce a novel vision-based system leveraging depth data to accurately establish the 3D locations of robotic joints. Specifically, we prove the ability of the proposed system to enhance its current pose estimation accuracy by jointly learning to forecast future poses. Indeed, we introduce the concept of Pose Nowcasting, denoting the capability of a system to exploit the learned knowledge of the future to improve the estimation of the present. The experimental evaluation is conducted on two different datasets, providing state-of-the-art and real-time performance and confirming the validity of the proposed method on both the robotic and human scenarios.
Authors: Jian Liang, Lijun Sheng, Zhengbo Wang, Ran He, Tieniu Tan
The emergence of vision-language models (VLMs), such as CLIP, has spurred a significant research effort towards their application for downstream supervised learning tasks. Although some previous studies have explored the unsupervised fine-tuning of CLIP, they often rely on prior knowledge in the form of class names associated with ground truth labels. In this paper, we delve into a realistic unsupervised fine-tuning scenario by assuming that the unlabeled data might contain out-of-distribution samples from unknown classes. Furthermore, we emphasize the importance of simultaneously enhancing out-of-distribution detection capabilities alongside the recognition of instances associated with predefined class labels.
To tackle this problem, we present a simple, efficient, and effective fine-tuning approach called Universal Entropy Optimization (UEO). UEO leverages sample-level confidence to approximately minimize the conditional entropy of confident instances and maximize the marginal entropy of less confident instances. Apart from optimizing the textual prompts, UEO also incorporates optimization of channel-wise affine transformations within the visual branch of CLIP. Through extensive experiments conducted across 15 domains and 4 different types of prior knowledge, we demonstrate that UEO surpasses baseline methods in terms of both generalization and out-of-distribution detection.
Authors: Jia-Quan Yu, Soo-Chang Pei
Image segmentation and depth estimation are crucial tasks in computer vision, especially in autonomous driving scenarios. Although these tasks are typically addressed separately, we propose an innovative approach to combine them in our novel deep learning network, Panoptic-DepthLab. By incorporating an additional depth estimation branch into the segmentation network, it can predict the depth of each instance segment. Evaluating on Cityscape dataset, we demonstrate the effectiveness of our method in achieving high-quality segmentation results with depth and visualize it with a color map. Our proposed method demonstrates a new possibility of combining different tasks and networks to generate a more comprehensive image recognition result to facilitate the safety of autonomous driving vehicles.
Authors: Jia-Quan Yu, Soo-Chang Pei
Monocular 3D object detection is a crucial and challenging task for autonomous driving vehicle, while it uses only a single camera image to infer 3D objects in the scene. To address the difficulty of predicting depth using only pictorial clue, we propose a novel perspective-aware convolutional layer that captures long-range dependencies in images. By enforcing convolutional kernels to extract features along the depth axis of every image pixel, we incorporates perspective information into network architecture. We integrate our perspective-aware convolutional layer into a 3D object detector and demonstrate improved performance on the KITTI3D dataset, achieving a 23.9\% average precision in the easy benchmark. These results underscore the importance of modeling scene clues for accurate depth inference and highlight the benefits of incorporating scene structure in network design. Our perspective-aware convolutional layer has the potential to enhance object detection accuracy by providing more precise and context-aware feature extraction.
Authors: Ximeng Sun, Kihyuk Sohn, Kate Saenko, Clayton Mellina, Xiao Bian
The cost of labeling data often limits the performance of machine learning systems. In multi-task learning, related tasks provide information to each other and improve overall performance, but the label cost can vary among tasks. How should the label budget (i.e. the amount of money spent on labeling) be allocated among different tasks to achieve optimal multi-task performance? We are the first to propose and formally define the label budget allocation problem in multi-task learning and to empirically show that different budget allocation strategies make a big difference to its performance. We propose a Task-Adaptive Budget Allocation algorithm to robustly generate the optimal budget allocation adaptive to different multi-task learning settings. Specifically, we estimate and then maximize the extent of new information obtained from the allocated budget as a proxy for multi-task learning performance. Experiments on PASCAL VOC and Taskonomy demonstrate the efficacy of our approach over other widely used heuristic labeling strategies.
Authors: Huafeng Kuang, Jie Wu, Xiawu Zheng, Ming Li, Xuefeng Xiao, Rui Wang, Min Zheng, Rongrong Ji
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model compression. However, existing knowledge distillation techniques lack an in-depth investigation and analysis of VLP, and practical guidelines for VLP-oriented distillation are still not yet explored. In this paper, we present DLIP, a simple yet efficient Distilling Language-Image Pre-training framework, through which we investigate how to distill a light VLP model. Specifically, we dissect the model distillation from multiple dimensions, such as the architecture characteristics of different modules and the information transfer of different modalities. We conduct comprehensive experiments and provide insights on distilling a light but performant VLP model. Experimental results reveal that DLIP can achieve a state-of-the-art accuracy/efficiency trade-off across diverse cross-modal tasks, e.g., image-text retrieval, image captioning and visual question answering. For example, DLIP compresses BLIP by 1.9x, from 213M to 108M parameters, while achieving comparable or better performance. Furthermore, DLIP succeeds in retaining more than 95% of the performance with 22.4% parameters and 24.8% FLOPs compared to the teacher model and accelerates inference speed by 2.7x.
Authors: Sheng Zhang, Muzammal Naseer, Guangyi Chen, Zhiqiang Shen, Salman Khan, Kun Zhang, Fahad Khan
Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. Despite the success, most traditional VLMs-based methods are restricted by the assumption of partial source supervision or ideal vocabularies, which rarely satisfy the open-world scenario. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. To address this challenge, we propose the Self Structural Semantic Alignment (S^3A) framework, which extracts the structural semantic information from unlabeled data while simultaneously self-learning. Our S^3A framework adopts a unique Cluster-Vote-Prompt-Realign (CVPR) algorithm, which iteratively groups unlabeled data to derive structural semantics for pseudo-supervision. Our CVPR process includes iterative clustering on images, voting within each cluster to identify initial class candidates from the vocabulary, generating discriminative prompts with large language models to discern confusing candidates, and realigning images and the vocabulary as structural semantic alignment. Finally, we propose to self-learn the CLIP image encoder with both individual and structural semantic alignment through a teacher-student learning strategy. Our comprehensive experiments across various generic and fine-grained benchmarks demonstrate that the S^3A method offers substantial improvements over existing VLMs-based approaches, achieving a more than 15% accuracy improvement over CLIP on average. Our codes, models, and prompts are publicly released at https://github.com/sheng-eatamath/S3A.
Authors: Xiangyang Zhu, Renrui Zhang, Bowei He, Ziyu Guo, Jiaming Liu, Hao Dong, Peng Gao
To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the models on `seen' classes, and then evaluate their generalization performance on `unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead, but also incurs a significant domain gap on `unseen' classes. To tackle these issues, we propose an efficient Training-free Few-shot 3D Segmentation netwrok, TFS3D, and a further training-based variant, TFS3D-T. Without any learnable parameters, TFS3D extracts dense representations by trigonometric positional encodings, and achieves comparable performance to previous training-based methods. Due to the elimination of pre-training, TFS3D can alleviate the domain gap issue and save a substantial amount of time. Building upon TFS3D, TFS3D-T only requires to train a lightweight query-support transferring attention (QUEST), which enhances the interaction between the few-shot query and support data. Experiments demonstrate TFS3D-T improves previous state-of-the-art methods by +6.93% and +17.96% mIoU respectively on S3DIS and ScanNet, while reducing the training time by -90%, indicating superior effectiveness and efficiency.
Authors: David Fan, Jue Wang, Shuai Liao, Yi Zhu, Vimal Bhat, Hector Santos-Villalobos, Rohith MV, Xinyu Li
Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video understanding. This suggests that the random masking strategy that is inherited from the image MAE is less effective for video MAE. This motivates the design of a novel masking algorithm that can more efficiently make use of video saliency. Specifically, we propose a motion-guided masking algorithm (MGM) which leverages motion vectors to guide the position of each mask over time. Crucially, these motion-based correspondences can be directly obtained from information stored in the compressed format of the video, which makes our method efficient and scalable. On two challenging large-scale video benchmarks (Kinetics-400 and Something-Something V2), we equip video MAE with our MGM and achieve up to +$1.3\%$ improvement compared to previous state-of-the-art methods. Additionally, our MGM achieves equivalent performance to previous video MAE using up to $66\%$ fewer training epochs. Lastly, we show that MGM generalizes better to downstream transfer learning and domain adaptation tasks on the UCF101, HMDB51, and Diving48 datasets, achieving up to +$4.9\%$ improvement compared to baseline methods.
Authors: Xiyue Zhu, Vlas Zyrianov, Zhijian Liu, Shenlong Wang
Despite tremendous advancements in bird's-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information (such as occlusion or limited coverage). In this work, we introduce MapPrior, a novel BEV perception framework that combines a traditional discriminative BEV perception model with a learned generative model for semantic map layouts. Our MapPrior delivers predictions with better accuracy, realism, and uncertainty awareness. We evaluate our model on the large-scale nuScenes benchmark. At the time of submission, MapPrior outperforms the strongest competing method, with significantly improved MMD and ECE scores in camera- and LiDAR-based BEV perception.
Authors: Yunji Kim, Jiyoung Lee, Jin-Hwa Kim, Jung-Woo Ha, Jun-Yan Zhu
Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a training-free method that adapts a pre-trained text-to-image model to handle such dense captions while offering control over the scene layout. We first analyze the relationship between generated images' layouts and the pre-trained model's intermediate attention maps. Next, we develop an attention modulation method that guides objects to appear in specific regions according to layout guidance. Without requiring additional fine-tuning or datasets, we improve image generation performance given dense captions regarding both automatic and human evaluation scores. In addition, we achieve similar-quality visual results with models specifically trained with layout conditions.
Authors: Sai Kumar Dwivedi, Cordelia Schmid, Hongwei Yi, Michael J. Black, Dimitrios Tzionas
The regression of 3D Human Pose and Shape (HPS) from an image is becoming increasingly accurate. This makes the results useful for downstream tasks like human action recognition or 3D graphics. Yet, no regressor is perfect, and accuracy can be affected by ambiguous image evidence or by poses and appearance that are unseen during training. Most current HPS regressors, however, do not report the confidence of their outputs, meaning that downstream tasks cannot differentiate accurate estimates from inaccurate ones. To address this, we develop POCO, a novel framework for training HPS regressors to estimate not only a 3D human body, but also their confidence, in a single feed-forward pass. Specifically, POCO estimates both the 3D body pose and a per-sample variance. The key idea is to introduce a Dual Conditioning Strategy (DCS) for regressing uncertainty that is highly correlated to pose reconstruction quality. The POCO framework can be applied to any HPS regressor and here we evaluate it by modifying HMR, PARE, and CLIFF. In all cases, training the network to reason about uncertainty helps it learn to more accurately estimate 3D pose. While this was not our goal, the improvement is modest but consistent. Our main motivation is to provide uncertainty estimates for downstream tasks; we demonstrate this in two ways: (1) We use the confidence estimates to bootstrap HPS training. Given unlabelled image data, we take the confident estimates of a POCO-trained regressor as pseudo ground truth. Retraining with this automatically-curated data improves accuracy. (2) We exploit uncertainty in video pose estimation by automatically identifying uncertain frames (e.g. due to occlusion) and inpainting these from confident frames. Code and models will be available for research at https://poco.is.tue.mpg.de.
Authors: Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, Jingren Zhou
We introduce the Qwen-VL series, a set of large-scale vision-language models designed to perceive and understand both text and images. Comprising Qwen-VL and Qwen-VL-Chat, these models exhibit remarkable performance in tasks like image captioning, question answering, visual localization, and flexible interaction. The evaluation covers a wide range of tasks including zero-shot captioning, visual or document visual question answering, and grounding. We demonstrate the Qwen-VL outperforms existing Large Vision Language Models (LVLMs). We present their architecture, training, capabilities, and performance, highlighting their contributions to advancing multimodal artificial intelligence. Code, demo and models are available at https://github.com/QwenLM/Qwen-VL.
Authors: Muhammad Zubair Irshad, Sergey Zakharov, Katherine Liu, Vitor Guizilini, Thomas Kollar, Adrien Gaidon, Zsolt Kira, Rares Ambrus
Recent implicit neural representations have shown great results for novel view synthesis. However, existing methods require expensive per-scene optimization from many views hence limiting their application to real-world unbounded urban settings where the objects of interest or backgrounds are observed from very few views. To mitigate this challenge, we introduce a new approach called NeO 360, Neural fields for sparse view synthesis of outdoor scenes. NeO 360 is a generalizable method that reconstructs 360{\deg} scenes from a single or a few posed RGB images. The essence of our approach is in capturing the distribution of complex real-world outdoor 3D scenes and using a hybrid image-conditional triplanar representation that can be queried from any world point. Our representation combines the best of both voxel-based and bird's-eye-view (BEV) representations and is more effective and expressive than each. NeO 360's representation allows us to learn from a large collection of unbounded 3D scenes while offering generalizability to new views and novel scenes from as few as a single image during inference. We demonstrate our approach on the proposed challenging 360{\deg} unbounded dataset, called NeRDS 360, and show that NeO 360 outperforms state-of-the-art generalizable methods for novel view synthesis while also offering editing and composition capabilities. Project page: https://zubair-irshad.github.io/projects/neo360.html
Authors: Yuxin Jiang, Liming Jiang, Shuai Yang, Chen Change Loy
Automatic high-quality rendering of anime scenes from complex real-world images is of significant practical value. The challenges of this task lie in the complexity of the scenes, the unique features of anime style, and the lack of high-quality datasets to bridge the domain gap. Despite promising attempts, previous efforts are still incompetent in achieving satisfactory results with consistent semantic preservation, evident stylization, and fine details. In this study, we propose Scenimefy, a novel semi-supervised image-to-image translation framework that addresses these challenges. Our approach guides the learning with structure-consistent pseudo paired data, simplifying the pure unsupervised setting. The pseudo data are derived uniquely from a semantic-constrained StyleGAN leveraging rich model priors like CLIP. We further apply segmentation-guided data selection to obtain high-quality pseudo supervision. A patch-wise contrastive style loss is introduced to improve stylization and fine details. Besides, we contribute a high-resolution anime scene dataset to facilitate future research. Our extensive experiments demonstrate the superiority of our method over state-of-the-art baselines in terms of both perceptual quality and quantitative performance.
Authors: Wanyue Zhang, Rishabh Dabral, Thomas Leimkühler, Vladislav Golyanik, Marc Habermann, Christian Theobalt
Existing automatic approaches for 3D virtual character motion synthesis supporting scene interactions do not generalise well to new objects outside training distributions, even when trained on extensive motion capture datasets with diverse objects and annotated interactions. This paper addresses this limitation and shows that robustness and generalisation to novel scene objects in 3D object-aware character synthesis can be achieved by training a motion model with as few as one reference object. We leverage an implicit feature representation trained on object-only datasets, which encodes an SE(3)-equivariant descriptor field around the object. Given an unseen object and a reference pose-object pair, we optimise for the object-aware pose that is closest in the feature space to the reference pose. Finally, we use l-NSM, i.e., our motion generation model that is trained to seamlessly transition from locomotion to object interaction with the proposed bidirectional pose blending scheme. Through comprehensive numerical comparisons to state-of-the-art methods and in a user study, we demonstrate substantial improvements in 3D virtual character motion and interaction quality and robustness to scenarios with unseen objects. Our project page is available at https://vcai.mpi-inf.mpg.de/projects/ROAM/.
Authors: Jonathan Ventura, Zuzana Kukelova, Torsten Sattler, Dániel Baráth
Affine correspondences have traditionally been used to improve feature matching over wide baselines. While recent work has successfully used affine correspondences to solve various relative camera pose estimation problems, less attention has been given to their use in absolute pose estimation. We introduce the first general solution to the problem of estimating the pose of a calibrated camera given a single observation of an oriented point and an affine correspondence. The advantage of our approach (P1AC) is that it requires only a single correspondence, in comparison to the traditional point-based approach (P3P), significantly reducing the combinatorics in robust estimation. P1AC provides a general solution that removes restrictive assumptions made in prior work and is applicable to large-scale image-based localization. We propose a minimal solution to the P1AC problem and evaluate our novel solver on synthetic data, showing its numerical stability and performance under various types of noise. On standard image-based localization benchmarks we show that P1AC achieves more accurate results than the widely used P3P algorithm. Code for our method is available at https://github.com/jonathanventura/P1AC/ .
Authors: Wenbin Li, Xuesong Yang, Meihao Kong, Lei Wang, Jing Huo, Yang Gao, Jiebo Luo
Contrastive self-supervised learning (SSL) methods, such as MoCo and SimCLR, have achieved great success in unsupervised visual representation learning. They rely on a large number of negative pairs and thus require either large memory banks or large batches. Some recent non-contrastive SSL methods, such as BYOL and SimSiam, attempt to discard negative pairs and have also shown remarkable performance. To avoid collapsed solutions caused by not using negative pairs, these methods require non-trivial asymmetry designs. However, in small data regimes, we can not obtain a sufficient number of negative pairs or effectively avoid the over-fitting problem when negatives are not used at all. To address this situation, we argue that negative pairs are still important but one is generally sufficient for each positive pair. We show that a simple Triplet-based loss (Trip) can achieve surprisingly good performance without requiring large batches or asymmetry designs. Moreover, to alleviate the over-fitting problem in small data regimes and further enhance the effect of Trip, we propose a simple plug-and-play RandOm MApping (ROMA) strategy by randomly mapping samples into other spaces and requiring these randomly projected samples to satisfy the same relationship indicated by the triplets. Integrating the triplet-based loss with random mapping, we obtain the proposed method Trip-ROMA. Extensive experiments, including unsupervised representation learning and unsupervised few-shot learning, have been conducted on ImageNet-1K and seven small datasets. They successfully demonstrate the effectiveness of Trip-ROMA and consistently show that ROMA can further effectively boost other SSL methods. Code is available at https://github.com/WenbinLee/Trip-ROMA.
Authors: Yijun Yang, Shujun Wang, Lei Zhu, Lequan Yu
Modern deep neural networks struggle to transfer knowledge and generalize across diverse domains when deployed to real-world applications. Currently, domain generalization (DG) is introduced to learn a universal representation from multiple domains to improve the network generalization ability on unseen domains. However, previous DG methods only focus on the data-level consistency scheme without considering the synergistic regularization among different consistency schemes. In this paper, we present a novel Hierarchical Consistency framework for Domain Generalization (HCDG) by integrating Extrinsic Consistency and Intrinsic Consistency synergistically. Particularly, for the Extrinsic Consistency, we leverage the knowledge across multiple source domains to enforce data-level consistency. To better enhance such consistency, we design a novel Amplitude Gaussian-mixing strategy into Fourier-based data augmentation called DomainUp. For the Intrinsic Consistency, we perform task-level consistency for the same instance under the dual-task scenario. We evaluate the proposed HCDG framework on two medical image segmentation tasks, i.e., optic cup/disc segmentation on fundus images and prostate MRI segmentation. Extensive experimental results manifest the effectiveness and versatility of our HCDG framework.
Authors: Roy Miles, Krystian Mikolajczyk
We present an efficient alternative to the convolutional layer using cheap spatial transformations. This construction exploits an inherent spatial redundancy of the learned convolutional filters to enable a much greater parameter efficiency, while maintaining the top-end accuracy of their dense counter-parts. Training these networks is modelled as a generalised pruning problem, whereby the pruned filters are replaced with cheap transformations from the set of non-pruned filters. We provide an efficient implementation of the proposed layer, followed by two natural extensions to avoid excessive feature compression and to improve the expressivity of the transformed features. We show that these networks can achieve comparable or improved performance to state-of-the-art pruning models across both the CIFAR-10 and ImageNet-1K datasets.
Authors: Fangneng Zhan, Yingchen Yu, Rongliang Wu, Jiahui Zhang, Shijian Lu, Lingjie Liu, Adam Kortylewski, Christian Theobalt, Eric Xing
As information exists in various modalities in real world, effective interaction and fusion among multimodal information plays a key role for the creation and perception of multimodal data in computer vision and deep learning research. With superb power in modeling the interaction among multimodal information, multimodal image synthesis and editing has become a hot research topic in recent years. Instead of providing explicit guidance for network training, multimodal guidance offers intuitive and flexible means for image synthesis and editing. On the other hand, this field is also facing several challenges in alignment of multimodal features, synthesis of high-resolution images, faithful evaluation metrics, etc. In this survey, we comprehensively contextualize the advance of the recent multimodal image synthesis and editing and formulate taxonomies according to data modalities and model types. We start with an introduction to different guidance modalities in image synthesis and editing, and then describe multimodal image synthesis and editing approaches extensively according to their model types. After that, we describe benchmark datasets and evaluation metrics as well as corresponding experimental results. Finally, we provide insights about the current research challenges and possible directions for future research. A project associated with this survey is available at https://github.com/fnzhan/Generative-AI.
Authors: Renrui Zhang, Han Qiu, Tai Wang, Ziyu Guo, Xuanzhuo Xu, Ziteng Cui, Yu Qiao, Peng Gao, Hongsheng Li
Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and then predict 3D attributes by neighboring features. However, only using local visual features is insufficient to understand the scene-level 3D spatial structures and ignores the long-range inter-object depth relations. In this paper, we introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR. We modify the vanilla transformer to be depth-aware and guide the whole detection process by contextual depth cues. Specifically, concurrent to the visual encoder that captures object appearances, we introduce to predict a foreground depth map, and specialize a depth encoder to extract non-local depth embeddings. Then, we formulate 3D object candidates as learnable queries and propose a depth-guided decoder to conduct object-scene depth interactions. In this way, each object query estimates its 3D attributes adaptively from the depth-guided regions on the image and is no longer constrained to local visual features. On KITTI benchmark with monocular images as input, MonoDETR achieves state-of-the-art performance and requires no extra dense depth annotations. Besides, our depth-guided modules can also be plug-and-play to enhance multi-view 3D object detectors on nuScenes dataset, demonstrating our superior generalization capacity. Code is available at https://github.com/ZrrSkywalker/MonoDETR.
Authors: Kithmini Herath, Udith Haputhanthri, Ramith Hettiarachchi, Hasindu Kariyawasam, Raja N. Ahmad, Azeem Ahmad, Balpreet S. Ahluwalia, Chamira U. S. Edussooriya, Dushan N. Wadduwage
Since the late 16th century, scientists have continuously innovated and developed new microscope types for various applications. Creating a new architecture from the ground up requires substantial scientific expertise and creativity, often spanning years or even decades. In this study, we propose an alternative approach called "Differentiable Microscopy," which introduces a top-down design paradigm for optical microscopes. Using all-optical phase retrieval as an illustrative example, we demonstrate the effectiveness of data-driven microscopy design through $\partial\mu$. Furthermore, we conduct comprehensive comparisons with competing methods, showcasing the consistent superiority of our learned designs across multiple datasets, including biological samples. To substantiate our ideas, we experimentally validate the functionality of one of the learned designs, providing a proof of concept. The proposed differentiable microscopy framework supplements the creative process of designing new optical systems and would perhaps lead to unconventional but better optical designs.
Authors: Sayna Ebrahimi, Sercan O. Arik, Tomas Pfister
For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-time remains to be an unexplored area. We propose DocTTA, a novel test-time adaptation method for documents, that does source-free domain adaptation using unlabeled target document data. DocTTA leverages cross-modality self-supervised learning via masked visual language modeling, as well as pseudo labeling to adapt models learned on a \textit{source} domain to an unlabeled \textit{target} domain at test time. We introduce new benchmarks using existing public datasets for various VDU tasks, including entity recognition, key-value extraction, and document visual question answering. DocTTA shows significant improvements on these compared to the source model performance, up to 1.89\% in (F1 score), 3.43\% (F1 score), and 17.68\% (ANLS score), respectively. Our benchmark datasets are available at \url{https://saynaebrahimi.github.io/DocTTA.html}.
Authors: Alexander Bauer, Shinichi Nakajima, Klaus-Robert Müller
Deep autoencoders provide an effective tool for learning non-linear dimensionality reduction in an unsupervised way. Recently, they have been used for the task of anomaly detection in the visual domain. By optimizing for the reconstruction error using anomaly-free examples, the common belief is that a corresponding network should fail to accurately reconstruct anomalous regions in the application phase. This goal is typically addressed by controlling the capacity of the network, either by reducing the size of the bottleneck layer or by enforcing sparsity constraints on the activations. However, neither of these techniques does explicitly penalize reconstruction of anomalous signals often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that allows the use of discriminative information during training but focuses on the data manifold of normal examples. We emphasize that inference with our approach is very efficient during training and prediction requiring a single forward pass for each input image. Our experiments on the MVTec AD dataset demonstrate high detection and localization performance. On the texture-subset, in particular, our approach consistently outperforms recent anomaly detection methods by a significant margin.
Authors: Zhengyi Li, Cong Guo, Zhanda Zhu, Yangjie Zhou, Yuxian Qiu, Xiaotian Gao, Jingwen Leng, Minyi Guo
Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method for DNN quantization, prior research has demonstrated its suboptimal nature when applied to weight quantization. They propose optimizing weight rounding schemes by leveraging output error rather than the traditional weight quantization error. Our study reveals that similar rounding challenges also extend to activation quantization. Despite the easy generalization, the challenges lie in the dynamic nature of activation. Adaptive rounding is expected for varying activations and the method is subjected to runtime overhead. To tackle this, we propose the AQuant quantization framework with a novel perspective to reduce output error by adjusting rounding schemes of activations. Instead of using the constant rounding border 0.5 of the rounding-to-nearest operation, we make the border become a function w.r.t. the activation value to change the activation rounding by the adaptive border. To deal with the runtime overhead, we use a coarse-grained version of the border function. Finally, we introduce our framework to optimize the border function. Extensive experiments show that AQuant achieves notable improvements compared to state-of-the-art works and pushes the accuracy of ResNet-18 up to 60.31% under the 2-bit weight and activation quantization.
Authors: Susung Hong, Gyuseong Lee, Wooseok Jang, Seungryong Kim
Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier and classifier-free guidance. In this paper, we present a more comprehensive perspective that goes beyond the traditional guidance methods. From this generalized perspective, we introduce novel condition- and training-free strategies to enhance the quality of generated images. As a simple solution, blur guidance improves the suitability of intermediate samples for their fine-scale information and structures, enabling diffusion models to generate higher quality samples with a moderate guidance scale. Improving upon this, Self-Attention Guidance (SAG) uses the intermediate self-attention maps of diffusion models to enhance their stability and efficacy. Specifically, SAG adversarially blurs only the regions that diffusion models attend to at each iteration and guides them accordingly. Our experimental results show that our SAG improves the performance of various diffusion models, including ADM, IDDPM, Stable Diffusion, and DiT. Moreover, combining SAG with conventional guidance methods leads to further improvement.
Authors: Bernard Lange, Masha Itkina, Mykel J. Kochenderfer
Environment prediction frameworks are integral for autonomous vehicles, enabling safe navigation in dynamic environments. LiDAR generated occupancy grid maps (L-OGMs) offer a robust bird's eye-view scene representation that facilitates joint scene predictions without relying on manual labeling unlike commonly used trajectory prediction frameworks. Prior approaches have optimized deterministic L-OGM prediction architectures directly in grid cell space. While these methods have achieved some degree of success in prediction, they occasionally grapple with unrealistic and incorrect predictions. We claim that the quality and realism of the forecasted occupancy grids can be enhanced with the use of generative models. We propose a framework that decouples occupancy prediction into: representation learning and stochastic prediction within the learned latent space. Our approach allows for conditioning the model on other available sensor modalities such as RGB-cameras and high definition maps. We demonstrate that our approach achieves state-of-the-art performance and is readily transferable between different robotic platforms on the real-world NuScenes, Waymo Open, and a custom dataset we collected on an experimental vehicle platform.
Authors: Sawinder Kaur, Yi Xiao, Asif Salekin
AI's widespread integration has led to neural networks (NNs) deployment on edge and similar limited-resource platforms for safety-critical scenarios. Yet, NN's fragility raises concerns about reliable inference. Moreover, constrained platforms demand compact networks. This study introduces VeriCompress, a tool that automates the search and training of compressed models with robustness guarantees. These models are well-suited for safety-critical applications and adhere to predefined architecture and size limitations, making them deployable on resource-restricted platforms. The method trains models 2-3 times faster than the state-of-the-art approaches, surpassing relevant baseline approaches by average accuracy and robustness gains of 15.1 and 9.8 percentage points, respectively. When deployed on a resource-restricted generic platform, these models require 5-8 times less memory and 2-4 times less inference time than models used in verified robustness literature. Our comprehensive evaluation across various model architectures and datasets, including MNIST, CIFAR, SVHN, and a relevant pedestrian detection dataset, showcases VeriCompress's capacity to identify compressed verified robust models with reduced computation overhead compared to current standards. This underscores its potential as a valuable tool for end users, such as developers of safety-critical applications on edge or Internet of Things platforms, empowering them to create suitable models for safety-critical, resource-constrained platforms in their respective domains.
Authors: Chen Naveh, Yacov Hel-Or
This paper describes a new technique for finding disentangled semantic directions in the latent space of StyleGAN. Our method identifies meaningful orthogonal subspaces that allow editing of one human face attribute, while minimizing undesired changes in other attributes. Our model is capable of editing a single attribute in multiple directions, resulting in a range of possible generated images. We compare our scheme with three state-of-the-art models and show that our method outperforms them in terms of face editing and disentanglement capabilities. Additionally, we suggest quantitative measures for evaluating attribute separation and disentanglement, and exhibit the superiority of our model with respect to those measures.
Authors: Félix Dumais, Jon Haitz Legarreta, Carl Lemaire, Philippe Poulin, François Rheault, Laurent Petit, Muhamed Barakovic, Stefano Magon, Maxime Descoteaux, Pierre-Marc Jodoin (for the Alzheimer's Disease Neuroimaging Initiative)
White matter bundle segmentation is a cornerstone of modern tractography to study the brain's structural connectivity in domains such as neurological disorders, neurosurgery, and aging. In this study, we present FIESTA (FIbEr Segmentation in Tractography using Autoencoders), a reliable and robust, fully automated, and easily semi-automatically calibrated pipeline based on deep autoencoders that can dissect and fully populate white matter bundles. This pipeline is built upon previous works that demonstrated how autoencoders can be used successfully for streamline filtering, bundle segmentation, and streamline generation in tractography. Our proposed method improves bundle segmentation coverage by recovering hard-to-track bundles with generative sampling through the latent space seeding of the subject bundle and the atlas bundle. A latent space of streamlines is learned using autoencoder-based modeling combined with contrastive learning. Using an atlas of bundles in standard space (MNI), our proposed method segments new tractograms using the autoencoder latent distance between each tractogram streamline and its closest neighbor bundle in the atlas of bundles. Intra-subject bundle reliability is improved by recovering hard-to-track streamlines, using the autoencoder to generate new streamlines that increase the spatial coverage of each bundle while remaining anatomically correct. Results show that our method is more reliable than state-of-the-art automated virtual dissection methods such as RecoBundles, RecoBundlesX, TractSeg, White Matter Analysis and XTRACT. Our framework allows for the transition from one anatomical bundle definition to another with marginal calibration efforts. Overall, these results show that our framework improves the practicality and usability of current state-of-the-art bundle segmentation framework.
Authors: Zhijie Wu, Yuhe Jin, Kwang Moo Yi
We present a novel method to provide efficient and highly detailed reconstructions. Inspired by wavelets, we learn a neural field that decompose the signal both spatially and frequency-wise. We follow the recent grid-based paradigm for spatial decomposition, but unlike existing work, encourage specific frequencies to be stored in each grid via Fourier features encodings. We then apply a multi-layer perceptron with sine activations, taking these Fourier encoded features in at appropriate layers so that higher-frequency components are accumulated on top of lower-frequency components sequentially, which we sum up to form the final output. We demonstrate that our method outperforms the state of the art regarding model compactness and convergence speed on multiple tasks: 2D image fitting, 3D shape reconstruction, and neural radiance fields. Our code is available at https://github.com/ubc-vision/NFFB.
Authors: Jie Hong, Shi Qiu, Weihao Li, Saeed Anwar, Mehrtash Harandi, Nick Barnes, Lars Petersson
Point cloud learning is receiving increasing attention, however, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper mainly discusses point cloud learning under open-set settings, where we train the model without data from unknown classes and identify them in the inference stage. Basically, we propose to solve open-set point cloud learning using a novel Point Cut-and-Mix mechanism consisting of Unknown-Point Simulator and Unknown-Point Estimator modules. Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partial known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context for discriminating the known and unknown data. Extensive experiments show the plausibility of open-set point cloud learning and the effectiveness of our proposed solutions. Our code is available at \url{https://github.com/ShiQiu0419/pointcam}.
Authors: Ege Erdil, Tamay Besiroglu
We investigate algorithmic progress in image classification on ImageNet, perhaps the most well-known test bed for computer vision. We estimate a model, informed by work on neural scaling laws, and infer a decomposition of progress into the scaling of compute, data, and algorithms. Using Shapley values to attribute performance improvements, we find that algorithmic improvements have been roughly as important as the scaling of compute for progress computer vision. Our estimates indicate that algorithmic innovations mostly take the form of compute-augmenting algorithmic advances (which enable researchers to get better performance from less compute), not data-augmenting algorithmic advances. We find that compute-augmenting algorithmic advances are made at a pace more than twice as fast as the rate usually associated with Moore's law. In particular, we estimate that compute-augmenting innovations halve compute requirements every nine months (95\% confidence interval: 4 to 25 months).
Authors: Tianjiao Ding, Shengbang Tong, Kwan Ho Ryan Chan, Xili Dai, Yi Ma, Benjamin D. Haeffele
We consider the problem of simultaneously clustering and learning a linear representation of data lying close to a union of low-dimensional manifolds, a fundamental task in machine learning and computer vision. When the manifolds are assumed to be linear subspaces, this reduces to the classical problem of subspace clustering, which has been studied extensively over the past two decades. Unfortunately, many real-world datasets such as natural images can not be well approximated by linear subspaces. On the other hand, numerous works have attempted to learn an appropriate transformation of the data, such that data is mapped from a union of general non-linear manifolds to a union of linear subspaces (with points from the same manifold being mapped to the same subspace). However, many existing works have limitations such as assuming knowledge of the membership of samples to clusters, requiring high sampling density, or being shown theoretically to learn trivial representations. In this paper, we propose to optimize the Maximal Coding Rate Reduction metric with respect to both the data representation and a novel doubly stochastic cluster membership, inspired by state-of-the-art subspace clustering results. We give a parameterization of such a representation and membership, allowing efficient mini-batching and one-shot initialization. Experiments on CIFAR-10, -20, -100, and TinyImageNet-200 datasets show that the proposed method is much more accurate and scalable than state-of-the-art deep clustering methods, and further learns a latent linear representation of the data.
Authors: Alexander Swerdlow, Runsheng Xu, Bolei Zhou
Bird's-Eye View (BEV) Perception has received increasing attention in recent years as it provides a concise and unified spatial representation across views and benefits a diverse set of downstream driving applications. While the focus has been placed on discriminative tasks such as BEV segmentation, the dual generative task of creating street-view images from a BEV layout has rarely been explored. The ability to generate realistic street-view images that align with a given HD map and traffic layout is critical for visualizing complex traffic scenarios and developing robust perception models for autonomous driving. In this paper, we propose BEVGen, a conditional generative model that synthesizes a set of realistic and spatially consistent surrounding images that match the BEV layout of a traffic scenario. BEVGen incorporates a novel cross-view transformation and spatial attention design which learn the relationship between cameras and map views to ensure their consistency. Our model can accurately render road and lane lines, as well as generate traffic scenes under different weather conditions and times of day. The code will be made publicly available.
Authors: Joowon Lim, Jannes Gladrow, Douglas Kelly, Greg O'Shea, Govert Verkes, Ioan Stefanovici, Sebastian Nowozin, Benn Thomsen
Retrieving images transmitted through multi-mode fibers is of growing interest, thanks to their ability to confine and transport light efficiently in a compact system. Here, we demonstrate machine-learning-based decoding of large-scale digital images (pages), maximizing page capacity for optical storage applications. Using a millimeter-sized square cross-section waveguide, we image an 8-bit spatial light modulator, presenting data as a matrix of symbols. Normally, decoders will incur a prohibitive O(n^2) computational scaling to decode n symbols in spatially scrambled data. However, by combining a digital twin of the setup with a U-Net, we can retrieve up to 66 kB using efficient convolutional operations only. We compare trainable ray-tracing-based with eigenmode-based twins and show the former to be superior thanks to its ability to overcome the simulation-to-experiment gap by adjusting to optical imperfections. We train the pipeline end-to-end using a differentiable mutual-information estimator based on the von-Mises distribution, generally applicable to phase-coding channels.
Authors: Minjung Shin, Yunji Seo, Jeongmin Bae, Young Sun Choi, Hyunsu Kim, Hyeran Byun, Youngjung Uh
3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images, they suffer from unstable training or degenerate solutions where the 3D geometry is unnatural. We hypothesize that the 3D geometry is underdetermined due to the insufficient constraint, i.e., being classified as real image to the discriminator is not enough. To solve this problem, we propose to approximate the background as a spherical surface and represent a scene as a union of the foreground placed in the sphere and the thin spherical background. It reduces the degree of freedom in the background field. Accordingly, we modify the volume rendering equation and incorporate dedicated constraints to design a novel 3D-aware GAN framework named BallGAN. BallGAN has multiple advantages as follows. 1) It produces more reasonable 3D geometry; the images of a scene across different viewpoints have better photometric consistency and fidelity than the state-of-the-art methods. 2) The training becomes much more stable. 3) The foreground can be separately rendered on top of different arbitrary backgrounds.
Authors: Jiahua Dong, Hongliu Li, Yang Cong, Gan Sun, Yulun Zhang, Luc Van Gool
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://github.com/JiahuaDong/LGA.
Authors: Saemi Moon, Seunghyuk Cho, Dongwoo Kim
We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs. Unlike a common unlearning task where an unlearning target is a subset of the training set, we aim to unlearn a specific feature, such as hairstyle from facial images, from the pre-trained generative models. As the target feature is only presented in a local region of an image, unlearning the entire image from the pre-trained model may result in losing other details in the remaining region of the image. To specify which features to unlearn, we collect randomly generated images that contain the target features. We then identify a latent representation corresponding to the target feature and then use the representation to fine-tune the pre-trained model. Through experiments on MNIST and CelebA datasets, we show that target features are successfully removed while keeping the fidelity of the original models. Further experiments with an adversarial attack show that the unlearned model is more robust under the presence of malicious parties.
Authors: Ke Zou, Tian Lin, Xuedong Yuan, Haoyu Chen, Xiaojing Shen, Meng Wang, Huazhu Fu
Multimodality eye disease screening is crucial in ophthalmology as it integrates information from diverse sources to complement their respective performances. However, the existing methods are weak in assessing the reliability of each unimodality, and directly fusing an unreliable modality may cause screening errors. To address this issue, we introduce a novel multimodality evidential fusion pipeline for eye disease screening, EyeMoSt, which provides a measure of confidence for unimodality and elegantly integrates the multimodality information from a multi-distribution fusion perspective. Specifically, our model estimates both local uncertainty for unimodality and global uncertainty for the fusion modality to produce reliable classification results. More importantly, the proposed mixture of Student's $t$ distributions adaptively integrates different modalities to endow the model with heavy-tailed properties, increasing robustness and reliability. Our experimental findings on both public and in-house datasets show that our model is more reliable than current methods. Additionally, EyeMost has the potential ability to serve as a data quality discriminator, enabling reliable decision-making for multimodality eye disease screening.
Authors: Peipei Li, Rui Wang, Huaibo Huang, Ran He, Zhaofeng He
Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input. Most existing methods often produce one deterministic estimation. This paper proposes a novel CLIP-driven Pluralistic Aging Diffusion Autoencoder (PADA) to enhance the diversity of aging patterns. First, we employ diffusion models to generate diverse low-level aging details via a sequential denoising reverse process. Second, we present Probabilistic Aging Embedding (PAE) to capture diverse high-level aging patterns, which represents age information as probabilistic distributions in the common CLIP latent space. A text-guided KL-divergence loss is designed to guide this learning. Our method can achieve pluralistic face aging conditioned on open-world aging texts and arbitrary unseen face images. Qualitative and quantitative experiments demonstrate that our method can generate more diverse and high-quality plausible aging results.
Authors: Bo Jiang, Shaoyu Chen, Qing Xu, Bencheng Liao, Jiajie Chen, Helong Zhou, Qian Zhang, Wenyu Liu, Chang Huang, Xinggang Wang
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representation (e.g., agent occupancy and semantic map) to perform planning, which is computationally intensive and misses the instance-level structure information. In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation. The proposed vectorized paradigm has two significant advantages. On one hand, VAD exploits the vectorized agent motion and map elements as explicit instance-level planning constraints which effectively improves planning safety. On the other hand, VAD runs much faster than previous end-to-end planning methods by getting rid of computation-intensive rasterized representation and hand-designed post-processing steps. VAD achieves state-of-the-art end-to-end planning performance on the nuScenes dataset, outperforming the previous best method by a large margin. Our base model, VAD-Base, greatly reduces the average collision rate by 29.0% and runs 2.5x faster. Besides, a lightweight variant, VAD-Tiny, greatly improves the inference speed (up to 9.3x) while achieving comparable planning performance. We believe the excellent performance and the high efficiency of VAD are critical for the real-world deployment of an autonomous driving system. Code and models are available at https://github.com/hustvl/VAD for facilitating future research.
Authors: Koutilya Pnvr, Bharat Singh, Pallabi Ghosh, Behjat Siddiquie, David Jacobs
Large-scale pre-training tasks like image classification, captioning, or self-supervised techniques do not incentivize learning the semantic boundaries of objects. However, recent generative foundation models built using text-based latent diffusion techniques may learn semantic boundaries. This is because they have to synthesize intricate details about all objects in an image based on a text description. Therefore, we present a technique for segmenting real and AI-generated images using latent diffusion models (LDMs) trained on internet-scale datasets. First, we show that the latent space of LDMs (z-space) is a better input representation compared to other feature representations like RGB images or CLIP encodings for text-based image segmentation. By training the segmentation models on the latent z-space, which creates a compressed representation across several domains like different forms of art, cartoons, illustrations, and photographs, we are also able to bridge the domain gap between real and AI-generated images. We show that the internal features of LDMs contain rich semantic information and present a technique in the form of LD-ZNet to further boost the performance of text-based segmentation. Overall, we show up to 6% improvement over standard baselines for text-to-image segmentation on natural images. For AI-generated imagery, we show close to 20% improvement compared to state-of-the-art techniques. The project is available at https://koutilya-pnvr.github.io/LD-ZNet/.
Authors: Yi Lin, Xiao Fang, Dong Zhang, Kwang-Ting Cheng, Hao Chen
Recently, the advent of vision Transformer (ViT) has brought substantial advancements in 3D dataset benchmarks, particularly in 3D volumetric medical image segmentation (Vol-MedSeg). Concurrently, multi-layer perceptron (MLP) network has regained popularity among researchers due to their comparable results to ViT, albeit with the exclusion of the resource-intensive self-attention module. In this work, we propose a novel permutable hybrid network for Vol-MedSeg, named PHNet, which capitalizes on the strengths of both convolution neural networks (CNNs) and MLP. PHNet addresses the intrinsic isotropy problem of 3D volumetric data by employing a combination of 2D and 3D CNNs to extract local features. Besides, we propose an efficient multi-layer permute perceptron (MLPP) module that captures long-range dependence while preserving positional information. This is achieved through an axis decomposition operation that permutes the input tensor along different axes, thereby enabling the separate encoding of the positional information. Furthermore, MLPP tackles the resolution sensitivity issue of MLP in Vol-MedSeg with a token segmentation operation, which divides the feature into smaller tokens and processes them individually. Extensive experimental results validate that PHNet outperforms the state-of-the-art methods with lower computational costs on the widely-used yet challenging COVID-19-20 and Synapse benchmarks. The ablation study also demonstrates the effectiveness of PHNet in harnessing the strengths of both CNNs and MLP.
Authors: Wenjia Wang, Yongtao Ge, Haiyi Mei, Zhongang Cai, Qingping Sun, Yanjun Wang, Chunhua Shen, Lei Yang, Taku Komura
As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body. The naive focal length assumptions can harm this task with the incorrectly formulated projection matrices. To solve this, we propose Zolly, the first 3DHMR method focusing on perspective-distorted images. Our approach begins with analysing the reason for perspective distortion, which we find is mainly caused by the relative location of the human body to the camera center. We propose a new camera model and a novel 2D representation, termed distortion image, which describes the 2D dense distortion scale of the human body. We then estimate the distance from distortion scale features rather than environment context features. Afterwards, we integrate the distortion feature with image features to reconstruct the body mesh. To formulate the correct projection matrix and locate the human body position, we simultaneously use perspective and weak-perspective projection loss. Since existing datasets could not handle this task, we propose the first synthetic dataset PDHuman and extend two real-world datasets tailored for this task, all containing perspective-distorted human images. Extensive experiments show that Zolly outperforms existing state-of-the-art methods on both perspective-distorted datasets and the standard benchmark (3DPW).
Authors: Liwen Wu, Rui Zhu, Mustafa B. Yaldiz, Yinhao Zhu, Hong Cai, Janarbek Matai, Fatih Porikli, Tzu-Mao Li, Manmohan Chandraker, Ravi Ramamoorthi
Inverse path tracing has recently been applied to joint material and lighting estimation, given geometry and multi-view HDR observations of an indoor scene. However, it has two major limitations: path tracing is expensive to compute, and ambiguities exist between reflection and emission. Our Factorized Inverse Path Tracing (FIPT) addresses these challenges by using a factored light transport formulation and finds emitters driven by rendering errors. Our algorithm enables accurate material and lighting optimization faster than previous work, and is more effective at resolving ambiguities. The exhaustive experiments on synthetic scenes show that our method (1) outperforms state-of-the-art indoor inverse rendering and relighting methods particularly in the presence of complex illumination effects; (2) speeds up inverse path tracing optimization to less than an hour. We further demonstrate robustness to noisy inputs through material and lighting estimates that allow plausible relighting in a real scene. The source code is available at: https://github.com/lwwu2/fipt
Authors: Martin Knoche, Gerhard Rigoll
Nowadays, face recognition systems surpass human performance on several datasets. However, there are still edge cases that the machine can't correctly classify. This paper investigates the effect of a combination of machine and human operators in the face verification task. First, we look closer at the edge cases for several state-of-the-art models to discover common datasets' challenging settings. Then, we conduct a study with 60 participants on these selected tasks with humans and provide an extensive analysis. Finally, we demonstrate that combining machine and human decisions can further improve the performance of state-of-the-art face verification systems on various benchmark datasets. Code and data are publicly available on GitHub.
Authors: Haiyu Wu, Kevin W. Bowyer
The issue of demographic disparities in face recognition accuracy has attracted increasing attention in recent years. Various face image datasets have been proposed as 'fair' or 'balanced' to assess the accuracy of face recognition algorithms across demographics. These datasets typically balance the number of identities and images across demographics. It is important to note that the number of identities and images in an evaluation dataset are {\em not} driving factors for 1-to-1 face matching accuracy. Moreover, balancing the number of identities and images does not ensure balance in other factors known to impact accuracy, such as head pose, brightness, and image quality. We demonstrate these issues using several recently proposed datasets. To improve the ability to perform less biased evaluations, we propose a bias-aware toolkit that facilitates creation of cross-demographic evaluation datasets balanced on factors mentioned in this paper.
Authors: Chao Wang, Shuren Qi, Zhiqiu Huang, Yushu Zhang, Rushi Lan, Xiaochun Cao
The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical risk for modern vision systems, e.g., the popular Deep Learning as a Service (DLaaS) frameworks. For protecting off-the-shelf deep models while not modifying them, current algorithms typically detect adversarial patterns through discriminative decomposition of natural-artificial data. However, these decompositions are biased towards frequency or spatial discriminability, thus failing to capture adversarial patterns comprehensively. More seriously, successful defense-aware (secondary) adversarial attack (i.e., evading the detector as well as fooling the model) is practical under the assumption that the adversary is fully aware of the detector (i.e., the Kerckhoffs's principle). Motivated by such facts, we propose an accurate and secure adversarial example detector, relying on a spatial-frequency discriminative decomposition with secret keys. It expands the above works on two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability and thereby is more suitable for capturing adversarial patterns than the common trigonometric or wavelet basis; 2) the extensive parameters for decomposition are generated by a pseudo-random function with secret keys, hence blocking the defense-aware adversarial attack. Theoretical and numerical analysis demonstrates the increased accuracy and security of our detector with respect to a number of state-of-the-art algorithms.
Authors: Rui-Yang Ju, Yu-Shian Lin, Jen-Shiun Chiang, Chih-Chia Chen, Wei-Han Chen, Chun-Tse Chien
To efficiently extract textual information from color degraded document images is a significant research area. The prolonged imperfect preservation of ancient documents has led to various types of degradation, such as page staining, paper yellowing, and ink bleeding. These types of degradation badly impact the image processing for features extraction. This paper introduces a novelty method employing generative adversarial networks based on color channel using discrete wavelet transform (CCDWT-GAN). The proposed method involves three stages: image preprocessing, image enhancement, and image binarization. In the initial step, we apply discrete wavelet transform (DWT) to retain the low-low (LL) subband image, thereby enhancing image quality. Subsequently, we divide the original input image into four single-channel colors (red, green, blue, and gray) to separately train adversarial networks. For the extraction of global and local features, we utilize the output image from the image enhancement stage and the entire input image to train adversarial networks independently, and then combine these two results as the final output. To validate the positive impact of the image enhancement and binarization stages on model performance, we conduct an ablation study. This work compares the performance of the proposed method with other state-of-the-art (SOTA) methods on DIBCO and H-DIBCO ((Handwritten) Document Image Binarization Competition) datasets. The experimental results demonstrate that CCDWT-GAN achieves a top two performance on multiple benchmark datasets. Notably, on DIBCO 2013 and 2016 dataset, our method achieves F-measure (FM) values of 95.24 and 91.46, respectively.
Authors: Abanob Soliman, Fabien Bonardi, Désiré Sidibé, Samia Bouchafa
This paper presents a robust approach for a visual parallel tracking and mapping (PTAM) system that excels in challenging environments. Our proposed method combines the strengths of heterogeneous multi-modal visual sensors, including stereo event-based and frame-based sensors, in a unified reference frame through a novel spatio-temporal synchronization of stereo visual frames and stereo event streams. We employ deep learning-based feature extraction and description for estimation to enhance robustness further. We also introduce an end-to-end parallel tracking and mapping optimization layer complemented by a simple loop-closure algorithm for efficient SLAM behavior. Through comprehensive experiments on both small-scale and large-scale real-world sequences of VECtor and TUM-VIE benchmarks, our proposed method (DH-PTAM) demonstrates superior performance in terms of robustness and accuracy in adverse conditions, especially in large-scale HDR scenarios. Our implementation's research-based Python API is publicly available on GitHub for further research and development: https://github.com/AbanobSoliman/DH-PTAM.
Authors: Li Xu, Bo Liu, Ameer Hamza Khan, Lu Fan, Xiao-Ming Wu
With the availability of large-scale, comprehensive, and general-purpose vision-language (VL) datasets such as MSCOCO, vision-language pre-training (VLP) has become an active area of research and proven to be effective for various VL tasks such as visual-question answering. However, studies on VLP in the medical domain have so far been scanty. To provide a comprehensive perspective on VLP for medical VL tasks, we conduct a thorough experimental analysis to study key factors that may affect the performance of VLP with a unified vision-language Transformer. To allow making sound and quick pre-training decisions, we propose RadioGraphy Captions (RGC), a high-quality, multi-modality radiographic dataset containing 18,434 image-caption pairs collected from an open-access online database MedPix. RGC can be used as a pre-training dataset or a new benchmark for medical report generation and medical image-text retrieval. By utilizing RGC and other available datasets for pre-training, we develop several key insights that can guide future medical VLP research and new strong baselines for various medical VL tasks.
Authors: Shuqiang Cao, Weixin Luo, Bairui Wang, Wei Zhang, Lin Ma
Recently, there has been a growing trend toward feature-based approaches for Online Action Detection (OAD). However, these approaches have limitations due to their fixed backbone design, which ignores the potential capability of a trainable backbone. In this paper, we propose the first end-to-end OAD model, termed E2E-LOAD, designed to address the major challenge of OAD, namely, long-term understanding and efficient online reasoning. Specifically, our proposed approach adopts an initial spatial model that is shared by all frames and maintains a long sequence cache for inference at a low computational cost. We also advocate an asymmetric spatial-temporal model for long-form and short-form modeling effectively. Furthermore, we propose a novel and efficient inference mechanism that accelerates heavy spatial-temporal exploration. Extensive ablation studies and experiments demonstrate the effectiveness and efficiency of our proposed method. Notably, we achieve 17.3 (+12.6) FPS for end-to-end OAD with 72.4%~(+1.2%), 90.3%~(+0.7%), and 48.1%~(+26.0%) mAP on THMOUS14, TVSeries, and HDD, respectively, which is 3x faster than previous approaches. The source code will be made publicly available.
Authors: Chiara Plizzari, Toby Perrett, Barbara Caputo, Dima Damen
We propose and address a new generalisation problem: can a model trained for action recognition successfully classify actions when they are performed within a previously unseen scenario and in a previously unseen location? To answer this question, we introduce the Action Recognition Generalisation Over scenarios and locations dataset (ARGO1M), which contains 1.1M video clips from the large-scale Ego4D dataset, across 10 scenarios and 13 locations. We demonstrate recognition models struggle to generalise over 10 proposed test splits, each of an unseen scenario in an unseen location. We thus propose CIR, a method to represent each video as a Cross-Instance Reconstruction of videos from other domains. Reconstructions are paired with text narrations to guide the learning of a domain generalisable representation. We provide extensive analysis and ablations on ARGO1M that show CIR outperforms prior domain generalisation works on all test splits. Code and data: https://chiaraplizz.github.io/what-can-a-cook/.
Authors: Syed Talal Wasim, Muhammad Uzair Khattak, Muzammal Naseer, Salman Khan, Mubarak Shah, Fahad Shahbaz Khan
Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency. Further, the aggregation step and the interaction step are both implemented using efficient convolution and element-wise multiplication operations that are computationally less expensive than their self-attention counterparts on video representations. We extensively explore the design space of focal modulation-based spatio-temporal context modeling and demonstrate our parallel spatial and temporal encoding design to be the optimal choice. Video-FocalNets perform favorably well against the state-of-the-art transformer-based models for video recognition on five large-scale datasets (Kinetics-400, Kinetics-600, SS-v2, Diving-48, and ActivityNet-1.3) at a lower computational cost. Our code/models are released at https://github.com/TalalWasim/Video-FocalNets.
Authors: Muhammad Uzair Khattak, Syed Talal Wasim, Muzammal Naseer, Salman Khan, Ming-Hsuan Yang, Fahad Shahbaz Khan
Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. Conventionally trained using the task-specific objective, i.e., cross-entropy loss, prompts tend to overfit downstream data distributions and find it challenging to capture task-agnostic general features from the frozen CLIP. This leads to the loss of the model's original generalization capability. To address this issue, our work introduces a self-regularization framework for prompting called PromptSRC (Prompting with Self-regulating Constraints). PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations using a three-pronged approach by: (a) regulating prompted representations via mutual agreement maximization with the frozen model, (b) regulating with self-ensemble of prompts over the training trajectory to encode their complementary strengths, and (c) regulating with textual diversity to mitigate sample diversity imbalance with the visual branch. To the best of our knowledge, this is the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity. PromptSRC explicitly steers the prompts to learn a representation space that maximizes performance on downstream tasks without compromising CLIP generalization. We perform extensive experiments on 4 benchmarks where PromptSRC overall performs favorably well compared to the existing methods. Our code and pre-trained models are publicly available at: https://github.com/muzairkhattak/PromptSRC.
Authors: Chengyu Fang, Xianfeng Han
In this paper, we investigate the problem of automatically controllable artistic character line drawing generation from photographs by proposing a Vector Flow Aware and Line Controllable Image-to-Image Translation architecture, which can be viewed as an appealing intersection between Artificial Intelligence and Arts. Specifically, we first present an Image-to-Flow network (I2FNet) to efficiently and robustly create the vector flow field in a learning-based manner, which can provide a direction guide for drawing lines. Then, we introduce our well-designed Double Flow Generator (DFG) framework to fuse features from learned vector flow and input image flow guaranteeing the spatial coherence of lines. Meanwhile, in order to allow for controllable character line drawing generation, we integrate a Line Control Matrix (LCM) into DFG and train a Line Control Regressor (LCR) to synthesize drawings with different styles by elaborately controlling the level of details, such as thickness, smoothness, and continuity, of lines. Finally, we design a Fourier Transformation Loss to further constrain the character line generation from the frequency domain view of the point. Quantitative and qualitative experiments demonstrate that our approach can obtain superior performance in producing high-resolution character line-drawing images with perceptually realistic characteristics.
Authors: Jiahe Li, Jiawei Zhang, Xiao Bai, Jun Zhou, Lin Gu
This paper presents ER-NeRF, a novel conditional Neural Radiance Fields (NeRF) based architecture for talking portrait synthesis that can concurrently achieve fast convergence, real-time rendering, and state-of-the-art performance with small model size. Our idea is to explicitly exploit the unequal contribution of spatial regions to guide talking portrait modeling. Specifically, to improve the accuracy of dynamic head reconstruction, a compact and expressive NeRF-based Tri-Plane Hash Representation is introduced by pruning empty spatial regions with three planar hash encoders. For speech audio, we propose a Region Attention Module to generate region-aware condition feature via an attention mechanism. Different from existing methods that utilize an MLP-based encoder to learn the cross-modal relation implicitly, the attention mechanism builds an explicit connection between audio features and spatial regions to capture the priors of local motions. Moreover, a direct and fast Adaptive Pose Encoding is introduced to optimize the head-torso separation problem by mapping the complex transformation of the head pose into spatial coordinates. Extensive experiments demonstrate that our method renders better high-fidelity and audio-lips synchronized talking portrait videos, with realistic details and high efficiency compared to previous methods.
Authors: Van Nguyen Nguyen, Tomas Hodan, Georgy Ponimatkin, Thibault Groueix, Vincent Lepetit
We propose a simple three-stage approach to segment unseen objects in RGB images using their CAD models. Leveraging recent powerful foundation models, DINOv2 and Segment Anything, we create descriptors and generate proposals, including binary masks for a given input RGB image. By matching proposals with reference descriptors created from CAD models, we achieve precise object ID assignment along with modal masks. We experimentally demonstrate that our method achieves state-of-the-art results in CAD-based novel object segmentation, surpassing existing approaches on the seven core datasets of the BOP challenge by 19.8% AP using the same BOP evaluation protocol. Our source code is available at https://github.com/nv-nguyen/cnos.
Authors: Reuben Moyo, Stanley Ndebvu, Michael Zimba, Jimmy Mbelwa
Examinations are a crucial part of the learning process, and academic institutions invest significant resources into maintaining their integrity by preventing cheating from students or facilitators. However, cheating has become rampant in examination setups, compromising their integrity. The traditional method of relying on invigilators to monitor every student is impractical and ineffective. To address this issue, there is a need to continuously record exam sessions to monitor students for suspicious activities. However, these recordings are often too lengthy for invigilators to analyze effectively, and fatigue may cause them to miss significant details. To widen the coverage, invigilators could use fixed overhead or wearable cameras. This paper introduces a framework that uses automation to analyze videos and detect suspicious activities during examinations efficiently and effectively. We utilized the OpenPose framework and Convolutional Neural Network (CNN) to identify students exchanging objects during exams. This detection system is vital in preventing cheating and promoting academic integrity, fairness, and quality education for institutions.
Authors: Yihan Wang, Qiao Yan, Yi Wang
LiDAR-based 3D object detection is of paramount importance for autonomous driving. Recent trends show a remarkable improvement for bird's-eye-view (BEV) based and point-based methods as they demonstrate superior performance compared to range-view counterparts. This paper presents an insight that leverages range-view representation to enhance 3D points for accurate 3D object detection. Specifically, we introduce a Redemption from Range-view Module (R2M), a plug-and-play approach for 3D surface texture enhancement from the 2D range view to the 3D point view. R2M comprises BasicBlock for 2D feature extraction, Hierarchical-dilated (HD) Meta Kernel for expanding the 3D receptive field, and Feature Points Redemption (FPR) for recovering 3D surface texture information. R2M can be seamlessly integrated into state-of-the-art LiDAR-based 3D object detectors as preprocessing and achieve appealing improvement, e.g., 1.39%, 1.67%, and 1.97% mAP improvement on easy, moderate, and hard difficulty level of KITTI val set, respectively. Based on R2M, we further propose R2Detector (R2Det) with the Synchronous-Grid RoI Pooling for accurate box refinement. R2Det outperforms existing range-view-based methods by a significant margin on both the KITTI benchmark and the Waymo Open Dataset. Codes will be made publicly available.
Authors: Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang
Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. To represent the previously visited environment, most approaches for VLN implement memory using recurrent states, topological maps, or top-down semantic maps. In contrast to these approaches, we build the top-down egocentric and dynamically growing Grid Memory Map (i.e., GridMM) to structure the visited environment. From a global perspective, historical observations are projected into a unified grid map in a top-down view, which can better represent the spatial relations of the environment. From a local perspective, we further propose an instruction relevance aggregation method to capture fine-grained visual clues in each grid region. Extensive experiments are conducted on both the REVERIE, R2R, SOON datasets in the discrete environments, and the R2R-CE dataset in the continuous environments, showing the superiority of our proposed method.
Authors: Quankai Gao, Qiangeng Xu, Hao Su, Ulrich Neumann, Zexiang Xu
We propose Strivec, a novel neural representation that models a 3D scene as a radiance field with sparsely distributed and compactly factorized local tensor feature grids. Our approach leverages tensor decomposition, following the recent work TensoRF, to model the tensor grids. In contrast to TensoRF which uses a global tensor and focuses on their vector-matrix decomposition, we propose to utilize a cloud of local tensors and apply the classic CANDECOMP/PARAFAC (CP) decomposition to factorize each tensor into triple vectors that express local feature distributions along spatial axes and compactly encode a local neural field. We also apply multi-scale tensor grids to discover the geometry and appearance commonalities and exploit spatial coherence with the tri-vector factorization at multiple local scales. The final radiance field properties are regressed by aggregating neural features from multiple local tensors across all scales. Our tri-vector tensors are sparsely distributed around the actual scene surface, discovered by a fast coarse reconstruction, leveraging the sparsity of a 3D scene. We demonstrate that our model can achieve better rendering quality while using significantly fewer parameters than previous methods, including TensoRF and Instant-NGP.
Authors: Jiahua Dong, Wenqi Liang, Yang Cong, Gan Sun
Class-incremental learning (CIL) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However, most existing CIL methods unreasonably assume that all old categories have the same forgetting pace, and neglect negative influence of forgetting heterogeneity among different old classes on forgetting compensation. To surmount the above challenges, we develop a novel Heterogeneous Forgetting Compensation (HFC) model, which can resolve heterogeneous forgetting of easy-to-forget and hard-to-forget old categories from both representation and gradient aspects. Specifically, we design a task-semantic aggregation block to alleviate heterogeneous forgetting from representation aspect. It aggregates local category information within each task to learn task-shared global representations. Moreover, we develop two novel plug-and-play losses: a gradient-balanced forgetting compensation loss and a gradient-balanced relation distillation loss to alleviate forgetting from gradient aspect. They consider gradient-balanced compensation to rectify forgetting heterogeneity of old categories and heterogeneous relation consistency. Experiments on several representative datasets illustrate effectiveness of our HFC model. The code is available at https://github.com/JiahuaDong/HFC.
Authors: Qi Yang, Joel Jung, Xiaozhong Xu, Shan Liu
Static meshes with texture maps have attracted considerable attention in both industrial manufacturing and academic research, leading to an urgent requirement for effective and robust objective quality evaluation. However, current model-based static mesh quality metrics have obvious limitations: most of them only consider geometry information, while color information is ignored, and they have strict constraints for the meshes' geometrical topology. Other metrics, such as image-based and point-based metrics, are easily influenced by the prepossessing algorithms, e.g., projection and sampling, hampering their ability to perform at their best. In this paper, we propose Geodesic Patch Similarity (GeodesicPSIM), a novel model-based metric to accurately predict human perception quality for static meshes. After selecting a group keypoints, 1-hop geodesic patches are constructed based on both the reference and distorted meshes cleaned by an effective mesh cleaning algorithm. A two-step patch cropping algorithm and a patch texture mapping module refine the size of 1-hop geodesic patches and build the relationship between the mesh geometry and color information, resulting in the generation of 1-hop textured geodesic patches. Three types of features are extracted to quantify the distortion: patch color smoothness, patch discrete mean curvature, and patch pixel color average and variance. To the best of our knowledge, GeodesicPSIM is the first model-based metric especially designed for static meshes with texture maps. GeodesicPSIM provides state-of-the-art performance in comparison with image-based, point-based, and video-based metrics on a newly created and challenging database. We also prove the robustness of GeodesicPSIM by introducing different settings of hyperparameters. Ablation studies also exhibit the effectiveness of three proposed features and the patch cropping algorithm.
Authors: Xin Dong, Rui Wang, Siyuan Liang, Aishan Liu, Lihua Jing
Billions of people are sharing their daily live images on social media everyday. However, malicious collectors use deep face recognition systems to easily steal their biometric information (e.g., faces) from these images. Some studies are being conducted to generate encrypted face photos using adversarial attacks by introducing imperceptible perturbations to reduce face information leakage. However, existing studies need stronger black-box scenario feasibility and more natural visual appearances, which challenge the feasibility of privacy protection. To address these problems, we propose a frequency-restricted identity-agnostic (FRIA) framework to encrypt face images from unauthorized face recognition without access to personal information. As for the weak black-box scenario feasibility, we obverse that representations of the average feature in multiple face recognition models are similar, thus we propose to utilize the average feature via the crawled dataset from the Internet as the target to guide the generation, which is also agnostic to identities of unknown face recognition systems; in nature, the low-frequency perturbations are more visually perceptible by the human vision system. Inspired by this, we restrict the perturbation in the low-frequency facial regions by discrete cosine transform to achieve the visual naturalness guarantee. Extensive experiments on several face recognition models demonstrate that our FRIA outperforms other state-of-the-art methods in generating more natural encrypted faces while attaining high black-box attack success rates of 96%. In addition, we validate the efficacy of FRIA using real-world black-box commercial API, which reveals the potential of FRIA in practice. Our codes can be found in https://github.com/XinDong10/FRIA.
Authors: Daniel Wolf, Tristan Payer, Catharina Silvia Lisson, Christoph Gerhard Lisson, Meinrad Beer, Timo Ropinski, Michael Götz
Deep learning in medical imaging has the potential to minimize the risk of diagnostic errors, reduce radiologist workload, and accelerate diagnosis. Training such deep learning models requires large and accurate datasets, with annotations for all training samples. However, in the medical imaging domain, annotated datasets for specific tasks are often small due to the high complexity of annotations, limited access, or the rarity of diseases. To address this challenge, deep learning models can be pre-trained on large image datasets without annotations using methods from the field of self-supervised learning. After pre-training, small annotated datasets are sufficient to fine-tune the models for a specific task. The most popular self-supervised pre-training approaches in medical imaging are based on contrastive learning. However, recent studies in natural image processing indicate a strong potential for masked autoencoder approaches. Our work compares state-of-the-art contrastive learning methods with the recently introduced masked autoencoder approach "SparK" for convolutional neural networks (CNNs) on medical images. Therefore we pre-train on a large unannotated CT image dataset and fine-tune on several CT classification tasks. Due to the challenge of obtaining sufficient annotated training data in medical imaging, it is of particular interest to evaluate how the self-supervised pre-training methods perform when fine-tuning on small datasets. By experimenting with gradually reducing the training dataset size for fine-tuning, we find that the reduction has different effects depending on the type of pre-training chosen. The SparK pre-training method is more robust to the training dataset size than the contrastive methods. Based on our results, we propose the SparK pre-training for medical imaging tasks with only small annotated datasets.
Authors: Liyan Wang, Qinyu Yang, Cong Wang, Wei Wang, Jinshan Pan, Zhixun Su
Recent years have witnessed the remarkable performance of diffusion models in various vision tasks. However, for image restoration that aims to recover clear images with sharper details from given degraded observations, diffusion-based methods may fail to recover promising results due to inaccurate noise estimation. Moreover, simple constraining noises cannot effectively learn complex degradation information, which subsequently hinders the model capacity. To solve the above problems, we propose a coarse-to-fine diffusion Transformer (C2F-DFT) for image restoration. Specifically, our C2F-DFT contains diffusion self-attention (DFSA) and diffusion feed-forward network (DFN) within a new coarse-to-fine training scheme. The DFSA and DFN respectively capture the long-range diffusion dependencies and learn hierarchy diffusion representation to facilitate better restoration. In the coarse training stage, our C2F-DFT estimates noises and then generates the final clean image by a sampling algorithm. To further improve the restoration quality, we propose a simple yet effective fine training scheme. It first exploits the coarse-trained diffusion model with fixed steps to generate restoration results, which then would be constrained with corresponding ground-truth ones to optimize the models to remedy the unsatisfactory results affected by inaccurate noise estimation. Extensive experiments show that C2F-DFT significantly outperforms diffusion-based restoration method IR-SDE and achieves competitive performance compared with Transformer-based state-of-the-art methods on $3$ tasks, including deraining, deblurring, and real denoising. The code is available at https://github.com/wlydlut/C2F-DFT.
Authors: Yijie Tang, Jiazhao Zhang, Zhinan Yu, He Wang, Kai Xu
We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation -- multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either flexibility with a single neural map or scalability due to extra storage of feature grids, we propose a pure neural representation tackling both difficulties with a divide-and-conquer design. In our method, neural submaps are incrementally allocated alongside the scanning trajectory and efficiently learned with local neural bundle adjustments. The submaps can be refined individually in a back-end optimization and optimized jointly to realize submap-level loop closure. Meanwhile, we propose a hybrid tracking approach combining randomized and gradient-based pose optimizations. For the first time, randomized optimization is made possible in neural tracking with several key designs to the learning process, enabling efficient and robust tracking even under fast camera motions. The extensive evaluation demonstrates that our method attains higher reconstruction quality than the state of the arts for large-scale scenes and under fast camera motions.
Authors: Kaixin Xu, Zhe Wang, Xue Geng, Jie Lin, Min Wu, Xiaoli Li, Weisi Lin
In this paper, we propose a novel layer-adaptive weight-pruning approach for Deep Neural Networks (DNNs) that addresses the challenge of optimizing the output distortion minimization while adhering to a target pruning ratio constraint. Our approach takes into account the collective influence of all layers to design a layer-adaptive pruning scheme. We discover and utilize a very important additivity property of output distortion caused by pruning weights on multiple layers. This property enables us to formulate the pruning as a combinatorial optimization problem and efficiently solve it through dynamic programming. By decomposing the problem into sub-problems, we achieve linear time complexity, making our optimization algorithm fast and feasible to run on CPUs. Our extensive experiments demonstrate the superiority of our approach over existing methods on the ImageNet and CIFAR-10 datasets. On CIFAR-10, our method achieves remarkable improvements, outperforming others by up to 1.0% for ResNet-32, 0.5% for VGG-16, and 0.7% for DenseNet-121 in terms of top-1 accuracy. On ImageNet, we achieve up to 4.7% and 4.6% higher top-1 accuracy compared to other methods for VGG-16 and ResNet-50, respectively. These results highlight the effectiveness and practicality of our approach for enhancing DNN performance through layer-adaptive weight pruning. Code will be available on https://github.com/Akimoto-Cris/RD_VIT_PRUNE.
Authors: Muhammad Asif Khan, Hamid Menouar, Ridha Hamila
Over the last decade, there has been a remarkable surge in interest in automated crowd monitoring within the computer vision community. Modern deep-learning approaches have made it possible to develop fully-automated vision-based crowd-monitoring applications. However, despite the magnitude of the issue at hand, the significant technological advancements, and the consistent interest of the research community, there are still numerous challenges that need to be overcome. In this article, we delve into six major areas of visual crowd analysis, emphasizing the key developments in each of these areas. We outline the crucial unresolved issues that must be tackled in future works, in order to ensure that the field of automated crowd monitoring continues to progress and thrive. Several surveys related to this topic have been conducted in the past. Nonetheless, this article thoroughly examines and presents a more intuitive categorization of works, while also depicting the latest breakthroughs within the field, incorporating more recent studies carried out within the last few years in a concise manner. By carefully choosing prominent works with significant contributions in terms of novelty or performance gains, this paper presents a more comprehensive exposition of advancements in the current state-of-the-art.
Authors: Zichen Yu, Quanli Liu, Wei Wang, Liyong Zhang, Xiaoguang Zhao
Rail detection is one of the key factors for intelligent train. In the paper, motivated by the anchor line-based lane detection methods, we propose a rail detection network called DALNet based on dynamic anchor line. Aiming to solve the problem that the predefined anchor line is image agnostic, we design a novel dynamic anchor line mechanism. It utilizes a dynamic anchor line generator to dynamically generate an appropriate anchor line for each rail instance based on the position and shape of the rails in the input image. These dynamically generated anchor lines can be considered as better position references to accurately localize the rails than the predefined anchor lines. In addition, we present a challenging urban rail detection dataset DL-Rail with high-quality annotations and scenario diversity. DL-Rail contains 7000 pairs of images and annotations along with scene tags, and it is expected to encourage the development of rail detection. We extensively compare DALNet with many competitive lane methods. The results show that our DALNet achieves state-of-the-art performance on our DL-Rail rail detection dataset and the popular Tusimple and LLAMAS lane detection benchmarks. The code will be released at https://github.com/Yzichen/mmLaneDet.
Authors: Haechan Mark Bong, Rongge Zhang, Ricardo de Azambuja, Giovanni Beltrame
This work targets what we consider to be the foundational step for urban airborne robots, a safe landing. Our attention is directed toward what we deem the most crucial aspect of the safe landing perception stack: segmentation. We present a streamlined reactive UAV system that employs visual servoing by harnessing the capabilities of open vocabulary image segmentation. This approach can adapt to various scenarios with minimal adjustments, bypassing the necessity for extensive data accumulation for refining internal models, thanks to its open vocabulary methodology. Given the limitations imposed by local authorities, our primary focus centers on operations originating from altitudes of 100 meters. This choice is deliberate, as numerous preceding works have dealt with altitudes up to 30 meters, aligning with the capabilities of small stereo cameras. Consequently, we leave the remaining 20m to be navigated using conventional 3D path planning methods. Utilizing monocular cameras and image segmentation, our findings demonstrate the system's capability to successfully execute landing maneuvers at altitudes as low as 20 meters. However, this approach is vulnerable to intermittent and occasionally abrupt fluctuations in the segmentation between frames in a video stream. To address this challenge, we enhance the image segmentation output by introducing what we call a dynamic focus: a masking mechanism that self adjusts according to the current landing stage. This dynamic focus guides the control system to avoid regions beyond the drone's safety radius projected onto the ground, thus mitigating the problems with fluctuations. Through the implementation of this supplementary layer, our experiments have reached improvements in the landing success rate of almost tenfold when compared to global segmentation. All the source code is open source and available online (github.com/MISTLab/DOVESEI).
Authors: Yash Patel, Tirth Shah, Mrinal Kanti Dhar, Taiyu Zhang, Jeffrey Niezgoda, Sandeep Gopalakrishnan, Zeyun Yu
The global burden of acute and chronic wounds presents a compelling case for enhancing wound classification methods, a vital step in diagnosing and determining optimal treatments. Recognizing this need, we introduce an innovative multi-modal network based on a deep convolutional neural network for categorizing wounds into four categories: diabetic, pressure, surgical, and venous ulcers. Our multi-modal network uses wound images and their corresponding body locations for more precise classification. A unique aspect of our methodology is incorporating a body map system that facilitates accurate wound location tagging, improving upon traditional wound image classification techniques. A distinctive feature of our approach is the integration of models such as VGG16, ResNet152, and EfficientNet within a novel architecture. This architecture includes elements like spatial and channel-wise Squeeze-and-Excitation modules, Axial Attention, and an Adaptive Gated Multi-Layer Perceptron, providing a robust foundation for classification. Our multi-modal network was trained and evaluated on two distinct datasets comprising relevant images and corresponding location information. Notably, our proposed network outperformed traditional methods, reaching an accuracy range of 74.79% to 100% for Region of Interest (ROI) without location classifications, 73.98% to 100% for ROI with location classifications, and 78.10% to 100% for whole image classifications. This marks a significant enhancement over previously reported performance metrics in the literature. Our results indicate the potential of our multi-modal network as an effective decision-support tool for wound image classification, paving the way for its application in various clinical contexts.
Authors: Cheng Zhu, Jiayi Zhu, Lijuan Zhang, Xi Wu, Shuqi Yang, Ping Liang, Honghan Chen, Ying Tan
Graph Convolutional Networks (GCNs) can capture non-Euclidean spatial dependence between different brain regions, and the graph pooling operator in GCNs is key to enhancing the representation learning capability and acquiring abnormal brain maps. However, the majority of existing research designs graph pooling operators only from the perspective of nodes while disregarding the original edge features, in a way that not only confines graph pooling application scenarios, but also diminishes its ability to capture critical substructures. In this study, a clustering graph pooling method that first supports multidimensional edge features, called Edge-aware hard clustering graph pooling (EHCPool), is developed. EHCPool proposes the first 'Edge-to-node' score evaluation criterion based on edge features to assess node feature significance. To more effectively capture the critical subgraphs, a novel Iteration n-top strategy is further designed to adaptively learn sparse hard clustering assignments for graphs. Subsequently, an innovative N-E Aggregation strategy is presented to aggregate node and edge feature information in each independent subgraph. The proposed model was evaluated on multi-site brain imaging public datasets and yielded state-of-the-art performance. We believe this method is the first deep learning tool with the potential to probe different types of abnormal functional brain networks from data-driven perspective.
Authors: Hyekang Park, Jongyoun Noh, Youngmin Oh, Donghyeon Baek, Bumsub Ham
We address the problem of network calibration adjusting miscalibrated confidences of deep neural networks. Many approaches to network calibration adopt a regularization-based method that exploits a regularization term to smooth the miscalibrated confidences. Although these approaches have shown the effectiveness on calibrating the networks, there is still a lack of understanding on the underlying principles of regularization in terms of network calibration. We present in this paper an in-depth analysis of existing regularization-based methods, providing a better understanding on how they affect to network calibration. Specifically, we have observed that 1) the regularization-based methods can be interpreted as variants of label smoothing, and 2) they do not always behave desirably. Based on the analysis, we introduce a novel loss function, dubbed ACLS, that unifies the merits of existing regularization methods, while avoiding the limitations. We show extensive experimental results for image classification and semantic segmentation on standard benchmarks, including CIFAR10, Tiny-ImageNet, ImageNet, and PASCAL VOC, demonstrating the effectiveness of our loss function.
Authors: Hualiang Wang, Yi Li, Huifeng Yao, Xiaomeng Li
Out-of-distribution (OOD) detection refers to training the model on an in-distribution (ID) dataset to classify whether the input images come from unknown classes. Considerable effort has been invested in designing various OOD detection methods based on either convolutional neural networks or transformers. However, zero-shot OOD detection methods driven by CLIP, which only require class names for ID, have received less attention. This paper presents a novel method, namely CLIP saying no (CLIPN), which empowers the logic of saying no within CLIP. Our key motivation is to equip CLIP with the capability of distinguishing OOD and ID samples using positive-semantic prompts and negation-semantic prompts. Specifically, we design a novel learnable no prompt and a no text encoder to capture negation semantics within images. Subsequently, we introduce two loss functions: the image-text binary-opposite loss and the text semantic-opposite loss, which we use to teach CLIPN to associate images with no prompts, thereby enabling it to identify unknown samples. Furthermore, we propose two threshold-free inference algorithms to perform OOD detection by utilizing negation semantics from no prompts and the text encoder. Experimental results on 9 benchmark datasets (3 ID datasets and 6 OOD datasets) for the OOD detection task demonstrate that CLIPN, based on ViT-B-16, outperforms 7 well-used algorithms by at least 2.34% and 11.64% in terms of AUROC and FPR95 for zero-shot OOD detection on ImageNet-1K. Our CLIPN can serve as a solid foundation for effectively leveraging CLIP in downstream OOD tasks. The code is available on https://github.com/xmed-lab/CLIPN.
Authors: Rafael Henrique Vareto, Araceli Marcia Sandanha, William Robson Schwartz
A face spoofing attack occurs when an intruder attempts to impersonate someone who carries a gainful authentication clearance. It is a trending topic due to the increasing demand for biometric authentication on mobile devices, high-security areas, among others. This work introduces a new database named Sense Wax Attack dataset (SWAX), comprised of real human and wax figure images and videos that endorse the problem of face spoofing detection. The dataset consists of more than 1800 face images and 110 videos of 55 people/waxworks, arranged in training, validation and test sets with a large range in expression, illumination and pose variations. Experiments performed with baseline methods show that despite the progress in recent years, advanced spoofing methods are still vulnerable to high-quality violation attempts.
Authors: Rafael Henrique Vareto, William Robson Schwartz
Open-set face recognition describes a scenario where unknown subjects, unseen during the training stage, appear on test time. Not only it requires methods that accurately identify individuals of interest, but also demands approaches that effectively deal with unfamiliar faces. This work details a scalable open-set face identification approach to galleries composed of hundreds and thousands of subjects. It is composed of clustering and an ensemble of binary learning algorithms that estimates when query face samples belong to the face gallery and then retrieves their correct identity. The approach selects the most suitable gallery subjects and uses the ensemble to improve prediction performance. We carry out experiments on well-known LFW and YTF benchmarks. Results show that competitive performance can be achieved even when targeting scalability.