Authors: Amir Ali
In recent times, the use of chest Computed Tomography (CT) images for detecting coronavirus infections has gained significant attention, owing to their ability to reveal bilateral changes in affected individuals. However, classifying patients from medical images presents a formidable challenge, particularly in identifying such bilateral changes. To tackle this challenge, our study harnesses the power of deep learning models for the precise classification of infected patients. Our research involves a comparative analysis of deep transfer learning-based classification models, including DenseNet201, GoogleNet, and AlexNet, against carefully chosen supervised learning models. Additionally, our work encompasses Covid-19 classification, which involves the identification and differentiation of medical images, such as X-rays and electrocardiograms, that exhibit telltale signs of Covid-19 infection. This comprehensive approach ensures that our models can handle a wide range of medical image types and effectively identify characteristic patterns indicative of Covid-19. By conducting meticulous research and employing advanced deep learning techniques, we have made significant strides in enhancing the accuracy and speed of Covid-19 diagnosis. Our results demonstrate the effectiveness of these models and their potential to make substantial contributions to the global effort to combat COVID-19.
Authors: Haoli Yin, Jiayao Li (Emily), Eva Schiller, Luke McDermott, Daniel Cummings
Object Re-Identification (ReID) is pivotal in computer vision, witnessing an escalating demand for adept multimodal representation learning. Current models, although promising, reveal scalability limitations with increasing modalities as they rely heavily on late fusion, which postpones the integration of specific modality insights. Addressing this, we introduce the \textbf{Gradual Fusion Transformer (GraFT)} for multimodal ReID. At its core, GraFT employs learnable fusion tokens that guide self-attention across encoders, adeptly capturing both modality-specific and object-specific features. Further bolstering its efficacy, we introduce a novel training paradigm combined with an augmented triplet loss, optimizing the ReID feature embedding space. We demonstrate these enhancements through extensive ablation studies and show that GraFT consistently surpasses established multimodal ReID benchmarks. Additionally, aiming for deployment versatility, we've integrated neural network pruning into GraFT, offering a balance between model size and performance.
Authors: Dadong Jiang, Zhihui Ke, Xiaobo Zhou, Xidong Shi
This paper targets interactive object-level editing(e.g., deletion, recoloring, transformation, composition) in dynamic scenes. Recently, some methods aiming for flexible editing static scenes represented by neural radiance field (NeRF) have shown impressive synthesis quality, while similar capabilities in time-variant dynamic scenes remain limited. To solve this problem, we propose 4D-Editor, an interactive semantic-driven editing framework, allowing editing multiple objects in dynamic NeRF based on user strokes on a single frame. Our dynamic scene representation is built upon hybrid semantic feature fields so that the spatial-temporal consistency can be maintained after editing. In addition, we design recursive selection refinement that significantly boosts segmentation accuracy in a dynamic NeRF to aid the editing process. Moreover, we develop multi-view reprojection inpainting to fill holes caused by incomplete scene capture after editing. Extensive experiments and editing examples on real-world demonstrate that 4D-Editor achieves photo-realistic dynamic NeRF editing. Project page: https://patrickddj.github.io/4D-Editor
Authors: Zhe Li, Zhangyang Gao, Cheng Tan, Stan Z. Li, Laurence T. Yang
The pre-training architectures of large language models encompass various types, including autoencoding models, autoregressive models, and encoder-decoder models. We posit that any modality can potentially benefit from a large language model, as long as it undergoes vector quantization to become discrete tokens. Inspired by GLM, we propose a General Point Model (GPM) which seamlessly integrates autoencoding and autoregressive tasks in point cloud transformer. This model is versatile, allowing fine-tuning for downstream point cloud representation tasks, as well as unconditional and conditional generation tasks. GPM enhances masked prediction in autoencoding through various forms of mask padding tasks, leading to improved performance in point cloud understanding. Additionally, GPM demonstrates highly competitive results in unconditional point cloud generation tasks, even exhibiting the potential for conditional generation tasks by modifying the input's conditional information. Compared to models like Point-BERT, MaskPoint and PointMAE, our GPM achieves superior performance in point cloud understanding tasks. Furthermore, the integration of autoregressive and autoencoding within the same transformer underscores its versatility across different downstream tasks.
Authors: Yunsheng Ma, Juanwu Lu, Can Cui, Sicheng ZHao, Xu Cao, Wenqian Ye, Ziran Wang
Vehicle-to-vehicle (V2V) communications have greatly enhanced the perception capabilities of connected and automated vehicles (CAVs) by enabling information sharing to "see through the occlusions", resulting in significant performance improvements. However, developing and training complex multi-agent perception models from scratch can be expensive and unnecessary when existing single-agent models show remarkable generalization capabilities. In this paper, we propose a new framework termed MACP, which equips a single-agent pre-trained model with cooperation capabilities. We approach this objective by identifying the key challenges of shifting from single-agent to cooperative settings, adapting the model by freezing most of its parameters and adding a few lightweight modules. We demonstrate in our experiments that the proposed framework can effectively utilize cooperative observations and outperform other state-of-the-art approaches in both simulated and real-world cooperative perception benchmarks while requiring substantially fewer tunable parameters with reduced communication costs. Our source code is available at https://github.com/PurdueDigitalTwin/MACP.
Authors: Hariharan Ravishankar, Rohan Patil, Vikram Melapudi, Parminder Bhatia, Kass-Hout Taha, Pavan Annangi
In this paper, we present SonoSAM - a promptable foundational model for segmenting objects of interest on ultrasound images. Fine-tuned exclusively on a rich, diverse set of objects from roughly 200k ultrasound image-mask pairs, SonoSAM demonstrates state-of-the-art performance on 8 unseen ultrasound data-sets, outperforming competing methods by a significant margin on all metrics of interest. SonoSAM achieves average dice similarity score of more than 90% on almost all test datasets within 2-6 clicks on an average, making it a valuable tool for annotating ultrasound images. We also extend SonoSAM to 3-D (2-D +t) applications and demonstrate superior performance making it a valuable tool for generating dense annotations from ultrasound cine-loops. Further, to increase practical utility of SonoSAM, we propose a two-step process of fine-tuning followed by knowledge distillation to a smaller footprint model without comprising the performance. We present detailed qualitative and quantitative comparisons of SonoSAM with state-of-the art methods showcasing efficacy of SonoSAM as one of the first reliable, generic foundational model for ultrasound.
Authors: Yinan Liang, Ziwei Wang, Xiuwei Xu, Yansong Tang, Zhou Jie, Jiwen Lu
Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Conventional methods successfully enable convolutional neural network inference of high resolution images on microcontrollers, while the framework for vision transformers that achieve the state-of-the-art performance in many vision applications still remains unexplored. In this paper, we propose a hardware-algorithm co-optimizations method called MCUFormer to deploy vision transformers on microcontrollers with extremely limited memory, where we jointly design transformer architecture and construct the inference operator library to fit the memory resource constraint. More specifically, we generalize the one-shot network architecture search (NAS) to discover the optimal architecture with highest task performance given the memory budget from the microcontrollers, where we enlarge the existing search space of vision transformers by considering the low-rank decomposition dimensions and patch resolution for memory reduction. For the construction of the inference operator library of vision transformers, we schedule the memory buffer during inference through operator integration, patch embedding decomposition, and token overwriting, allowing the memory buffer to be fully utilized to adapt to the forward pass of the vision transformer. Experimental results demonstrate that our MCUFormer achieves 73.62\% top-1 accuracy on ImageNet for image classification with 320KB memory on STM32F746 microcontroller. Code is available at https://github.com/liangyn22/MCUFormer.
Authors: Jianwei Fei, Zhihua Xia, Benedetta Tondi, Mauro Barni
We propose a novel multi-bit box-free watermarking method for the protection of Intellectual Property Rights (IPR) of GANs with improved robustness against white-box attacks like fine-tuning, pruning, quantization, and surrogate model attacks. The watermark is embedded by adding an extra watermarking loss term during GAN training, ensuring that the images generated by the GAN contain an invisible watermark that can be retrieved by a pre-trained watermark decoder. In order to improve the robustness against white-box model-level attacks, we make sure that the model converges to a wide flat minimum of the watermarking loss term, in such a way that any modification of the model parameters does not erase the watermark. To do so, we add random noise vectors to the parameters of the generator and require that the watermarking loss term is as invariant as possible with respect to the presence of noise. This procedure forces the generator to converge to a wide flat minimum of the watermarking loss. The proposed method is architectureand dataset-agnostic, thus being applicable to many different generation tasks and models, as well as to CNN-based image processing architectures. We present the results of extensive experiments showing that the presence of the watermark has a negligible impact on the quality of the generated images, and proving the superior robustness of the watermark against model modification and surrogate model attacks.
Authors: Yasmine Mustafa, Tie Luo
Alzheimer's disease (AD) is a prevalent and debilitating neurodegenerative disorder impacting a large aging population. Detecting AD in all its presymptomatic and symptomatic stages is crucial for early intervention and treatment. An active research direction is to explore machine learning methods that harness multimodal data fusion to outperform human inspection of medical scans. However, existing multimodal fusion models have limitations, including redundant computation, complex architecture, and simplistic handling of missing data. Moreover, the preprocessing pipelines of medical scans remain inadequately detailed and are seldom optimized for individual subjects. In this paper, we propose an efficient early-late fusion (ELF) approach, which leverages a convolutional neural network for automated feature extraction and random forests for their competitive performance on small datasets. Additionally, we introduce a robust preprocessing pipeline that adapts to the unique characteristics of individual subjects and makes use of whole brain images rather than slices or patches. Moreover, to tackle the challenge of detecting subtle changes in brain volume, we transform images into the Jacobian domain (JD) to enhance both accuracy and robustness in our classification. Using MRI and CT images from the OASIS-3 dataset, our experiments demonstrate the effectiveness of the ELF approach in classifying AD into four stages with an accuracy of 97.19%.
Authors: Fabi Prezja, Leevi Annala, Sampsa Kiiskinen, Suvi Lahtinen, Timo Ojala, Pekka Ruusuvuori, Teijo Kuopio
In routine colorectal cancer management, histologic samples stained with hematoxylin and eosin are commonly used. Nonetheless, their potential for defining objective biomarkers for patient stratification and treatment selection is still being explored. The current gold standard relies on expensive and time-consuming genetic tests. However, recent research highlights the potential of convolutional neural networks (CNNs) in facilitating the extraction of clinically relevant biomarkers from these readily available images. These CNN-based biomarkers can predict patient outcomes comparably to golden standards, with the added advantages of speed, automation, and minimal cost. The predictive potential of CNN-based biomarkers fundamentally relies on the ability of convolutional neural networks (CNNs) to classify diverse tissue types from whole slide microscope images accurately. Consequently, enhancing the accuracy of tissue class decomposition is critical to amplifying the prognostic potential of imaging-based biomarkers. This study introduces a hybrid Deep and ensemble machine learning model that surpassed all preceding solutions for this classification task. Our model achieved 96.74% accuracy on the external test set and 99.89% on the internal test set. Recognizing the potential of these models in advancing the task, we have made them publicly available for further research and development.
Authors: S M Atikur Rahman, Sifat Ibtisum, Ehsan Bazgir, Tumpa Barai
The global need for effective disease diagnosis remains substantial, given the complexities of various disease mechanisms and diverse patient symptoms. To tackle these challenges, researchers, physicians, and patients are turning to machine learning (ML), an artificial intelligence (AI) discipline, to develop solutions. By leveraging sophisticated ML and AI methods, healthcare stakeholders gain enhanced diagnostic and treatment capabilities. However, there is a scarcity of research focused on ML algorithms for enhancing the accuracy and computational efficiency. This research investigates the capacity of machine learning algorithms to improve the transmission of heart rate data in time series healthcare metrics, concentrating particularly on optimizing accuracy and efficiency. By exploring various ML algorithms used in healthcare applications, the review presents the latest trends and approaches in ML-based disease diagnosis (MLBDD). The factors under consideration include the algorithm utilized, the types of diseases targeted, the data types employed, the applications, and the evaluation metrics. This review aims to shed light on the prospects of ML in healthcare, particularly in disease diagnosis. By analyzing the current literature, the study provides insights into state-of-the-art methodologies and their performance metrics.
Authors: Xingchen Zhao, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi, Han-Pang Chiu, Supun Samarasekera
Deep learning-based solutions for semantic segmentation suffer from significant performance degradation when tested on data with different characteristics than what was used during the training. Adapting the models using annotated data from the new domain is not always practical. Unsupervised Domain Adaptation (UDA) approaches are crucial in deploying these models in the actual operating conditions. Recent state-of-the-art (SOTA) UDA methods employ a teacher-student self-training approach, where a teacher model is used to generate pseudo-labels for the new data which in turn guide the training process of the student model. Though this approach has seen a lot of success, it suffers from the issue of noisy pseudo-labels being propagated in the training process. To address this issue, we propose an auxiliary pseudo-label refinement network (PRN) for online refining of the pseudo labels and also localizing the pixels whose predicted labels are likely to be noisy. Being able to improve the quality of pseudo labels and select highly reliable ones, PRN helps self-training of segmentation models to be robust against pseudo label noise propagation during different stages of adaptation. We evaluate our approach on benchmark datasets with three different domain shifts, and our approach consistently performs significantly better than the previous state-of-the-art methods.
Authors: Mohtasim Hadi Rafi, Mohammad Ratul Mahjabin, Md Sabbir Rahman
One of the biggest challenges that the farmers go through is to fight insect pests during agricultural product yields. The problem can be solved easily and avoid economic losses by taking timely preventive measures. This requires identifying insect pests in an easy and effective manner. Most of the insect species have similarities between them. Without proper help from the agriculturist academician it is very challenging for the farmers to identify the crop pests accurately. To address this issue we have done extensive experiments considering different methods to find out the best method among all. This paper presents a detailed overview of the experiments done on mainly a robust dataset named IP102 including transfer learning with finetuning, attention mechanism and custom architecture. Some example from another dataset D0 is also shown to show robustness of our experimented techniques.
Authors: Fahim Ahmed Zaman, Xiaodong Wu, Weiyu Xu, Milan Sonka, Raghuraman Mudumbai
We describe a method for verifying the output of a deep neural network for medical image segmentation that is robust to several classes of random as well as worst-case perturbations i.e. adversarial attacks. This method is based on a general approach recently developed by the authors called ``Trust, but Verify" wherein an auxiliary verification network produces predictions about certain masked features in the input image using the segmentation as an input. A well-designed auxiliary network will produce high-quality predictions when the input segmentations are accurate, but will produce low-quality predictions when the segmentations are incorrect. Checking the predictions of such a network with the original image allows us to detect bad segmentations. However, to ensure the verification method is truly robust, we need a method for checking the quality of the predictions that does not itself rely on a black-box neural network. Indeed, we show that previous methods for segmentation evaluation that do use deep neural regression networks are vulnerable to false negatives i.e. can inaccurately label bad segmentations as good. We describe the design of a verification network that avoids such vulnerability and present results to demonstrate its robustness compared to previous methods.
Authors: Juyoung Yun
In the rapidly advancing domain of deep learning optimization, this paper unveils the StochGradAdam optimizer, a novel adaptation of the well-regarded Adam algorithm. Central to StochGradAdam is its gradient sampling technique. This method not only ensures stable convergence but also leverages the advantages of selective gradient consideration, fostering robust training by potentially mitigating the effects of noisy or outlier data and enhancing the exploration of the loss landscape for more dependable convergence. In both image classification and segmentation tasks, StochGradAdam has demonstrated superior performance compared to the traditional Adam optimizer. By judiciously sampling a subset of gradients at each iteration, the optimizer is optimized for managing intricate models. The paper provides a comprehensive exploration of StochGradAdam's methodology, from its mathematical foundations to bias correction strategies, heralding a promising advancement in deep learning training techniques.
Authors: Zaid Khan, Vijay Kumar BG, Samuel Schulter, Manmohan Chandraker, Yun Fu
Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering strategies. We explore a question decomposition strategy for VQA to overcome this limitation. We probe the ability of recently developed large vision-language models to use human-written decompositions and produce their own decompositions of visual questions, finding they are capable of learning both tasks from demonstrations alone. However, we show that naive application of model-written decompositions can hurt performance. We introduce a model-driven selective decomposition approach for second-guessing predictions and correcting errors, and validate its effectiveness on eight VQA tasks across three domains, showing consistent improvements in accuracy, including improvements of >20% on medical VQA datasets and boosting the zero-shot performance of BLIP-2 above chance on a VQA reformulation of the challenging Winoground task. Project Site: https://zaidkhan.me/decomposition-0shot-vqa/
Authors: Sudarshan Babu, Richard Liu, Avery Zhou, Michael Maire, Greg Shakhnarovich, Rana Hanocka
We introduce HyperFields, a method for generating text-conditioned Neural Radiance Fields (NeRFs) with a single forward pass and (optionally) some fine-tuning. Key to our approach are: (i) a dynamic hypernetwork, which learns a smooth mapping from text token embeddings to the space of NeRFs; (ii) NeRF distillation training, which distills scenes encoded in individual NeRFs into one dynamic hypernetwork. These techniques enable a single network to fit over a hundred unique scenes. We further demonstrate that HyperFields learns a more general map between text and NeRFs, and consequently is capable of predicting novel in-distribution and out-of-distribution scenes -- either zero-shot or with a few finetuning steps. Finetuning HyperFields benefits from accelerated convergence thanks to the learned general map, and is capable of synthesizing novel scenes 5 to 10 times faster than existing neural optimization-based methods. Our ablation experiments show that both the dynamic architecture and NeRF distillation are critical to the expressivity of HyperFields.
Authors: Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau
In this paper, we propose a novel deep learning method based on a new Hybrid ConvNet-Transformer architecture to detect and stage Parkinson's disease (PD) from gait data. We adopt a two-step approach by dividing the problem into two sub-problems. Our Hybrid ConvNet-Transformer model first distinguishes healthy versus parkinsonian patients. If the patient is parkinsonian, a multi-class Hybrid ConvNet-Transformer model determines the Hoehn and Yahr (H&Y) score to assess the PD severity stage. Our hybrid architecture exploits the strengths of both Convolutional Neural Networks (ConvNets) and Transformers to accurately detect PD and determine the severity stage. In particular, we take advantage of ConvNets to capture local patterns and correlations in the data, while we exploit Transformers for handling long-term dependencies in the input signal. We show that our hybrid method achieves superior performance when compared to other state-of-the-art methods, with a PD detection accuracy of 97% and a severity staging accuracy of 87%. Our source code is available at: https://github.com/SafwenNaimi
Authors: Safwen Naimi, Olfa Koubaa, Wassim Bouachir, Guillaume-Alexandre Bilodeau, Gregory Jeddore, Patricia Baines, David Correia, Andre Arsenault
Lichens are symbiotic organisms composed of fungi, algae, and/or cyanobacteria that thrive in a variety of environments. They play important roles in carbon and nitrogen cycling, and contribute directly and indirectly to biodiversity. Ecologists typically monitor lichens by using them as indicators to assess air quality and habitat conditions. In particular, epiphytic lichens, which live on trees, are key markers of air quality and environmental health. A new method of monitoring epiphytic lichens involves using time-lapse cameras to gather images of lichen populations. These cameras are used by ecologists in Newfoundland and Labrador to subsequently analyze and manually segment the images to determine lichen thalli condition and change. These methods are time-consuming and susceptible to observer bias. In this work, we aim to automate the monitoring of lichens over extended periods and to estimate their biomass and condition to facilitate the task of ecologists. To accomplish this, our proposed framework uses semantic segmentation with an effective training approach to automate monitoring and biomass estimation of epiphytic lichens on time-lapse images. We show that our method has the potential to significantly improve the accuracy and efficiency of lichen population monitoring, making it a valuable tool for forest ecologists and environmental scientists to evaluate the impact of climate change on Canada's forests. To the best of our knowledge, this is the first time that such an approach has been used to assist ecologists in monitoring and analyzing epiphytic lichens.
Authors: Taehyeon Kim, Eric Lin, Junu Lee, Christian Lau, Vaikkunth Mugunthan
Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. To address these hurdles, we navigate the uncharted waters of Semi-Supervised Federated Object Detection (SSFOD). We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data. Notably, our method represents the inaugural implementation of SSFOD for clients with 0% labeled non-IID data, a stark contrast to previous studies that maintain some subset of labels at each client. We propose FedSTO, a two-stage strategy encompassing Selective Training followed by Orthogonally enhanced full-parameter training, to effectively address data shift (e.g. weather conditions) between server and clients. Our contributions include selectively refining the backbone of the detector to avert overfitting, orthogonality regularization to boost representation divergence, and local EMA-driven pseudo label assignment to yield high-quality pseudo labels. Extensive validation on prominent autonomous driving datasets (BDD100K, Cityscapes, and SODA10M) attests to the efficacy of our approach, demonstrating state-of-the-art results. Remarkably, FedSTO, using just 20-30% of labels, performs nearly as well as fully-supervised centralized training methods.
Authors: Chau Pham, Truong Vu, Khoi Nguyen
This paper addresses the challenging problem of open-vocabulary object detection (OVOD) where an object detector must identify both seen and unseen classes in test images without labeled examples of the unseen classes in training. A typical approach for OVOD is to use joint text-image embeddings of CLIP to assign box proposals to their closest text label. However, this method has a critical issue: many low-quality boxes, such as over- and under-covered-object boxes, have the same similarity score as high-quality boxes since CLIP is not trained on exact object location information. To address this issue, we propose a novel method, LP-OVOD, that discards low-quality boxes by training a sigmoid linear classifier on pseudo labels retrieved from the top relevant region proposals to the novel text. Experimental results on COCO affirm the superior performance of our approach over the state of the art, achieving $\textbf{40.5}$ in $\text{AP}_{novel}$ using ResNet50 as the backbone and without external datasets or knowing novel classes during training. Our code will be available at https://github.com/VinAIResearch/LP-OVOD.
Authors: Rafael Pires de Lima, Behzad Vahedi, Nick Hughes, Andrew P. Barrett, Walter Meier, Morteza Karimzadeh
Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, models trained with our largest training set have weighted F1 scores all greater than 0.95 for January and July test scenes. Specifically, the median weighted F1 score was 0.98, indicating high performance for both months. By comparison, a competitive baseline U-Net has a weighted average F1 score of ranging from 0.92 to 0.94 (median 0.93) for July, and 0.97 to 0.98 (median 0.97) for January. Multiclass ice type classification is more challenging, and even though our models achieve 2% improvement in weighted F1 average compared to the baseline U-Net, test weighted F1 is generally between 0.6 and 0.80. Our approach can efficiently segment full SAR scenes in one run, is faster than the baseline U-Net, retains spatial resolution and dimension, and is more robust against noise compared to approaches that rely on patch classification.
Authors: Morteza Karimzadeh, Rafael Pires de Lima
Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and ocean currents. Therefore, frequent mapping of sea ice is necessary to ensure safe marine navigation. However, there is a general shortage of expert-labeled data to train deep learning algorithms. Fine-tuning a pre-trained model on SAR imagery is a potential solution. In this paper, we compare the performance of deep learning models trained from scratch using randomly initialized weights against pre-trained models that we fine-tune for this purpose. Our results show that pre-trained models lead to better results, especially on test samples from the melt season.
Authors: Rachana Sathish, Rahul Venkataramani, K S Shriram, Prasad Sudhakar
Promptable foundation models, particularly Segment Anything Model (SAM), have emerged as a promising alternative to the traditional task-specific supervised learning for image segmentation. However, many evaluation studies have found that their performance on medical imaging modalities to be underwhelming compared to conventional deep learning methods. In the world of large pre-trained language and vision-language models, learning prompt from downstream tasks has achieved considerable success in improving performance. In this work, we propose a plug-and-play Prompt Optimization Technique for foundation models like SAM (SAMPOT) that utilizes the downstream segmentation task to optimize the human-provided prompt to obtain improved performance. We demonstrate the utility of SAMPOT on lung segmentation in chest X-ray images and obtain an improvement on a significant number of cases ($\sim75\%$) over human-provided initial prompts. We hope this work will lead to further investigations in the nascent field of automatic visual prompt-tuning.
Authors: Junhong Gou, Bo Zhang, Li Niu, Jianfu Zhang, Jianlou Si, Chen Qian, Liqing Zhang
The virtual try-on task refers to fitting the clothes from one image onto another portrait image. In this paper, we focus on virtual accessory try-on, which fits accessory (e.g., glasses, ties) onto a face or portrait image. Unlike clothing try-on, which relies on human silhouette as guidance, accessory try-on warps the accessory into an appropriate location and shape to generate a plausible composite image. In contrast to previous try-on methods that treat foreground (i.e., accessories) and background (i.e., human faces or bodies) equally, we propose a background-oriented network to utilize the prior knowledge of human bodies and accessories. Specifically, our approach learns the human body priors and hallucinates the target locations of specified foreground keypoints in the background. Then our approach will inject foreground information with accessory priors into the background UNet. Based on the hallucinated target locations, the warping parameters are calculated to warp the foreground. Moreover, this background-oriented network can also easily incorporate auxiliary human face/body semantic segmentation supervision to further boost performance. Experiments conducted on STRAT dataset validate the effectiveness of our proposed method.
Authors: Rafael Pires de Lima, Behzad Vahedi, Morteza Karimzadeh
Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN models still need to undergo scrutiny as higher metrics performance not always translate to adequate outputs. Sea ice type classes are imbalanced, requiring special treatment during training. We evaluate how three different loss functions, some developed for imbalanced class problems, affect the performance of CNN models trained to predict the dominant ice type in Sentinel-1 images. Despite the fact that Dice and Focal loss produce higher metrics, results from cross-entropy seem generally more physically consistent.
Authors: Anand Sharma (MIET, Meerut), A. G. Ramakrishnan (IISc, Bengaluru)
A classifier is developed that defines a joint distribution of global character features, number of sub-units and local sub-unit features to model Hindi online handwritten characters. The classifier uses latent variables to model the structure of sub-units. The classifier uses histograms of points, orientations, and dynamics of orientations (HPOD) features to represent characters at global character level and local sub-unit level and is independent of character stroke order and stroke direction variations. The parameters of the classifier is estimated using maximum likelihood method. Different classifiers and features used in other studies are considered in this study for classification performance comparison with the developed classifier. The classifiers considered are Second Order Statistics (SOS), Sub-space (SS), Fisher Discriminant (FD), Feedforward Neural Network (FFN) and Support Vector Machines (SVM) and the features considered are Spatio Temporal (ST), Discrete Fourier Transform (DFT), Discrete Cosine Transform (SCT), Discrete Wavelet Transform (DWT), Spatial (SP) and Histograms of Oriented Gradients (HOG). Hindi character datasets used for training and testing the developed classifier consist of samples of handwritten characters from 96 different character classes. There are 12832 samples with an average of 133 samples per character class in the training set and 2821 samples with an average of 29 samples per character class in the testing set. The developed classifier has the highest accuracy of 93.5\% on the testing set compared to that of the classifiers trained on different features extracted from the same training set and evaluated on the same testing set considered in this study.
Authors: Zicheng Zhang, Yingjie Zhou, Wei Sun, Xiongkuo Min, Guangtao Zhai
Point clouds are widely used in 3D content representation and have various applications in multimedia. However, compression and simplification processes inevitably result in the loss of quality-aware information under storage and bandwidth constraints. Therefore, there is an increasing need for effective methods to quantify the degree of distortion in point clouds. In this paper, we propose simple baselines for projection-based point cloud quality assessment (PCQA) to tackle this challenge. We use multi-projections obtained via a common cube-like projection process from the point clouds for both full-reference (FR) and no-reference (NR) PCQA tasks. Quality-aware features are extracted with popular vision backbones. The FR quality representation is computed as the similarity between the feature maps of reference and distorted projections while the NR quality representation is obtained by simply squeezing the feature maps of distorted projections with average pooling The corresponding quality representations are regressed into visual quality scores by fully-connected layers. Taking part in the ICIP 2023 PCVQA Challenge, we succeeded in achieving the top spot in four out of the five competition tracks.
Authors: Rupsa Bhattacharjee, Zehra Akkaya, Johanna Luitjens, Pan Su, Yang Yang, Valentina Pedoia, Sharmila Majumdar
In the current study, our purpose is to evaluate the feasibility of applying deep learning (DL) enabled algorithms to quantify bilateral knee biomarkers in healthy controls scanned at 0.55T and compared with 3.0T. The current study assesses the performance of standard in-practice bone, and cartilage segmentation algorithms at 0.55T, both qualitatively and quantitatively, in terms of comparing segmentation performance, areas of improvement, and compartment-wise cartilage thickness values between 0.55T vs. 3.0T. Initial results demonstrate a usable to good technical feasibility of translating existing quantitative deep-learning-based image segmentation techniques, trained on 3.0T, out of 0.55T for knee MRI, in a multi-vendor acquisition environment. Especially in terms of segmenting cartilage compartments, the models perform almost equivalent to 3.0T in terms of Likert ranking. The 0.55T low-field sustainable and easy-to-install MRI, as demonstrated, thus, can be utilized for evaluating knee cartilage thickness and bone segmentations aided by established DL algorithms trained at higher-field strengths out-of-the-box initially. This could be utilized at the far-spread point-of-care locations with a lack of radiologists available to manually segment low-field images, at least till a decent base of low-field data pool is collated. With further fine-tuning with manual labeling of low-field data or utilizing synthesized higher SNR images from low-field images, OA biomarker quantification performance is potentially guaranteed to be further improved.
Authors: Haipeng Xiong, Angela Yao
Regression tasks in computer vision, such as age estimation or counting, are often formulated into classification by quantizing the target space into classes. Yet real-world data is often imbalanced -- the majority of training samples lie in a head range of target values, while a minority of samples span a usually larger tail range. By selecting the class quantization, one can adjust imbalanced regression targets into balanced classification outputs, though there are trade-offs in balancing classification accuracy and quantization error. To improve regression performance over the entire range of data, we propose to construct hierarchical classifiers for solving imbalanced regression tasks. The fine-grained classifiers limit the quantization error while being modulated by the coarse predictions to ensure high accuracy. Standard hierarchical classification approaches, however, when applied to the regression problem, fail to ensure that predicted ranges remain consistent across the hierarchy. As such, we propose a range-preserving distillation process that can effectively learn a single classifier from the set of hierarchical classifiers. Our novel hierarchical classification adjustment (HCA) for imbalanced regression shows superior results on three diverse tasks: age estimation, crowd counting and depth estimation. We will release the source code upon acceptance.
Authors: Zhenwei Luo
Learning single image depth estimation model from monocular video sequence is a very challenging problem. In this paper, we propose a novel training loss which enables us to include more images for supervision during the training process. We propose a simple yet effective model to account the frame to frame pixel motion. We also design a novel network architecture for single image estimation. When combined, our method produces state of the art results for monocular depth estimation on the KITTI dataset in the self-supervised setting.
Authors: Daniel S. Roll, Zeyneb Kurt, Wai Lok Woo
The Kessler syndrome refers to the escalating space debris from frequent space activities, threatening future space exploration. Addressing this issue is vital. Several AI models, including Convolutional Neural Networks (CNN), Kernel Principal Component Analysis (KPCA), and Model-Agnostic Meta-Learning (MAML), have been assessed with various data types. Earlier studies highlighted the combination of the YOLO object detector and a linear Kalman filter for object detection and tracking. Building on this, our project introduces CosmosDSR, a novel methodology combining YOLOv3 with an Unscented Kalman Filter for tracking satellites in sequential images, compared to a linear Kalman filter. Using the SPARK dataset from the University of Luxembourg for training and testing, the YOLOv3 precisely detected and classified all satellite categories (mAP=97.18%, F1=0.95) with few errors (TP=4163, FP=209, FN=237). Both CosmosDSR and the LKF tracked satellites accurately (UKF: MSE=2.83/RMSE=1.66, LKF: MSE=2.84/RMSE=1.66). Despite concerns of class imbalance and the absence of real images, the model shows promise. Future work should address these limitations, increase tracking sample size, and improve metrics. This research suggests the algorithm's potential in detecting and tracking satellites, paving the way for solutions to the Kessler syndrome.
Authors: Yingwen Wu, Tao Li, Xinwen Cheng, Jie Yang, Xiaolin Huang
Detecting out-of-distribution (OOD) samples is essential for ensuring the reliability of deep neural networks (DNNs) in real-world scenarios. While previous research has predominantly investigated the disparity between in-distribution (ID) and OOD data through forward information analysis, the discrepancy in parameter gradients during the backward process of DNNs has received insufficient attention. Existing studies on gradient disparities mainly focus on the utilization of gradient norms, neglecting the wealth of information embedded in gradient directions. To bridge this gap, in this paper, we conduct a comprehensive investigation into leveraging the entirety of gradient information for OOD detection. The primary challenge arises from the high dimensionality of gradients due to the large number of network parameters. To solve this problem, we propose performing linear dimension reduction on the gradient using a designated subspace that comprises principal components. This innovative technique enables us to obtain a low-dimensional representation of the gradient with minimal information loss. Subsequently, by integrating the reduced gradient with various existing detection score functions, our approach demonstrates superior performance across a wide range of detection tasks. For instance, on the ImageNet benchmark, our method achieves an average reduction of 11.15% in the false positive rate at 95% recall (FPR95) compared to the current state-of-the-art approach. The code would be released.
Authors: Long-Huei Chen, Mohana Prasad Sathya Moorthy, Pratyaksh Sharma
The protein-protein interaction (PPI) network provides an overview of the complex biological reactions vital to an organism's metabolism and survival. Even though in the past PPI network were compared across organisms in detail, there has not been large-scale research on how individual PPI networks reflect on the species relationships. In this study we aim to increase our understanding of the tree of life and taxonomy by gleaming information from the PPI networks. We successful created (1) a predictor of network statistics based on known traits of existing species in the phylogeny, and (2) a taxonomic classifier of organism using the known protein network statistics, whether experimentally determined or predicted de novo. With the knowledge of protein interactions at its core, our two models effectively connects two field with widely diverging methodologies - the phylogeny and taxonomy of species.
Authors: Zhenkai Zhang, Krista A. Ehinger, Tom Drummond
This paper introduces two key contributions aimed at improving the speed and quality of images generated through inverse diffusion processes. The first contribution involves reparameterizing the diffusion process in terms of the angle on a quarter-circular arc between the image and noise, specifically setting the conventional $\displaystyle \sqrt{\bar{\alpha}}=\cos(\eta)$. This reparameterization eliminates two singularities and allows for the expression of diffusion evolution as a well-behaved ordinary differential equation (ODE). In turn, this allows higher order ODE solvers such as Runge-Kutta methods to be used effectively. The second contribution is to directly estimate both the image ($\mathbf{x}_0$) and noise ($\mathbf{\epsilon}$) using our network, which enables more stable calculations of the update step in the inverse diffusion steps, as accurate estimation of both the image and noise are crucial at different stages of the process. Together with these changes, our model achieves faster generation, with the ability to converge on high-quality images more quickly, and higher quality of the generated images, as measured by metrics such as Frechet Inception Distance (FID), spatial Frechet Inception Distance (sFID), precision, and recall.
Authors: Liao Pan, Yang Feng, Wu Di, Liu Bo, Zhang Xingle
This paper aims to address critical issues in the field of Multi-Object Tracking (MOT) by proposing an efficient and computationally resource-efficient end-to-end multi-object tracking model, named MO-YOLO. Traditional MOT methods typically involve two separate steps: object detection and object tracking, leading to computational complexity and error propagation issues. Recent research has demonstrated outstanding performance in end-to-end MOT models based on Transformer architectures, but they require substantial hardware support. MO-YOLO combines the strengths of YOLO and RT-DETR models to construct a high-efficiency, lightweight, and resource-efficient end-to-end multi-object tracking network, offering new opportunities in the multi-object tracking domain. On the MOT17 dataset, MOTR\cite{zeng2022motr} requires training with 8 GeForce 2080 Ti GPUs for 4 days to achieve satisfactory results, while MO-YOLO only requires 1 GeForce 2080 Ti GPU and 12 hours of training to achieve comparable performance.
Authors: Mrinal Kanti Dhar, Mou Deb, D. Madhab, Zeyun Yu
Accurate teeth segmentation and orientation are fundamental in modern oral healthcare, enabling precise diagnosis, treatment planning, and dental implant design. In this study, we present a comprehensive approach to teeth segmentation and orientation from panoramic X-ray images, leveraging deep learning techniques. We build our model based on FUSegNet, a popular model originally developed for wound segmentation, and introduce modifications by incorporating grid-based attention gates into the skip connections. We introduce oriented bounding box (OBB) generation through principal component analysis (PCA) for precise tooth orientation estimation. Evaluating our approach on the publicly available DNS dataset, comprising 543 panoramic X-ray images, we achieve the highest Intersection-over-Union (IoU) score of 82.43% and Dice Similarity Coefficient (DSC) score of 90.37% among compared models in teeth instance segmentation. In OBB analysis, we obtain the Rotated IoU (RIoU) score of 82.82%. We also conduct detailed analyses of individual tooth labels and categorical performance, shedding light on strengths and weaknesses. The proposed model's accuracy and versatility offer promising prospects for improving dental diagnoses, treatment planning, and personalized healthcare in the oral domain. Our generated OBB coordinates and codes are available at https://github.com/mrinal054/Instance_teeth_segmentation.
Authors: Fengyuan Shi, Limin Wang
Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant tokens. A key to improving token pruning is using well-trained models as initialization for faster convergence and better performance. However, current base models usually adopt full image training, i.e., using full images as inputs and keeping the whole feature maps through the forward process, which causes inconsistencies with dynamic models that gradually reduce tokens, including calculation pattern, information amount and token selection strategy inconsistencies. Inspired by MAE which performs masking and reconstruction self-supervised task, we devise masked fine-tuning to bridge the gaps between pre-trained base models used for initialization and token pruning based dynamic vision transformers, by masking image patches and predicting the image class label based on left unmasked patches. Extensive experiments on ImageNet demonstrate that base models via masked fine-tuning gain strong occlusion robustness and ability against information loss. With this better initialization, Dynamic ViT achieves higher accuracies, especially under large token pruning ratios (e.g., 81.9% vs. 81.3%, and 62.3% vs. 58.9% for DeiT based Dynamic ViT/0.8 and Dynamic ViT/0.3). Moreover, we apply our method into different token pruning based dynamic vision transformers, different pre-trained models and randomly initialized models to demonstrate the generalization ability.
Authors: Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Brano Kusy, Zi Huang
Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimension mismatch between the teacher and the student networks. Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance. In addition, projectors even improve logit distillation if we add them to the architecture too. Inspired by these surprising findings and the general lack of understanding of the projectors in the knowledge distillation process from existing literature, this paper investigates the implicit role that projectors play but so far have been overlooked. Our empirical study shows that the student with a projector (1) obtains a better trade-off between the training accuracy and the testing accuracy compared to the student without a projector when it has the same feature dimensions as the teacher, (2) better preserves its similarity to the teacher beyond shallow and numeric resemblance, from the view of Centered Kernel Alignment (CKA), and (3) avoids being over-confident as the teacher does at the testing phase. Motivated by the positive effects of projectors, we propose a projector ensemble-based feature distillation method to further improve distillation performance. Despite the simplicity of the proposed strategy, empirical results from the evaluation of classification tasks on benchmark datasets demonstrate the superior classification performance of our method on a broad range of teacher-student pairs and verify from the aspects of CKA and model calibration that the student's features are of improved quality with the projector ensemble design.
Authors: Rui Qin, Ming Sun, Fangyuan Zhang, Xing Wen, Bin Wang
Blind super-resolution (BSR) methods based on high-resolution (HR) reconstruction codebooks have achieved promising results in recent years. However, we find that a codebook based on HR reconstruction may not effectively capture the complex correlations between low-resolution (LR) and HR images. In detail, multiple HR images may produce similar LR versions due to complex blind degradations, causing the HR-dependent only codebooks having limited texture diversity when faced with confusing LR inputs. To alleviate this problem, we propose the Rich Texture-aware Codebook-based Network (RTCNet), which consists of the Degradation-robust Texture Prior Module (DTPM) and the Patch-aware Texture Prior Module (PTPM). DTPM effectively mines the cross-resolution correlation of textures between LR and HR images by exploiting the cross-resolution correspondence of textures. PTPM uses patch-wise semantic pre-training to correct the misperception of texture similarity in the high-level semantic regularization. By taking advantage of this, RTCNet effectively gets rid of the misalignment of confusing textures between HR and LR in the BSR scenarios. Experiments show that RTCNet outperforms state-of-the-art methods on various benchmarks by up to 0.16 ~ 0.46dB.
Authors: Xiao Liang, Tao Shi, Yaoyuan Liang, Te Tao, Shao-Lun Huang
Video grounding aims to localize the target moment in an untrimmed video corresponding to a given sentence query. Existing methods typically select the best prediction from a set of predefined proposals or directly regress the target span in a single-shot manner, resulting in the absence of a systematical prediction refinement process. In this paper, we propose DiffusionVG, a novel framework with diffusion models that formulates video grounding as a conditional generation task, where the target span is generated from Gaussian noise inputs and interatively refined in the reverse diffusion process. During training, DiffusionVG progressively adds noise to the target span with a fixed forward diffusion process and learns to recover the target span in the reverse diffusion process. In inference, DiffusionVG can generate the target span from Gaussian noise inputs by the learned reverse diffusion process conditioned on the video-sentence representations. Our DiffusionVG follows the encoder-decoder architecture, which firstly encodes the video-sentence features and iteratively denoises the predicted spans in its specialized span refining decoder. Without bells and whistles, our DiffusionVG demonstrates competitive or even superior performance compared to existing well-crafted models on mainstream Charades-STA and ActivityNet Captions benchmarks.
Authors: Feng Zhang, Ming Tian, Zhiqiang Li, Bin Xu, Qingbo Lu, Changxin Gao, Nong Sang
Tone mapping aims to convert high dynamic range (HDR) images to low dynamic range (LDR) representations, a critical task in the camera imaging pipeline. In recent years, 3-Dimensional LookUp Table (3D LUT) based methods have gained attention due to their ability to strike a favorable balance between enhancement performance and computational efficiency. However, these methods often fail to deliver satisfactory results in local areas since the look-up table is a global operator for tone mapping, which works based on pixel values and fails to incorporate crucial local information. To this end, this paper aims to address this issue by exploring a novel strategy that integrates global and local operators by utilizing closed-form Laplacian pyramid decomposition and reconstruction. Specifically, we employ image-adaptive 3D LUTs to manipulate the tone in the low-frequency image by leveraging the specific characteristics of the frequency information. Furthermore, we utilize local Laplacian filters to refine the edge details in the high-frequency components in an adaptive manner. Local Laplacian filters are widely used to preserve edge details in photographs, but their conventional usage involves manual tuning and fixed implementation within camera imaging pipelines or photo editing tools. We propose to learn parameter value maps progressively for local Laplacian filters from annotated data using a lightweight network. Our model achieves simultaneous global tone manipulation and local edge detail preservation in an end-to-end manner. Extensive experimental results on two benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art methods.
Authors: Roy Hirsch, Regev Cohen, Mathilde Caron, Tomer Golany, Daniel Freedman, Ehud Rivlin
A key element of computer-assisted surgery systems is phase recognition of surgical videos. Existing phase recognition algorithms require frame-wise annotation of a large number of videos, which is time and money consuming. In this work we join concepts of graph segmentation with self-supervised learning to derive a random-walk solution for per-frame phase prediction. Furthermore, we utilize within our method two forms of weak supervision: sparse timestamps or few-shot learning. The proposed algorithm enjoys low complexity and can operate in lowdata regimes. We validate our method by running experiments with the public Cholec80 dataset of laparoscopic cholecystectomy videos, demonstrating promising performance in multiple setups.
Authors: Junxiao Xue, Jie Wang, Xuecheng Wu, Liangyu Fu
Video emotion recognition is an important branch of affective computing, and its solutions can be applied in different fields such as human-computer interaction (HCI) and intelligent medical treatment. Although the number of papers published in the field of emotion recognition is increasing, there are few comprehensive literature reviews covering related research on video emotion recognition. Therefore, this paper selects articles published from 2015 to 2023 to systematize the existing trends in video emotion recognition in related studies. In this paper, we first talk about two typical emotion models, then we talk about databases that are frequently utilized for video emotion recognition, including unimodal databases and multimodal databases. Next, we look at and classify the specific structure and performance of modern unimodal and multimodal video emotion recognition methods, talk about the benefits and drawbacks of each, and then we compare them in detail in the tables. Further, we sum up the primary difficulties right now looked by video emotion recognition undertakings and point out probably the most encouraging future headings, such as establishing an open benchmark database and better multimodal fusion strategys. The essential objective of this paper is to assist scholarly and modern scientists with keeping up to date with the most recent advances and new improvements in this speedy, high-influence field of video emotion recognition.
Authors: Christoph Angermann, Johannes Bereiter-Payr, Kerstin Stock, Markus Haltmeier, Gerald Degenhart
Medical image processing has been highlighted as an area where deep learning-based models have the greatest potential. However, in the medical field in particular, problems of data availability and privacy are hampering research progress and thus rapid implementation in clinical routine. The generation of synthetic data not only ensures privacy, but also allows to \textit{draw} new patients with specific characteristics, enabling the development of data-driven models on a much larger scale. This work demonstrates that three-dimensional generative adversarial networks (GANs) can be efficiently trained to generate high-resolution medical volumes with finely detailed voxel-based architectures. In addition, GAN inversion is successfully implemented for the three-dimensional setting and used for extensive research on model interpretability and applications such as image morphing, attribute editing and style mixing. The results are comprehensively validated on a database of three-dimensional HR-pQCT instances representing the bone micro-architecture of the distal radius.
Authors: Jiachen Li, Xiaojin Gong
This work aims to adapt large-scale pre-trained vision-language models, such as contrastive language-image pretraining (CLIP), to enhance the performance of object reidentification (Re-ID) across various supervision settings. Although prompt learning has enabled a recent work named CLIP-ReID to achieve promising performance, the underlying mechanisms and the necessity of prompt learning remain unclear due to the absence of semantic labels in ReID tasks. In this work, we first analyze the role prompt learning in CLIP-ReID and identify its limitations. Based on our investigations, we propose a simple yet effective approach to adapt CLIP for supervised object Re-ID. Our approach directly fine-tunes the image encoder of CLIP using a prototypical contrastive learning (PCL) loss, eliminating the need for prompt learning. Experimental results on both person and vehicle Re-ID datasets demonstrate the competitiveness of our method compared to CLIP-ReID. Furthermore, we extend our PCL-based CLIP fine-tuning approach to unsupervised scenarios, where we achieve state-of-the art performance.
Authors: Chamuditha Jayanga Galappaththige, Gayal Kuruppu, Muhammad Haris Khan
Diabetic retinopathy (DR). is caused by long-standing diabetes and is among the fifth leading cause for visual impairments. The process of early diagnosis and treatments could be helpful in curing the disease, however, the detection procedure is rather challenging and mostly tedious. Therefore, automated diabetic retinopathy classification using deep learning techniques has gained interest in the medical imaging community. Akin to several other real-world applications of deep learning, the typical assumption of i.i.d data is also violated in DR classification that relies on deep learning. Therefore, developing DR classification methods robust to unseen distributions is of great value. In this paper, we study the problem of generalizing a model to unseen distributions or domains (a.k.a domain generalization) in DR classification. To this end, we propose a simple and effective domain generalization (DG) approach that achieves self-distillation in vision transformers (ViT) via a novel prediction softening mechanism. This prediction softening is an adaptive convex combination one-hot labels with the model's own knowledge. We perform extensive experiments on challenging open-source DR classification datasets under both multi-source and single-source DG settings with three different ViT backbones to establish the efficacy and applicability of our approach against competing methods. For the first time, we report the performance of several state-of-the-art DG methods on open-source DR classification datasets after conducting thorough experiments. Finally, our method is also capable of delivering improved calibration performance than other methods, showing its suitability for safety-critical applications, including healthcare. We hope that our contributions would investigate more DG research across the medical imaging community.
Authors: Dongkyun Kim, Mingi Kwon, Youngjung Uh
When the training dataset comprises a 1:1 proportion of dogs to cats, a generative model that produces 1:1 dogs and cats better resembles the training species distribution than another model with 3:1 dogs and cats. Can we capture this phenomenon using existing metrics? Unfortunately, we cannot, because these metrics do not provide any interpretability beyond "diversity". In this context, we propose a new evaluation protocol that measures the divergence of a set of generated images from the training set regarding the distribution of attribute strengths as follows. Single-attribute Divergence (SaD) measures the divergence regarding PDFs of a single attribute. Paired-attribute Divergence (PaD) measures the divergence regarding joint PDFs of a pair of attributes. They provide which attributes the models struggle. For measuring the attribute strengths of an image, we propose Heterogeneous CLIPScore (HCS) which measures the cosine similarity between image and text vectors with heterogeneous initial points. With SaD and PaD, we reveal the following about existing generative models. ProjectedGAN generates implausible attribute relationships such as a baby with a beard even though it has competitive scores of existing metrics. Diffusion models struggle to capture diverse colors in the datasets. The larger sampling timesteps of latent diffusion model generate the more minor objects including earrings and necklaces. Stable Diffusion v1.5 better captures the attributes than v2.1. Our metrics lay a foundation for explainable evaluations of generative models.
Authors: Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit
We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds. We design a contrastive loss between features of Lidar scans captured in the same scene. Several such approaches have been proposed in the literature from PointConstrast, which uses a contrast at the level of points, to the state-of-the-art TARL, which uses a contrast at the level of segments, roughly corresponding to objects. While the former enjoys a great simplicity of implementation, it is surpassed by the latter, which however requires a costly pre-processing. In BEVContrast, we define our contrast at the level of 2D cells in the Bird's Eye View plane. Resulting cell-level representations offer a good trade-off between the point-level representations exploited in PointContrast and segment-level representations exploited in TARL: we retain the simplicity of PointContrast (cell representations are cheap to compute) while surpassing the performance of TARL in downstream semantic segmentation.
Authors: Mengxue Qu, Yu Wu, Wu Liu, Xiaodan Liang, Jingkuan Song, Yao Zhao, Yunchao Wei
Intention-oriented object detection aims to detect desired objects based on specific intentions or requirements. For instance, when we desire to "lie down and rest", we instinctively seek out a suitable option such as a "bed" or a "sofa" that can fulfill our needs. Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for intention objects. These limitations make it challenging to handle intentions in open environments effectively. To facilitate this research, we construct a comprehensive dataset called Reasoning Intention-Oriented Objects (RIO). In particular, RIO is specifically designed to incorporate diverse real-world scenarios and a wide range of object categories. It offers the following key features: 1) intention descriptions in RIO are represented as natural sentences rather than a mere word or verb phrase, making them more practical and meaningful; 2) the intention descriptions are contextually relevant to the scene, enabling a broader range of potential functionalities associated with the objects; 3) the dataset comprises a total of 40,214 images and 130,585 intention-object pairs. With the proposed RIO, we evaluate the ability of some existing models to reason intention-oriented objects in open environments.
Authors: Zhewei Huang, Ailin Huang, Xiaotao Hu, Chen Hu, Jun Xu, Shuchang Zhou
The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR). However, facing the challenge of the additional temporal dimension and scale inconsistency, most existing STVSR methods are complex and inflexible in dynamically modeling different motion amplitudes. In this work, we find that choosing an appropriate processing scale achieves remarkable benefits in flow-based feature propagation. We propose a novel Scale-Adaptive Feature Aggregation (SAFA) network that adaptively selects sub-networks with different processing scales for individual samples. Experiments on four public STVSR benchmarks demonstrate that SAFA achieves state-of-the-art performance. Our SAFA network outperforms recent state-of-the-art methods such as TMNet and VideoINR by an average improvement of over 0.5dB on PSNR, while requiring less than half the number of parameters and only 1/3 computational costs.
Authors: Shuai Yang, Zhifei Chen, Pengguang Chen, Xi Fang, Shu Liu, Yingcong Chen
Defect inspection is paramount within the closed-loop manufacturing system. However, existing datasets for defect inspection often lack precision and semantic granularity required for practical applications. In this paper, we introduce the Defect Spectrum, a comprehensive benchmark that offers precise, semantic-abundant, and large-scale annotations for a wide range of industrial defects. Building on four key industrial benchmarks, our dataset refines existing annotations and introduces rich semantic details, distinguishing multiple defect types within a single image. Furthermore, we introduce Defect-Gen, a two-stage diffusion-based generator designed to create high-quality and diverse defective images, even when working with limited datasets. The synthetic images generated by Defect-Gen significantly enhance the efficacy of defect inspection models. Overall, The Defect Spectrum dataset demonstrates its potential in defect inspection research, offering a solid platform for testing and refining advanced models.
Authors: Tim J. Schoonbeek, Tim Houben, Hans Onvlee, Peter H.N. de With, Fons van der Sommen
Although action recognition for procedural tasks has received notable attention, it has a fundamental flaw in that no measure of success for actions is provided. This limits the applicability of such systems especially within the industrial domain, since the outcome of procedural actions is often significantly more important than the mere execution. To address this limitation, we define the novel task of procedure step recognition (PSR), focusing on recognizing the correct completion and order of procedural steps. Alongside the new task, we also present the multi-modal IndustReal dataset. Unlike currently available datasets, IndustReal contains procedural errors (such as omissions) as well as execution errors. A significant part of these errors are exclusively present in the validation and test sets, making IndustReal suitable to evaluate robustness of algorithms to new, unseen mistakes. Additionally, to encourage reproducibility and allow for scalable approaches trained on synthetic data, the 3D models of all parts are publicly available. Annotations and benchmark performance are provided for action recognition and assembly state detection, as well as the new PSR task. IndustReal, along with the code and model weights, is available at: https://github.com/TimSchoonbeek/IndustReal .
Authors: Xiaoyu Liu, Jiaxin Yuan, Bang An, Yuancheng Xu, Yifan Yang, Furong Huang
Representation learning assumes that real-world data is generated by a few semantically meaningful generative factors (i.e., sources of variation) and aims to discover them in the latent space. These factors are expected to be causally disentangled, meaning that distinct factors are encoded into separate latent variables, and changes in one factor will not affect the values of the others. Compared to statistical independence, causal disentanglement allows more controllable data generation, improved robustness, and better generalization. However, most existing work assumes unconfoundedness in the discovery process, that there are no common causes to the generative factors and thus obtain only statistical independence. In this paper, we recognize the importance of modeling confounders in discovering causal generative factors. Unfortunately, such factors are not identifiable without proper inductive bias. We fill the gap by introducing a framework entitled Confounded-Disentanglement (C-Disentanglement), the first framework that explicitly introduces the inductive bias of confounder via labels from domain expertise. In addition, we accordingly propose an approach to sufficiently identify the causally disentangled factors under any inductive bias of the confounder. We conduct extensive experiments on both synthetic and real-world datasets. Our method demonstrates competitive results compared to various SOTA baselines in obtaining causally disentangled features and downstream tasks under domain shifts.
Authors: Seyedmorteza Sadat, Jakob Buhmann, Derek Bradely, Otmar Hilliges, Romann M. Weber
While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high classifier-free guidance scale for optimal image quality or when trained on small datasets. We attribute this problem to the role of the conditioning signal in inference and offer an improved sampling strategy for diffusion models that can increase generation diversity, especially at high guidance scales, with minimal loss of sample quality. Our sampling strategy anneals the conditioning signal by adding scheduled, monotonically decreasing Gaussian noise to the conditioning vector during inference to balance diversity and condition alignment. Our Condition-Annealed Diffusion Sampler (CADS) can be used with any pretrained model and sampling algorithm, and we show that it boosts the diversity of diffusion models in various conditional generation tasks. Further, using an existing pretrained diffusion model, CADS achieves a new state-of-the-art FID of 1.70 and 2.31 for class-conditional ImageNet generation at 256$\times$256 and 512$\times$512 respectively.
Authors: Anas Al-lahham, Obaidah Theeb, Khaled Elalem, Tariq A. Alshawi, Saleh A. Alshebeili
Ahead-of-time forecasting of the output power of power plants is essential for the stability of the electricity grid and ensuring uninterrupted service. However, forecasting renewable energy sources is difficult due to the chaotic behavior of natural energy sources. This paper presents a new approach to estimate short-term solar irradiance from sky images. The~proposed algorithm extracts features from sky images and use learning-based techniques to estimate the solar irradiance. The~performance of proposed machine learning (ML) algorithm is evaluated using two publicly available datasets of sky images. The~datasets contain over 350,000 images for an interval of 16 years, from 2004 to 2020, with the corresponding global horizontal irradiance (GHI) of each image as the ground truth. Compared to the state-of-the-art computationally heavy algorithms proposed in the literature, our approach achieves competitive results with much less computational complexity for both nowcasting and forecasting up to 4 h ahead of time.
Authors: Haobo Jiang, Mathieu Salzmann, Zheng Dang, Jin Xie, Jian Yang
In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which progressively refines the pose of the source point cloud to obtain a precise alignment with the model point cloud. Training our framework involves two operations: An SE(3) diffusion process and an SE(3) reverse process. The SE(3) diffusion process gradually perturbs the optimal rigid transformation of a pair of point clouds by continuously injecting noise (perturbation transformation). By contrast, the SE(3) reverse process focuses on learning a denoising network that refines the noisy transformation step-by-step, bringing it closer to the optimal transformation for accurate pose estimation. Unlike standard diffusion models used in linear Euclidean spaces, our diffusion model operates on the SE(3) manifold. This requires exploiting the linear Lie algebra $\mathfrak{se}(3)$ associated with SE(3) to constrain the transformation transitions during the diffusion and reverse processes. Additionally, to effectively train our denoising network, we derive a registration-specific variational lower bound as the optimization objective for model learning. Furthermore, we show that our denoising network can be constructed with a surrogate registration model, making our approach applicable to different deep registration networks. Extensive experiments demonstrate that our diffusion registration framework presents outstanding pose estimation performance on the real-world TUD-L, LINEMOD, and Occluded-LINEMOD datasets.
Authors: Chang Liu, Liguo Zhou, Yanliang Huang, Alois Knoll
Vehicle perception systems strive to achieve comprehensive and rapid visual interpretation of their surroundings for improved safety and navigation. We introduce YOLO-BEV, an efficient framework that harnesses a unique surrounding cameras setup to generate a 2D bird's-eye view of the vehicular environment. By strategically positioning eight cameras, each at a 45-degree interval, our system captures and integrates imagery into a coherent 3x3 grid format, leaving the center blank, providing an enriched spatial representation that facilitates efficient processing. In our approach, we employ YOLO's detection mechanism, favoring its inherent advantages of swift response and compact model structure. Instead of leveraging the conventional YOLO detection head, we augment it with a custom-designed detection head, translating the panoramically captured data into a unified bird's-eye view map of ego car. Preliminary results validate the feasibility of YOLO-BEV in real-time vehicular perception tasks. With its streamlined architecture and potential for rapid deployment due to minimized parameters, YOLO-BEV poses as a promising tool that may reshape future perspectives in autonomous driving systems.
Authors: Kevin Flanagan, Dima Damen, Michael Wray
The onset of long-form egocentric datasets such as Ego4D and EPIC-Kitchens presents a new challenge for the task of Temporal Sentence Grounding (TSG). Compared to traditional benchmarks on which this task is evaluated, these datasets offer finer-grained sentences to ground in notably longer videos. In this paper, we develop an approach for learning to ground sentences in these datasets using only narrations and their corresponding rough narration timestamps. We propose to artificially merge clips to train for temporal grounding in a contrastive manner using text-conditioning attention. This Clip Merging (CliMer) approach is shown to be effective when compared with a high performing TSG method -- e.g. mean R@1 improves from 3.9 to 5.7 on Ego4D and from 10.7 to 13.0 on EPIC-Kitchens. Code and data splits available from: https://github.com/keflanagan/CliMer
Authors: Erik Scheurer, Jenny Schmalfuss, Alexander Lis, Andrés Bruhn
Adversarial patches undermine the reliability of optical flow predictions when placed in arbitrary scene locations. Therefore, they pose a realistic threat to real-world motion detection and its downstream applications. Potential remedies are defense strategies that detect and remove adversarial patches, but their influence on the underlying motion prediction has not been investigated. In this paper, we thoroughly examine the currently available detect-and-remove defenses ILP and LGS for a wide selection of state-of-the-art optical flow methods, and illuminate their side effects on the quality and robustness of the final flow predictions. In particular, we implement defense-aware attacks to investigate whether current defenses are able to withstand attacks that take the defense mechanism into account. Our experiments yield two surprising results: Detect-and-remove defenses do not only lower the optical flow quality on benign scenes, in doing so, they also harm the robustness under patch attacks for all tested optical flow methods except FlowNetC. As currently employed detect-and-remove defenses fail to deliver the promised adversarial robustness for optical flow, they evoke a false sense of security. The code is available at https://github.com/cv-stuttgart/DetectionDefenses.
Authors: Jialv Zou, Xinggang Wang, Jiahao Guo, Wenyu Liu, Qian Zhang, Chang Huang
As the size of circuit designs continues to grow rapidly, artificial intelligence technologies are being extensively used in Electronic Design Automation (EDA) to assist with circuit design. Placement and routing are the most time-consuming parts of the physical design process, and how to quickly evaluate the placement has become a hot research topic. Prior works either transformed circuit designs into images using hand-crafted methods and then used Convolutional Neural Networks (CNN) to extract features, which are limited by the quality of the hand-crafted methods and could not achieve end-to-end training, or treated the circuit design as a graph structure and used Graph Neural Networks (GNN) to extract features, which require time-consuming preprocessing. In our work, we propose a novel perspective for circuit design by treating circuit components as point clouds and using Transformer-based point cloud perception methods to extract features from the circuit. This approach enables direct feature extraction from raw data without any preprocessing, allows for end-to-end training, and results in high performance. Experimental results show that our method achieves state-of-the-art performance in congestion prediction tasks on both the CircuitNet and ISPD2015 datasets, as well as in design rule check (DRC) violation prediction tasks on the CircuitNet dataset. Our method establishes a bridge between the relatively mature point cloud perception methods and the fast-developing EDA algorithms, enabling us to leverage more collective intelligence to solve this task. To facilitate the research of open EDA design, source codes and pre-trained models are released at https://github.com/hustvl/circuitformer.
Authors: You-Ming Chang, Chen Yeh, Wei-Chen Chiu, Ning Yu
Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically learn classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, being inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel approach using VLMs (e.g. InstructBLIP) and prompt tuning techniques to improve the deepfake detection accuracy over unseen data. We formulate deepfake detection as a visual question answering problem, and tune soft prompts for InstructBLIP to answer the real/fake information of a query image. We conduct full-spectrum experiments on datasets from 3 held-in and 13 held-out generative models, covering modern text-to-image generation, image editing and image attacks. Results demonstrate that (1) the deepfake detection accuracy can be significantly and consistently improved (from 58.8% to 91.31%, in average accuracy over unseen data) using pretrained vision-language models with prompt tuning; (2) our superior performance is at less cost of trainable parameters, resulting in an effective and efficient solution for deepfake detection. Code and models can be found at https://github.com/nctu-eva-lab/AntifakePrompt.
Authors: Facundo Manuel Quiroga, Franco Ronchetti, Laura Lanzarini, Cesar Eestrebou
Human action recognition from skeletal data is an important and active area of research in which the state of the art has not yet achieved near-perfect accuracy on many well-known datasets. In this paper, we introduce the Distribution of Action Movements Descriptor, a novel action descriptor based on the distribution of the directions of the motions of the joints between frames, over the set of all possible motions in the dataset. The descriptor is computed as a normalized histogram over a set of representative directions of the joints, which are in turn obtained via clustering. While the descriptor is global in the sense that it represents the overall distribution of movement directions of an action, it is able to partially retain its temporal structure by applying a windowing scheme.
The descriptor, together with a standard classifier, outperforms several state-of-the-art techniques on many well-known datasets.
Authors: Franco Ronchetti, Facundo Manuel Quiroga, César Estrebou, Laura Lanzarini
Automatic sign language recognition is an important topic within the areas of human-computer interaction and machine learning. On the one hand, it poses a complex challenge that requires the intervention of various knowledge areas, such as video processing, image processing, intelligent systems and linguistics. On the other hand, robust recognition of sign language could assist in the translation process and the integration of hearing-impaired people.
This paper offers two main contributions: first, the creation of a database of handshapes for the Argentinian Sign Language (LSA), which is a topic that has barely been discussed so far. Secondly, a technique for image processing, descriptor extraction and subsequent handshape classification using a supervised adaptation of self-organizing maps that is called ProbSom. This technique is compared to others in the state of the art, such as Support Vector Machines (SVM), Random Forests, and Neural Networks.
The database that was built contains 800 images with 16 LSA handshapes, and is a first step towards building a comprehensive database of Argentinian signs. The ProbSom-based neural classifier, using the proposed descriptor, achieved an accuracy rate above 90%.
Authors: Franco Ronchetti, Facundo Manuel Quiroga, César Estrebou, Laura Lanzarini, Alejandro Rosete
Automatic sign language recognition is a research area that encompasses human-computer interaction, computer vision and machine learning. Robust automatic recognition of sign language could assist in the translation process and the integration of hearing-impaired people, as well as the teaching of sign language to the hearing population. Sign languages differ significantly in different countries and even regions, and their syntax and semantics are different as well from those of written languages. While the techniques for automatic sign language recognition are mostly the same for different languages, training a recognition system for a new language requires having an entire dataset for that language. This paper presents a dataset of 64 signs from the Argentinian Sign Language (LSA). The dataset, called LSA64, contains 3200 videos of 64 different LSA signs recorded by 10 subjects, and is a first step towards building a comprehensive research-level dataset of Argentinian signs, specifically tailored to sign language recognition or other machine learning tasks. The subjects that performed the signs wore colored gloves to ease the hand tracking and segmentation steps, allowing experiments on the dataset to focus specifically on the recognition of signs. We also present a pre-processed version of the dataset, from which we computed statistics of movement, position and handshape of the signs.
Authors: Kira Maag, Asja Fischer
State-of-the-art deep neural networks have been shown to be extremely powerful in a variety of perceptual tasks like semantic segmentation. However, these networks are vulnerable to adversarial perturbations of the input which are imperceptible for humans but lead to incorrect predictions. Treating image segmentation as a sum of pixel-wise classifications, adversarial attacks developed for classification models were shown to be applicable to segmentation models as well. In this work, we present simple uncertainty-based weighting schemes for the loss functions of such attacks that (i) put higher weights on pixel classifications which can more easily perturbed and (ii) zero-out the pixel-wise losses corresponding to those pixels that are already confidently misclassified. The weighting schemes can be easily integrated into the loss function of a range of well-known adversarial attackers with minimal additional computational overhead, but lead to significant improved perturbation performance, as we demonstrate in our empirical analysis on several datasets and models.
Authors: Franco Ronchetti, Facundo Manuel Quiroga, César Estrebou, Laura Lanzarini, Alejandro Rosete
Automatic sign language recognition (SLR) is an important topic within the areas of human-computer interaction and machine learning. On the one hand, it poses a complex challenge that requires the intervention of various knowledge areas, such as video processing, image processing, intelligent systems and linguistics. On the other hand, robust recognition of sign language could assist in the translation process and the integration of hearing-impaired people, as well as the teaching of sign language for the hearing population.
SLR systems usually employ Hidden Markov Models, Dynamic Time Warping or similar models to recognize signs. Such techniques exploit the sequential ordering of frames to reduce the number of hypothesis. This paper presents a general probabilistic model for sign classification that combines sub-classifiers based on different types of features such as position, movement and handshape. The model employs a bag-of-words approach in all classification steps, to explore the hypothesis that ordering is not essential for recognition. The proposed model achieved an accuracy rate of 97% on an Argentinian Sign Language dataset containing 64 classes of signs and 3200 samples, providing some evidence that indeed recognition without ordering is possible.
Authors: Yifei Peng, Yu Jin, Zhexu Luo, Yao-Xiang Ding, Wang-Zhou Dai, Zhong Ren, Kun Zhou
Despite the great success of neural visual generative models in recent years, integrating them with strong symbolic knowledge reasoning systems remains a challenging task. The main challenges are two-fold: one is symbol assignment, i.e. bonding latent factors of neural visual generators with meaningful symbols from knowledge reasoning systems. Another is rule learning, i.e. learning new rules, which govern the generative process of the data, to augment the knowledge reasoning systems. To deal with these symbol grounding problems, we propose a neural-symbolic learning approach, Abductive Visual Generation (AbdGen), for integrating logic programming systems with neural visual generative models based on the abductive learning framework. To achieve reliable and efficient symbol assignment, the quantized abduction method is introduced for generating abduction proposals by the nearest-neighbor lookups within semantic codebooks. To achieve precise rule learning, the contrastive meta-abduction method is proposed to eliminate wrong rules with positive cases and avoid less-informative rules with negative cases simultaneously. Experimental results on various benchmark datasets show that compared to the baselines, AbdGen requires significantly fewer instance-level labeling information for symbol assignment. Furthermore, our approach can effectively learn underlying logical generative rules from data, which is out of the capability of existing approaches.
Authors: Zhiquan Tan, Kaipeng Zheng, Weiran Huang
Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function. By utilizing optimal transport, our proposed method consistently outperforms established state-of-the-art methods. Notably, we observed a substantial improvement of a certain percentage in accuracy compared to the current state-of-the-art method, FreeMatch. OTMatch achieves 3.18%, 3.46%, and 1.28% error rate reduction over FreeMatch on CIFAR-10 with 1 label per class, STL-10 with 4 labels per class, and ImageNet with 100 labels per class, respectively. This demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting.
Authors: Daniel Kienzle, Julian Lorenz, Katja Ludwig, Rainer Lienhart
We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels. No expensive 3D labels are needed. Thus, instead of using 3D labels, our model is trained with easy-to-annotate 2D labels along with the physical knowledge of the object's motion. Given this information, the model can infer the latent third dimension, even though it has never seen this information during training. Our method is evaluated on both synthetic and real-world datasets, and we are able to achieve a mean distance error of just 6 cm in our experiments on real data. The results indicate the method's potential as a step towards learning 3D object location estimation, where collecting 3D data for training is not feasible.
Authors: Yang Qin, Yuan Sun, Dezhong Peng, Joey Tianyi Zhou, Xi Peng, Peng Hu
Recently, image-text matching has attracted more and more attention from academia and industry, which is fundamental to understanding the latent correspondence across visual and textual modalities. However, most existing methods implicitly assume the training pairs are well-aligned while ignoring the ubiquitous annotation noise, a.k.a noisy correspondence (NC), thereby inevitably leading to a performance drop. Although some methods attempt to address such noise, they still face two challenging problems: excessive memorizing/overfitting and unreliable correction for NC, especially under high noise. To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods. Specifically, ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision, leading to theoretically and experimentally demonstrated robustness against NC. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences, thereby alleviating error accumulation and achieving accurate and stable corrections. We carry out extensive experiments on three image-text benchmarks, i.e., Flickr30K, MS-COCO, and CC152K, to verify the superior robustness of our CRCL against synthetic and real-world noisy correspondences.
Authors: Salman Khan, Izzeddin Teeti, Andrew Bradley, Mohamed Elhoseiny, Fabio Cuzzolin
Interpretation and understanding of video presents a challenging computer vision task in numerous fields - e.g. autonomous driving and sports analytics. Existing approaches to interpreting the actions taking place within a video clip are based upon Temporal Action Localisation (TAL), which typically identifies short-term actions. The emerging field of Complex Activity Detection (CompAD) extends this analysis to long-term activities, with a deeper understanding obtained by modelling the internal structure of a complex activity taking place within the video. We address the CompAD problem using a hybrid graph neural network which combines attention applied to a graph encoding the local (short-term) dynamic scene with a temporal graph modelling the overall long-duration activity. Our approach is as follows: i) Firstly, we propose a novel feature extraction technique which, for each video snippet, generates spatiotemporal `tubes' for the active elements (`agents') in the (local) scene by detecting individual objects, tracking them and then extracting 3D features from all the agent tubes as well as the overall scene. ii) Next, we construct a local scene graph where each node (representing either an agent tube or the scene) is connected to all other nodes. Attention is then applied to this graph to obtain an overall representation of the local dynamic scene. iii) Finally, all local scene graph representations are interconnected via a temporal graph, to estimate the complex activity class together with its start and end time. The proposed framework outperforms all previous state-of-the-art methods on all three datasets including ActivityNet-1.3, Thumos-14, and ROAD.
Authors: Gilles Puy, Spyros Gidaris, Alexandre Boulch, Oriane Siméoni, Corentin Sautier, Patrick Pérez, Andrei Bursuc, Renaud Marlet
Self-supervised image networks can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervision. However, self-supervised 3D networks on lidar data do not perform as well for now. A few methods therefore propose to distill high-quality self-supervised 2D features into 3D networks. The most recent ones doing so on autonomous driving data show promising results. Yet, a performance gap persists between these distilled features and fully-supervised ones. In this work, we revisit 2D-to-3D distillation. First, we propose, for semantic segmentation, a simple approach that leads to a significant improvement compared to prior 3D distillation methods. Second, we show that distillation in high capacity 3D networks is key to reach high quality 3D features. This actually allows us to significantly close the gap between unsupervised distilled 3D features and fully-supervised ones. Last, we show that our high-quality distilled representations can also be used for open-vocabulary segmentation and background/foreground discovery.
Authors: Shrisha Bharadwaj, Yufeng Zheng, Otmar Hilliges, Michael J. Black, Victoria Fernandez-Abrevaya
Our goal is to efficiently learn personalized animatable 3D head avatars from videos that are geometrically accurate, realistic, relightable, and compatible with current rendering systems. While 3D meshes enable efficient processing and are highly portable, they lack realism in terms of shape and appearance. Neural representations, on the other hand, are realistic but lack compatibility and are slow to train and render. Our key insight is that it is possible to efficiently learn high-fidelity 3D mesh representations via differentiable rendering by exploiting highly-optimized methods from traditional computer graphics and approximating some of the components with neural networks. To that end, we introduce \moniker, a technique that enables the creation of animatable and relightable mesh avatars from a single monocular video. First, we learn a canonical geometry using a mesh representation, enabling efficient differentiable rasterization and straightforward animation via learned blendshapes and linear blend skinning weights. Second, we follow physically-based rendering and factor observed colors into intrinsic albedo, roughness, and a neural representation of the illumination, allowing the learned avatars to be relit in novel scenes. Since our input videos are captured on a single device with a narrow field of view, modeling the surrounding environment light is non-trivial. Based on the split-sum approximation for modeling specular reflections, we address this by approximating the pre-filtered environment map with a multi-layer perceptron (MLP) modulated by the surface roughness, eliminating the need to explicitly model the light. We demonstrate that our mesh-based avatar formulation, combined with learned deformation, material, and lighting MLPs, produces avatars with high-quality geometry and appearance, while also being efficient to train and render compared to existing approaches.
Authors: Feng Wang, Zilong Chen, Guokang Wang, Yafei Song, Huaping Liu
In this paper, we propose the Masked Space-Time Hash encoding (MSTH), a novel method for efficiently reconstructing dynamic 3D scenes from multi-view or monocular videos. Based on the observation that dynamic scenes often contain substantial static areas that result in redundancy in storage and computations, MSTH represents a dynamic scene as a weighted combination of a 3D hash encoding and a 4D hash encoding. The weights for the two components are represented by a learnable mask which is guided by an uncertainty-based objective to reflect the spatial and temporal importance of each 3D position. With this design, our method can reduce the hash collision rate by avoiding redundant queries and modifications on static areas, making it feasible to represent a large number of space-time voxels by hash tables with small size.Besides, without the requirements to fit the large numbers of temporally redundant features independently, our method is easier to optimize and converge rapidly with only twenty minutes of training for a 300-frame dynamic scene.As a result, MSTH obtains consistently better results than previous methods with only 20 minutes of training time and 130 MB of memory storage. Code is available at https://github.com/masked-spacetime-hashing/msth
Authors: Laura Cabello, Emanuele Bugliarello, Stephanie Brandl, Desmond Elliott
Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind those prejudicial biases to ensure that model performance does not result in discriminatory behaviour toward certain groups or populations. In this work, we define gender bias as our case study. We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models. We investigate the connection, if any, between the two learning stages, and evaluate how bias amplification reflects on model performance. Overall, we find that bias amplification in pretraining and after fine-tuning are independent. We then examine the effect of continued pretraining on gender-neutral data, finding that this reduces group disparities, i.e., promotes fairness, on VQAv2 and retrieval tasks without significantly compromising task performance.
Authors: Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans
Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary's knowledge and current literature lacks a cohesive organization centered around the threat model. To systematize knowledge in this area, we propose a taxonomy over the threat space spanning the axes of feedback granularity, the access of interactive queries, and the quality and quantity of the auxiliary data available to the attacker. Our new taxonomy provides three key insights. 1) Despite extensive literature, numerous under-explored threat spaces exist, which cannot be trivially solved by adapting techniques from well-explored settings. We demonstrate this by establishing a new state-of-the-art in the less-studied setting of access to top-k confidence scores by adapting techniques from well-explored settings of accessing the complete confidence vector, but show how it still falls short of the more restrictive setting that only obtains the prediction label, highlighting the need for more research. 2) Identification the threat model of different attacks uncovers stronger baselines that challenge prior state-of-the-art claims. We demonstrate this by enhancing an initially weaker baseline (under interactive query access) via surrogate models, effectively overturning claims in the respective paper. 3) Our taxonomy reveals interactions between attacker knowledge that connect well to related areas, such as model inversion and extraction attacks. We discuss how advances in other areas can enable potentially stronger black-box attacks. Finally, we emphasize the need for a more realistic assessment of attack success by factoring in local attack runtime. This approach reveals the potential for certain attacks to achieve notably higher success rates and the need to evaluate attacks in diverse and harder settings, highlighting the need for better selection criteria.
Authors: Oliver Turnbull, George Cevora
Adversarial examples resulting from instability of current computer vision models are an extremely important topic due to their potential to compromise any application. In this paper we demonstrate that instability is inevitable due to a) symmetries (translational invariance) of the data, b) the categorical nature of the classification task, and c) the fundamental discrepancy of classifying images as objects themselves. The issue is further exacerbated by non-exhaustive labelling of the training data. Therefore we conclude that instability is a necessary result of how the problem of computer vision is currently formulated. While the problem cannot be eliminated, through the analysis of the causes, we have arrived at ways how it can be partially alleviated. These include i) increasing the resolution of images, ii) providing contextual information for the image, iii) exhaustive labelling of training data, and iv) preventing attackers from frequent access to the computer vision system.
Authors: Qingsong Xu, Chaojun Ouyang, Tianhai Jiang, Xuanmei Fan, Duoxiang Cheng
Automatic recognition and segmentation methods now become the essential requirement in identifying co-seismic landslides, which are fundamental for disaster assessment and mitigation in large-scale earthquakes. This approach used to be carried out through pixel-based or object-oriented methods. However, due to the massive amount of remote sensing data, variations in different earthquake scenarios, and the efficiency requirement for post-earthquake rescue, these methods are difficult to develop into an accurate, rapid, comprehensive, and general (cross-scene) solution for co-seismic landslide recognition. This paper develops a robust model, Dense Feature Pyramid with Encoder-decoder Network (DFPENet), to understand and fuse the multi-scale features of objects in remote sensing images. The proposed method achieves a competitive segmentation accuracy on the public ISPRS 2D Semantic. Furthermore, a comprehensive and widely-used scheme is proposed for co-seismic landslide recognition, which integrates image features extracted from the DFPENet model, geologic features, temporal resolution, landslide spatial analysis, and transfer learning, while only RGB images are used. To corroborate its feasibility and applicability, the proposed scheme is applied to two earthquake-triggered landslides in Jiuzhaigou (China) and Hokkaido (Japan), using available pre- and post-earthquake remote sensing images.
Authors: Risheng Liu, Zhu Liu, Pan Mu, Xin Fan, Zhongxuan Luo
In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate image/feature propagation. There is a lack of unified consideration to construct propagative modules, provide theoretical analysis tools, and design effective learning mechanisms. To mitigate the above issues, this paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC for short) principles with strong generalization for diverse optimization models. Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i.e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations. We design two control mechanisms that provide the non-trivial theoretical guarantees for both fully- and partially-defined optimization formulations. Under the support of theoretical guarantees, we can introduce diverse architecture augmentation strategies such as normalization and search to ensure stable propagation with convergence and seamlessly integrate the suitable modules into the propagation respectively. Extensive experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC. The codes are available at https://github.com/LiuZhu-CV/GDC-OptimizationLearning
Authors: Morgan B. Talbot, Rushikesh Zawar, Rohil Badkundri, Mengmi Zhang, Gabriel Kreiman
Our brains extract durable, generalizable knowledge from transient experiences of the world. Artificial neural networks come nowhere close: when tasked with learning to classify objects by training on non-repeating video frames in temporal order (online stream learning), models that learn well from shuffled datasets catastrophically forget old knowledge upon learning new stimuli. We propose a new continual learning algorithm, Compositional Replay Using Memory Blocks (CRUMB), which mitigates forgetting by replaying feature maps reconstructed by recombining generic parts. CRUMB concatenates trainable and re-usable "memory block" vectors to compositionally reconstruct feature map tensors in convolutional neural networks, like crumbs forming a loaf of bread. CRUMB stores the indices of memory blocks used to reconstruct new stimuli, enabling replay of specific memories during later tasks. This reconstruction mechanism also primes the neural network to minimize catastrophic forgetting by forcing it to attend to information about object shapes more than information about image textures, and stabilizes the network during stream learning by providing a shared feature-level basis for all training examples. These properties allow CRUMB to outperform an otherwise identical algorithm that stores and replays raw images while occupying only 3.6% as much memory. We stress-tested CRUMB alongside 13 competing methods on 7 challenging datasets. To address the limited number of existing online stream learning datasets, we introduce 2 new benchmarks by adapting existing datasets for stream learning. With about 4% as much memory and 30% as much runtime, CRUMB mitigates catastrophic forgetting more effectively than the prior state-of-the-art. Our code is available on GitHub at https://github.com/MorganBDT/crumb.
Authors: Lu Yang, Qing Song, Xueshi Xin, Wenhe Jia, Zhiwei Liu
This is a very short technical report, which introduces the solution of the Team BUPT-CASIA for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021.
Face parsing has recently attracted increasing interest due to its numerous application potentials. Generally speaking, it has a lot in common with human parsing, such as task setting, data characteristics, number of categories and so on. Therefore, this work applies state-of-the-art human parsing method to face parsing task to explore the similarities and differences between them. Our submission achieves 86.84% score and wins the 2nd place in the challenge.
Authors: Lingbo Liu, Mengmeng Liu, Guanbin Li, Ziyi Wu, Junfan Lin, Liang Lin
Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem, which can help greatly reduce the number of the required traffic monitoring sensors for cost savings. In this work, we notice that traffic flow has a high correlation with road network, which was either completely ignored or simply treated as an external factor in previous works. To facilitate this problem, we propose a novel Road-Aware Traffic Flow Magnifier (RATFM) that explicitly exploits the prior knowledge of road networks to fully learn the road-aware spatial distribution of fine-grained traffic flow. Specifically, a multi-directional 1D convolutional layer is first introduced to extract the semantic feature of the road network. Subsequently, we incorporate the road network feature and coarse-grained flow feature to regularize the short-range spatial distribution modeling of road-relative traffic flow. Furthermore, we take the road network feature as a query to capture the long-range spatial distribution of traffic flow with a transformer architecture. Benefiting from the road-aware inference mechanism, our method can generate high-quality fine-grained traffic flow maps. Extensive experiments on three real-world datasets show that the proposed RATFM outperforms state-of-the-art models under various scenarios. Our code and datasets are released at {\url{https://github.com/luimoli/RATFM}}.
Authors: James R. Wootton, Marcel Pfaffhauser
Though some years remain before quantum computation can fully outperform conventional computation, it already provides resources that can be used for exploratory purposes in various fields. This includes certain tasks for procedural generation in computer games, music and art. The so-called `Quantum Blur' method represents the first step on this journey, providing a simple proof-of-principle example of how quantum software can be useful in these areas today. Here we analyse the `Quantum Blur' method and compare it to conventional blur effects. This investigation was guided by discussions with the most prominent user of the method, to determine which features were found most useful. In particular we determine how these features depend on the quantum phenomena of superposition and entanglement.
Authors: Lin Zhang, Li Shen, Liang Ding, Dacheng Tao, Ling-Yu Duan
Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. Data heterogeneity is one of the main challenges in FL, which results in slow convergence and degraded performance. Most existing approaches only tackle the heterogeneity challenge by restricting the local model update in client, ignoring the performance drop caused by direct global model aggregation. Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation. Concretely, FedFTG explores the input space of local models through a generator, and uses it to transfer the knowledge from local models to the global model. Besides, we propose a hard sample mining scheme to achieve effective knowledge distillation throughout the training. In addition, we develop customized label sampling and class-level ensemble to derive maximum utilization of knowledge, which implicitly mitigates the distribution discrepancy across clients. Extensive experiments show that our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
Authors: Hongbin Xu, Weitao Chen, Yang Liu, Zhipeng Zhou, Haihong Xiao, Baigui Sun, Xuansong Xie, Wenxiong Kang
Significant progress has been witnessed in learning-based Multi-view Stereo (MVS) under supervised and unsupervised settings. To combine their respective merits in accuracy and completeness, meantime reducing the demand for expensive labeled data, this paper explores the problem of learning-based MVS in a semi-supervised setting that only a tiny part of the MVS data is attached with dense depth ground truth. However, due to huge variation of scenarios and flexible settings in views, it may break the basic assumption in classic semi-supervised learning, that unlabeled data and labeled data share the same label space and data distribution, named as semi-supervised distribution-gap ambiguity in the MVS problem. To handle these issues, we propose a novel semi-supervised distribution-augmented MVS framework, namely SDA-MVS. For the simple case that the basic assumption works in MVS data, consistency regularization encourages the model predictions to be consistent between original sample and randomly augmented sample. For further troublesome case that the basic assumption is conflicted in MVS data, we propose a novel style consistency loss to alleviate the negative effect caused by the distribution gap. The visual style of unlabeled sample is transferred to labeled sample to shrink the gap, and the model prediction of generated sample is further supervised with the label in original labeled sample. The experimental results in semi-supervised settings of multiple MVS datasets show the superior performance of the proposed method. With the same settings in backbone network, our proposed SDA-MVS outperforms its fully-supervised and unsupervised baselines.
Authors: Siddharth Saravanan, Aditya Challa, Sravan Danda
State-of-the-art methods for semantic segmentation of images involve computationally intensive neural network architectures. Most of these methods are not adaptable to high-resolution image segmentation due to memory and other computational issues. Typical approaches in literature involve design of neural network architectures that can fuse global information from low-resolution images and local information from the high-resolution counterparts. However, architectures designed for processing high resolution images are unnecessarily complex and involve a lot of hyper parameters that can be difficult to tune. Also, most of these architectures require ground truth annotations of the high resolution images to train, which can be hard to obtain. In this article, we develop a robust pipeline based on mathematical morphological (MM) operators that can seamlessly extend any existing semantic segmentation algorithm to high resolution images. Our method does not require the ground truth annotations of the high resolution images. It is based on efficiently utilizing information from the low-resolution counterparts, and gradient information on the high-resolution images. We obtain high quality seeds from the inferred labels on low-resolution images using traditional morphological operators and propagate seed labels using a random walker to refine the semantic labels at the boundaries. We show that the semantic segmentation results obtained by our method beat the existing state-of-the-art algorithms on high-resolution images. We empirically prove the robustness of our approach to the hyper parameters used in our pipeline. Further, we characterize some necessary conditions under which our pipeline is applicable and provide an in-depth analysis of the proposed approach.
Authors: Fengyuan Shi, Ruopeng Gao, Weilin Huang, Limin Wang
Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention operation with quadratic time complexity. To address this issue, we present a new multimodal transformer architecture, coined as Dynamic Mutilmodal DETR (Dynamic MDETR), by decoupling the whole grounding process into encoding and decoding phases. The key observation is that there exists high spatial redundancy in images. Thus, we devise a new dynamic multimodal transformer decoder by exploiting this sparsity prior to speed up the visual grounding process. Specifically, our dynamic decoder is composed of a 2D adaptive sampling module and a text guided decoding module. The sampling module aims to select these informative patches by predicting the offsets with respect to a reference point, while the decoding module works for extracting the grounded object information by performing cross attention between image features and text features. These two modules are stacked alternatively to gradually bridge the modality gap and iteratively refine the reference point of grounded object, eventually realizing the objective of visual grounding. Extensive experiments on five benchmarks demonstrate that our proposed Dynamic MDETR achieves competitive trade-offs between computation and accuracy. Notably, using only 9% feature points in the decoder, we can reduce ~44% GFLOPs of the multimodal transformer, but still get higher accuracy than the encoder-only counterpart. In addition, to verify its generalization ability and scale up our Dynamic MDETR, we build the first one-stage CLIP empowered visual grounding framework, and achieve the state-of-the-art performance on these benchmarks.
Authors: Di Huang, Sida Peng, Tong He, Honghui Yang, Xiaowei Zhou, Wanli Ouyang
We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance cues and render realistic images, we train a point-cloud encoder within a devised point-based neural renderer by comparing the rendered images with real images on massive RGB-D data. The learned point-cloud encoder can be easily integrated into various downstream tasks, including not only high-level tasks like 3D detection and segmentation, but low-level tasks like 3D reconstruction and image synthesis. Extensive experiments on various tasks demonstrate the superiority of our approach compared to existing pre-training methods.
Authors: Salma Haidar, José Oramas
With their combined spectral depth and geometric resolution, hyperspectral remote sensing images embed a wealth of complex, non-linear information that challenges traditional computer vision techniques. Yet, deep learning methods known for their representation learning capabilities prove more suitable for handling such complexities. Unlike applications that focus on single-label, pixel-level classification methods for hyperspectral remote sensing images, we propose a multi-label, patch-level classification method based on a two-component deep-learning network. We use patches of reduced spatial dimension and a complete spectral depth extracted from the remote sensing images. Additionally, we investigate three training schemes for our network: Iterative, Joint, and Cascade. Experiments suggest that the Joint scheme is the best-performing scheme; however, its application requires an expensive search for the best weight combination of the loss constituents. The Iterative scheme enables the sharing of features between the two parts of the network at the early stages of training. It performs better on complex data with multi-labels. Further experiments showed that methods designed with different architectures performed well when trained on patches extracted and labeled according to our sampling method.
Authors: Chengmin Gao, Bin Li
When perceiving the world from multiple viewpoints, humans have the ability to reason about the complete objects in a compositional manner even when an object is completely occluded from certain viewpoints. Meanwhile, humans are able to imagine novel views after observing multiple viewpoints. Recent remarkable advances in multi-view object-centric learning still leaves some unresolved problems: 1) The shapes of partially or completely occluded objects can not be well reconstructed. 2) The novel viewpoint prediction depends on expensive viewpoint annotations rather than implicit rules in view representations. In this paper, we introduce a time-conditioned generative model for videos. To reconstruct the complete shape of an object accurately, we enhance the disentanglement between the latent representations of objects and views, where the latent representations of time-conditioned views are jointly inferred with a Transformer and then are input to a sequential extension of Slot Attention to learn object-centric representations. In addition, Gaussian processes are employed as priors of view latent variables for video generation and novel-view prediction without viewpoint annotations. Experiments on multiple datasets demonstrate that the proposed model can make object-centric video decomposition, reconstruct the complete shapes of occluded objects, and make novel-view predictions.
Authors: Jerome Quenum, Iryna Zenyuk, Daniela Ushizima
Lithium metal battery (LMB) has the potential to be the next-generation battery system because of its high theoretical energy density. However, defects known as dendrites are formed by heterogeneous lithium (Li) plating, which hinders the development and utilization of LMBs. Non-destructive techniques to observe the dendrite morphology often use X-ray computed tomography (XCT) to provide cross-sectional views. To retrieve three-dimensional structures inside a battery, image segmentation becomes essential to quantitatively analyze XCT images. This work proposes a new semantic segmentation approach using a transformer-based neural network called TransforCNN that is capable of segmenting out dendrites from XCT data. In addition, we compare the performance of the proposed TransforCNN with three other algorithms, such as U-Net, Y-Net, and E-Net, consisting of an Ensemble Network model for XCT analysis. Our results show the advantages of using TransforCNN when evaluating over-segmentation metrics, such as mean Intersection over Union (mIoU) and mean Dice Similarity Coefficient (mDSC) as well as through several qualitatively comparative visualizations.
Authors: Sifan Song, Jinfeng Wang, Zilong Wang, Shaopeng Wang, Jionglong Su, Xiaowei Ding, Kang Dang
Accurate fovea localization is essential for analyzing retinal diseases to prevent irreversible vision loss. While current deep learning-based methods outperform traditional ones, they still face challenges such as the lack of local anatomical landmarks around the fovea, the inability to robustly handle diseased retinal images, and the variations in image conditions. In this paper, we propose a novel transformer-based architecture called DualStreamFoveaNet (DSFN) for multi-cue fusion. This architecture explicitly incorporates long-range connections and global features using retina and vessel distributions for robust fovea localization. We introduce a spatial attention mechanism in the dual-stream encoder to extract and fuse self-learned anatomical information, focusing more on features distributed along blood vessels and significantly reducing computational costs by decreasing token numbers. Our extensive experiments show that the proposed architecture achieves state-of-the-art performance on two public datasets and one large-scale private dataset. Furthermore, we demonstrate that the DSFN is more robust on both normal and diseased retina images and has better generalization capacity in cross-dataset experiments.
Authors: Yun-Yun Tsai, Chengzhi Mao, Junfeng Yang
Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting. While visual prompts offer a lightweight method of input-space adaptation for large-scale vision models, they rely on a high-dimensional additive vector and labeled data. This leads to overfitting when adapting models in a self-supervised test-time setting without labels. We introduce convolutional visual prompts (CVP) for label-free test-time adaptation for robust visual perception. The structured nature of CVP demands fewer trainable parameters, less than 1\% compared to standard visual prompts, combating overfitting. Extensive experiments and analysis on a wide variety of OOD visual perception tasks show that our approach is effective, improving robustness by up to 5.87% over several large-scale models.
Authors: Austin Stone, Ted Xiao, Yao Lu, Keerthana Gopalakrishnan, Kuang-Huei Lee, Quan Vuong, Paul Wohlhart, Sean Kirmani, Brianna Zitkovich, Fei Xia, Chelsea Finn, Karol Hausman
For robots to follow instructions from people, they must be able to connect the rich semantic information in human vocabulary, e.g. "can you get me the pink stuffed whale?" to their sensory observations and actions. This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information. We would like a robot's policy to be able to perceive and pick up the pink stuffed whale, even if it has never seen any data interacting with a stuffed whale before. Fortunately, static data on the internet has vast semantic information, and this information is captured in pre-trained vision-language models. In this paper, we study whether we can interface robot policies with these pre-trained models, with the aim of allowing robots to complete instructions involving object categories that the robot has never seen first-hand. We develop a simple approach, which we call Manipulation of Open-World Objects (MOO), which leverages a pre-trained vision-language model to extract object-identifying information from the language command and image, and conditions the robot policy on the current image, the instruction, and the extracted object information. In a variety of experiments on a real mobile manipulator, we find that MOO generalizes zero-shot to a wide range of novel object categories and environments. In addition, we show how MOO generalizes to other, non-language-based input modalities to specify the object of interest such as finger pointing, and how it can be further extended to enable open-world navigation and manipulation. The project's website and evaluation videos can be found at https://robot-moo.github.io/
Authors: Yulei Qiu, Jihong Zhu, Cosimo Della Santina, Michael Gienger, Jens Kober
Deformable Object Manipulation (DOM) is an important field of research as it contributes to practical tasks such as automatic cloth handling, cable routing, surgical operation, etc. Perception is considered one of the major challenges in DOM due to the complex dynamics and high degree of freedom of deformable objects. In this paper, we develop a novel image-processing algorithm based on Gabor filters to extract useful features from cloth, and based on this, devise a strategy for cloth flattening tasks. We also evaluate the overall framework experimentally and compare it with three human operators. The results show that our algorithm can determine the direction of wrinkles on the cloth accurately in simulation as well as in real robot experiments. Furthermore, our dewrinkling strategy compares favorably to baseline methods. The experiment video is available on https://sites.google.com/view/robotic-fabric-flattening/home
Authors: Karim Slimani, Brahim Tamadazte, Catherine Achard
This paper introduces a new method for 3D point cloud registration based on deep learning. The architecture is composed of three distinct blocs: (i) an encoder composed of a convolutional graph-based descriptor that encodes the immediate neighbourhood of each point and an attention mechanism that encodes the variations of the surface normals. Such descriptors are refined by highlighting attention between the points of the same set and then between the points of the two sets. (ii) a matching process that estimates a matrix of correspondences using the Sinkhorn algorithm. (iii) Finally, the rigid transformation between the two point clouds is calculated by RANSAC using the Kc best scores from the correspondence matrix. We conduct experiments on the ModelNet40 dataset, and our proposed architecture shows very promising results, outperforming state-of-the-art methods in most of the simulated configurations, including partial overlap and data augmentation with Gaussian noise.
Authors: Hannah Schieber, Fabian Deuser, Bernhard Egger, Norbert Oswald, Daniel Roth
Novel view synthesis using neural radiance fields (NeRF) is the state-of-the-art technique for generating high-quality images from novel viewpoints. Existing methods require a priori knowledge about extrinsic and intrinsic camera parameters. This limits their applicability to synthetic scenes, or real-world scenarios with the necessity of a preprocessing step. Current research on the joint optimization of camera parameters and NeRF focuses on refining noisy extrinsic camera parameters and often relies on the preprocessing of intrinsic camera parameters. Further approaches are limited to cover only one single camera intrinsic. To address these limitations, we propose a novel end-to-end trainable approach called NeRFtrinsic Four. We utilize Gaussian Fourier features to estimate extrinsic camera parameters and dynamically predict varying intrinsic camera parameters through the supervision of the projection error. Our approach outperforms existing joint optimization methods on LLFF and BLEFF. In addition to these existing datasets, we introduce a new dataset called iFF with varying intrinsic camera parameters. NeRFtrinsic Four is a step forward in joint optimization NeRF-based view synthesis and enables more realistic and flexible rendering in real-world scenarios with varying camera parameters.
Authors: Ananta R. Bhattarai, Matthias Nießner, Artem Sevastopolsky
Recent progress in NeRF-based GANs has introduced a number of approaches for high-resolution and high-fidelity generative modeling of human heads with a possibility for novel view rendering. At the same time, one must solve an inverse problem to be able to re-render or modify an existing image or video. Despite the success of universal optimization-based methods for 2D GAN inversion, those applied to 3D GANs may fail to extrapolate the result onto the novel view, whereas optimization-based 3D GAN inversion methods are time-consuming and can require at least several minutes per image. Fast encoder-based techniques, such as those developed for StyleGAN, may also be less appealing due to the lack of identity preservation. Our work introduces a fast technique that bridges the gap between the two approaches by directly utilizing the tri-plane representation presented for the EG3D generative model. In particular, we build upon a feed-forward convolutional encoder for the latent code and extend it with a fully-convolutional predictor of tri-plane numerical offsets. The renderings are similar in quality to the ones produced by optimization-based techniques and outperform the ones by encoder-based methods. As we empirically prove, this is a consequence of directly operating in the tri-plane space, not in the GAN parameter space, while making use of an encoder-based trainable approach. Finally, we demonstrate significantly more correct embedding of a face image in 3D than for all the baselines, further strengthened by a probably symmetric prior enabled during training.
Authors: Shizhen Chang, Pedram Ghamisi
In recent years, advanced research has focused on the direct learning and analysis of remote sensing images using natural language processing (NLP) techniques. The ability to accurately describe changes occurring in multi-temporal remote sensing images is becoming increasingly important for geospatial understanding and land planning. Unlike natural image change captioning tasks, remote sensing change captioning aims to capture the most significant changes, irrespective of various influential factors such as illumination, seasonal effects, and complex land covers. In this study, we highlight the significance of accurately describing changes in remote sensing images and present a comparison of the change captioning task for natural and synthetic images and remote sensing images. To address the challenge of generating accurate captions, we propose an attentive changes-to-captions network, called Chg2Cap for short, for bi-temporal remote sensing images. The network comprises three main components: 1) a Siamese CNN-based feature extractor to collect high-level representations for each image pair; 2) an attentive decoder that includes a hierarchical self-attention block to locate change-related features and a residual block to generate the image embedding; and 3) a transformer-based caption generator to decode the relationship between the image embedding and the word embedding into a description. The proposed Chg2Cap network is evaluated on two representative remote sensing datasets, and a comprehensive experimental analysis is provided. The code and pre-trained models will be available online at https://github.com/ShizhenChang/Chg2Cap.
Authors: Madeline Chantry Schiappa, Michael Cogswell, Ajay Divakaran, Yogesh Singh Rawat
In recent years large visual-language (V+L) models have achieved great success in various downstream tasks. However, it is not well studied whether these models have a conceptual grasp of the visual content. In this work we focus on conceptual understanding of these large V+L models.To facilitate this study, we propose novel benchmarking datasets for probing three different aspects of content understanding, 1) relations, 2) composition and 3) context. Our probes are grounded in cognitive science and help determine if a V+L model can, for example, determine if ``snow garnished with a man'' is implausible, or if it can identify beach furniture by knowing it is located on a beach. We experimented with five different state-of-the-art V+L models and observe that these models mostly fail to demonstrate a conceptual understanding. This study reveals several interesting insights such as cross-attention helps learning conceptual understanding, and that CNNs are better with texture and patterns, while Transformers are better at color and shape. We further utilize some of these insights and propose a baseline for improving performance by a simple finetuning technique that rewards the three conceptual understanding measures with promising initial results. We believe that the proposed benchmarks will help the community assess and improve the conceptual understanding capabilities of large V+L models.
Authors: Jiatao Gu, Qingzhe Gao, Shuangfei Zhai, Baoquan Chen, Lingjie Liu, Josh Susskind
Diffusion models have recently become the de-facto approach for generative modeling in the 2D domain. However, extending diffusion models to 3D is challenging due to the difficulties in acquiring 3D ground truth data for training. On the other hand, 3D GANs that integrate implicit 3D representations into GANs have shown remarkable 3D-aware generation when trained only on single-view image datasets. However, 3D GANs do not provide straightforward ways to precisely control image synthesis. To address these challenges, We present Control3Diff, a 3D diffusion model that combines the strengths of diffusion models and 3D GANs for versatile, controllable 3D-aware image synthesis for single-view datasets. Control3Diff explicitly models the underlying latent distribution (optionally conditioned on external inputs), thus enabling direct control during the diffusion process. Moreover, our approach is general and applicable to any type of controlling input, allowing us to train it with the same diffusion objective without any auxiliary supervision. We validate the efficacy of Control3Diff on standard image generation benchmarks, including FFHQ, AFHQ, and ShapeNet, using various conditioning inputs such as images, sketches, and text prompts. Please see the project website (\url{https://jiataogu.me/control3diff}) for video comparisons.
Authors: Zisheng Chen, Hongbin Xu, Weitao Chen, Zhipeng Zhou, Haihong Xiao, Baigui Sun, Xuansong Xie, Wenxiong Kang
Semantic segmentation of point clouds usually requires exhausting efforts of human annotations, hence it attracts wide attention to the challenging topic of learning from unlabeled or weaker forms of annotations. In this paper, we take the first attempt for fully unsupervised semantic segmentation of point clouds, which aims to delineate semantically meaningful objects without any form of annotations. Previous works of unsupervised pipeline on 2D images fails in this task of point clouds, due to: 1) Clustering Ambiguity caused by limited magnitude of data and imbalanced class distribution; 2) Irregularity Ambiguity caused by the irregular sparsity of point cloud. Therefore, we propose a novel framework, PointDC, which is comprised of two steps that handle the aforementioned problems respectively: Cross-Modal Distillation (CMD) and Super-Voxel Clustering (SVC). In the first stage of CMD, multi-view visual features are back-projected to the 3D space and aggregated to a unified point feature to distill the training of the point representation. In the second stage of SVC, the point features are aggregated to super-voxels and then fed to the iterative clustering process for excavating semantic classes. PointDC yields a significant improvement over the prior state-of-the-art unsupervised methods, on both the ScanNet-v2 (+18.4 mIoU) and S3DIS (+11.5 mIoU) semantic segmentation benchmarks.
Authors: Chen Ziwen, Kaushik Patnaik, Shuangfei Zhai, Alvin Wan, Zhile Ren, Alex Schwing, Alex Colburn, Li Fuxin
Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling strategy in convolutional deep networks treats all areas equally. Hence, small objects are represented in very few spatial locations, leading to worse results in tasks such as segmentation. Intuitively, retaining more pixels representing small objects during downsampling helps to preserve important information. To achieve this, we propose AutoFocusFormer (AFF), a local-attention transformer image recognition backbone, which performs adaptive downsampling by learning to retain the most important pixels for the task. Since adaptive downsampling generates a set of pixels irregularly distributed on the image plane, we abandon the classic grid structure. Instead, we develop a novel point-based local attention block, facilitated by a balanced clustering module and a learnable neighborhood merging module, which yields representations for our point-based versions of state-of-the-art segmentation heads. Experiments show that our AutoFocusFormer (AFF) improves significantly over baseline models of similar sizes.
Authors: Yanchen Wang, Yunlong Xu, Feng Vankee Lin, Ehsan Adeli
Computerized cognitive training (CCT) is a scalable, well-tolerated intervention that has promise for slowing cognitive decline. Outcomes from CCT are limited by a lack of effective engagement, which is decreased by factors such as mental fatigue, particularly in older adults at risk for dementia. There is a need for scalable, automated measures that can monitor mental fatigue during CCT. Here, we develop and validate a novel Recurrent Video Transformer (RVT) method for monitoring real-time mental fatigue in older adults with mild cognitive impairment from video-recorded facial gestures during CCT. The RVT model achieved the highest balanced accuracy(78%) and precision (0.82) compared to the prior state-of-the-art models for binary and multi-class classification of mental fatigue and was additionally validated via significant association (p=0.023) with CCT reaction time. By leveraging dynamic temporal information, the RVT model demonstrates the potential to accurately measure real-time mental fatigue, laying the foundation for future personalized CCT that increase effective engagement.
Authors: Wei Fang, Zhaofei Yu, Zhaokun Zhou, Ding Chen, Yanqi Chen, Zhengyu Ma, Timothée Masquelier, Yonghong Tian
Vanilla spiking neurons in Spiking Neural Networks (SNNs) use charge-fire-reset neuronal dynamics, which can only be simulated serially and can hardly learn long-time dependencies. We find that when removing reset, the neuronal dynamics can be reformulated in a non-iterative form and parallelized. By rewriting neuronal dynamics without reset to a general formulation, we propose the Parallel Spiking Neuron (PSN), which generates hidden states that are independent of their predecessors, resulting in parallelizable neuronal dynamics and extremely high simulation speed. The weights of inputs in the PSN are fully connected, which maximizes the utilization of temporal information. To avoid the use of future inputs for step-by-step inference, the weights of the PSN can be masked, resulting in the masked PSN. By sharing weights across time-steps based on the masked PSN, the sliding PSN is proposed to handle sequences of varying lengths. We evaluate the PSN family on simulation speed and temporal/static data classification, and the results show the overwhelming advantage of the PSN family in efficiency and accuracy. To the best of our knowledge, this is the first study about parallelizing spiking neurons and can be a cornerstone for the spiking deep learning research. Our codes are available at \url{https://github.com/fangwei123456/Parallel-Spiking-Neuron}.
Authors: Ding Li, Yongqiang Tang, Zhizhong Zhang, Wensheng Zhang
Self-supervised skeleton-based action recognition enjoys a rapid growth along with the development of contrastive learning. The existing methods rely on imposing invariance to augmentations of 3D skeleton within a single data stream, which merely leverages the easy positive pairs and limits the ability to explore the complicated movement patterns. In this paper, we advocate that the defect of single-stream contrast and the lack of necessary feature transformation are responsible for easy positives, and therefore propose a Cross-Stream Contrastive Learning framework for skeleton-based action Representation learning (CSCLR). Specifically, the proposed CSCLR not only utilizes intra-stream contrast pairs, but introduces inter-stream contrast pairs as hard samples to formulate a better representation learning. Besides, to further exploit the potential of positive pairs and increase the robustness of self-supervised representation learning, we propose a Positive Feature Transformation (PFT) strategy which adopts feature-level manipulation to increase the variance of positive pairs. To validate the effectiveness of our method, we conduct extensive experiments on three benchmark datasets NTU-RGB+D 60, NTU-RGB+D 120 and PKU-MMD. Experimental results show that our proposed CSCLR exceeds the state-of-the-art methods on a diverse range of evaluation protocols.
Authors: Ning Ding, Kazuya Takeda, Wenhui Jin, Yingjiu Bei, Keisuke Fujii
The application of visual tracking to the performance analysis of sports players in dynamic competitions is vital for effective coaching. In doubles matches, coordinated positioning is crucial for maintaining control of the court and minimizing opponents' scoring opportunities. The analysis of such teamwork plays a vital role in understanding the dynamics of the game. However, previous studies have primarily focused on analyzing and assessing singles players without considering occlusion in broadcast videos. These studies have relied on discrete representations, which involve the analysis and representation of specific actions (e.g., strokes) or events that occur during the game while overlooking the meaningful spatial distribution. In this work, we present the first annotated drone dataset from top and back views in badminton doubles and propose a framework to estimate the control area probability map, which can be used to evaluate teamwork performance. We present an efficient framework of deep neural networks that enables the calculation of full probability surfaces. This framework utilizes the embedding of a Gaussian mixture map of players' positions and employs graph convolution on their poses. In the experiment, we verify our approach by comparing various baselines and discovering the correlations between the score and control area. Additionally, we propose a practical application for assessing optimal positioning to provide instructions during a game. Our approach offers both visual and quantitative evaluations of players' movements, thereby providing valuable insights into doubles teamwork. The dataset and related project code is available at https://github.com/Ning-D/Drone_BD_ControlArea
Authors: Aanisha Bhattacharya, Yaman K Singla, Balaji Krishnamurthy, Rajiv Ratn Shah, Changyou Chen
Multimedia content, such as advertisements and story videos, exhibit a rich blend of creativity and multiple modalities. They incorporate elements like text, visuals, audio, and storytelling techniques, employing devices like emotions, symbolism, and slogans to convey meaning. There is a dearth of large annotated training datasets in the multimedia domain hindering the development of supervised learning models with satisfactory performance for real-world applications. On the other hand, the rise of large language models (LLMs) has witnessed remarkable zero-shot performance in various natural language processing (NLP) tasks, such as emotion classification, question-answering, and topic classification. To leverage such advanced techniques to bridge this performance gap in multimedia understanding, we propose verbalizing long videos to generate their descriptions in natural language, followed by performing video-understanding tasks on the generated story as opposed to the original video. Through extensive experiments on fifteen video-understanding tasks, we demonstrate that our method, despite being zero-shot, achieves significantly better results than supervised baselines for video understanding. Furthermore, to alleviate a lack of story understanding benchmarks, we publicly release the first dataset on a crucial task in computational social science on persuasion strategy identification.
Authors: Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne Xin Zhao, Ji-Rong Wen
Inspired by the superior language abilities of large language models (LLM), large vision-language models (LVLM) have been recently explored by integrating powerful LLMs for improving the performance on complex multimodal tasks. Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i.e. they tend to generate objects that are inconsistent with the target images in the descriptions. To investigate it, this work presents the first systematic study on object hallucination of LVLMs. We conduct the evaluation experiments on several representative LVLMs, and show that they mostly suffer from severe object hallucination issue. We further discuss that the visual instructions may influence the hallucination, and find that: objects that frequently occur in the visual instructions or co-occur with the image objects, are obviously prone to be hallucinated by LVLMs. Besides, we find that existing evaluation methods might be affected by the input instructions and generation styles of LVLMs. Thus, we further design an improved evaluation method for object hallucination by proposing a polling-based query method called POPE. Experiment results demonstrate that our POPE can evaluate the object hallucination in a more stable and flexible way. Our codes and data are publicly available at https://github.com/RUCAIBox/POPE.
Authors: Mubashara Akhtar, Michael Schlichtkrull, Zhijiang Guo, Oana Cocarascu, Elena Simperl, Andreas Vlachos
Misinformation is often conveyed in multiple modalities, e.g. a miscaptioned image. Multimodal misinformation is perceived as more credible by humans, and spreads faster than its text-only counterparts. While an increasing body of research investigates automated fact-checking (AFC), previous surveys mostly focus on text. In this survey, we conceptualise a framework for AFC including subtasks unique to multimodal misinformation. Furthermore, we discuss related terms used in different communities and map them to our framework. We focus on four modalities prevalent in real-world fact-checking: text, image, audio, and video. We survey benchmarks and models, and discuss limitations and promising directions for future research
Authors: Martin Gonzalez, Nelson Fernandez, Thuy Tran, Elies Gherbi, Hatem Hajri, Nader Masmoudi
A potent class of generative models known as Diffusion Probabilistic Models (DPMs) has become prominent. A forward diffusion process adds gradually noise to data, while a model learns to gradually denoise. Sampling from pre-trained DPMs is obtained by solving differential equations (DE) defined by the learnt model, a process which has shown to be prohibitively slow. Numerous efforts on speeding-up this process have consisted on crafting powerful ODE solvers. Despite being quick, such solvers do not usually reach the optimal quality achieved by available slow SDE solvers. Our goal is to propose SDE solvers that reach optimal quality without requiring several hundreds or thousands of NFEs to achieve that goal. We propose Stochastic Explicit Exponential Derivative-free Solvers (SEEDS), improving and generalizing Exponential Integrator approaches to the stochastic case on several frameworks. After carefully analyzing the formulation of exact solutions of diffusion SDEs, we craft SEEDS to analytically compute the linear part of such solutions. Inspired by the Exponential Time-Differencing method, SEEDS use a novel treatment of the stochastic components of solutions, enabling the analytical computation of their variance, and contains high-order terms allowing to reach optimal quality sampling $\sim3$-$5\times$ faster than previous SDE methods. We validate our approach on several image generation benchmarks, showing that SEEDS outperform or are competitive with previous SDE solvers. Contrary to the latter, SEEDS are derivative and training free, and we fully prove strong convergence guarantees for them.
Authors: Jinjin Gu, Xianzheng Ma, Xiangtao Kong, Yu Qiao, Chao Dong
Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using highly complex data for training, with the expectation that richer image background content will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discover that this strategy does not enhance the generalization capability of these networks. On the contrary, it exacerbates the tendency of networks to overfit specific degradations. Our experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training background images. This is because that the networks are ``slacking off'' during training, that is, learning the least complex elements in the image background and degradation to minimize training loss. When the background images are less complex than the rain streaks, the network will prioritize the background reconstruction, thereby suppressing overfitting the rain patterns and leading to improved generalization performance. Our research offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks and displays promising potential for practical application.
Authors: Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bézenac, Mickaël Chen, Alain Rakotomamonjy
Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions using differential equations is conventionally seen as opposed to the previously widespread generative adversarial networks (GANs), which involve training a pushforward generator network. In this paper we challenge this interpretation, and propose a novel framework that unifies particle and adversarial generative models by framing generator training as a generalization of particle models. This suggests that a generator is an optional addition to any such generative model. Consequently, integrating a generator into a score-based diffusion model and training a GAN without a generator naturally emerge from our framework. We empirically test the viability of these original models as proofs of concepts of potential applications of our framework.
Authors: Gabriel Raya, Luca Ambrogioni
Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spontaneous symmetry breaking that divides the generative dynamics into two distinct phases: 1) A linear steady-state dynamics around a central fixed-point and 2) an attractor dynamics directed towards the data manifold. These two "phases" are separated by the change in stability of the central fixed-point, with the resulting window of instability being responsible for the diversity of the generated samples. Using both theoretical and empirical evidence, we show that an accurate simulation of the early dynamics does not significantly contribute to the final generation, since early fluctuations are reverted to the central fixed point. To leverage this insight, we propose a Gaussian late initialization scheme, which significantly improves model performance, achieving up to 3x FID improvements on fast samplers, while also increasing sample diversity (e.g., racial composition of generated CelebA images). Our work offers a new way to understand the generative dynamics of diffusion models that has the potential to bring about higher performance and less biased fast-samplers.
Authors: Yingying Fan, Yu Wu, Bo Du, Yutian Lin
We focus on the weakly-supervised audio-visual video parsing task (AVVP), which aims to identify and locate all the events in audio/visual modalities. Previous works only concentrate on video-level overall label denoising across modalities, but overlook the segment-level label noise, where adjacent video segments (i.e., 1-second video clips) may contain different events. However, recognizing events in the segment is challenging because its label could be any combination of events that occur in the video. To address this issue, we consider tackling AVVP from the language perspective, since language could freely describe how various events appear in each segment beyond fixed labels. Specifically, we design language prompts to describe all cases of event appearance for each video. Then, the similarity between language prompts and segments is calculated, where the event of the most similar prompt is regarded as the segment-level label. In addition, to deal with the mislabeled segments, we propose to perform dynamic re-weighting on the unreliable segments to adjust their labels. Experiments show that our simple yet effective approach outperforms state-of-the-art methods by a large margin.
Authors: Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao
It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can achieve promising results on different tasks or benchmarks. Previous works mainly focus on the self-supervised pre-training pipeline, meaning that they perform the pre-training and fine-tuning on the same benchmark, which is difficult to attain the performance scalability and cross-dataset application for the pre-training checkpoint. In this paper, for the first time, we are committed to building a large-scale pre-training point-cloud dataset with diverse data distribution, and meanwhile learning generalizable representations from such a diverse pre-training dataset. We formulate the point-cloud pre-training task as a semi-supervised problem, which leverages the few-shot labeled and massive unlabeled point-cloud data to generate the unified backbone representations that can be directly applied to many baseline models and benchmarks, decoupling the AD-related pre-training process and downstream fine-tuning task. During the period of backbone pre-training, by enhancing the scene- and instance-level distribution diversity and exploiting the backbone's ability to learn from unknown instances, we achieve significant performance gains on a series of downstream perception benchmarks including Waymo, nuScenes, and KITTI, under different baseline models like PV-RCNN++, SECOND, CenterPoint.
Authors: Robert A. Marsden, Mario Döbler, Bin Yang
Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. Clearly, a method proposed for online TTA has to perform well for all kinds of environmental conditions. By introducing the variable factors domain non-stationarity and temporal correlation, we first unfold all practically relevant settings and define the entity as universal TTA. We want to highlight that this is the first work that covers such a broad spectrum, which is indispensable for the use in practice. To tackle the problem of universal TTA, we identify and highlight several challenges a self-training based method has to deal with: 1) model bias and the occurrence of trivial solutions when performing entropy minimization on varying sequence lengths with and without multiple domain shifts, 2) loss of generalization which exacerbates the adaptation to multiple domain shifts and the occurrence of catastrophic forgetting, and 3) performance degradation due to shifts in class prior. To prevent the model from becoming biased, we leverage a dataset and model-agnostic certainty and diversity weighting. In order to maintain generalization and prevent catastrophic forgetting, we propose to continually weight-average the source and adapted model. To compensate for disparities in the class prior during test-time, we propose an adaptive prior correction scheme that reweights the model's predictions. We evaluate our approach, named ROID, on a wide range of settings, datasets, and models, setting new standards in the field of universal TTA. Code is available at: https://github.com/mariodoebler/test-time-adaptation
Authors: Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, Dilip Krishnan
We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural question in the light of the excellent performance of such models in generating high-quality images. We consider specifically the Stable Diffusion, one of the leading open source text-to-image models. We show that (1) when the generative model is configured with proper classifier-free guidance scale, training self-supervised methods on synthetic images can match or beat the real image counterpart; (2) by treating the multiple images generated from the same text prompt as positives for each other, we develop a multi-positive contrastive learning method, which we call StableRep. With solely synthetic images, the representations learned by StableRep surpass the performance of representations learned by SimCLR and CLIP using the same set of text prompts and corresponding real images, on large scale datasets. When we further add language supervision, StableRep trained with 20M synthetic images achieves better accuracy than CLIP trained with 50M real images.
Authors: Noriaki Hirose, Dhruv Shah, Ajay Sridhar, Sergey Levine
Machine learning provides a powerful tool for building socially compliant robotic systems that go beyond simple predictive models of human behavior. By observing and understanding human interactions from past experiences, learning can enable effective social navigation behaviors directly from data. In this paper, our goal is to develop methods for training policies for socially unobtrusive navigation, such that robots can navigate among humans in ways that don't disturb human behavior. We introduce a definition for such behavior based on the counterfactual perturbation of the human: if the robot had not intruded into the space, would the human have acted in the same way? By minimizing this counterfactual perturbation, we can induce robots to behave in ways that do not alter the natural behavior of humans in the shared space. Instantiating this principle requires training policies to minimize their effect on human behavior, and this in turn requires data that allows us to model the behavior of humans in the presence of robots. Therefore, our approach is based on two key contributions. First, we collect a large dataset where an indoor mobile robot interacts with human bystanders. Second, we utilize this dataset to train policies that minimize counterfactual perturbation. We provide supplementary videos and make publicly available the largest-of-its-kind visual navigation dataset on our project page.
Authors: Md Ashequr Rahman, Zitong Yu, Richard Laforest, Craig K. Abbey, Barry A. Siegel, Abhinav K. Jha
There is an important need for methods to process myocardial perfusion imaging (MPI) SPECT images acquired at lower radiation dose and/or acquisition time such that the processed images improve observer performance on the clinical task of detecting perfusion defects. To address this need, we build upon concepts from model-observer theory and our understanding of the human visual system to propose a Detection task-specific deep-learning-based approach for denoising MPI SPECT images (DEMIST). The approach, while performing denoising, is designed to preserve features that influence observer performance on detection tasks. We objectively evaluated DEMIST on the task of detecting perfusion defects using a retrospective study with anonymized clinical data in patients who underwent MPI studies across two scanners (N = 338). The evaluation was performed at low-dose levels of 6.25%, 12.5% and 25% and using an anthropomorphic channelized Hotelling observer. Performance was quantified using area under the receiver operating characteristics curve (AUC). Images denoised with DEMIST yielded significantly higher AUC compared to corresponding low-dose images and images denoised with a commonly used task-agnostic DL-based denoising method. Similar results were observed with stratified analysis based on patient sex and defect type. Additionally, DEMIST improved visual fidelity of the low-dose images as quantified using root mean squared error and structural similarity index metric. A mathematical analysis revealed that DEMIST preserved features that assist in detection tasks while improving the noise properties, resulting in improved observer performance. The results provide strong evidence for further clinical evaluation of DEMIST to denoise low-count images in MPI SPECT.
Authors: Ruoyu Wang, Yongqi Yang, Zhihao Qian, Ye Zhu, Yu Wu
Originating from the diffusion phenomenon in physics that describes particle movement, the diffusion generative models inherit the characteristics of stochastic random walk in the data space along the denoising trajectory. However, the intrinsic mutual interference among image regions contradicts the need for practical downstream application scenarios where the preservation of low-level pixel information from given conditioning is desired (e.g., customization tasks like personalized generation and inpainting based on a user-provided single image). In this work, we investigate the diffusion (physics) in diffusion (machine learning) properties and propose our Cyclic One-Way Diffusion (COW) method to control the direction of diffusion phenomenon given a pre-trained frozen diffusion model for versatile customization application scenarios, where the low-level pixel information from the conditioning needs to be preserved. Notably, unlike most current methods that incorporate additional conditions by fine-tuning the base text-to-image diffusion model or learning auxiliary networks, our method provides a novel perspective to understand the task needs and is applicable to a wider range of customization scenarios in a learning-free manner. Extensive experiment results show that our proposed COW can achieve more flexible customization based on strict visual conditions in different application settings.
Authors: Zhiyu Jin, Xuli Shen, Bin Li, Xiangyang Xue
Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and evaluated on the images with fixed sizes. However, users are demanding for various images with specific sizes and various aspect ratio. This paper focuses on adapting text-to-image diffusion models to handle such variety while maintaining visual fidelity. First we observe that, during the synthesis, lower resolution images suffer from incomplete object portrayal, while higher resolution images exhibit repetitively disordered presentation. Next, we establish a statistical relationship indicating that attention entropy changes with token quantity, suggesting that models aggregate spatial information in proportion to image resolution. The subsequent interpretation on our observations is that objects are incompletely depicted due to limited spatial information for low resolutions, while repetitively disorganized presentation arises from redundant spatial information for high resolutions. From this perspective, we propose a scaling factor to alleviate the change of attention entropy and mitigate the defective pattern observed. Extensive experimental results validate the efficacy of the proposed scaling factor, enabling models to achieve better visual effects, image quality, and text alignment. Notably, these improvements are achieved without additional training or fine-tuning techniques.
Authors: Ximing Xing, Chuang Wang, Haitao Zhou, Jing Zhang, Qian Yu, Dong Xu
Even though trained mainly on images, we discover that pretrained diffusion models show impressive power in guiding sketch synthesis. In this paper, we present DiffSketcher, an innovative algorithm that creates \textit{vectorized} free-hand sketches using natural language input. DiffSketcher is developed based on a pre-trained text-to-image diffusion model. It performs the task by directly optimizing a set of B\'ezier curves with an extended version of the score distillation sampling (SDS) loss, which allows us to use a raster-level diffusion model as a prior for optimizing a parametric vectorized sketch generator. Furthermore, we explore attention maps embedded in the diffusion model for effective stroke initialization to speed up the generation process. The generated sketches demonstrate multiple levels of abstraction while maintaining recognizability, underlying structure, and essential visual details of the subject drawn. Our experiments show that DiffSketcher achieves greater quality than prior work. The code and demo of DiffSketcher can be found at https://ximinng.github.io/DiffSketcher-project/.
Authors: Yiren Jian, Chongyang Gao, Soroush Vosoughi
We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training. The current paradigm uses visual features as prompts to guide language models, with a focus on determining the most relevant visual features for corresponding text. Our approach diverges by concentrating on the language component, specifically identifying the optimal prompts to align with visual features. We introduce the Prompt-Transformer (P-Former), a model that predicts these ideal prompts, which is trained exclusively on linguistic data, bypassing the need for image-text pairings. This strategy subtly bifurcates the end-to-end VL training process into an additional, separate stage. Our experiments reveal that our framework significantly enhances the performance of a robust image-to-text baseline (BLIP-2), and effectively narrows the performance gap between models trained with either 4M or 129M image-text pairs. Importantly, our framework is modality-agnostic and flexible in terms of architectural design, as validated by its successful application in a video learning task using varied base modules. The code will be made available at https://github.com/yiren-jian/BLIText.
Authors: Pietro Bonazzi, Thomas Ruegg, Sizhen Bian, Yawei Li, Michele Magno
Intelligent edge vision tasks encounter the critical challenge of ensuring power and latency efficiency due to the typically heavy computational load they impose on edge platforms.This work leverages one of the first "AI in sensor" vision platforms, IMX500 by Sony, to achieve ultra-fast and ultra-low-power end-to-end edge vision applications. We evaluate the IMX500 and compare it to other edge platforms, such as the Google Coral Dev Micro and Sony Spresense, by exploring gaze estimation as a case study. We propose TinyTracker, a highly efficient, fully quantized model for 2D gaze estimation designed to maximize the performance of the edge vision systems considered in this study. TinyTracker achieves a 41x size reduction (600Kb) compared to iTracker [1] without significant loss in gaze estimation accuracy (maximum of 0.16 cm when fully quantized). TinyTracker's deployment on the Sony IMX500 vision sensor results in end-to-end latency of around 19ms. The camera takes around 17.9ms to read, process and transmit the pixels to the accelerator. The inference time of the network is 0.86ms with an additional 0.24 ms for retrieving the results from the sensor. The overall energy consumption of the end-to-end system is 4.9 mJ, including 0.06 mJ for inference. The end-to-end study shows that IMX500 is 1.7x faster than CoralMicro (19ms vs 34.4ms) and 7x more power efficient (4.9mJ VS 34.2mJ)
Authors: Thao Nguyen, Samir Yitzhak Gadre, Gabriel Ilharco, Sewoong Oh, Ludwig Schmidt
Massive web datasets play a key role in the success of large vision-language models like CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to reduce noise often come at the expense of data diversity. Our work focuses on caption quality as one major source of noise, and studies how generated captions can increase the utility of web-scraped datapoints with nondescript text. Through exploring different mixing strategies for raw and generated captions, we outperform the best filtering method proposed by the DataComp benchmark by 2% on ImageNet and 4% on average across 38 tasks, given a candidate pool of 128M image-text pairs. Our best approach is also 2x better at Flickr and MS-COCO retrieval. We then analyze what makes synthetic captions an effective source of text supervision. In experimenting with different image captioning models, we also demonstrate that the performance of a model on standard image captioning benchmarks (e.g., NoCaps CIDEr) is not a reliable indicator of the utility of the captions it generates for multimodal training. Finally, our experiments with using generated captions at DataComp's large scale (1.28B image-text pairs) offer insights into the limitations of synthetic text, as well as the importance of image curation with increasing training data quantity. The synthetic captions used in our experiments are now available on HuggingFace.
Authors: Kanchana Ranasinghe, Michael Ryoo
Recent contrastive language image pre-training has led to learning highly transferable and robust image representations. However, adapting these models to video domains with minimal supervision remains an open problem. We explore a simple step in that direction, using language tied self-supervised learning to adapt an image CLIP model to the video domain. A backbone modified for temporal modeling is trained under self-distillation settings with train objectives operating in an action concept space. Feature vectors of various action concepts extracted from a language encoder using relevant textual prompts construct this space. We introduce two train objectives, concept distillation and concept alignment, that retain generality of original representations while enforcing relations between actions and their attributes. Our approach improves zero-shot and linear probing performance on three action recognition benchmarks.
Authors: Muyu Xu, Fangneng Zhan, Jiahui Zhang, Yingchen Yu, Xiaoqin Zhang, Christian Theobalt, Ling Shao, Shijian Lu
Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation. However, it usually suffers from poor scalability as requiring densely sampled images for each new scene. Several studies have attempted to mitigate this problem by integrating Multi-View Stereo (MVS) technique into NeRF while they still entail a cumbersome fine-tuning process for new scenes. Notably, the rendering quality will drop severely without this fine-tuning process and the errors mainly appear around the high-frequency features. In the light of this observation, we design WaveNeRF, which integrates wavelet frequency decomposition into MVS and NeRF to achieve generalizable yet high-quality synthesis without any per-scene optimization. To preserve high-frequency information when generating 3D feature volumes, WaveNeRF builds Multi-View Stereo in the Wavelet domain by integrating the discrete wavelet transform into the classical cascade MVS, which disentangles high-frequency information explicitly. With that, disentangled frequency features can be injected into classic NeRF via a novel hybrid neural renderer to yield faithful high-frequency details, and an intuitive frequency-guided sampling strategy can be designed to suppress artifacts around high-frequency regions. Extensive experiments over three widely studied benchmarks show that WaveNeRF achieves superior generalizable radiance field modeling when only given three images as input.
Authors: Chenyangguang Zhang, Yan Di, Ruida Zhang, Guangyao Zhai, Fabian Manhardt, Federico Tombari, Xiangyang Ji
Reconstructing hand-held objects from a single RGB image is an important and challenging problem. Existing works utilizing Signed Distance Fields (SDF) reveal limitations in comprehensively capturing the complex hand-object interactions, since SDF is only reliable within the proximity of the target, and hence, infeasible to simultaneously encode local hand and object cues. To address this issue, we propose DDF-HO, a novel approach leveraging Directed Distance Field (DDF) as the shape representation. Unlike SDF, DDF maps a ray in 3D space, consisting of an origin and a direction, to corresponding DDF values, including a binary visibility signal determining whether the ray intersects the objects and a distance value measuring the distance from origin to target in the given direction. We randomly sample multiple rays and collect local to global geometric features for them by introducing a novel 2D ray-based feature aggregation scheme and a 3D intersection-aware hand pose embedding, combining 2D-3D features to model hand-object interactions. Extensive experiments on synthetic and real-world datasets demonstrate that DDF-HO consistently outperforms all baseline methods by a large margin, especially under Chamfer Distance, with about 80% leap forward. Codes are available at https://github.com/ZhangCYG/DDFHO.
Authors: Ashmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya, Yaman K Singla, Somesh Singh, Uttaran Bhattacharya, Ishita Dasgupta, Stefano Petrangeli, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy
Shannon, in his seminal paper introducing information theory, divided the communication into three levels: technical, semantic, and effectivenss. While the technical level is concerned with accurate reconstruction of transmitted symbols, the semantic and effectiveness levels deal with the inferred meaning and its effect on the receiver. Thanks to telecommunications, the first level problem has produced great advances like the internet. Large Language Models (LLMs) make some progress towards the second goal, but the third level still remains largely untouched. The third problem deals with predicting and optimizing communication for desired receiver behavior. LLMs, while showing wide generalization capabilities across a wide range of tasks, are unable to solve for this. One reason for the underperformance could be a lack of ``behavior tokens'' in LLMs' training corpora. Behavior tokens define receiver behavior over a communication, such as shares, likes, clicks, purchases, retweets, etc. While preprocessing data for LLM training, behavior tokens are often removed from the corpora as noise. Therefore, in this paper, we make some initial progress towards reintroducing behavior tokens in LLM training. The trained models, other than showing similar performance to LLMs on content understanding tasks, show generalization capabilities on behavior simulation, content simulation, behavior understanding, and behavior domain adaptation. Using a wide range of tasks on two corpora, we show results on all these capabilities. We call these models Large Content and Behavior Models (LCBMs). Further, to spur more research on LCBMs, we release our new Content Behavior Corpus (CBC), a repository containing communicator, message, and corresponding receiver behavior.
Authors: Julien Denize, Mykola Liashuha, Jaonary Rabarisoa, Astrid Orcesi, Romain Hérault
We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation. Action spotting is a timestamp-level temporal action detection task. Our pipeline consists of three steps, with two initialization stages. First, we perform self-supervised initialization of a spatial transformer using short videos as input. Additionally, we initialize a temporal transformer that enhances the spatial transformer's outputs with global context through knowledge distillation from a pre-computed feature bank aligned with each short video segment. In the final step, we fine-tune the transformers to the action spotting task. The experiments, conducted on the SoccerNet-v2 dataset, demonstrate state-of-the-art performance and validate the effectiveness of COMEDIAN's pretraining paradigm. Our results highlight several advantages of our pretraining pipeline, including improved performance and faster convergence compared to non-pretrained models.
Authors: Yafei Zhang, Keying Du, Huafeng Li, Zhengtao Yu, Yu Liu
Current infrared and visible image fusion (IVIF) methods go to great lengths to excavate complementary features and design complex fusion strategies, which is extremely challenging. To this end, we rethink the IVIF outside the box, proposing a complementary to harmonious information transfer network (CHITNet). It reasonably transfers complementary information into harmonious one, which integrates both the shared and complementary features from two modalities. Specifically, to skillfully sidestep aggregating complementary information in IVIF, we design a mutual information transfer (MIT) module to mutually represent features from two modalities, roughly transferring complementary information into harmonious one. Then, a harmonious information acquisition supervised by source image (HIASSI) module is devised to further ensure the complementary to harmonious information transfer after MIT. Meanwhile, we also propose a structure information preservation (SIP) module to guarantee that the edge structure information of the source images can be transferred to the fusion results. Moreover, a mutual promotion training paradigm (MPTP) with interaction loss is adopted to facilitate better collaboration among MIT, HIASSI and SIP. In this way, the proposed method is able to generate fused images with higher qualities. Extensive experimental results demonstrate the superiority of our CHITNet over state-of-the-art algorithms in terms of visual quality and quantitative evaluations.
Authors: Chenghao Li, Dake Chen, Yuke Zhang, Peter A. Beerel
While diffusion models demonstrate a remarkable capability for generating high-quality images, their tendency to `replicate' training data raises privacy concerns. Although recent research suggests that this replication may stem from the insufficient generalization of training data captions and duplication of training images, effective mitigation strategies remain elusive. To address this gap, our paper first introduces a generality score that measures the caption generality and employ large language model (LLM) to generalize training captions. Subsequently, we leverage generalized captions and propose a novel dual fusion enhancement approach to mitigate the replication of diffusion models. Our empirical results demonstrate that our proposed methods can significantly reduce replication by 43.5% compared to the original diffusion model while maintaining the diversity and quality of generations.
Authors: Ruihai Wu, Kai Cheng, Yan Shen, Chuanruo Ning, Guanqi Zhan, Hao Dong
Perceiving and manipulating 3D articulated objects in diverse environments is essential for home-assistant robots. Recent studies have shown that point-level affordance provides actionable priors for downstream manipulation tasks. However, existing works primarily focus on single-object scenarios with homogeneous agents, overlooking the realistic constraints imposed by the environment and the agent's morphology, e.g., occlusions and physical limitations. In this paper, we propose an environment-aware affordance framework that incorporates both object-level actionable priors and environment constraints. Unlike object-centric affordance approaches, learning environment-aware affordance faces the challenge of combinatorial explosion due to the complexity of various occlusions, characterized by their quantities, geometries, positions and poses. To address this and enhance data efficiency, we introduce a novel contrastive affordance learning framework capable of training on scenes containing a single occluder and generalizing to scenes with complex occluder combinations. Experiments demonstrate the effectiveness of our proposed approach in learning affordance considering environment constraints. Project page at https://chengkaiacademycity.github.io/EnvAwareAfford/
Authors: Dongsheng Wang, Miaoge Li, Xinyang Liu, MingSheng Xu, Bo Chen, Hanwang Zhang
Advancements in prompt tuning of vision-language models have underscored their potential in enhancing open-world visual concept comprehension. However, prior works only primarily focus on single-mode (only one prompt for each modality) and holistic level (image or sentence) semantic alignment, which fails to capture the sample diversity, leading to sub-optimal prompt discovery. To address the limitation, we propose a multi-mode token-level tuning framework that leverages the optimal transportation to learn and align a set of prompt tokens across modalities. Specifically, we rely on two essential factors: 1) multi-mode prompts discovery, which guarantees diverse semantic representations, and 2) token-level alignment, which helps explore fine-grained similarity. Consequently, the similarity can be calculated as a hierarchical transportation problem between the modality-specific sets. Extensive experiments on popular image recognition benchmarks show the superior generalization and few-shot abilities of our approach. The qualitative analysis demonstrates that the learned prompt tokens have the ability to capture diverse visual concepts.
Authors: Shuhao Kang, Youqi Liao, Jianping Li, Fuxun Liang, Yuhao Li, Fangning Li, Zhen Dong, Bisheng Yang
Image-to-point cloud (I2P) registration is a fundamental task in the field of autonomous vehicles and transportation systems for cross-modality data fusion and localization. Existing I2P registration methods estimate correspondences at the point/pixel level, often overlooking global alignment. However, I2P matching can easily converge to a local optimum when performed without high-level guidance from global constraints. To address this issue, this paper introduces CoFiI2P, a novel I2P registration network that extracts correspondences in a coarse-to-fine manner to achieve the globally optimal solution. First, the image and point cloud data are processed through a Siamese encoder-decoder network for hierarchical feature extraction. Second, a coarse-to-fine matching module is designed to leverage these features and establish robust feature correspondences. Specifically, In the coarse matching phase, a novel I2P transformer module is employed to capture both homogeneous and heterogeneous global information from the image and point cloud data. This enables the estimation of coarse super-point/super-pixel matching pairs with discriminative descriptors. In the fine matching module, point/pixel pairs are established with the guidance of super-point/super-pixel correspondences. Finally, based on matching pairs, the transform matrix is estimated with the EPnP-RANSAC algorithm. Extensive experiments conducted on the KITTI dataset demonstrate that CoFiI2P achieves impressive results, with a relative rotation error (RRE) of 1.14 degrees and a relative translation error (RTE) of 0.29 meters. These results represent a significant improvement of 84\% in RRE and 89\% in RTE compared to the current state-of-the-art (SOTA) method. Qualitative results are available at https://youtu.be/ovbedasXuZE. The source code will be publicly released at https://github.com/kang-1-2-3/CoFiI2P.
Authors: Alloy Das, Sanket Biswas, Ayan Banerjee, Saumik Bhattacharya, Josep Lladós, Umapada Pal
The adaptation capability to a wide range of domains is crucial for scene text spotting models when deployed to real-world conditions. However, existing state-of-the-art (SOTA) approaches usually incorporate scene text detection and recognition simply by pretraining on natural scene text datasets, which do not directly exploit the intermediate feature representations between multiple domains. Here, we investigate the problem of domain-adaptive scene text spotting, i.e., training a model on multi-domain source data such that it can directly adapt to target domains rather than being specialized for a specific domain or scenario. Further, we investigate a transformer baseline called Swin-TESTR to focus on solving scene-text spotting for both regular and arbitrary-shaped scene text along with an exhaustive evaluation. The results clearly demonstrate the potential of intermediate representations to achieve significant performance on text spotting benchmarks across multiple domains (e.g. language, synth-to-real, and documents). both in terms of accuracy and efficiency.
Authors: Lei Li
The task of identifying and segmenting buildings within remote sensing imagery has perennially stood at the forefront of scholarly investigations. This manuscript accentuates the potency of harnessing diversified datasets in tandem with cutting-edge representation learning paradigms for building segmentation in such images. Through the strategic amalgamation of disparate datasets, we have not only expanded the informational horizon accessible for model training but also manifested unparalleled performance metrics across multiple datasets. Our avant-garde joint training regimen underscores the merit of our approach, bearing significant implications in pivotal domains such as urban infrastructural development, disaster mitigation strategies, and ecological surveillance. Our methodology, predicated upon the fusion of datasets and gleaning insights from pre-trained models, carves a new benchmark in the annals of building segmentation endeavors. The outcomes of this research both fortify the foundations for ensuing scholarly pursuits and presage a horizon replete with innovative applications in the discipline of building segmentation.
Authors: Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, Jianfeng Gao
Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in visual contexts has not been systematically studied. To bridge this gap, we present MathVista, a benchmark designed to combine challenges from diverse mathematical and visual tasks. It consists of 6,141 examples, derived from 28 existing multimodal datasets involving mathematics and 3 newly created datasets (i.e., IQTest, FunctionQA, and PaperQA). Completing these tasks requires fine-grained, deep visual understanding and compositional reasoning, which all state-of-the-art foundation models find challenging. With MathVista, we have conducted a comprehensive, quantitative evaluation of 12 prominent foundation models. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. Our in-depth analysis reveals that the superiority of GPT-4V is mainly attributed to its enhanced visual perception and mathematical reasoning. However, GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning. This significant gap underscores the critical role that MathVista will play in the development of general-purpose AI agents capable of tackling mathematically intensive and visually rich real-world tasks. We further explore the new ability of self-verification, the application of self-consistency, and the interactive chatbot capabilities of GPT-4V, highlighting its promising potential for future research. The project is available at https://mathvista.github.io/.
Authors: Jiayu Xiao, Liang Li, Henglei Lv, Shuhui Wang, Qingming Huang
Recent text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images given text-prompts as input. However, these models fail to convey appropriate spatial composition specified by a layout instruction. In this work, we probe into zero-shot grounded T2I generation with diffusion models, that is, generating images corresponding to the input layout information without training auxiliary modules or finetuning diffusion models. We propose a Region and Boundary (R&B) aware cross-attention guidance approach that gradually modulates the attention maps of diffusion model during generative process, and assists the model to synthesize images (1) with high fidelity, (2) highly compatible with textual input, and (3) interpreting layout instructions accurately. Specifically, we leverage the discrete sampling to bridge the gap between consecutive attention maps and discrete layout constraints, and design a region-aware loss to refine the generative layout during diffusion process. We further propose a boundary-aware loss to strengthen object discriminability within the corresponding regions. Experimental results show that our method outperforms existing state-of-the-art zero-shot grounded T2I generation methods by a large margin both qualitatively and quantitatively on several benchmarks.
Authors: Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, Mohamed Elhoseiny
Large language models have shown their remarkable capabilities as a general interface for various language-related applications. Motivated by this, we target to build a unified interface for completing many vision-language tasks including image description, visual question answering, and visual grounding, among others. The challenge is to use a single model for performing diverse vision-language tasks effectively with simple multi-modal instructions. Towards this objective, we introduce MiniGPT-v2, a model that can be treated as a unified interface for better handling various vision-language tasks. We propose using unique identifiers for different tasks when training the model. These identifiers enable our model to better distinguish each task instruction effortlessly and also improve the model learning efficiency for each task. After the three-stage training, the experimental results show that MiniGPT-v2 achieves strong performance on many visual question-answering and visual grounding benchmarks compared to other vision-language generalist models. Our model and codes are available at https://minigpt-v2.github.io/
Authors: Kaiwen Zheng, Cheng Lu, Jianfei Chen, Jun Zhu
Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity image generation while suffering from inefficient sampling. Recent works accelerate the sampling procedure by proposing fast ODE solvers that leverage the specific ODE form of DPMs. However, they highly rely on specific parameterization during inference (such as noise/data prediction), which might not be the optimal choice. In this work, we propose a novel formulation towards the optimal parameterization during sampling that minimizes the first-order discretization error of the ODE solution. Based on such formulation, we propose \textit{DPM-Solver-v3}, a new fast ODE solver for DPMs by introducing several coefficients efficiently computed on the pretrained model, which we call \textit{empirical model statistics}. We further incorporate multistep methods and a predictor-corrector framework, and propose some techniques for improving sample quality at small numbers of function evaluations (NFE) or large guidance scales. Experiments show that DPM-Solver-v3 achieves consistently better or comparable performance in both unconditional and conditional sampling with both pixel-space and latent-space DPMs, especially in 5$\sim$10 NFEs. We achieve FIDs of 12.21 (5 NFE), 2.51 (10 NFE) on unconditional CIFAR10, and MSE of 0.55 (5 NFE, 7.5 guidance scale) on Stable Diffusion, bringing a speed-up of 15\%$\sim$30\% compared to previous state-of-the-art training-free methods. Code is available at \url{https://github.com/thu-ml/DPM-Solver-v3}.
Authors: Dayoon Ko, Sangho Lee, Gunhee Kim
As short-form funny videos on social networks are gaining popularity, it becomes demanding for AI models to understand them for better communication with humans. Unfortunately, previous video humor datasets target specific domains, such as speeches or sitcoms, and mostly focus on verbal cues. We curate a user-generated dataset of 10K multimodal funny videos from YouTube, called ExFunTube. Using a video filtering pipeline with GPT-3.5, we verify both verbal and visual elements contributing to humor. After filtering, we annotate each video with timestamps and text explanations for funny moments. Our ExFunTube is unique over existing datasets in that our videos cover a wide range of domains with various types of humor that necessitate a multimodal understanding of the content. Also, we develop a zero-shot video-to-text prompting to maximize video humor understanding of large language models (LLMs). With three different evaluation methods using automatic scores, rationale quality experiments, and human evaluations, we show that our prompting significantly improves LLMs' ability for humor explanation.
Authors: Kun Song, Huimin Ma, Bochao Zou, Huishuai Zhang, Weiran Huang
Due to the limited availability of data, existing few-shot learning methods trained from scratch fail to achieve satisfactory performance. In contrast, large-scale pre-trained models such as CLIP demonstrate remarkable few-shot and zero-shot capabilities. To enhance the performance of pre-trained models for downstream tasks, fine-tuning the model on downstream data is frequently necessary. However, fine-tuning the pre-trained model leads to a decrease in its generalizability in the presence of distribution shift, while the limited number of samples in few-shot learning makes the model highly susceptible to overfitting. Consequently, existing methods for fine-tuning few-shot learning primarily focus on fine-tuning the model's classification head or introducing additional structure. In this paper, we introduce a fine-tuning approach termed Feature Discrimination Alignment (FD-Align). Our method aims to bolster the model's generalizability by preserving the consistency of spurious features across the fine-tuning process. Extensive experimental results validate the efficacy of our approach for both ID and OOD tasks. Once fine-tuned, the model can seamlessly integrate with existing methods, leading to performance improvements. Our code can be found in https://github.com/skingorz/FD-Align.
Authors: Hyun-Song Kwon, Sung-Hee Lee
Realistic reconstruction of 3D clothing from an image has wide applications, such as avatar creation and virtual try-on. This paper presents a novel framework that reconstructs the texture map for 3D garments from a single image with pose. Assuming that 3D garments are modeled by stitching 2D garment sewing patterns, our specific goal is to generate a texture image for the sewing patterns. A key component of our framework, the Texture Unwarper, infers the original texture image from the input clothing image, which exhibits warping and occlusion of texture due to the user's body shape and pose. The Texture Unwarper effectively transforms between the input and output images by mapping the latent spaces of the two images. By inferring the unwarped original texture of the input garment, our method helps reconstruct 3D garment models that can show high-quality texture images realistically deformed for new poses. We validate the effectiveness of our approach through a comparison with other methods and ablation studies.
Authors: Hanlin Chen, Chen Li, Mengqi Guo, Zhiwen Yan, Gim Hee Lee
3D scene segmentation based on neural implicit representation has emerged recently with the advantage of training only on 2D supervision. However, existing approaches still requires expensive per-scene optimization that prohibits generalization to novel scenes during inference. To circumvent this problem, we introduce a generalizable 3D segmentation framework based on implicit representation. Specifically, our framework takes in multi-view image features and semantic maps as the inputs instead of only spatial information to avoid overfitting to scene-specific geometric and semantic information. We propose a novel soft voting mechanism to aggregate the 2D semantic information from different views for each 3D point. In addition to the image features, view difference information is also encoded in our framework to predict the voting scores. Intuitively, this allows the semantic information from nearby views to contribute more compared to distant ones. Furthermore, a visibility module is also designed to detect and filter out detrimental information from occluded views. Due to the generalizability of our proposed method, we can synthesize semantic maps or conduct 3D semantic segmentation for novel scenes with solely 2D semantic supervision. Experimental results show that our approach achieves comparable performance with scene-specific approaches. More importantly, our approach can even outperform existing strong supervision-based approaches with only 2D annotations. Our source code is available at: https://github.com/HLinChen/GNeSF.
Authors: Jinbin Bai, Zhen Dong, Aosong Feng, Xiao Zhang, Tian Ye, Kaicheng Zhou, Mike Zheng Shou
In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge. This paper introduces a pioneering framework that integrates viewpoint information to enhance the control of image editing tasks. By surveying existing object editing methodologies, we distill three essential criteria, consistency, controllability, and harmony, that should be met for an image editing method. In contrast to previous approaches, our method takes the lead in satisfying all three requirements for addressing the challenge of image synthesis. Through comprehensive experiments, encompassing both quantitative assessments and qualitative comparisons with contemporary state-of-the-art methods, we present compelling evidence of our framework's superior performance across multiple dimensions. This work establishes a promising avenue for advancing image synthesis techniques and empowering precise object modifications while preserving the visual coherence of the entire composition.
Authors: Joey Wilson, Yuewei Fu, Joshua Friesen, Parker Ewen, Andrew Capodieci, Paramsothy Jayakumar, Kira Barton, Maani Ghaffari
In this paper, we develop a modular neural network for real-time semantic mapping in uncertain environments, which explicitly updates per-voxel probabilistic distributions within a neural network layer. Our approach combines the reliability of classical probabilistic algorithms with the performance and efficiency of modern neural networks. Although robotic perception is often divided between modern differentiable methods and classical explicit methods, a union of both is necessary for real-time and trustworthy performance. We introduce a novel Convolutional Bayesian Kernel Inference (ConvBKI) layer which incorporates semantic segmentation predictions online into a 3D map through a depthwise convolution layer by leveraging conjugate priors. We compare ConvBKI against state-of-the-art deep learning approaches and probabilistic algorithms for mapping to evaluate reliability and performance. We also create a Robot Operating System (ROS) package of ConvBKI and test it on real-world perceptually challenging off-road driving data.
Authors: Ge Zheng, Bin Yang, Jiajin Tang, Hong-Yu Zhou, Sibei Yang
A long-standing goal of AI systems is to perform complex multimodal reasoning like humans. Recently, large language models (LLMs) have made remarkable strides in such multi-step reasoning on the language modality solely by leveraging the chain of thought (CoT) to mimic human thinking. However, the transfer of these advancements to multimodal contexts introduces heightened challenges, including but not limited to the impractical need for labor-intensive annotation and the limitations in terms of flexibility, generalizability, and explainability. To evoke CoT reasoning in multimodality, this work first conducts an in-depth analysis of these challenges posed by multimodality and presents two key insights: "keeping critical thinking" and "letting everyone do their jobs" in multimodal CoT reasoning. Furthermore, this study proposes a novel DDCoT prompting that maintains a critical attitude through negative-space prompting and incorporates multimodality into reasoning by first dividing the reasoning responsibility of LLMs into reasoning and recognition and then integrating the visual recognition capability of visual models into the joint reasoning process. The rationales generated by DDCoT not only improve the reasoning abilities of both large and small language models in zero-shot prompting and fine-tuning learning, significantly outperforming state-of-the-art methods but also exhibit impressive generalizability and explainability.
Authors: Jessica Echterhoff, An Yan, Kyungtae Han, Amr Abdelraouf, Rohit Gupta, Julian McAuley
Concept bottleneck models have been successfully used for explainable machine learning by encoding information within the model with a set of human-defined concepts. In the context of human-assisted or autonomous driving, explainability models can help user acceptance and understanding of decisions made by the autonomous vehicle, which can be used to rationalize and explain driver or vehicle behavior. We propose a new approach using concept bottlenecks as visual features for control command predictions and explanations of user and vehicle behavior. We learn a human-understandable concept layer that we use to explain sequential driving scenes while learning vehicle control commands. This approach can then be used to determine whether a change in a preferred gap or steering commands from a human (or autonomous vehicle) is led by an external stimulus or change in preferences. We achieve competitive performance to latent visual features while gaining interpretability within our model setup.
Authors: Jingxiang Sun, Bo Zhang, Ruizhi Shao, Lizhen Wang, Wen Liu, Zhenda Xie, Yebin Liu
We present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation. Code available at https://github.com/deepseek-ai/DreamCraft3D.
Authors: Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent advances in MTR theory and show that they can provide novel insights for popular meta-learning algorithms when analyzed within this framework. In particular, we highlight a fundamental difference between gradient-based and metric-based algorithms in practice and put forward a theoretical analysis to explain it. Finally, we use the derived insights to improve the performance of meta-learning methods via a new spectral-based regularization term and confirm its efficiency through experimental studies on few-shot classification benchmarks. To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of MTR theory into practice for the task of few-shot classification.
Authors: Ali Golmakani (MULTISPEECH), Mostafa Sadeghi (MULTISPEECH), Xavier Alameda-Pineda (ROBOTLEARN), Romain Serizel (MULTISPEECH)
We address speech enhancement based on variational autoencoders, which involves learning a speech prior distribution in the time-frequency (TF) domain. A zero-mean complex-valued Gaussian distribution is usually assumed for the generative model, where the speech information is encoded in the variance as a function of a latent variable. In contrast to this commonly used approach, we propose a weighted variance generative model, where the contribution of each spectrogram time-frame in parameter learning is weighted. We impose a Gamma prior distribution on the weights, which would effectively lead to a Student's t-distribution instead of Gaussian for speech generative modeling. We develop efficient training and speech enhancement algorithms based on the proposed generative model. Our experimental results on spectrogram auto-encoding and speech enhancement demonstrate the effectiveness and robustness of the proposed approach compared to the standard unweighted variance model.