Authors: Faraz Waseem, Pratyush Muthukumar
We approached the goal of applying meta-learning to self-supervised masked autoencoders for spatiotemporal learning in three steps. Broadly, we seek to understand the impact of applying meta-learning to existing state-of-the-art representation learning architectures. Thus, we test spatiotemporal learning through: a meta-learning architecture only, a representation learning architecture only, and an architecture applying representation learning alongside a meta learning architecture. We utilize the Memory Augmented Neural Network (MANN) architecture to apply meta-learning to our framework. Specifically, we first experiment with applying a pre-trained MAE and fine-tuning on our small-scale spatiotemporal dataset for video reconstruction tasks. Next, we experiment with training an MAE encoder and applying a classification head for action classification tasks. Finally, we experiment with applying a pre-trained MAE and fine-tune with MANN backbone for action classification tasks.
Authors: Yunfei Guo, Tao Zhang, Wu Huang
Emotion recognition is an important research direction in artificial intelligence, helping machines understand and adapt to human emotional states. Multimodal electrophysiological(ME) signals, such as EEG, GSR, respiration(Resp), and temperature(Temp), are effective biomarkers for reflecting changes in human emotions. However, using electrophysiological signals for emotion recognition faces challenges such as data scarcity, inconsistent labeling, and difficulty in cross-individual generalization. To address these issues, we propose ME-MHACL, a self-supervised contrastive learning-based multimodal emotion recognition method that can learn meaningful feature representations from unlabeled electrophysiological signals and use multi-head attention mechanisms for feature fusion to improve recognition performance. Our method includes two stages: first, we use the Meiosis method to group sample and augment unlabeled electrophysiological signals and design a self-supervised contrastive learning task; second, we apply the trained feature extractor to labeled electrophysiological signals and use multi-head attention mechanisms for feature fusion. We conducted experiments on two public datasets, DEAP and MAHNOB-HCI, and our method outperformed existing benchmark methods in emotion recognition tasks and had good cross-individual generalization ability.
Authors: Dr Petar Radanliev, Professor David De Roure, Dr Peter Novitzky, Dr Ivo Sluganovic
Despite the proliferation of Blockchain Metaverse projects, the inclusion of physically disabled individuals in the Metaverse remains distant, with limited standards and regulations in place. However, the article proposes a concept of the Metaverse that leverages emerging technologies, such as Virtual and Augmented Reality, and the Internet of Things, to enable greater engagement of disabled creatives. This approach aims to enhance inclusiveness in the Metaverse landscape. Based on the findings, the paper concludes that the active involvement of physically disabled individuals in the design and development of Metaverse platforms is crucial for promoting inclusivity. The proposed framework for accessibility and inclusiveness in Virtual, Augmented, and Mixed realities of decentralised Metaverses provides a basis for the meaningful participation of disabled creatives. The article emphasises the importance of addressing the mechanisms for art production by individuals with disabilities in the emerging Metaverse landscape. Additionally, it highlights the need for further research and collaboration to establish standards and regulations that facilitate the inclusion of physically disabled individuals in Metaverse projects.
Authors: Aditya Golatkar, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto
We introduce Compartmentalized Diffusion Models (CDM), a method to train different diffusion models (or prompts) on distinct data sources and arbitrarily compose them at inference time. The individual models can be trained in isolation, at different times, and on different distributions and domains and can be later composed to achieve performance comparable to a paragon model trained on all data simultaneously. Furthermore, each model only contains information about the subset of the data it was exposed to during training, enabling several forms of training data protection. In particular, CDMs are the first method to enable both selective forgetting and continual learning for large-scale diffusion models, as well as allowing serving customized models based on the user's access rights. CDMs also allow determining the importance of a subset of the data in generating particular samples.
Authors: Qi Yang, Joel Jung, Haiqiang Wang, Xiaozhong Xu, Shan Liu
Static meshes with texture map are widely used in modern industrial and manufacturing sectors, attracting considerable attention in the mesh compression community due to its huge amount of data. To facilitate the study of static mesh compression algorithm and objective quality metric, we create the Tencent - Static Mesh Dataset (TSMD) containing 42 reference meshes with rich visual characteristics. 210 distorted samples are generated by the lossy compression scheme developed for the Call for Proposals on polygonal static mesh coding, released on June 23 by the Alliance for Open Media Volumetric Visual Media group. Using processed video sequences, a large-scale, crowdsourcing-based, subjective experiment was conducted to collect subjective scores from 74 viewers. The dataset undergoes analysis to validate its sample diversity and Mean Opinion Scores (MOS) accuracy, establishing its heterogeneous nature and reliability. State-of-the-art objective metrics are evaluated on the new dataset. Pearson and Spearman correlations around 0.75 are reported, deviating from results typically observed on less heterogeneous datasets, demonstrating the need for further development of more robust metrics. The TSMD, including meshes, PVSs, bitstreams, and MOS, is made publicly available at the following location: https://multimedia.tencent.com/resources/tsmd.
Authors: Yuang Liu, Qiang Zhou, Jing Wang, Fan Wang, Jun Wang, Wei Zhang
Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe. In this paper, we introduce dynamic token-pass vision transformers (DoViT) for semantic segmentation, which can adaptively reduce the inference cost for images with different complexity. DoViT gradually stops partial easy tokens from self-attention calculation and keeps the hard tokens forwarding until meeting the stopping criteria. We employ lightweight auxiliary heads to make the token-pass decision and divide the tokens into keeping/stopping parts. With a token separate calculation, the self-attention layers are speeded up with sparse tokens and still work friendly with hardware. A token reconstruction module is built to collect and reset the grouped tokens to their original position in the sequence, which is necessary to predict correct semantic masks. We conduct extensive experiments on two common semantic segmentation tasks, and demonstrate that our method greatly reduces about 40% $\sim$ 60% FLOPs and the drop of mIoU is within 0.8% for various segmentation transformers. The throughput and inference speed of ViT-L/B are increased to more than 2$\times$ on Cityscapes.
Authors: Jannik Brinkmann, Paul Swoboda, Christian Bartelt
The embedding spaces of image models have been shown to encode a range of social biases such as racism and sexism. Here, we investigate specific factors that contribute to the emergence of these biases in Vision Transformers (ViT). Therefore, we measure the impact of training data, model architecture, and training objectives on social biases in the learned representations of ViTs. Our findings indicate that counterfactual augmentation training using diffusion-based image editing can mitigate biases, but does not eliminate them. Moreover, we find that larger models are less biased than smaller models, and that models trained using discriminative objectives are less biased than those trained using generative objectives. In addition, we observe inconsistencies in the learned social biases. To our surprise, ViTs can exhibit opposite biases when trained on the same data set using different self-supervised objectives. Our findings give insights into the factors that contribute to the emergence of social biases and suggests that we could achieve substantial fairness improvements based on model design choices.
Authors: Saleem Ahmed, Pengyu Yan, David Doermann, Srirangaraj Setlur, Venu Govindaraju
We introduce a novel bottom-up approach for the extraction of chart data. Our model utilizes images of charts as inputs and learns to detect keypoints (KP), which are used to reconstruct the components within the plot area. Our novelty lies in detecting a fusion of continuous and discrete KP as predicted heatmaps. A combination of sparse and dense per-pixel objectives coupled with a uni-modal self-attention-based feature-fusion layer is applied to learn KP embeddings. Further leveraging deep metric learning for unsupervised clustering, allows us to segment the chart plot area into various objects. By further matching the chart components to the legend, we are able to obtain the data series names. A post-processing threshold is applied to the KP embeddings to refine the object reconstructions and improve accuracy. Our extensive experiments include an evaluation of different modules for KP estimation and the combination of deep layer aggregation and corner pooling approaches. The results of our experiments provide extensive evaluation for the task of real-world chart data extraction.
Authors: Saleem Ahmed, Bhavin Jawade, Shubham Pandey, Srirangaraj Setlur, Venu Govindaraju
We present a comprehensive study of chart visual question-answering(QA) task, to address the challenges faced in comprehending and extracting data from chart visualizations within documents. Despite efforts to tackle this problem using synthetic charts, solutions are limited by the shortage of annotated real-world data. To fill this gap, we introduce a benchmark and dataset for chart visual QA on real-world charts, offering a systematic analysis of the task and a novel taxonomy for template-based chart question creation. Our contribution includes the introduction of a new answer type, 'list', with both ranked and unranked variations. Our study is conducted on a real-world chart dataset from scientific literature, showcasing higher visual complexity compared to other works. Our focus is on template-based QA and how it can serve as a standard for evaluating the first-order logic capabilities of models. The results of our experiments, conducted on a real-world out-of-distribution dataset, provide a robust evaluation of large-scale pre-trained models and advance the field of chart visual QA and formal logic verification for neural networks in general.
Authors: Yongcheng Yao, Junru Zhong, Liping Zhang, Sheheryar Khan, Weitian Chen
We introduce CartiMorph, a framework for automated knee articular cartilage morphometrics. It takes an image as input and generates quantitative metrics for cartilage subregions, including the percentage of full-thickness cartilage loss (FCL), mean thickness, surface area, and volume. CartiMorph leverages the power of deep learning models for hierarchical image feature representation. Deep learning models were trained and validated for tissue segmentation, template construction, and template-to-image registration. We established methods for surface-normal-based cartilage thickness mapping, FCL estimation, and rule-based cartilage parcellation. Our cartilage thickness map showed less error in thin and peripheral regions. We evaluated the effectiveness of the adopted segmentation model by comparing the quantitative metrics obtained from model segmentation and those from manual segmentation. The root-mean-squared deviation of the FCL measurements was less than 8%, and strong correlations were observed for the mean thickness (Pearson's correlation coefficient $\rho \in [0.82,0.97]$), surface area ($\rho \in [0.82,0.98]$) and volume ($\rho \in [0.89,0.98]$) measurements. We compared our FCL measurements with those from a previous study and found that our measurements deviated less from the ground truths. We observed superior performance of the proposed rule-based cartilage parcellation method compared with the atlas-based approach. CartiMorph has the potential to promote imaging biomarkers discovery for knee osteoarthritis.
Authors: Amir Akbarnejad, Nilanjan Ray, Penny J. Barnes, Gilbert Bigras
Despite the advances in machine learning and digital pathology, it is not yet clear if machine learning methods can accurately predict molecular information merely from histomorphology. In a quest to answer this question, we built a large-scale dataset (185538 images) with reliable measurements for Ki67, ER, PR, and HER2 statuses. The dataset is composed of mirrored images of H\&E and corresponding images of immunohistochemistry (IHC) assays (Ki67, ER, PR, and HER2. These images are mirrored through registration. To increase reliability, individual pairs were inspected and discarded if artifacts were present (tissue folding, bubbles, etc). Measurements for Ki67, ER and PR were determined by calculating H-Score from image analysis. HER2 measurement is based on binary classification: 0 and 1+ (IHC scores representing a negative subset) vs 3+ (IHC score positive subset). Cases with IHC equivocal score (2+) were excluded. We show that a standard ViT-based pipeline can achieve prediction performances around 90% in terms of Area Under the Curve (AUC) when trained with a proper labeling protocol. Finally, we shed light on the ability of the trained classifiers to localize relevant regions, which encourages future work to improve the localizations. Our proposed dataset is publicly available: https://ihc4bc.github.io/
Authors: Chengjia Wang, Giorgos Papanastasiou
Clinical decision making from magnetic resonance imaging (MRI) combines complementary information from multiple MRI sequences (defined as 'modalities'). MRI image registration aims to geometrically 'pair' diagnoses from different modalities, time points and slices. Both intra- and inter-modality MRI registration are essential components in clinical MRI settings. Further, an MRI image processing pipeline that can address both afine and non-rigid registration is critical, as both types of deformations may be occuring in real MRI data scenarios. Unlike image classification, explainability is not commonly addressed in image registration deep learning (DL) methods, as it is challenging to interpet model-data behaviours against transformation fields. To properly address this, we incorporate Grad-CAM-based explainability frameworks in each major component of our unsupervised multi-modal and multi-organ image registration DL methodology. We previously demonstrated that we were able to reach superior performance (against the current standard Syn method). In this work, we show that our DL model becomes fully explainable, setting the framework to generalise our approach on further medical imaging data.
Authors: Junyan Cheng, Peter Chin
Bridging the huge disparity between neural and symbolic representation can potentially enable the incorporation of symbolic thinking into neural networks from essence. Motivated by how human gradually builds complex symbolic representation from the prototype symbols that are learned through perception and environmental interactions. We propose a Neural-Symbolic Transitional Dictionary Learning (TDL) framework that employs an EM algorithm to learn a transitional representation of data that compresses high-dimension information of visual parts of an input into a set of tensors as neural variables and discover the implicit predicate structure in a self-supervised way. We implement the framework with a diffusion model by regarding the decomposition of input as a cooperative game, then learn predicates by prototype clustering. We additionally use RL enabled by the Markovian of diffusion models to further tune the learned prototypes by incorporating subjective factors. Extensive experiments on 3 abstract compositional visual objects datasets that require the model to segment parts without any visual features like texture, color, or shadows apart from shape and 3 neural/symbolic downstream tasks demonstrate the learned representation enables interpretable decomposition of visual input and smooth adaption to downstream tasks which are not available by existing methods.
Authors: Mohsen Gholami, Mohammad Akbari, Xinglu Wang, Behnam Kamranian, Yong Zhang
This paper addresses the problem of ranking pre-trained models for object detection and image classification. Selecting the best pre-trained model by fine-tuning is an expensive and time-consuming task. Previous works have proposed transferability estimation based on features extracted by the pre-trained models. We argue that quantifying whether the target dataset is in-distribution (IND) or out-of-distribution (OOD) for the pre-trained model is an important factor in the transferability estimation. To this end, we propose ETran, an energy-based transferability assessment metric, which includes three scores: 1) energy score, 2) classification score, and 3) regression score. We use energy-based models to determine whether the target dataset is OOD or IND for the pre-trained model. In contrast to the prior works, ETran is applicable to a wide range of tasks including classification, regression, and object detection (classification+regression). This is the first work that proposes transferability estimation for object detection task. Our extensive experiments on four benchmarks and two tasks show that ETran outperforms previous works on object detection and classification benchmarks by an average of 21% and 12%, respectively, and achieves SOTA in transferability assessment.
Authors: Alexey Nekrasov, Alexander Hermans, Lars Kuhnert, Bastian Leibe
A single unexpected object on the road can cause an accident or may lead to injuries. To prevent this, we need a reliable mechanism for finding anomalous objects on the road. This task, called anomaly segmentation, can be a stepping stone to safe and reliable autonomous driving. Current approaches tackle anomaly segmentation by assigning an anomaly score to each pixel and by grouping anomalous regions using simple heuristics. However, pixel grouping is a limiting factor when it comes to evaluating the segmentation performance of individual anomalous objects. To address the issue of grouping multiple anomaly instances into one, we propose an approach that produces accurate anomaly instance masks. Our approach centers on an out-of-distribution segmentation model for identifying uncertain regions and a strong generalist segmentation model for anomaly instances segmentation. We investigate ways to use uncertain regions to guide such a segmentation model to perform segmentation of anomalous instances. By incorporating strong object priors from a generalist model we additionally improve the per-pixel anomaly segmentation performance. Our approach outperforms current pixel-level anomaly segmentation methods, achieving an AP of 80.08% and 88.98% on the Fishyscapes Lost and Found and the RoadAnomaly validation sets respectively. Project page: https://vision.rwth-aachen.de/ugains
Authors: Alessandro Fontanella, Grant Mair, Joanna Wardlaw, Emanuele Trucco, Amos Storkey
Segmentation masks of pathological areas are useful in many medical applications, such as brain tumour and stroke management. Moreover, healthy counterfactuals of diseased images can be used to enhance radiologists' training files and to improve the interpretability of segmentation models. In this work, we present a weakly supervised method to generate a healthy version of a diseased image and then use it to obtain a pixel-wise anomaly map. To do so, we start by considering a saliency map that approximately covers the pathological areas, obtained with ACAT. Then, we propose a technique that allows to perform targeted modifications to these regions, while preserving the rest of the image. In particular, we employ a diffusion model trained on healthy samples and combine Denoising Diffusion Probabilistic Model (DDPM) and Denoising Diffusion Implicit Model (DDIM) at each step of the sampling process. DDPM is used to modify the areas affected by a lesion within the saliency map, while DDIM guarantees reconstruction of the normal anatomy outside of it. The two parts are also fused at each timestep, to guarantee the generation of a sample with a coherent appearance and a seamless transition between edited and unedited parts. We verify that when our method is applied to healthy samples, the input images are reconstructed without significant modifications. We compare our approach with alternative weakly supervised methods on IST-3 for stroke lesion segmentation and on BraTS2021 for brain tumour segmentation, where we improve the DICE score of the best competing method from $0.6534$ to $0.7056$.
Authors: Vishnu Naresh Boddeti, Gautam Sreekumar, Arun Ross
There has been tremendous progress in generating realistic faces with high fidelity over the past few years. Despite this progress, a crucial question remains unanswered: "Given a generative face model, how many unique identities can it generate?" In other words, what is the biometric capacity of the generative face model? A scientific basis for answering this question will benefit evaluating and comparing different generative face models and establish an upper bound on their scalability. This paper proposes a statistical approach to estimate the biometric capacity of generated face images in a hyperspherical feature space. We employ our approach on multiple generative models, including unconditional generators like StyleGAN, Latent Diffusion Model, and "Generated Photos," as well as DCFace, a class-conditional generator. We also estimate capacity w.r.t. demographic attributes such as gender and age. Our capacity estimates indicate that (a) under ArcFace representation at a false acceptance rate (FAR) of 0.1%, StyleGAN3 and DCFace have a capacity upper bound of $1.43\times10^6$ and $1.190\times10^4$, respectively; (b) the capacity reduces drastically as we lower the desired FAR with an estimate of $1.796\times10^4$ and $562$ at FAR of 1% and 10%, respectively, for StyleGAN3; (c) there is no discernible disparity in the capacity w.r.t gender; and (d) for some generative models, there is an appreciable disparity in the capacity w.r.t age. Code is available at https://github.com/human-analysis/capacity-generative-face-models.
Authors: Chuntao Ding, Zhichao Lu, Shangguang Wang, Ran Cheng, Vishnu Naresh Boddeti
Multi-task learning (MTL) seeks to learn a single model to accomplish multiple tasks by leveraging shared information among the tasks. Existing MTL models, however, have been known to suffer from negative interference among tasks. Efforts to mitigate task interference have focused on either loss/gradient balancing or implicit parameter partitioning with partial overlaps among the tasks. In this paper, we propose ETR-NLP to mitigate task interference through a synergistic combination of non-learnable primitives (NLPs) and explicit task routing (ETR). Our key idea is to employ non-learnable primitives to extract a diverse set of task-agnostic features and recombine them into a shared branch common to all tasks and explicit task-specific branches reserved for each task. The non-learnable primitives and the explicit decoupling of learnable parameters into shared and task-specific ones afford the flexibility needed for minimizing task interference. We evaluate the efficacy of ETR-NLP networks for both image-level classification and pixel-level dense prediction MTL problems. Experimental results indicate that ETR-NLP significantly outperforms state-of-the-art baselines with fewer learnable parameters and similar FLOPs across all datasets. Code is available at this \href{https://github.com/zhichao-lu/etr-nlp-mtl}.
Authors: Zachary A. Daniels, Jun Hu, Michael Lomnitz, Phil Miller, Aswin Raghavan, Joe Zhang, Michael Piacentino, David Zhang
Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed on real devices, data distributions often shift over time due to changes in environmental factors, sensor characteristics, and task-of-interest. While it is possible to have a human-in-the-loop to monitor for distribution shifts and engineer new architectures in response to these shifts, such a setup is not cost-effective. Instead, non-stationary automated ML (AutoML) models are needed. This paper presents the Encoder-Adaptor-Reconfigurator (EAR) framework for efficient continual learning under domain shifts. The EAR framework uses a fixed deep neural network (DNN) feature encoder and trains shallow networks on top of the encoder to handle novel data. The EAR framework is capable of 1) detecting when new data is out-of-distribution (OOD) by combining DNNs with hyperdimensional computing (HDC), 2) identifying low-parameter neural adaptors to adapt the model to the OOD data using zero-shot neural architecture search (ZS-NAS), and 3) minimizing catastrophic forgetting on previous tasks by progressively growing the neural architecture as needed and dynamically routing data through the appropriate adaptors and reconfigurators for handling domain-incremental and class-incremental continual learning. We systematically evaluate our approach on several benchmark datasets for domain adaptation and demonstrate strong performance compared to state-of-the-art algorithms for OOD detection and few-/zero-shot NAS.
Authors: Jinyuan Liu, Zhu Liu, Guanyao Wu, Long Ma, Risheng Liu, Wei Zhong, Zhongxuan Luo, Xin Fan
Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. Early efforts focus on boosting the performance for only one task, \emph{e.g.,} fusion or segmentation, making it hard to reach~`Best of Both Worlds'. To overcome this issue, in this paper, we propose a \textbf{M}ulti-\textbf{i}nteractive \textbf{F}eature learning architecture for image fusion and \textbf{Seg}mentation, namely SegMiF, and exploit dual-task correlation to promote the performance of both tasks. The SegMiF is of a cascade structure, containing a fusion sub-network and a commonly used segmentation sub-network. By slickly bridging intermediate features between two components, the knowledge learned from the segmentation task can effectively assist the fusion task. Also, the benefited fusion network supports the segmentation one to perform more pretentiously. Besides, a hierarchical interactive attention block is established to ensure fine-grained mapping of all the vital information between two tasks, so that the modality/semantic features can be fully mutual-interactive. In addition, a dynamic weight factor is introduced to automatically adjust the corresponding weights of each task, which can balance the interactive feature correspondence and break through the limitation of laborious tuning. Furthermore, we construct a smart multi-wave binocular imaging system and collect a full-time multi-modality benchmark with 15 annotated pixel-level categories for image fusion and segmentation. Extensive experiments on several public datasets and our benchmark demonstrate that the proposed method outputs visually appealing fused images and perform averagely $7.66\%$ higher segmentation mIoU in the real-world scene than the state-of-the-art approaches. The source code and benchmark are available at \url{https://github.com/JinyuanLiu-CV/SegMiF}.
Authors: Yiran Sun, Tucker Netherton, Laurence Court, Ashok Veeraraghavan, Guha Balakrishnan
CT scans are the standard-of-care for many clinical ailments, and are needed for treatments like external beam radiotherapy. Unfortunately, CT scanners are rare in low and mid-resource settings due to their costs. Planar X-ray radiography units, in comparison, are far more prevalent, but can only provide limited 2D observations of the 3D anatomy. In this work, we propose a method to generate CT volumes from few (<5) planar X-ray observations using a prior data distribution, and perform the first evaluation of such a reconstruction algorithm for a clinical application: radiotherapy planning. We propose a deep generative model, building on advances in neural implicit representations to synthesize volumetric CT scans from few input planar X-ray images at different angles. To focus the generation task on clinically-relevant features, our model can also leverage anatomical guidance during training (via segmentation masks). We generated 2-field opposed, palliative radiotherapy plans on thoracic CTs reconstructed by our method, and found that isocenter radiation dose on reconstructed scans have <1% error with respect to the dose calculated on clinically acquired CTs using <=4 X-ray views. In addition, our method is better than recent sparse CT reconstruction baselines in terms of standard pixel and structure-level metrics (PSNR, SSIM, Dice score) on the public LIDC lung CT dataset. Code is available at: https://github.com/wanderinrain/Xray2CT.
Authors: Bryar Shareef, Min Xian, Aleksandar Vakanski, Haotian Wang
Capturing global contextual information plays a critical role in breast ultrasound (BUS) image classification. Although convolutional neural networks (CNNs) have demonstrated reliable performance in tumor classification, they have inherent limitations for modeling global and long-range dependencies due to the localized nature of convolution operations. Vision Transformers have an improved capability of capturing global contextual information but may distort the local image patterns due to the tokenization operations. In this study, we proposed a hybrid multitask deep neural network called Hybrid-MT-ESTAN, designed to perform BUS tumor classification and segmentation using a hybrid architecture composed of CNNs and Swin Transformer components. The proposed approach was compared to nine BUS classification methods and evaluated using seven quantitative metrics on a dataset of 3,320 BUS images. The results indicate that Hybrid-MT-ESTAN achieved the highest accuracy, sensitivity, and F1 score of 82.7%, 86.4%, and 86.0%, respectively.
Authors: Jiawei Chen, Xiao Yang, Heng Yin, Mingzhi Ma, Bihui Chen, Jianteng Peng, Yandong Guo, Zhaoxia Yin, Hang Su
Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art methods to defend against adversarial examples remains elusive. While several adversarial defense strategies have been proposed, they typically suffer from constrained practicability due to inevitable trade-offs between universality, effectiveness, and efficiency. To overcome these challenges, we thoroughly delve into the coupled relationship between adversarial detection and face anti-spoofing. Based on this, we propose a robust face anti-spoofing framework, namely AdvFAS, that leverages two coupled scores to accurately distinguish between correctly detected and wrongly detected face images. Extensive experiments demonstrate the effectiveness of our framework in a variety of settings, including different attacks, datasets, and backbones, meanwhile enjoying high accuracy on clean examples. Moreover, we successfully apply the proposed method to detect real-world adversarial examples.
Authors: Ling Yang, Ye Tian, Minkai Xu, Zhongyi Liu, Shenda Hong, Wei Qu, Wentao Zhang, Bin Cui, Muhan Zhang, Jure Leskovec
Graph Neural Networks (GNNs) conduct message passing which aggregates local neighbors to update node representations. Such message passing leads to scalability issues in practical latency-constrained applications. To address this issue, recent methods adopt knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (MLP) by mimicking the output of GNN. However, the existing GNN representation space may not be expressive enough for representing diverse local structures of the underlying graph, which limits the knowledge transfer from GNN to MLP. Here we present a novel framework VQGraph to learn a powerful graph representation space for bridging GNNs and MLPs. We adopt the encoder of a variant of a vector-quantized variational autoencoder (VQ-VAE) as a structure-aware graph tokenizer, which explicitly represents the nodes of diverse local structures as numerous discrete tokens and constitutes a meaningful codebook. Equipped with the learned codebook, we propose a new token-based distillation objective based on soft token assignments to sufficiently transfer the structural knowledge from GNN to MLP. Extensive experiments and analyses demonstrate the strong performance of VQGraph, where we achieve new state-of-the-art performance on GNN-MLP distillation in both transductive and inductive settings across seven graph datasets. We show that VQGraph with better performance infers faster than GNNs by 828x, and also achieves accuracy improvement over GNNs and stand-alone MLPs by 3.90% and 28.05% on average, respectively. Code: https://github.com/YangLing0818/VQGraph.
Authors: Hang-Cheng Dong, Yuhao Jiang, Yingyan Huang, Jingxiao Liao, Bingguo Liu, Dong Ye, Guodong Liu
Class activation maps are widely used for explaining deep neural networks. Due to its ability to highlight regions of interest, it has evolved in recent years as a key step in weakly supervised learning. A major limitation to the performance of the class activation maps is the small spatial resolution of the feature maps in the last layer of the convolutional neural network. Therefore, we expect to generate high-resolution feature maps that result in high-quality semantic information. In this paper, we rethink the properties of semantic information in shallow feature maps. We find that the shallow feature maps still have fine-grained non-discriminative features while mixing considerable non-target noise. Furthermore, we propose a simple gradient-based denoising method to filter the noise by truncating the positive gradient. Our proposed scheme can be easily deployed in other CAM-related methods, facilitating these methods to obtain higher-quality class activation maps. We evaluate the proposed approach through a weakly-supervised semantic segmentation task, and a large number of experiments demonstrate the effectiveness of our approach.
Authors: Mingzhe Hu, Xiaofeng Yang
This study presents a lightweight pipeline for skin lesion detection, addressing the challenges posed by imbalanced class distribution and subtle or atypical appearances of some lesions. The pipeline is built around a lightweight model that leverages ghosted features and the DFC attention mechanism to reduce computational complexity while maintaining high performance. The model was trained on the HAM10000 dataset, which includes various types of skin lesions. To address the class imbalance in the dataset, the synthetic minority over-sampling technique and various image augmentation techniques were used. The model also incorporates a knowledge-based loss weighting technique, which assigns different weights to the loss function at the class level and the instance level, helping the model focus on minority classes and challenging samples. This technique involves assigning different weights to the loss function on two levels - the class level and the instance level. By applying appropriate loss weights, the model pays more attention to the minority classes and challenging samples, thus improving its ability to correctly detect and classify different skin lesions. The model achieved an accuracy of 92.4%, a precision of 84.2%, a recall of 86.9%, a f1-score of 85.4% with particularly strong performance in identifying Benign Keratosis-like lesions (BKL) and Nevus (NV). Despite its superior performance, the model's computational cost is considerably lower than some models with less accuracy, making it an optimal solution for real-world applications where both accuracy and efficiency are essential.
Authors: Takayuki Kanai, Igor Vasiljevic, Vitor Guizilini, Adrien Gaidon, Rares Ambrus
Autonomous vehicles and robots need to operate over a wide variety of scenarios in order to complete tasks efficiently and safely. Multi-camera self-supervised monocular depth estimation from videos is a promising way to reason about the environment, as it generates metrically scaled geometric predictions from visual data without requiring additional sensors. However, most works assume well-calibrated extrinsics to fully leverage this multi-camera setup, even though accurate and efficient calibration is still a challenging problem. In this work, we introduce a novel method for extrinsic calibration that builds upon the principles of self-supervised monocular depth and ego-motion learning. Our proposed curriculum learning strategy uses monocular depth and pose estimators with velocity supervision to estimate extrinsics, and then jointly learns extrinsic calibration along with depth and pose for a set of overlapping cameras rigidly attached to a moving vehicle. Experiments on a benchmark multi-camera dataset (DDAD) demonstrate that our method enables self-calibration in various scenes robustly and efficiently compared to a traditional vision-based pose estimation pipeline. Furthermore, we demonstrate the benefits of extrinsics self-calibration as a way to improve depth prediction via joint optimization.
Authors: Shikun Sun, Longhui Wei, Junliang Xing, Jia Jia, Qi Tian
Recent score-based diffusion models (SBDMs) show promising results in unpaired image-to-image translation (I2I). However, existing methods, either energy-based or statistically-based, provide no explicit form of the interfered intermediate generative distributions. This work presents a new score-decomposed diffusion model (SDDM) on manifolds to explicitly optimize the tangled distributions during image generation. SDDM derives manifolds to make the distributions of adjacent time steps separable and decompose the score function or energy guidance into an image ``denoising" part and a content ``refinement" part. To refine the image in the same noise level, we equalize the refinement parts of the score function and energy guidance, which permits multi-objective optimization on the manifold. We also leverage the block adaptive instance normalization module to construct manifolds with lower dimensions but still concentrated with the perturbed reference image. SDDM outperforms existing SBDM-based methods with much fewer diffusion steps on several I2I benchmarks.
Authors: Xin Liao, Siliang Chen, Jiaxin Chen, Tianyi Wang, Xiehua Li
Due to the progression of information technology in recent years, document images have been widely disseminated in social networks. With the help of powerful image editing tools, document images are easily forged without leaving visible manipulation traces, which leads to severe issues if significant information is falsified for malicious use. Therefore, the research of document image forensics is worth further exploring. In a document image, the character with specific semantic information is most vulnerable to tampering, for which capturing the forgery traces of the character is the key to localizing the forged region in document images. Considering both character and image textures, in this paper, we propose a Character Texture Perception Network (CTP-Net) to localize the forgery of document images. Based on optical character recognition, a Character Texture Stream (CTS) is designed to capture features of text areas that are essential components of a document image. Meanwhile, texture features of the whole document image are exploited by an Image Texture Stream (ITS). Combining the features extracted from the CTS and the ITS, the CTP-Net can reveal more subtle forgery traces from document images. To overcome the challenge caused by the lack of fake document images, we design a data generation strategy that is utilized to construct a Fake Chinese Trademark dataset (FCTM). Through a series of experiments, we show that the proposed CTP-Net is able to capture tampering traces in document images, especially in text regions. Experimental results demonstrate that CTP-Net can localize multi-scale forged areas in document images and outperform the state-of-the-art forgery localization methods.
Authors: Jiyong Moon, Junseok Lee, Yunju Lee, Seongsik Park
Recently, vision Transformers (ViTs) have been actively applied to fine-grained visual recognition (FGVR). ViT can effectively model the interdependencies between patch-divided object regions through an inherent self-attention mechanism. In addition, patch selection is used with ViT to remove redundant patch information and highlight the most discriminative object patches. However, existing ViT-based FGVR models are limited to single-scale processing, and their fixed receptive fields hinder representational richness and exacerbate vulnerability to scale variability. Therefore, we propose multi-scale patch selection (MSPS) to improve the multi-scale capabilities of existing ViT-based models. Specifically, MSPS selects salient patches of different scales at different stages of a multi-scale vision Transformer (MS-ViT). In addition, we introduce class token transfer (CTT) and multi-scale cross-attention (MSCA) to model cross-scale interactions between selected multi-scale patches and fully reflect them in model decisions. Compared to previous single-scale patch selection (SSPS), our proposed MSPS encourages richer object representations based on feature hierarchy and consistently improves performance from small-sized to large-sized objects. As a result, we propose M2Former, which outperforms CNN-/ViT-based models on several widely used FGVR benchmarks.
Authors: Wangbo Zhao, Kepan Nan, Songyang Zhang, Kai Chen, Dahua Lin, Yang You
Referring video object segmentation (RVOS) is a task that aims to segment the target object in all video frames based on a sentence describing the object. Previous RVOS methods have achieved significant performance with densely-annotated datasets, whose construction is expensive and time-consuming. To relieve the burden of data annotation while maintaining sufficient supervision for segmentation, we propose a new annotation scheme, in which we label the frame where the object first appears with a mask and use bounding boxes for the subsequent frames. Based on this scheme, we propose a method to learn from this weak annotation. Specifically, we design a cross frame segmentation method, which uses the language-guided dynamic filters to thoroughly leverage the valuable mask annotation and bounding boxes. We further develop a bi-level contrastive learning method to encourage the model to learn discriminative representation at the pixel level. Extensive experiments and ablative analyses show that our method is able to achieve competitive performance without the demand of dense mask annotation. The code will be available at https://github.com/wangbo-zhao/WRVOS/.
Authors: Ravikiran Parameshwara, Ibrahim Radwan, Akshay Asthana, Iman Abbasnejad, Ramanathan Subramanian, Roland Goecke
Whilst deep learning techniques have achieved excellent emotion prediction, they still require large amounts of labelled training data, which are (a) onerous and tedious to compile, and (b) prone to errors and biases. We propose Multi-Task Contrastive Learning for Affect Representation (\textbf{MT-CLAR}) for few-shot affect inference. MT-CLAR combines multi-task learning with a Siamese network trained via contrastive learning to infer from a pair of expressive facial images (a) the (dis)similarity between the facial expressions, and (b) the difference in valence and arousal levels of the two faces. We further extend the image-based MT-CLAR framework for automated video labelling where, given one or a few labelled video frames (termed \textit{support-set}), MT-CLAR labels the remainder of the video for valence and arousal. Experiments are performed on the AFEW-VA dataset with multiple support-set configurations; moreover, supervised learning on representations learnt via MT-CLAR are used for valence, arousal and categorical emotion prediction on the AffectNet and AFEW-VA datasets. The results show that valence and arousal predictions via MT-CLAR are very comparable to the state-of-the-art (SOTA), and we significantly outperform SOTA with a support-set $\approx$6\% the size of the video dataset.
Authors: Jieteng Yao, Junjie Chen, Li Niu, Bin Sheng
Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics. In this paper, we focus on contextual affordance learning, i.e., using affordance as context to generate a reasonable human pose in a scene. Existing scene-aware human pose generation methods could be divided into two categories depending on whether using pose templates. Our proposed method belongs to the template-based category, which benefits from the representative pose templates. Moreover, inspired by recent transformer-based methods, we associate each query embedding with a pose template, and use the interaction between query embeddings and scene feature map to effectively predict the scale and offsets for each pose template. In addition, we employ knowledge distillation to facilitate the offset learning given the predicted scale. Comprehensive experiments on Sitcom dataset demonstrate the effectiveness of our method.
Authors: Martin Bikandi, Gorka Velez, Naiara Aginako, Itziar Irigoien
Anomaly detection, or outlier detection, is a crucial task in various domains to identify instances that significantly deviate from established patterns or the majority of data. In the context of autonomous driving, the identification of anomalies is particularly important to prevent safety-critical incidents, as deep learning models often exhibit overconfidence in anomalous or outlier samples. In this study, we explore different strategies for training an image semantic segmentation model with an anomaly detection module. By introducing modifications to the training stage of the state-of-the-art DenseHybrid model, we achieve significant performance improvements in anomaly detection. Moreover, we propose a simplified detector that achieves comparable results to our modified DenseHybrid approach, while also surpassing the performance of the original DenseHybrid model. These findings demonstrate the efficacy of our proposed strategies for enhancing anomaly detection in the context of autonomous driving.
Authors: Qiang Zhou, Chaohui Yu, Jingliang Li, Yuang Liu, Jing Wang, Zhibin Wang
Compared to the multi-stage self-supervised multi-view stereo (MVS) method, the end-to-end (E2E) approach has received more attention due to its concise and efficient training pipeline. Recent E2E self-supervised MVS approaches have integrated third-party models (such as optical flow models, semantic segmentation models, NeRF models, etc.) to provide additional consistency constraints, which grows GPU memory consumption and complicates the model's structure and training pipeline. In this work, we propose an efficient framework for end-to-end self-supervised MVS, dubbed ES-MVSNet. To alleviate the high memory consumption of current E2E self-supervised MVS frameworks, we present a memory-efficient architecture that reduces memory usage by 43% without compromising model performance. Furthermore, with the novel design of asymmetric view selection policy and region-aware depth consistency, we achieve state-of-the-art performance among E2E self-supervised MVS methods, without relying on third-party models for additional consistency signals. Extensive experiments on DTU and Tanks&Temples benchmarks demonstrate that the proposed ES-MVSNet approach achieves state-of-the-art performance among E2E self-supervised MVS methods and competitive performance to many supervised and multi-stage self-supervised methods.
Authors: Gaspard Goupy, Pierre Tirilly, Ioan Marius Bilasco
Direct training of Spiking Neural Networks (SNNs) on neuromorphic hardware has the potential to significantly reduce the high energy consumption of Artificial Neural Networks (ANNs) training on modern computers. The biological plausibility of SNNs allows them to benefit from bio-inspired plasticity rules, such as Spike Timing-Dependent Plasticity (STDP). STDP offers gradient-free and unsupervised local learning, which can be easily implemented on neuromorphic hardware. However, relying solely on unsupervised STDP to perform classification tasks is not enough. In this paper, we propose Stabilized Supervised STDP (S2-STDP), a supervised STDP learning rule to train the classification layer of an SNN equipped with unsupervised STDP. S2-STDP integrates error-modulated weight updates that align neuron spikes with desired timestamps derived from the average firing time within the layer. Then, we introduce a training architecture called Paired Competing Neurons (PCN) to further enhance the learning capabilities of our classification layer trained with S2-STDP. PCN associates each class with paired neurons and encourages neuron specialization through intra-class competition. We evaluated our proposed methods on image recognition datasets, including MNIST, Fashion-MNIST, and CIFAR-10. Results showed that our methods outperform current supervised STDP-based state of the art, for comparable architectures and numbers of neurons. Also, the use of PCN enhances the performance of S2-STDP, regardless of the configuration, and without introducing any hyperparameters.Further analysis demonstrated that our methods exhibited improved hyperparameter robustness, which reduces the need for tuning.
Authors: Tianhao Qi, Hongtao Xie, Pandeng Li, Jiannan Ge, Yongdong Zhang
Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. In this paper, we contend that the learning bias originates from two factors: 1) the unequal competition arising from the imbalanced distribution of foreground categories, and 2) the lack of sample diversity in tail categories. To tackle these issues, we introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution and dynamic intensification of sample diversities in a synchronized manner. Specifically, a novel foreground classification balance loss (FCBL) is developed to ameliorate the domination of head categories and shift attention to difficult-to-differentiate categories by introducing pairwise class-aware margins and auto-adjusted weight terms, respectively. This loss prevents the over-suppression of tail categories in the context of unequal competition. Moreover, we propose a dynamic feature hallucination module (FHM), which enhances the representation of tail categories in the feature space by synthesizing hallucinated samples to introduce additional data variances. In this divide-and-conquer approach, BACL sets a new state-of-the-art on the challenging LVIS benchmark with a decoupled training pipeline, surpassing vanilla Faster R-CNN with ResNet-50-FPN by 5.8% AP and 16.1% AP for overall and tail categories. Extensive experiments demonstrate that BACL consistently achieves performance improvements across various datasets with different backbones and architectures. Code and models are available at https://github.com/Tianhao-Qi/BACL.
Authors: Yi Wang, Chenying Liu, Arti Tiwari, Micha Silver, Arnon Karnieli, Xiao Xiang Zhu, Conrad M Albrecht
Discovering ancient agricultural terraces in desert regions is important for the monitoring of long-term climate changes on the Earth's surface. However, traditional ground surveys are both costly and limited in scale. With the increasing accessibility of aerial and satellite data, machine learning techniques bear large potential for the automatic detection and recognition of archaeological landscapes. In this paper, we propose a deep semantic model fusion method for ancient agricultural terrace detection. The input data includes aerial images and LiDAR generated terrain features in the Negev desert. Two deep semantic segmentation models, namely DeepLabv3+ and UNet, with EfficientNet backbone, are trained and fused to provide segmentation maps of ancient terraces and walls. The proposed method won the first prize in the International AI Archaeology Challenge. Codes are available at https://github.com/wangyi111/international-archaeology-ai-challenge.
Authors: Lingxiao Lu, Jiangtong Li, Junyan Cao, Li Niu, Liqing Zhang
Painterly image harmonization aims to insert photographic objects into paintings and obtain artistically coherent composite images. Previous methods for this task mainly rely on inference optimization or generative adversarial network, but they are either very time-consuming or struggling at fine control of the foreground objects (e.g., texture and content details). To address these issues, we propose a novel Painterly Harmonization stable Diffusion model (PHDiffusion), which includes a lightweight adaptive encoder and a Dual Encoder Fusion (DEF) module. Specifically, the adaptive encoder and the DEF module first stylize foreground features within each encoder. Then, the stylized foreground features from both encoders are combined to guide the harmonization process. During training, besides the noise loss in diffusion model, we additionally employ content loss and two style losses, i.e., AdaIN style loss and contrastive style loss, aiming to balance the trade-off between style migration and content preservation. Compared with the state-of-the-art models from related fields, our PHDiffusion can stylize the foreground more sufficiently and simultaneously retain finer content. Our code and model are available at https://github.com/bcmi/PHDiffusion-Painterly-Image-Harmonization.
Authors: Zhiqi Li, Zhiding Yu, Wenhai Wang, Anima Anandkumar, Tong Lu, Jose M. Alvarez
View Transformation Module (VTM), where transformations happen between multi-view image features and Bird-Eye-View (BEV) representation, is a crucial step in camera-based BEV perception systems. Currently, the two most prominent VTM paradigms are forward projection and backward projection. Forward projection, represented by Lift-Splat-Shoot, leads to sparsely projected BEV features without post-processing. Backward projection, with BEVFormer being an example, tends to generate false-positive BEV features from incorrect projections due to the lack of utilization on depth. To address the above limitations, we propose a novel forward-backward view transformation module. Our approach compensates for the deficiencies in both existing methods, allowing them to enhance each other to obtain higher quality BEV representations mutually. We instantiate the proposed module with FB-BEV, which achieves a new state-of-the-art result of 62.4\% NDS on the nuScenes test set. The code will be released at \url{https://github.com/NVlabs/FB-BEV}.
Authors: Haoyi Xiu, Xin Liu, Weimin Wang, Kyoung-Sook Kim, Masashi Matsuoka
Estimating surface normals from 3D point clouds is critical for various applications, including surface reconstruction and rendering. While existing methods for normal estimation perform well in regions where normals change slowly, they tend to fail where normals vary rapidly. To address this issue, we propose a novel approach called MSECNet, which improves estimation in normal varying regions by treating normal variation modeling as an edge detection problem. MSECNet consists of a backbone network and a multi-scale edge conditioning (MSEC) stream. The MSEC stream achieves robust edge detection through multi-scale feature fusion and adaptive edge detection. The detected edges are then combined with the output of the backbone network using the edge conditioning module to produce edge-aware representations. Extensive experiments show that MSECNet outperforms existing methods on both synthetic (PCPNet) and real-world (SceneNN) datasets while running significantly faster. We also conduct various analyses to investigate the contribution of each component in the MSEC stream. Finally, we demonstrate the effectiveness of our approach in surface reconstruction.
Authors: Haowen Wang, Zhipeng Fan, Zhen Zhao, Zhengping Che, Zhiyuan Xu, Dong Liu, Feifei Feng, Yakun Huang, Xiuquan Qiao, Jian Tang
Estimating 6D poses and reconstructing 3D shapes of objects in open-world scenes from RGB-depth image pairs is challenging. Many existing methods rely on learning geometric features that correspond to specific templates while disregarding shape variations and pose differences among objects in the same category. As a result, these methods underperform when handling unseen object instances in complex environments. In contrast, other approaches aim to achieve category-level estimation and reconstruction by leveraging normalized geometric structure priors, but the static prior-based reconstruction struggles with substantial intra-class variations. To solve these problems, we propose the DTF-Net, a novel framework for pose estimation and shape reconstruction based on implicit neural fields of object categories. In DTF-Net, we design a deformable template field to represent the general category-wise shape latent features and intra-category geometric deformation features. The field establishes continuous shape correspondences, deforming the category template into arbitrary observed instances to accomplish shape reconstruction. We introduce a pose regression module that shares the deformation features and template codes from the fields to estimate the accurate 6D pose of each object in the scene. We integrate a multi-modal representation extraction module to extract object features and semantic masks, enabling end-to-end inference. Moreover, during training, we implement a shape-invariant training strategy and a viewpoint sampling method to further enhance the model's capability to extract object pose features. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superiority of DTF-Net in both synthetic and real scenes. Furthermore, we show that DTF-Net effectively supports grasping tasks with a real robot arm.
Authors: Mariella Dreissig, Florian Piewak, Joschka Boedecker
The confidence calibration of deep learning-based perception models plays a crucial role in their reliability. Especially in the context of autonomous driving, downstream tasks like prediction and planning depend on accurate confidence estimates. In point-wise multiclass classification tasks like sematic segmentation the model has to deal with heavy class imbalances. Due to their underrepresentation, the confidence calibration of classes with smaller instances is challenging but essential, not only for safety reasons. We propose a metric to measure the confidence calibration quality of a semantic segmentation model with respect to individual classes. It is calculated by computing sparsification curves for each class based on the uncertainty estimates. We use the classification calibration metric to evaluate uncertainty estimation methods with respect to their confidence calibration of underrepresented classes. We furthermore suggest a double use for the method to automatically find label problems to improve the quality of hand- or auto-annotated datasets.
Authors: Kai Storms, Ken Mori, Steven Peters
To evaluate perception components of an automated driving system, it is necessary to define the relevant objects. While the urban domain is popular among perception datasets, relevance is insufficiently specified for this domain. Therefore, this work adopts an existing method to define relevance in the highway domain and expands it to the urban domain. While different conceptualizations and definitions of relevance are present in literature, there is a lack of methods to validate these definitions. Therefore, this work presents a novel relevance validation method leveraging a motion prediction component. The validation leverages the idea that removing irrelevant objects should not influence a prediction component which reflects human driving behavior. The influence on the prediction is quantified by considering the statistical distribution of prediction performance across a large-scale dataset. The validation procedure is verified using criteria specifically designed to exclude relevant objects. The validation method is successfully applied to the relevance criteria from this work, thus supporting their validity.
Authors: Jiaqi Li, Yiran Wang, Zihao Huang, Jinghong Zheng, Ke Xian, Zhiguo Cao, Jianming Zhang
Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid pixels and fail to restore spatial structures. Self-supervised methods are proposed for the problem. Their robustness is limited by pose estimation, leading to erroneous results in natural scenes. In this paper, we propose a supervised framework termed Diffusion-Augmented Depth Prediction (DADP). We leverage the structural characteristics of diffusion model to enforce depth structures of depth models in a plug-and-play manner. An object-guided integrality loss is also proposed to further enhance regional structure integrality by fetching objective information. We evaluate DADP on three driving benchmarks and achieve significant improvements in depth structures and robustness. Our work provides a new perspective on depth estimation with sparse annotations in autonomous driving scenes.
Authors: Qiang Zhou, Chaohui Yu, Shaofeng Zhang, Sitong Wu, Zhibing Wang, Fan Wang
In this work, we investigate extending the comprehension of Multi-modal Large Language Models (MLLMs) to regional objects. To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning. To effectively extract regional features from regular image features and irregular point cloud features, we present a novel and unified position-assisted feature extraction module. Furthermore, training an MLLM from scratch is highly time-consuming. Thus, we propose incrementally extending existing pre-trained MLLMs to comprehend more modalities and the regional objects of those modalities. Specifically, we freeze the Q-Former from BLIP-2, an impressive MLLM, and optimize the modality-specific Lora parameters in Q-Former and LLM for each newly introduced modality. The freezing of the Q-Former eliminates the need for extensive pre-training on massive image-text data. The freezed Q-Former pre-trained from massive image-text data is also beneficial for the pre-training on image-region-text data. We name our framework RegionBLIP. We pre-train RegionBLIP on image-region-text, point-cloud-text, and point-cloud-region-text data. Experimental results verify that \Ours{} can preserve the image comprehension capability of BILP-2 and further gain a comprehension of the newly introduced point cloud modality and regional objects. The Data, Code, and Pre-trained models will be available at https://github.com/mightyzau/RegionBLIP.
Authors: Zhengyang Mao, Wei Ju, Yifang Qin, Xiao Luo, Ming Zhang
Graph classification is a crucial task in many real-world multimedia applications, where graphs can represent various multimedia data types such as images, videos, and social networks. Previous efforts have applied graph neural networks (GNNs) in balanced situations where the class distribution is balanced. However, real-world data typically exhibit long-tailed class distributions, resulting in a bias towards the head classes when using GNNs and limited generalization ability over the tail classes. Recent approaches mainly focus on re-balancing different classes during model training, which fails to explicitly introduce new knowledge and sacrifices the performance of the head classes. To address these drawbacks, we propose a novel framework called Retrieval Augmented Hybrid Network (RAHNet) to jointly learn a robust feature extractor and an unbiased classifier in a decoupled manner. In the feature extractor training stage, we develop a graph retrieval module to search for relevant graphs that directly enrich the intra-class diversity for the tail classes. Moreover, we innovatively optimize a category-centered supervised contrastive loss to obtain discriminative representations, which is more suitable for long-tailed scenarios. In the classifier fine-tuning stage, we balance the classifier weights with two weight regularization techniques, i.e., Max-norm and weight decay. Experiments on various popular benchmarks verify the superiority of the proposed method against state-of-the-art approaches.
Authors: Jingyi Wang, Can Zhang, Jinfa Huang, Botao Ren, Zhidong Deng
Recent advances in Scene Graph Generation (SGG) typically model the relationships among entities utilizing box-level features from pre-defined detectors. We argue that an overlooked problem in SGG is the coarse-grained interactions between boxes, which inadequately capture contextual semantics for relationship modeling, practically limiting the development of the field. In this paper, we take the initiative to explore and propose a generic paradigm termed Superpixel-based Interaction Learning (SIL) to remedy coarse-grained interactions at the box level. It allows us to model fine-grained interactions at the superpixel level in SGG. Specifically, (i) we treat a scene as a set of points and cluster them into superpixels representing sub-regions of the scene. (ii) We explore intra-entity and cross-entity interactions among the superpixels to enrich fine-grained interactions between entities at an earlier stage. Extensive experiments on two challenging benchmarks (Visual Genome and Open Image V6) prove that our SIL enables fine-grained interaction at the superpixel level above previous box-level methods, and significantly outperforms previous state-of-the-art methods across all metrics. More encouragingly, the proposed method can be applied to boost the performance of existing box-level approaches in a plug-and-play fashion. In particular, SIL brings an average improvement of 2.0% mR (even up to 3.4%) of baselines for the PredCls task on Visual Genome, which facilitates its integration into any existing box-level method.
Authors: Guanxiong Luo, Xiaoqing Wang, Mortiz Blumenthal, Martin Schilling, Erik Hans Ulrich Rauf, Raviteja Kotikalapudi, Niels Focke, Martin Uecker
Purpose: In this work, we present a workflow to construct generic and robust generative image priors from magnitude-only images. The priors can then be used for regularization in reconstruction to improve image quality. Methods: The workflow begins with the preparation of training datasets from magnitude-only MR images. This dataset is then augmented with phase information and used to train generative priors of complex images. Finally, trained priors are evaluated using both linear and nonlinear reconstruction for compressed sensing parallel imaging with various undersampling schemes. Results: The results of our experiments demonstrate that priors trained on complex images outperform priors trained only on magnitude images. Additionally, a prior trained on a larger dataset exhibits higher robustness. Finally, we show that the generative priors are superior to L1 -wavelet regularization for compressed sensing parallel imaging with high undersampling. Conclusion: These findings stress the importance of incorporating phase information and leveraging large datasets to raise the performance and reliability of the generative priors for MRI reconstruction. Phase augmentation makes it possible to use existing image databases for training.
Authors: Wenzhuo Liu, Xinjian Wu, Fei Zhu, Mingming Yu, Chuang Wang, Cheng-Lin Liu
Deep Neural Network (DNN) has achieved great success on datasets of closed class set. However, new classes, like new categories of social media topics, are continuously added to the real world, making it necessary to incrementally learn. This is hard for DNN because it tends to focus on fitting to new classes while ignoring old classes, a phenomenon known as catastrophic forgetting. State-of-the-art methods rely on knowledge distillation and data replay techniques but still have limitations. In this work, we analyze the causes of catastrophic forgetting in class incremental learning, which owes to three factors: representation drift, representation confusion, and classifier distortion. Based on this view, we propose a two-stage learning framework with a fixed encoder and an incrementally updated prototype classifier. The encoder is trained with self-supervised learning to generate a feature space with high intrinsic dimensionality, thus improving its transferability and generality. The classifier incrementally learns new prototypes while retaining the prototypes of previously learned data, which is crucial in preserving the decision boundary.Our method does not rely on preserved samples of old classes, is thus a non-exemplar based CIL method. Experiments on public datasets show that our method can significantly outperform state-of-the-art exemplar-based methods when they reserved 5 examplers per class, under the incremental setting of 10 phases, by 18.24% on CIFAR-100 and 9.37% on ImageNet100.
Authors: Yisong Xiao, Aishan Liu, Tianyuan Zhang, Haotong Qin, Jinyang Guo, Xianglong Liu
Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications. Despite the importance of evaluating the impact of quantization on robustness, existing research on this topic is limited and often disregards established principles of robustness evaluation, resulting in incomplete and inconclusive findings. To address this gap, we thoroughly evaluated the robustness of quantized models against various noises (adversarial attacks, natural corruptions, and systematic noises) on ImageNet. The comprehensive evaluation results empirically provide valuable insights into the robustness of quantized models in various scenarios, for example: (1) quantized models exhibit higher adversarial robustness than their floating-point counterparts, but are more vulnerable to natural corruptions and systematic noises; (2) in general, increasing the quantization bit-width results in a decrease in adversarial robustness, an increase in natural robustness, and an increase in systematic robustness; (3) among corruption methods, \textit{impulse noise} and \textit{glass blur} are the most harmful to quantized models, while \textit{brightness} has the least impact; (4) among systematic noises, the \textit{nearest neighbor interpolation} has the highest impact, while bilinear interpolation, cubic interpolation, and area interpolation are the three least harmful. Our research contributes to advancing the robust quantization of models and their deployment in real-world scenarios.
Authors: Connor Lane, Gregory Kiar
This is the Algonauts 2023 submission report for team "BlobGPT". Our model consists of a multi-subject linear encoding head attached to a pretrained trunk model. The multi-subject head consists of three components: (1) a shared multi-layer feature projection, (2) shared plus subject-specific low-dimension linear transformations, and (3) a shared PCA fMRI embedding. In this report, we explain these components in more detail and present some experimental results. Our code is available at https://github.com/cmi-dair/algonauts23.
Authors: Huan Zhong, Chen Wu
Remote sensing image change detection aims to identify the differences between images acquired at different times in the same area. It is widely used in land management, environmental monitoring, disaster assessment and other fields. Currently, most change detection methods are based on Siamese network structure or early fusion structure. Siamese structure focuses on extracting object features at different times but lacks attention to change information, which leads to false alarms and missed detections. Early fusion (EF) structure focuses on extracting features after the fusion of images of different phases but ignores the significance of object features at different times for detecting change details, making it difficult to accurately discern the edges of changed objects. To address these issues and obtain more accurate results, we propose a novel network, Triplet UNet(T-UNet), based on a three-branch encoder, which is capable to simultaneously extract the object features and the change features between the pre- and post-time-phase images through triplet encoder. To effectively interact and fuse the features extracted from the three branches of triplet encoder, we propose a multi-branch spatial-spectral cross-attention module (MBSSCA). In the decoder stage, we introduce the channel attention mechanism (CAM) and spatial attention mechanism (SAM) to fully mine and integrate detailed textures information at the shallow layer and semantic localization information at the deep layer.
Authors: Fang-Cheng Yeh
Deep learning models usually require sufficient training data to achieve high accuracy, but obtaining labeled data can be time-consuming and labor-intensive. Here we introduce a template-based training method to train a 3D U-Net model from scratch using only one population-averaged brain MRI template and its associated segmentation label. The process incorporated visual perception augmentation to enhance the model's robustness in handling diverse image inputs and mitigating overfitting. Leveraging this approach, we trained 3D U-Net models for mouse, rat, marmoset, rhesus, and human brain MRI to achieve segmentation tasks such as skull-stripping, brain segmentation, and tissue probability mapping. This tool effectively addresses the limited availability of training data and holds significant potential for expanding deep learning applications in image analysis, providing researchers with a unified solution to train deep neural networks with only one image sample.
Authors: JiaCheng Deng, Li Dong, Jiahao Chen, Diqun Yan, Rangding Wang, Dengpan Ye, Lingchen Zhao, Jinyu Tian
Optical Character Recognition (OCR) enables automatic text extraction from scanned or digitized text images, but it also makes it easy to pirate valuable or sensitive text from these images. Previous methods to prevent OCR piracy by distorting characters in text images are impractical in real-world scenarios, as pirates can capture arbitrary portions of the text images, rendering the defenses ineffective. In this work, we propose a novel and effective defense mechanism termed the Universal Defensive Underpainting Patch (UDUP) that modifies the underpainting of text images instead of the characters. UDUP is created through an iterative optimization process to craft a small, fixed-size defensive patch that can generate non-overlapping underpainting for text images of any size. Experimental results show that UDUP effectively defends against unauthorized OCR under the setting of any screenshot range or complex image background. It is agnostic to the content, size, colors, and languages of characters, and is robust to typical image operations such as scaling and compressing. In addition, the transferability of UDUP is demonstrated by evading several off-the-shelf OCRs. The code is available at https://github.com/QRICKDD/UDUP.
Authors: Yanyan Li, Ke Chen, Chong Chen, Jianping Zhang
Diffeomorphic registration has become a powerful approach for seeking a smooth and invertible spatial transformation between two coordinate systems which have been measured via the template and reference images. While the pointwise volume-preserving constraint is effective for some problems, it is too stringent for many other problems especially when the local deformations are relatively large, because it may lead to a poor large-deformation for enforcing local matching.In this paper, we propose a novel bi-variant diffeomorphic image registration model with the soft constraint of Jacobian equation, which allows local deformations to shrink and grow in a flexible range.The Jacobian determinant of the transformation is explicitly controlled by optimizing the relaxation function. To prevent deformation folding and enhance the smoothness of deformation, we not only impose a positivity constraint in optimizing the relaxation function, but also employ a regularizer to ensure the smoothness of the relaxation function.Furthermore, the positivity constraint ensures that is as close to one as possible, which helps to obtain a volume-preserving transformation on average.We further analyze the existence of the minimizer for the variational model and propose a penalty splitting method with a multilevel strategy to solve this model. Numerical experiments show that the proposed algorithm is convergent, and the positivity constraint can control the range of relative volume and not compromise registration accuracy. Moreover, the proposed model produces diffeomorphic maps for large deformation, and achieves better performance compared to the several existing registration models.
Authors: Sabri Mustafa Kahya, Muhammet Sami Yavuz, Eckehard Steinbach
Human presence detection in indoor environments using millimeter-wave frequency-modulated continuous-wave (FMCW) radar is challenging due to the presence of moving and stationary clutters in indoor places. This work proposes "HOOD" as a real-time robust human presence and out-of-distribution (OOD) detection method by exploiting 60 GHz short-range FMCW radar. We approach the presence detection application as an OOD detection problem and solve the two problems simultaneously using a single pipeline. Our solution relies on a reconstruction-based architecture and works with radar macro and micro range-Doppler images (RDIs). HOOD aims to accurately detect the "presence" of humans in the presence or absence of moving and stationary disturbers. Since it is also an OOD detector, it aims to detect moving or stationary clutters as OOD in humans' absence and predicts the current scene's output as "no presence." HOOD is an activity-free approach that performs well in different human scenarios. On our dataset collected with a 60 GHz short-range FMCW Radar, we achieve an average AUROC of 94.36%. Additionally, our extensive evaluations and experiments demonstrate that HOOD outperforms state-of-the-art (SOTA) OOD detection methods in terms of common OOD detection metrics. Our real-time experiments are available at: https://muskahya.github.io/HOOD
Authors: Adam Sinclair, Kayla Kautai, Seyed Reza Shahamiri
Automated exercise repetition counting has applications across the physical fitness realm, from personal health to rehabilitation. Motivated by the ubiquity of mobile phones and the benefits of tracking physical activity, this study explored the feasibility of counting exercise repetitions in real-time, using only on-device inference, on smartphones. In this work, after providing an extensive overview of the state-of-the-art automatic exercise repetition counting methods, we introduce a deep learning based exercise repetition counting system for smartphones consisting of five components: (1) Pose estimation, (2) Thresholding, (3) Optical flow, (4) State machine, and (5) Counter. The system is then implemented via a cross-platform mobile application named P\=uioio that uses only the smartphone camera to track repetitions in real time for three standard exercises: Squats, Push-ups, and Pull-ups. The proposed system was evaluated via a dataset of pre-recorded videos of individuals exercising as well as testing by subjects exercising in real time. Evaluation results indicated the system was 98.89% accurate in real-world tests and up to 98.85% when evaluated via the pre-recorded dataset. This makes it an effective, low-cost, and convenient alternative to existing solutions since the proposed system has minimal hardware requirements without requiring any wearable or specific sensors or network connectivity.
Authors: Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, Weidi Xie
In this study, we aim to initiate the development of Radiology Foundation Model, termed as RadFM.We consider the construction of foundational models from the perspectives of data, model design, and evaluation thoroughly. Our contribution can be concluded as follows: (i), we construct a large-scale Medical Multi-modal Dataset, MedMD, consisting of 16M 2D and 3D medical scans. To the best of our knowledge, this is the first multi-modal dataset containing 3D medical scans. (ii), We propose an architecture that enables visually conditioned generative pre-training, allowing for the integration of text input interleaved with 2D or 3D medical scans to generate response for diverse radiologic tasks. The model was initially pre-trained on MedMD and subsequently domain-specific fine-tuned on RadMD, a radiologic cleaned version of MedMD, containing 3M radiologic visual-language pairs. (iii), we propose a new evaluation benchmark that comprises five tasks, aiming to comprehensively assess the capability of foundation models in handling practical clinical problems. Our experimental results confirm that RadFM significantly outperforms existing multi-modal foundation models. The codes, data, and model checkpoint will all be made publicly available to promote further research and development in the field.
Authors: Qihang Yu, Ju He, Xueqing Deng, Xiaohui Shen, Liang-Chieh Chen
Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage multi-modal models, such as CLIP, to provide image and text features in a shared embedding space, which bridges the gap between closed-vocabulary and open-vocabulary recognition. Hence, existing methods often adopt a two-stage framework to tackle the problem, where the inputs first go through a mask generator and then through the CLIP model along with the predicted masks. This process involves extracting features from images multiple times, which can be ineffective and inefficient. By contrast, we propose to build everything into a single-stage framework using a shared Frozen Convolutional CLIP backbone, which not only significantly simplifies the current two-stage pipeline, but also remarkably yields a better accuracy-cost trade-off. The proposed FC-CLIP, benefits from the following observations: the frozen CLIP backbone maintains the ability of open-vocabulary classification and can also serve as a strong mask generator, and the convolutional CLIP generalizes well to a larger input resolution than the one used during contrastive image-text pretraining. When training on COCO panoptic data only and testing in a zero-shot manner, FC-CLIP achieve 26.8 PQ, 16.8 AP, and 34.1 mIoU on ADE20K, 18.2 PQ, 27.9 mIoU on Mapillary Vistas, 44.0 PQ, 26.8 AP, 56.2 mIoU on Cityscapes, outperforming the prior art by +4.2 PQ, +2.4 AP, +4.2 mIoU on ADE20K, +4.0 PQ on Mapillary Vistas and +20.1 PQ on Cityscapes, respectively. Additionally, the training and testing time of FC-CLIP is 7.5x and 6.6x significantly faster than the same prior art, while using 5.9x fewer parameters. FC-CLIP also sets a new state-of-the-art performance across various open-vocabulary semantic segmentation datasets. Code at https://github.com/bytedance/fc-clip
Authors: Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, Lijuan Wang
We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such as solving math problems written on the blackboard, reasoning about events and celebrities in news images, and explaining visual jokes. Rapid model advancements pose challenges to evaluation benchmark development. Problems include: (1) How to systematically structure and evaluate the complicated multimodal tasks; (2) How to design evaluation metrics that work well across question and answer types; and (3) How to give model insights beyond a simple performance ranking. To this end, we present MM-Vet, designed based on the insight that the intriguing ability to solve complicated tasks is often achieved by a generalist model being able to integrate different core vision-language (VL) capabilities. MM-Vet defines 6 core VL capabilities and examines the 16 integrations of interest derived from the capability combination. For evaluation metrics, we propose an LLM-based evaluator for open-ended outputs. The evaluator enables the evaluation across different question types and answer styles, resulting in a unified scoring metric. We evaluate representative LMMs on MM-Vet, providing insights into the capabilities of different LMM system paradigms and models. Code and data are available at https://github.com/yuweihao/MM-Vet.
Authors: Andres C. Rodriguez, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner
We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets. Our main motivation is the recognition of animal species for ecological applications such as biodiversity modelling, which is challenging because of long-tailed species distributions due to rare species, and strong dataset biases such as repetitive scene background in camera traps. To counteract these challenges, we propose a visual attention mechanism that is supervised via keypoint annotations that highlight important object parts. This privileged information, implemented as a novel privileged pooling operation, is only required during training and helps the model to focus on regions that are discriminative. In experiments with three different animal species datasets, we show that deep networks with privileged pooling can use small training sets more efficiently and generalize better.
Previous versions of sparse principal component analysis (PCA) have presumed that the eigen-basis (a $p \times k$ matrix) is approximately sparse. We propose a method that presumes the $p \times k$ matrix becomes approximately sparse after a $k \times k$ rotation. The simplest version of the algorithm initializes with the leading $k$ principal components. Then, the principal components are rotated with an $k \times k$ orthogonal rotation to make them approximately sparse. Finally, soft-thresholding is applied to the rotated principal components. This approach differs from prior approaches because it uses an orthogonal rotation to approximate a sparse basis. One consequence is that a sparse component need not to be a leading eigenvector, but rather a mixture of them. In this way, we propose a new (rotated) basis for sparse PCA. In addition, our approach avoids "deflation" and multiple tuning parameters required for that. Our sparse PCA framework is versatile; for example, it extends naturally to a two-way analysis of a data matrix for simultaneous dimensionality reduction of rows and columns. We provide evidence showing that for the same level of sparsity, the proposed sparse PCA method is more stable and can explain more variance compared to alternative methods. Through three applications -- sparse coding of images, analysis of transcriptome sequencing data, and large-scale clustering of social networks, we demonstrate the modern usefulness of sparse PCA in exploring multivariate data.
Authors: Gergely Szabo, Andras Horvath
Convolutional networks are considered shift invariant, but it was demonstrated that their response may vary according to the exact location of the objects. In this paper we will demonstrate that most commonly investigated datasets have a bias, where objects are over-represented at the center of the image during training. This bias and the boundary condition of these networks can have a significant effect on the performance of these architectures and their accuracy drops significantly as an object approaches the boundary. We will also demonstrate how this effect can be mitigated with data augmentation techniques.
Authors: Kailai Zhou, Yibo Wang, Tao Lv, Yunqian Li, Linsen Chen, Qiu Shen, Xun Cao
We endeavor on a rarely explored task named Insubstantial Object Detection (IOD), which aims to localize the object with following characteristics: (1) amorphous shape with indistinct boundary; (2) similarity to surroundings; (3) absence in color. Accordingly, it is far more challenging to distinguish insubstantial objects in a single static frame and the collaborative representation of spatial and temporal information is crucial. Thus, we construct an IOD-Video dataset comprised of 600 videos (141,017 frames) covering various distances, sizes, visibility, and scenes captured by different spectral ranges. In addition, we develop a spatio-temporal aggregation framework for IOD, in which different backbones are deployed and a spatio-temporal aggregation loss (STAloss) is elaborately designed to leverage the consistency along the time axis. Experiments conducted on IOD-Video dataset demonstrate that spatio-temporal aggregation can significantly improve the performance of IOD. We hope our work will attract further researches into this valuable yet challenging task. The code will be available at: \url{https://github.com/CalayZhou/IOD-Video}.
Authors: Toluwani Aremu, Li Zhiyuan, Reem Alameeri, Mustaqeem Khan, Abdulmotaleb El Saddik
Detection of violence and weaponized violence in closed-circuit television (CCTV) footage requires a comprehensive approach. In this work, we introduce the \emph{Smart-City CCTV Violence Detection (SCVD)} dataset, specifically designed to facilitate the learning of weapon distribution in surveillance videos. To tackle the complexities of analyzing 3D surveillance video for violence recognition tasks, we propose a novel technique called, \emph{SSIVD-Net} (\textbf{S}alient-\textbf{S}uper-\textbf{I}mage for \textbf{V}iolence \textbf{D}etection). Our method reduces 3D video data complexity, dimensionality, and information loss while improving inference, performance, and explainability through the use of Salient-Super-Image representations. Considering the scalability and sustainability requirements of futuristic smart cities, the authors introduce the \emph{Salient-Classifier}, a novel architecture combining a kernelized approach with a residual learning strategy. We evaluate variations of SSIVD-Net and Salient Classifier on our SCVD dataset and benchmark against state-of-the-art (SOTA) models commonly employed in violence detection. Our approach exhibits significant improvements in detecting both weaponized and non-weaponized violence instances. By advancing the SOTA in violence detection, our work offers a practical and scalable solution suitable for real-world applications. The proposed methodology not only addresses the challenges of violence detection in CCTV footage but also contributes to the understanding of weapon distribution in smart surveillance. Ultimately, our research findings should enable smarter and more secure cities, as well as enhance public safety measures.
Authors: Felix Ott, Nisha Lakshmana Raichur, David Rügamer, Tobias Feigl, Heiko Neumann, Bernd Bischl, Christopher Mutschler
Visual-inertial localization is a key problem in computer vision and robotics applications such as virtual reality, self-driving cars, and aerial vehicles. The goal is to estimate an accurate pose of an object when either the environment or the dynamics are known. Absolute pose regression (APR) techniques directly regress the absolute pose from an image input in a known scene using convolutional and spatio-temporal networks. Odometry methods perform relative pose regression (RPR) that predicts the relative pose from a known object dynamic (visual or inertial inputs). The localization task can be improved by retrieving information from both data sources for a cross-modal setup, which is a challenging problem due to contradictory tasks. In this work, we conduct a benchmark to evaluate deep multimodal fusion based on pose graph optimization and attention networks. Auxiliary and Bayesian learning are utilized for the APR task. We show accuracy improvements for the APR-RPR task and for the RPR-RPR task for aerial vehicles and hand-held devices. We conduct experiments on the EuRoC MAV and PennCOSYVIO datasets and record and evaluate a novel industry dataset.
Authors: Runnan Chen, Xinge Zhu, Nenglun Chen, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang
We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However, previous methods neglect the fine-grained relationship between the language and the 3D geometric elements. To this end, we propose a novel framework to learn the geometric primitives shared in seen and unseen categories' objects and employ a fine-grained alignment between language and the learned geometric primitives. Therefore, guided by language, the network recognizes the novel objects represented with geometric primitives. Specifically, we formulate a novel point visual representation, the similarity vector of the point's feature to the learnable prototypes, where the prototypes automatically encode geometric primitives via back-propagation. Besides, we propose a novel Unknown-aware InfoNCE Loss to fine-grained align the visual representation with language. Extensive experiments show that our method significantly outperforms other state-of-the-art methods in the harmonic mean-intersection-over-union (hIoU), with the improvement of 17.8\%, 30.4\%, 9.2\% and 7.9\% on S3DIS, ScanNet, SemanticKITTI and nuScenes datasets, respectively. Codes are available (https://github.com/runnanchen/Zero-Shot-Point-Cloud-Segmentation)
Authors: Chi-en Amy Tai, Hayden Gunraj, Nedim Hodzic, Nic Flanagan, Ali Sabri, Alexander Wong
Breast cancer is the second most common type of cancer in women in Canada and the United States, representing over 25\% of all new female cancer cases. As such, there has been immense research and progress on improving screening and clinical support for breast cancer. In this paper, we investigate enhancing clinical support for breast cancer with deep learning models using a newly introduced magnetic resonance imaging (MRI) modality called synthetic correlated diffusion imaging (CDI$^s$). More specifically, we leverage a volumetric convolutional neural network to learn volumetric deep radiomic features from a pre-treatment cohort and construct a predictor based on the learnt features for grade and post-treatment response prediction. As the first study to learn CDI$^s$-centric radiomic sequences within a deep learning perspective for clinical decision support, we evaluated the proposed approach using the ACRIN-6698 study against those learnt using gold-standard imaging modalities. We find that the proposed approach can achieve better performance for both grade and post-treatment response prediction and thus may be a useful tool to aid oncologists in improving recommendation of treatment of patients. Subsequently, the approach to leverage volumetric deep radiomic features for breast cancer can be further extended to other applications of CDI$^s$ in the cancer domain to further improve clinical support.
Authors: Le Zhuo, Zhaokai Wang, Baisen Wang, Yue Liao, Chenxi Bao, Stanley Peng, Songhao Han, Aixi Zhang, Fei Fang, Si Liu
Music is essential when editing videos, but selecting music manually is difficult and time-consuming. Thus, we seek to automatically generate background music tracks given video input. This is a challenging task since it requires music-video datasets, efficient architectures for video-to-music generation, and reasonable metrics, none of which currently exist. To close this gap, we introduce a complete recipe including dataset, benchmark model, and evaluation metric for video background music generation. We present SymMV, a video and symbolic music dataset with various musical annotations. To the best of our knowledge, it is the first video-music dataset with rich musical annotations. We also propose a benchmark video background music generation framework named V-MusProd, which utilizes music priors of chords, melody, and accompaniment along with video-music relations of semantic, color, and motion features. To address the lack of objective metrics for video-music correspondence, we design a retrieval-based metric VMCP built upon a powerful video-music representation learning model. Experiments show that with our dataset, V-MusProd outperforms the state-of-the-art method in both music quality and correspondence with videos. We believe our dataset, benchmark model, and evaluation metric will boost the development of video background music generation. Our dataset and code are available at https://github.com/zhuole1025/SymMV.
Authors: Gencer Sumbul, Begüm Demir
The development of deep learning based image representation learning (IRL) methods has attracted great attention for various image understanding problems. Most of these methods require the availability of a high quantity and quality of annotated training images, which can be time-consuming and costly to gather. To reduce labeling costs, crowdsourced data, automatic labeling procedures or citizen science projects can be considered. However, such approaches increase the risk of including label noise in training data. It may result in overfitting on noisy labels when discriminative reasoning is employed. This leads to sub-optimal learning procedures, and thus inaccurate characterization of images. To address this, we introduce a generative reasoning integrated label noise robust deep representation learning (GRID) approach. Our approach aims to model the complementary characteristics of discriminative and generative reasoning for IRL under noisy labels. To this end, we first integrate generative reasoning into discriminative reasoning through a supervised variational autoencoder. This allows GRID to automatically detect training samples with noisy labels. Then, through our label noise robust hybrid representation learning strategy, GRID adjusts the whole learning procedure for IRL of these samples through generative reasoning and that of other samples through discriminative reasoning. Our approach learns discriminative image representations while preventing interference of noisy labels independently from the IRL method being selected. Thus, unlike the existing methods, GRID does not depend on the type of annotation, neural network architecture, loss function or learning task, and thus can be directly utilized for various problems. Experimental results show its effectiveness compared to state-of-the-art methods. The code of GRID is publicly available at https://github.com/gencersumbul/GRID.
Authors: Guanzhou Ke, Guoqing Chao, Xiaoli Wang, Chenyang Xu, Yongqi Zhu, Yang Yu
The past two decades have seen increasingly rapid advances in the field of multi-view representation learning due to it extracting useful information from diverse domains to facilitate the development of multi-view applications. However, the community faces two challenges: i) how to learn robust representations from a large amount of unlabeled data to against noise or incomplete views setting, and ii) how to balance view consistency and complementary for various downstream tasks. To this end, we utilize a deep fusion network to fuse view-specific representations into the view-common representation, extracting high-level semantics for obtaining robust representation. In addition, we employ a clustering task to guide the fusion network to prevent it from leading to trivial solutions. For balancing consistency and complementary, then, we design an asymmetrical contrastive strategy that aligns the view-common representation and each view-specific representation. These modules are incorporated into a unified method known as CLustering-guided cOntrastiVE fusioN (CLOVEN). We quantitatively and qualitatively evaluate the proposed method on five datasets, demonstrating that CLOVEN outperforms 11 competitive multi-view learning methods in clustering and classification. In the incomplete view scenario, our proposed method resists noise interference better than those of our competitors. Furthermore, the visualization analysis shows that CLOVEN can preserve the intrinsic structure of view-specific representation while also improving the compactness of view-commom representation. Our source code will be available soon at https://github.com/guanzhou-ke/cloven.
Authors: Luca Tomasetti, Kjersti Engan, Liv Jorunn Høllesli, Kathinka Dæhli Kurz, Mahdieh Khanmohammadi
Precise and fast prediction methods for ischemic areas comprised of dead tissue, core, and salvageable tissue, penumbra, in acute ischemic stroke (AIS) patients are of significant clinical interest. They play an essential role in improving diagnosis and treatment planning. Computed Tomography (CT) scan is one of the primary modalities for early assessment in patients with suspected AIS. CT Perfusion (CTP) is often used as a primary assessment to determine stroke location, severity, and volume of ischemic lesions. Current automatic segmentation methods for CTP mostly use already processed 3D parametric maps conventionally used for clinical interpretation by radiologists as input. Alternatively, the raw CTP data is used on a slice-by-slice basis as 2D+time input, where the spatial information over the volume is ignored. In addition, these methods are only interested in segmenting core regions, while predicting penumbra can be essential for treatment planning. This paper investigates different methods to utilize the entire 4D CTP as input to fully exploit the spatio-temporal information, leading us to propose a novel 4D convolution layer. Our comprehensive experiments on a local dataset of 152 patients divided into three groups show that our proposed models generate more precise results than other methods explored. Adopting the proposed 4D mJ-Net, a Dice Coefficient of 0.53 and 0.23 is achieved for segmenting penumbra and core areas, respectively. The code is available on https://github.com/Biomedical-Data-Analysis-Laboratory/4D-mJ-Net.git.
Authors: Roy Miles, Krystian Mikolajczyk
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet.
Authors: Yuzhi Zhao, Lai-Man Po, Kangcheng Liu, Xuehui Wang, Wing-Yin Yu, Pengfei Xian, Yujia Zhang, Mengyang Liu
In this paper, we propose a scribble-based video colorization network with temporal aggregation called SVCNet. It can colorize monochrome videos based on different user-given color scribbles. It addresses three common issues in the scribble-based video colorization area: colorization vividness, temporal consistency, and color bleeding. To improve the colorization quality and strengthen the temporal consistency, we adopt two sequential sub-networks in SVCNet for precise colorization and temporal smoothing, respectively. The first stage includes a pyramid feature encoder to incorporate color scribbles with a grayscale frame, and a semantic feature encoder to extract semantics. The second stage finetunes the output from the first stage by aggregating the information of neighboring colorized frames (as short-range connections) and the first colorized frame (as a long-range connection). To alleviate the color bleeding artifacts, we learn video colorization and segmentation simultaneously. Furthermore, we set the majority of operations on a fixed small image resolution and use a Super-resolution Module at the tail of SVCNet to recover original sizes. It allows the SVCNet to fit different image resolutions at the inference. Finally, we evaluate the proposed SVCNet on DAVIS and Videvo benchmarks. The experimental results demonstrate that SVCNet produces both higher-quality and more temporally consistent videos than other well-known video colorization approaches. The codes and models can be found at https://github.com/zhaoyuzhi/SVCNet.
Authors: Xiaobao Guo, Nithish Muthuchamy Selvaraj, Zitong Yu, Adams Wai-Kin Kong, Bingquan Shen, Alex Kot
Deception detection in conversations is a challenging yet important task, having pivotal applications in many fields such as credibility assessment in business, multimedia anti-frauds, and custom security. Despite this, deception detection research is hindered by the lack of high-quality deception datasets, as well as the difficulties of learning multimodal features effectively. To address this issue, we introduce DOLOS\footnote {The name ``DOLOS" comes from Greek mythology.}, the largest gameshow deception detection dataset with rich deceptive conversations. DOLOS includes 1,675 video clips featuring 213 subjects, and it has been labeled with audio-visual feature annotations. We provide train-test, duration, and gender protocols to investigate the impact of different factors. We benchmark our dataset on previously proposed deception detection approaches. To further improve the performance by fine-tuning fewer parameters, we propose Parameter-Efficient Crossmodal Learning (PECL), where a Uniform Temporal Adapter (UT-Adapter) explores temporal attention in transformer-based architectures, and a crossmodal fusion module, Plug-in Audio-Visual Fusion (PAVF), combines crossmodal information from audio-visual features. Based on the rich fine-grained audio-visual annotations on DOLOS, we also exploit multi-task learning to enhance performance by concurrently predicting deception and audio-visual features. Experimental results demonstrate the desired quality of the DOLOS dataset and the effectiveness of the PECL. The DOLOS dataset and the source codes are available at https://github.com/NMS05/Audio-Visual-Deception-Detection-DOLOS-Dataset-and-Parameter-Efficient-Crossmodal-Learning/tree/main.
Authors: Yiwei Ma, Xiaioqing Zhang, Xiaoshuai Sun, Jiayi Ji, Haowei Wang, Guannan Jiang, Weilin Zhuang, Rongrong Ji
Text-driven 3D stylization is a complex and crucial task in the fields of computer vision (CV) and computer graphics (CG), aimed at transforming a bare mesh to fit a target text. Prior methods adopt text-independent multilayer perceptrons (MLPs) to predict the attributes of the target mesh with the supervision of CLIP loss. However, such text-independent architecture lacks textual guidance during predicting attributes, thus leading to unsatisfactory stylization and slow convergence. To address these limitations, we present X-Mesh, an innovative text-driven 3D stylization framework that incorporates a novel Text-guided Dynamic Attention Module (TDAM). The TDAM dynamically integrates the guidance of the target text by utilizing text-relevant spatial and channel-wise attentions during vertex feature extraction, resulting in more accurate attribute prediction and faster convergence speed. Furthermore, existing works lack standard benchmarks and automated metrics for evaluation, often relying on subjective and non-reproducible user studies to assess the quality of stylized 3D assets. To overcome this limitation, we introduce a new standard text-mesh benchmark, namely MIT-30, and two automated metrics, which will enable future research to achieve fair and objective comparisons. Our extensive qualitative and quantitative experiments demonstrate that X-Mesh outperforms previous state-of-the-art methods.
Authors: Yu Zhang, Xiaoguang Di, Junde Wu, Rao Fu, Yong Li, Yue Wang, Yanwu Xu, Guohui Yang, Chunhui Wang
Image enhancement is a common technique used to mitigate issues such as severe noise, low brightness, low contrast, and color deviation in low-light images. However, providing an optimal high-light image as a reference for low-light image enhancement tasks is impossible, which makes the learning process more difficult than other image processing tasks. As a result, although several low-light image enhancement methods have been proposed, most of them are either too complex or insufficient in addressing all the issues in low-light images. In this paper, to make the learning easier in low-light image enhancement, we introduce FLW-Net (Fast and LightWeight Network) and two relative loss functions. Specifically, we first recognize the challenges of the need for a large receptive field to obtain global contrast and the lack of an absolute reference, which limits the simplification of network structures in this task. Then, we propose an efficient global feature information extraction component and two loss functions based on relative information to overcome these challenges. Finally, we conducted comparative experiments to demonstrate the effectiveness of the proposed method, and the results confirm that the proposed method can significantly reduce the complexity of supervised low-light image enhancement networks while improving processing effect. The code is available at \url{https://github.com/hitzhangyu/FLW-Net}.
Authors: Rayson Laroca, Valter Estevam, Alceu S. Britto Jr., Rodrigo Minetto, David Menotti
This work draws attention to the large fraction of near-duplicates in the training and test sets of datasets widely adopted in License Plate Recognition (LPR) research. These duplicates refer to images that, although different, show the same license plate. Our experiments, conducted on the two most popular datasets in the field, show a substantial decrease in recognition rate when six well-known models are trained and tested under fair splits, that is, in the absence of duplicates in the training and test sets. Moreover, in one of the datasets, the ranking of models changed considerably when they were trained and tested under duplicate-free splits. These findings suggest that such duplicates have significantly biased the evaluation and development of deep learning-based models for LPR. The list of near-duplicates we have found and proposals for fair splits are publicly available for further research at https://raysonlaroca.github.io/supp/lpr-train-on-test/
Authors: Dilxat Muhtar, Xueliang Zhang, Pengfeng Xiao, Zhenshi Li, Feng Gu
Self-supervised learning (SSL) has gained widespread attention in the remote sensing (RS) and earth observation (EO) communities owing to its ability to learn task-agnostic representations without human-annotated labels. Nevertheless, most existing RS SSL methods are limited to learning either global semantic separable or local spatial perceptible representations. We argue that this learning strategy is suboptimal in the realm of RS, since the required representations for different RS downstream tasks are often varied and complex. In this study, we proposed a unified SSL framework that is better suited for RS images representation learning. The proposed SSL framework, Contrastive Mask Image Distillation (CMID), is capable of learning representations with both global semantic separability and local spatial perceptibility by combining contrastive learning (CL) with masked image modeling (MIM) in a self-distillation way. Furthermore, our CMID learning framework is architecture-agnostic, which is compatible with both convolutional neural networks (CNN) and vision transformers (ViT), allowing CMID to be easily adapted to a variety of deep learning (DL) applications for RS understanding. Comprehensive experiments have been carried out on four downstream tasks (i.e. scene classification, semantic segmentation, object-detection, and change detection) and the results show that models pre-trained using CMID achieve better performance than other state-of-the-art SSL methods on multiple downstream tasks. The code and pre-trained models will be made available at https://github.com/NJU-LHRS/official-CMID to facilitate SSL research and speed up the development of RS images DL applications.
Authors: Haoyang Peng, Baopu Li, Bo Zhang, Xin Chen, Tao Chen, Hongyuan Zhu
Point cloud based 3D deep model has wide applications in many applications such as autonomous driving, house robot, and so on. Inspired by the recent prompt learning in natural language processing, this work proposes a novel Multi-view Vision-Prompt Fusion Network (MvNet) for few-shot 3D point cloud classification. MvNet investigates the possibility of leveraging the off-the-shelf 2D pre-trained models to achieve the few-shot classification, which can alleviate the over-dependence issue of the existing baseline models towards the large-scale annotated 3D point cloud data. Specifically, MvNet first encodes a 3D point cloud into multi-view image features for a number of different views. Then, a novel multi-view prompt fusion module is developed to effectively fuse information from different views to bridge the gap between 3D point cloud data and 2D pre-trained models. A set of 2D image prompts can then be derived to better describe the suitable prior knowledge for a large-scale pre-trained image model for few-shot 3D point cloud classification. Extensive experiments on ModelNet, ScanObjectNN, and ShapeNet datasets demonstrate that MvNet achieves new state-of-the-art performance for 3D few-shot point cloud image classification. The source code of this work will be available soon.
Authors: Markus Schön, Michael Buchholz, Klaus Dietmayer
Panoptic segmentation is one of the most challenging scene parsing tasks, combining the tasks of semantic segmentation and instance segmentation. While much progress has been made, few works focus on the real-time application of panoptic segmentation methods. In this paper, we revisit the recently introduced K-Net architecture. We propose vital changes to the architecture, training, and inference procedure, which massively decrease latency and improve performance. Our resulting RT-K-Net sets a new state-of-the-art performance for real-time panoptic segmentation methods on the Cityscapes dataset and shows promising results on the challenging Mapillary Vistas dataset. On Cityscapes, RT-K-Net reaches 60.2 % PQ with an average inference time of 32 ms for full resolution 1024x2048 pixel images on a single Titan RTX GPU. On Mapillary Vistas, RT-K-Net reaches 33.2 % PQ with an average inference time of 69 ms. Source code is available at https://github.com/markusschoen/RT-K-Net.
Authors: Jing Zhao, Heliang Zheng, Chaoyue Wang, Long Lan, Wanrong Huang, Wenjing Yang
Classifier-free guidance is an effective sampling technique in diffusion models that has been widely adopted. The main idea is to extrapolate the model in the direction of text guidance and away from null-text guidance. In this paper, we demonstrate that null-text guidance in diffusion models is secretly a cartoon-style creator, i.e., the generated images can be efficiently transformed into cartoons by simply perturbing the null-text guidance. Specifically, we proposed two disturbance methods, i.e., Rollback disturbance (Back-D) and Image disturbance (Image-D), to construct misalignment between the noisy images used for predicting null-text guidance and text guidance (subsequently referred to as \textbf{null-text noisy image} and \textbf{text noisy image} respectively) in the sampling process. Back-D achieves cartoonization by altering the noise level of null-text noisy image via replacing $x_t$ with $x_{t+\Delta t}$. Image-D, alternatively, produces high-fidelity, diverse cartoons by defining $x_t$ as a clean input image, which further improves the incorporation of finer image details. Through comprehensive experiments, we delved into the principle of noise disturbing for null-text and uncovered that the efficacy of disturbance depends on the correlation between the null-text noisy image and the source image. Moreover, our proposed techniques, which can generate cartoon images and cartoonize specific ones, are training-free and easily integrated as a plug-and-play component in any classifier-free guided diffusion model. Project page is available at \url{https://nulltextforcartoon.github.io/}.
Authors: Yang Bai, Jingyao Wang, Min Cao, Chen Chen, Ziqiang Cao, Liqiang Nie, Min Zhang
Text-based person search (TBPS) aims to retrieve the images of the target person from a large image gallery based on a given natural language description. Existing methods are dominated by training models with parallel image-text pairs, which are very costly to collect. In this paper, we make the first attempt to explore TBPS without parallel image-text data ($\mu$-TBPS), in which only non-parallel images and texts, or even image-only data, can be adopted. Towards this end, we propose a two-stage framework, generation-then-retrieval (GTR), to first generate the corresponding pseudo text for each image and then perform the retrieval in a supervised manner. In the generation stage, we propose a fine-grained image captioning strategy to obtain an enriched description of the person image, which firstly utilizes a set of instruction prompts to activate the off-the-shelf pretrained vision-language model to capture and generate fine-grained person attributes, and then converts the extracted attributes into a textual description via the finetuned large language model or the hand-crafted template. In the retrieval stage, considering the noise interference of the generated texts for training model, we develop a confidence score-based training scheme by enabling more reliable texts to contribute more during the training. Experimental results on multiple TBPS benchmarks (i.e., CUHK-PEDES, ICFG-PEDES and RSTPReid) show that the proposed GTR can achieve a promising performance without relying on parallel image-text data.
Authors: Shilv Cai, Xu Zou, Liqun Chen, Luxin Yan, Sheng Zhong
Learning-based image compression methods have made great progress. Most of them are designed for generic natural images. In fact, low-light images frequently occur due to unavoidable environmental influences or technical limitations, such as insufficient lighting or limited exposure time. %When general-purpose image compression algorithms compress low-light images, useful detail information is lost, resulting in a dramatic decrease in image enhancement. Once low-light images are compressed by existing general image compression approaches, useful information(e.g., texture details) would be lost resulting in a dramatic performance decrease in low-light image enhancement. To simultaneously achieve a higher compression rate and better enhancement performance for low-light images, we propose a novel image compression framework with joint optimization of low-light image enhancement. We design an end-to-end trainable two-branch architecture with lower computational cost, which includes the main enhancement branch and the signal-to-noise ratio~(SNR) aware branch. Experimental results show that our proposed joint optimization framework achieves a significant improvement over existing ``Compress before Enhance" or ``Enhance before Compress" sequential solutions for low-light images. Source codes are included in the supplementary material.
Authors: Shengqin Jiang, Yaoyu Fang, Haokui Zhang, Qingshan Liu, Yuankai Qi, Yang Yang, Peng Wang
Rehearsal-based video incremental learning often employs knowledge distillation to mitigate catastrophic forgetting of previously learned data. However, this method faces two major challenges for video task: substantial computing resources from loading teacher model and limited replay capability from performance-limited teacher model. To address these problems, we first propose a knowledge distillation-free framework for rehearsal-based video incremental learning called \textit{Teacher Agent}. Instead of loading parameter-heavy teacher networks, we introduce an agent generator that is either parameter-free or uses only a few parameters to obtain accurate and reliable soft labels. This method not only greatly reduces the computing requirement but also circumvents the problem of knowledge misleading caused by inaccurate predictions of the teacher model. Moreover, we put forward a self-correction loss which provides an effective regularization signal for the review of old knowledge, which in turn alleviates the problem of catastrophic forgetting. Further, to ensure that the samples in the memory buffer are memory-efficient and representative, we introduce a unified sampler for rehearsal-based video incremental learning to mine fixed-length key video frames. Interestingly, based on the proposed strategies, the network exhibits a high level of robustness against spatial resolution reduction when compared to the baseline. Extensive experiments demonstrate the advantages of our method, yielding significant performance improvements while utilizing only half the spatial resolution of video clips as network inputs in the incremental phases.
Authors: Sainan Liu, Shan Lin, Jingpei Lu, Shreya Saha, Alexey Supikov, Michael Yip
Implicit neural representation has emerged as a powerful method for reconstructing 3D scenes from 2D images. Given a set of camera poses and associated images, the models can be trained to synthesize novel, unseen views. In order to expand the use cases for implicit neural representations, we need to incorporate camera pose estimation capabilities as part of the representation learning, as this is necessary for reconstructing scenes from real-world video sequences where cameras are generally not being tracked. Existing approaches like COLMAP and, most recently, bundle-adjusting neural radiance field methods often suffer from lengthy processing times. These delays ranging from hours to days, arise from laborious feature matching, hardware limitations, dense point sampling, and long training times required by a multi-layer perceptron structure with a large number of parameters. To address these challenges, we propose a framework called bundle-adjusting accelerated neural graphics primitives (BAA-NGP). Our approach leverages accelerated sampling and hash encoding to expedite both pose refinement/estimation and 3D scene reconstruction. Experimental results demonstrate that our method achieves a more than 10 to 20 $\times$ speed improvement in novel view synthesis compared to other bundle-adjusting neural radiance field methods without sacrificing the quality of pose estimation. The github repository can be found here https://github.com/IntelLabs/baa-ngp.
Authors: Takato Yasuno
In past decade, previous balanced datasets have been used to advance algorithms for classification, object detection, semantic segmentation, and anomaly detection in industrial applications. Specifically, for condition-based maintenance, automating visual inspection is crucial to ensure high quality. Deterioration prognostic attempts to optimize the fine decision process for predictive maintenance and proactive repair. In civil infrastructure and living environment, damage data mining cannot avoid the imbalanced data issue because of rare unseen events and high quality status by improved operations. For visual inspection, deteriorated class acquired from the surface of concrete and steel components are occasionally imbalanced. From numerous related surveys, we summarize that imbalanced data problems can be categorized into four types; 1) missing range of target and label valuables, 2) majority-minority class imbalance, 3) foreground-background of spatial imbalance, 4) long-tailed class of pixel-wise imbalance. Since 2015, there has been many imbalanced studies using deep learning approaches that includes regression, image classification, object detection, semantic segmentation. However, anomaly detection for imbalanced data is not yet well known. In the study, we highlight one-class anomaly detection application whether anomalous class or not, and demonstrate clear examples on imbalanced vision datasets: blood smear, lung infection, wooden, concrete deterioration, and disaster damage. We provide key results on damage vision mining advantage, hypothesizing that the more effective range of positive ratio, the higher accuracy gain of anomaly detection application. Finally, the applicability of the damage learning methods, limitations, and future works are mentioned.
Authors: Min Liu, Alberto Sangiovanni-Vincentelli, Xiangyu Yue
Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly reduced attack success rate, but their prediction accuracy on clean data still lags behind a clean model by a large margin. Inspired by the stealthiness and effectiveness of backdoor attack, we propose a simple but highly effective defense framework which injects non-adversarial backdoors targeting poisoned samples. Following the general steps in backdoor attack, we detect a small set of suspected samples and then apply a poisoning strategy to them. The non-adversarial backdoor, once triggered, suppresses the attacker's backdoor on poisoned data, but has limited influence on clean data. The defense can be carried out during data preprocessing, without any modification to the standard end-to-end training pipeline. We conduct extensive experiments on multiple benchmarks with different architectures and representative attacks. Results demonstrate that our method achieves state-of-the-art defense effectiveness with by far the lowest performance drop on clean data. Considering the surprising defense ability displayed by our framework, we call for more attention to utilizing backdoor for backdoor defense. Code is available at https://github.com/damianliumin/non-adversarial_backdoor.
Authors: Misgina Tsighe Hagos, Kathleen M. Curran, Brian Mac Namee
Medical image classification models are frequently trained using training datasets derived from multiple data sources. While leveraging multiple data sources is crucial for achieving model generalization, it is important to acknowledge that the diverse nature of these sources inherently introduces unintended confounders and other challenges that can impact both model accuracy and transparency. A notable confounding factor in medical image classification, particularly in musculoskeletal image classification, is skeletal maturation-induced bone growth observed during adolescence. We train a deep learning model using a Covid-19 chest X-ray dataset and we showcase how this dataset can lead to spurious correlations due to unintended confounding regions. eXplanation Based Learning (XBL) is a deep learning approach that goes beyond interpretability by utilizing model explanations to interactively unlearn spurious correlations. This is achieved by integrating interactive user feedback, specifically feature annotations. In our study, we employed two non-demanding manual feedback mechanisms to implement an XBL-based approach for effectively eliminating these spurious correlations. Our results underscore the promising potential of XBL in constructing robust models even in the presence of confounding factors.
Authors: Yu Wu, Yana Wei, Haozhe Wang, Yongfei Liu, Sibei Yang, Xuming He
This paper introduces Grounded Image Text Matching with Mismatched Relation (GITM-MR), a novel visual-linguistic joint task that evaluates the relation understanding capabilities of transformer-based pre-trained models. GITM-MR requires a model to first determine if an expression describes an image, then localize referred objects or ground the mismatched parts of the text. We provide a benchmark for evaluating pre-trained models on this task, with a focus on the challenging settings of limited data and out-of-distribution sentence lengths. Our evaluation demonstrates that pre-trained models lack data efficiency and length generalization ability. To address this, we propose the Relation-sensitive Correspondence Reasoning Network (RCRN), which incorporates relation-aware reasoning via bi-directional message propagation guided by language structure. RCRN can be interpreted as a modular program and delivers strong performance in both length generalization and data efficiency.
Authors: Shili Zhou, Xuhao Jiang, Weimin Tan, Ruian He, Bo Yan
In recent years, many deep learning-based methods have been proposed to tackle the problem of optical flow estimation and achieved promising results. However, they hardly consider that most videos are compressed and thus ignore the pre-computed information in compressed video streams. Motion vectors, one of the compression information, record the motion of the video frames. They can be directly extracted from the compression code stream without computational cost and serve as a solid prior for optical flow estimation. Therefore, we propose an optical flow model, MVFlow, which uses motion vectors to improve the speed and accuracy of optical flow estimation for compressed videos. In detail, MVFlow includes a key Motion-Vector Converting Module, which ensures that the motion vectors can be transformed into the same domain of optical flow and then be utilized fully by the flow estimation module. Meanwhile, we construct four optical flow datasets for compressed videos containing frames and motion vectors in pairs. The experimental results demonstrate the superiority of our proposed MVFlow, which can reduce the AEPE by 1.09 compared to existing models or save 52% time to achieve similar accuracy to existing models.
Authors: Guanzhou Ke, Yang Yu, Guoqing Chao, Xiaoli Wang, Chenyang Xu, Shengfeng He
Multi-view (or -modality) representation learning aims to understand the relationships between different view representations. Existing methods disentangle multi-view representations into consistent and view-specific representations by introducing strong inductive biases, which can limit their generalization ability. In this paper, we propose a novel multi-view representation disentangling method that aims to go beyond inductive biases, ensuring both interpretability and generalizability of the resulting representations. Our method is based on the observation that discovering multi-view consistency in advance can determine the disentangling information boundary, leading to a decoupled learning objective. We also found that the consistency can be easily extracted by maximizing the transformation invariance and clustering consistency between views. These observations drive us to propose a two-stage framework. In the first stage, we obtain multi-view consistency by training a consistent encoder to produce semantically-consistent representations across views as well as their corresponding pseudo-labels. In the second stage, we disentangle specificity from comprehensive representations by minimizing the upper bound of mutual information between consistent and comprehensive representations. Finally, we reconstruct the original data by concatenating pseudo-labels and view-specific representations. Our experiments on four multi-view datasets demonstrate that our proposed method outperforms 12 comparison methods in terms of clustering and classification performance. The visualization results also show that the extracted consistency and specificity are compact and interpretable. Our code can be found at \url{https://github.com/Guanzhou-Ke/DMRIB}.
Authors: Kairui Yang, Enhui Ma, Jibin Peng, Qing Guo, Di Lin, Kaicheng Yu
Using synthesized images to boost the performance of perception models is a long-standing research challenge in computer vision. It becomes more eminent in visual-centric autonomous driving systems with multi-view cameras as some long-tail scenarios can never be collected. Guided by the BEV segmentation layouts, the existing generative networks seem to synthesize photo-realistic street-view images when evaluated solely on scene-level metrics. However, once zoom-in, they usually fail to produce accurate foreground and background details such as heading. To this end, we propose a two-stage generative method, dubbed BEVControl, that can generate accurate foreground and background contents. In contrast to segmentation-like input, it also supports sketch style input, which is more flexible for humans to edit. In addition, we propose a comprehensive multi-level evaluation protocol to fairly compare the quality of the generated scene, foreground object, and background geometry. Our extensive experiments show that our BEVControl surpasses the state-of-the-art method, BEVGen, by a significant margin, from 5.89 to 26.80 on foreground segmentation mIoU. In addition, we show that using images generated by BEVControl to train the downstream perception model, it achieves on average 1.29 improvement in NDS score.
Authors: Mihai Fieraru, Mihai Zanfir, Elisabeta Oneata, Alin-Ionut Popa, Vlad Olaru, Cristian Sminchisescu
Understanding 3d human interactions is fundamental for fine-grained scene analysis and behavioural modeling. However, most of the existing models predict incorrect, lifeless 3d estimates, that miss the subtle human contact aspects--the essence of the event--and are of little use for detailed behavioral understanding. This paper addresses such issues with several contributions: (1) we introduce models for interaction signature estimation (ISP) encompassing contact detection, segmentation, and 3d contact signature prediction; (2) we show how such components can be leveraged to ensure contact consistency during 3d reconstruction; (3) we construct several large datasets for learning and evaluating 3d contact prediction and reconstruction methods; specifically, we introduce CHI3D, a lab-based accurate 3d motion capture dataset with 631 sequences containing $2,525$ contact events, $728,664$ ground truth 3d poses, as well as FlickrCI3D, a dataset of $11,216$ images, with $14,081$ processed pairs of people, and $81,233$ facet-level surface correspondences. Finally, (4) we propose methodology for recovering the ground-truth pose and shape of interacting people in a controlled setup and (5) annotate all 3d interaction motions in CHI3D with textual descriptions. Motion data in multiple formats (GHUM and SMPLX parameters, Human3.6m 3d joints) is made available for research purposes at \url{https://ci3d.imar.ro}, together with an evaluation server and a public benchmark.
Authors: Manasa Manohara, Sankalp Dayal, Tariq Afzal, Rahul Bakshi, Kahkuen Fu
Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conversion. Existing model quantization frameworks like Tensorflow QAT [1], TFLite PTQ [2], and Qualcomm AIMET [3] supports only a limited set of quantization schemes (e.g., only asymmetric per-tensor quantization in TF1.x QAT [4]). Accordingly, deep learning models cannot be easily quantized for diverse fixed-point hardwares, mainly due to slightly different quantization requirements. In this paper, we envision a new type of model quantization approach called MRQ (model re-quantization), which takes existing quantized models and quickly transforms the models to meet different quantization requirements (e.g., asymmetric -> symmetric, non-power-of-2 scale -> power-of-2 scale). Re-quantization is much simpler than quantizing from scratch because it avoids costly re-training and provides support for multiple quantization schemes simultaneously. To minimize re-quantization error, we developed a new set of re-quantization algorithms including weight correction and rounding error folding. We have demonstrated that MobileNetV2 QAT model [7] can be quickly re-quantized into two different quantization schemes (i.e., symmetric and symmetric+power-of-2 scale) with less than 0.64 units of accuracy loss. We believe our work is the first to leverage this concept of re-quantization for model quantization and models obtained from the re-quantization process have been successfully deployed on NNA in the Echo Show devices.