Digital media (e.g., photographs, video) can be easily created, edited, and shared. Tools for editing digital media are capable of doing so while also maintaining a high degree of photo-realism. While many types of edits to digital media are generally benign, others can also be applied for malicious purposes. State-of-the-art face editing tools and software can, for example, artificially make a person appear to be smiling at an inopportune time, or depict authority figures as frail and tired in order to discredit individuals. Given the increasing ease of editing digital media and the potential risks from misuse, a substantial amount of effort has gone into media forensics. To this end, we created a challenge dataset of edited facial images to assist the research community in developing novel approaches to address and classify the authenticity of digital media. Our dataset includes edits applied to controlled, portrait-style frontal face images and full-scene in-the-wild images that may include multiple (i.e., more than one) face per image. The goals of our dataset is to address the following challenge questions: (1) Can we determine the authenticity of a given image (edit detection)? (2) If an image has been edited, can we \textit{localize} the edit region? (3) If an image has been edited, can we deduce (classify) what edit type was performed? The majority of research in image forensics generally attempts to answer item (1), detection. To the best of our knowledge, there are no formal datasets specifically curated to evaluate items (2) and (3), localization and classification, respectively. Our hope is that our prepared evaluation protocol will assist researchers in improving the state-of-the-art in image forensics as they pertain to these challenges.
Image inpainting methods have shown significant improvements by using deep neural networks recently. However, many of these techniques often create distorted structures or blurry textures inconsistent with surrounding areas. The problem is rooted in the encoder layers' ineffectiveness in building a complete and faithful embedding of the missing regions. To address this problem, two-stage approaches deploy two separate networks for a coarse and fine estimate of the inpainted image. Some approaches utilize handcrafted features like edges or contours to guide the reconstruction process. These methods suffer from huge computational overheads owing to multiple generator networks, limited ability of handcrafted features, and sub-optimal utilization of the information present in the ground truth. Motivated by these observations, we propose a distillation based approach for inpainting, where we provide direct feature level supervision for the encoder layers in an adaptive manner. We deploy cross and self distillation techniques and discuss the need for a dedicated completion-block in encoder to achieve the distillation target. We conduct extensive evaluations on multiple datasets to validate our method.
Motion transfer is the task of synthesizing future video frames of a single source image according to the motion from a given driving video. In order to solve it, we face the challenging complexity of motion representation and the unknown relations between the driving video and the source image. Despite its difficulty, this problem attracted great interests from researches at the recent years, with gradual improvements. The goal is often thought as the decoupling of motion and appearance, which is may be solved by extracting the motion from keypoint movement. We chose to tackle the generic, unsupervised setting, where we need to apply animation to any arbitrary object, without any domain specific model for the structure of the input. In this work, we extract the structure from a keypoint heatmap, without an explicit motion representation. Then, the structures from the image and the video are extracted to warp the image according to the video, by a deep generator. We suggest two variants of the structure from different steps in the keypoint module, and show superior qualitative pose and quantitative scores.
Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the class token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, i.e., accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a token clustering layer to decrease the number of tokens and a token reconstruction layer to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks, including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation.
Achieving accurate and automated tumor segmentation plays an important role in both clinical practice and radiomics research. Segmentation in medicine is now often performed manually by experts, which is a laborious, expensive and error-prone task. Manual annotation relies heavily on the experience and knowledge of these experts. In addition, there is much intra- and interobserver variation. Therefore, it is of great significance to develop a method that can automatically segment tumor target regions. In this paper, we propose a deep learning segmentation method based on multimodal positron emission tomography-computed tomography (PET-CT), which combines the high sensitivity of PET and the precise anatomical information of CT. We design an improved spatial attention network(ISA-Net) to increase the accuracy of PET or CT in detecting tumors, which uses multi-scale convolution operation to extract feature information and can highlight the tumor region location information and suppress the non-tumor region location information. In addition, our network uses dual-channel inputs in the coding stage and fuses them in the decoding stage, which can take advantage of the differences and complementarities between PET and CT. We validated the proposed ISA-Net method on two clinical datasets, a soft tissue sarcoma(STS) and a head and neck tumor(HECKTOR) dataset, and compared with other attention methods for tumor segmentation. The DSC score of 0.8378 on STS dataset and 0.8076 on HECKTOR dataset show that ISA-Net method achieves better segmentation performance and has better generalization. Conclusions: The method proposed in this paper is based on multi-modal medical image tumor segmentation, which can effectively utilize the difference and complementarity of different modes. The method can also be applied to other multi-modal data or single-modal data by proper adjustment.
Camera images are ubiquitous in machine learning research. They also play a central role in the delivery of important services spanning medicine and environmental surveying. However, the application of machine learning models in these domains has been limited because of robustness concerns. A primary failure mode are performance drops due to differences between the training and deployment data. While there are methods to prospectively validate the robustness of machine learning models to such dataset drifts, existing approaches do not account for explicit models of the primary object of interest: the data. This makes it difficult to create physically faithful drift test cases or to provide specifications of data models that should be avoided when deploying a machine learning model. In this study, we demonstrate how these shortcomings can be overcome by pairing machine learning robustness validation with physical optics. We examine the role raw sensor data and differentiable data models can play in controlling performance risks related to image dataset drift. The findings are distilled into three applications. First, drift synthesis enables the controlled generation of physically faithful drift test cases. The experiments presented here show that the average decrease in model performance is ten to four times less severe than under post-hoc augmentation testing. Second, the gradient connection between task and data models allows for drift forensics that can be used to specify performance-sensitive data models which should be avoided during deployment of a machine learning model. Third, drift adjustment opens up the possibility for processing adjustments in the face of drift. This can lead to speed up and stabilization of classifier training at a margin of up to 20% in validation accuracy. A guide to access the open code and datasets is available at https://github.com/aiaudit-org/raw2logit.
The Munsell soil color chart (MSCC) is a in laboratories under controlled conditions. To support an appbased solution, this paper explores three research areas including: (i) identifying the most effective color space, (ii) establishing then important reference for many professionals in the area of soil color analysis. Currently, the functionality to identify Munsell soil colors (MSCs) automatically from an image is only feasible color difference calculation method with the highest accuracy and (iii) evaluating the effects of smartphone cameras on estimating the MSCs. The existing methods that we have analysed have returned promising results and will help inform other researchers to better understand and develop informed solutions. This study provides both researchers and developers with an insight into the best methods for automatically predicting MSCs. Future research is needed to improve the reliability of results under differing environmental conditions.
LiDAR and cameras are two complementary sensors for 3D perception in autonomous driving. LiDAR point clouds have accurate spatial and geometry information, while RGB images provide textural and color data for context reasoning. To exploit LiDAR and cameras jointly, existing fusion methods tend to align each 3D point to only one projected image pixel based on calibration, namely one-to-one mapping. However, the performance of these approaches highly relies on the calibration quality, which is sensitive to the temporal and spatial synchronization of sensors. Therefore, we propose a Dynamic Cross Attention (DCA) module with a novel one-to-many cross-modality mapping that learns multiple offsets from the initial projection towards the neighborhood and thus develops tolerance to calibration error. Moreover, a \textit{dynamic query enhancement} is proposed to perceive the model-independent calibration, which further strengthens DCA's tolerance to the initial misalignment. The whole fusion architecture named Dynamic Cross Attention Network (DCAN) exploits multi-level image features and adapts to multiple representations of point clouds, which allows DCA to serve as a plug-in fusion module. Extensive experiments on nuScenes and KITTI prove DCA's effectiveness. The proposed DCAN outperforms state-of-the-art methods on the nuScenes detection challenge.
Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoAugment, which have led to substantial gains in standard training of image classifiers, have not been successful with Adversarial Training. We first explain this contrasting behavior by viewing augmentation during training as a problem of domain generalization, and further propose Diverse Augmentation-based Joint Adversarial Training (DAJAT) to use data augmentations effectively in adversarial training. We aim to handle the conflicting goals of enhancing the diversity of the training dataset and training with data that is close to the test distribution by using a combination of simple and complex augmentations with separate batch normalization layers during training. We further utilize the popular Jensen-Shannon divergence loss to encourage the joint learning of the diverse augmentations, thereby allowing simple augmentations to guide the learning of complex ones. Lastly, to improve the computational efficiency of the proposed method, we propose and utilize a two-step defense, Ascending Constraint Adversarial Training (ACAT), that uses an increasing epsilon schedule and weight-space smoothing to prevent gradient masking. The proposed method DAJAT achieves substantially better robustness-accuracy trade-off when compared to existing methods on the RobustBench Leaderboard on ResNet-18 and WideResNet-34-10. The code for implementing DAJAT is available here: https://github.com/val-iisc/DAJAT.
The problem of inferring object shape from a single 2D image is underconstrained. Prior knowledge about what objects are plausible can help, but even given such prior knowledge there may still be uncertainty about the shapes of occluded parts of objects. Recently, conditional neural radiance field (NeRF) models have been developed that can learn to infer good point estimates of 3D models from single 2D images. The problem of inferring uncertainty estimates for these models has received less attention. In this work, we propose probabilistic NeRF (ProbNeRF), a model and inference strategy for learning probabilistic generative models of 3D objects' shapes and appearances, and for doing posterior inference to recover those properties from 2D images. ProbNeRF is trained as a variational autoencoder, but at test time we use Hamiltonian Monte Carlo (HMC) for inference. Given one or a few 2D images of an object (which may be partially occluded), ProbNeRF is able not only to accurately model the parts it sees, but also to propose realistic and diverse hypotheses about the parts it does not see. We show that key to the success of ProbNeRF are (i) a deterministic rendering scheme, (ii) an annealed-HMC strategy, (iii) a hypernetwork-based decoder architecture, and (iv) doing inference over a full set of NeRF weights, rather than just a low-dimensional code.