Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images. In this paper, a new end-to-end unsupervised motion transfer framework is proposed to overcome such issue. Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image. Secondly, in order to restore the missing regions more realistically, we leverage multi-resolution occlusion masks to achieve more effective feature fusion. Finally, additional auxiliary loss functions are designed to ensure that there is a clear division of labor in the network modules, encouraging the network to generate high-quality images. Our method can animate a variety of objects, including talking faces, human bodies, and pixel animations. Experiments demonstrate that our method performs better on most benchmarks than the state of the art with visible improvements in pose-related metrics.
Two-view structure from motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM (vSLAM). Many existing end-to-end learning-based methods usually formulate it as a brute regression problem. However, the inadequate utilization of traditional geometry model makes the model not robust in unseen environments. To improve the generalization capability and robustness of end-to-end two-view SfM network, we formulate the two-view SfM problem as a maximum likelihood estimation (MLE) and solve it with the proposed framework, denoted as DeepMLE. First, we propose to take the deep multi-scale correlation maps to depict the visual similarities of 2D image matches decided by ego-motion. In addition, in order to increase the robustness of our framework, we formulate the likelihood function of the correlations of 2D image matches as a Gaussian and Uniform mixture distribution which takes the uncertainty caused by illumination changes, image noise and moving objects into account. Meanwhile, an uncertainty prediction module is presented to predict the pixel-wise distribution parameters. Finally, we iteratively refine the depth and relative camera pose using the gradient-like information to maximize the likelihood function of the correlations. Extensive experimental results on several datasets prove that our method significantly outperforms the state-of-the-art end-to-end two-view SfM approaches in accuracy and generalization capability.
In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a \textbf{Hi}erarchical \textbf{V}ision-\textbf{}Language \textbf{P}re-Training (\textbf{HiVLP}) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimensional representation for large-scale coarse retrieval and high-dimensional representation for small-scale fine retrieval. We evaluate our proposed HiVLP on two popular image-text retrieval benchmarks, i.e., Flickr30k and COCO. Extensive experiments demonstrate that our HiVLP not only has fast inference speed but also can be easily scaled to large-scale ITR scenarios. The detailed results show that HiVLP is $1,427$$\sim$$120,649\times$ faster than the fusion-based model UNITER and 2$\sim$5 faster than the fastest embedding-based model LightingDot in different candidate scenarios. It also achieves about +4.9 AR on COCO and +3.8 AR on Flickr30K than LightingDot and achieves comparable performance with the state-of-the-art (SOTA) fusion-based model METER.
Aligning the visual and language spaces requires to train deep neural networks from scratch on giant multimodal datasets; CLIP trains both an image and a text encoder, while LiT manages to train just the latter by taking advantage of a pretrained vision network. In this paper, we show that sparse relative representations are sufficient to align text and images without training any network. Our method relies on readily available single-domain encoders (trained with or without supervision) and a modest (in comparison) number of image-text pairs. ASIF redefines what constitutes a multimodal model by explicitly disentangling memory from processing: here the model is defined by the embedded pairs of all the entries in the multimodal dataset, in addition to the parameters of the two encoders. Experiments on standard zero-shot visual benchmarks demonstrate the typical transfer ability of image-text models. Overall, our method represents a simple yet surprisingly strong baseline for foundation multimodal models, raising important questions on their data efficiency and on the role of retrieval in machine learning.
Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance. However, these models focus only on understanding tasks utilizing encoder-only architecture. In this paper, we propose ERNIE-UniX2, a unified cross-lingual cross-modal pre-training framework for both generation and understanding tasks. ERNIE-UniX2 integrates multiple pre-training paradigms (e.g., contrastive learning and language modeling) based on encoder-decoder architecture and attempts to learn a better joint representation across languages and modalities. Furthermore, ERNIE-UniX2 can be seamlessly fine-tuned for varieties of generation and understanding downstream tasks. Pre-trained on both multilingual text-only and image-text datasets, ERNIE-UniX2 achieves SOTA results on various cross-lingual cross-modal generation and understanding tasks such as multimodal machine translation and multilingual visual question answering.
Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be expressed by a linear combination of a few elements from a convolutional dictionary, are powerful tools for analyzing natural images with good theoretical interpretability and biological plausibility. However, such principled models have not demonstrated competitive performance when compared with empirically designed deep networks. This paper revisits the sparse convolutional modeling for image classification and bridges the gap between good empirical performance (of deep learning) and good interpretability (of sparse convolutional models). Our method uses differentiable optimization layers that are defined from convolutional sparse coding as drop-in replacements of standard convolutional layers in conventional deep neural networks. We show that such models have equally strong empirical performance on CIFAR-10, CIFAR-100, and ImageNet datasets when compared to conventional neural networks. By leveraging stable recovery property of sparse modeling, we further show that such models can be much more robust to input corruptions as well as adversarial perturbations in testing through a simple proper trade-off between sparse regularization and data reconstruction terms. Source code can be found at https://github.com/Delay-Xili/SDNet.
Gaze estimation has grown rapidly in accuracy in recent years. However, these models often fail to take advantage of different computer vision (CV) algorithms and techniques (such as small ResNet and Inception networks and ensemble models) that have been shown to improve results for other CV problems. Additionally, most current gaze estimation models require the use of either both eyes or an entire face, whereas real-world data may not always have both eyes in high resolution. Thus, we propose a gaze estimation model that implements the ResNet and Inception model architectures and makes predictions using only one eye image. Furthermore, we propose an ensemble calibration network that uses the predictions from several individual architectures for subject-specific predictions. With the use of lightweight architectures, we achieve high performance on the GazeCapture dataset with very low model parameter counts. When using two eyes as input, we achieve a prediction error of 1.591 cm on the test set without calibration and 1.439 cm with an ensemble calibration model. With just one eye as input, we still achieve an average prediction error of 2.312 cm on the test set without calibration and 1.951 cm with an ensemble calibration model. We also notice significantly lower errors on the right eye images in the test set, which could be important in the design of future gaze estimation-based tools.
End-to-end learned lossy image coders, as opposed to hand-crafted image codecs, have shown increasing superiority in terms of the rate-distortion performance. However, they are mainly treated as a black-box system and their interpretability is not well studied. In this paper, we investigate learned image coders from the perspective of linear transform coding by measuring their channel response and linearity. For different learned image coder designs, we show that their end-to-end learned non-linear transforms share similar properties with linear orthogonal transformations. Our analysis provides insights into understanding how learned image coders work and could benefit future design and development.
Deep learning methods exhibit outstanding performance in synthetic aperture radar (SAR) image interpretation tasks. However, these are black box models that limit the comprehension of their predictions. Therefore, to meet this challenge, we have utilized explainable artificial intelligence (XAI) methods for the SAR image classification task. Specifically, we trained state-of-the-art convolutional neural networks for each polarization format on OpenSARUrban dataset and then investigate eight explanation methods to analyze the predictions of the CNN classifiers of SAR images. These XAI methods are also evaluated qualitatively and quantitatively which shows that Occlusion achieves the most reliable interpretation performance in terms of Max-Sensitivity but with a low-resolution explanation heatmap. The explanation results provide some insights into the internal mechanism of black-box decisions for SAR image classification.
This paper presents a novel machine learning framework to consistently detect, localize and rate congenital cleft lip anomalies in human faces. The goal is to provide a universal, objective measure of facial differences and reconstructive surgical outcomes that matches human judgments. The proposed method employs the StyleGAN2 generative adversarial network with model adaptation to produce normalized transformations of cleft-affected faces in order to allow for subsequent measurement of deformity using a pixel-wise subtraction approach. The complete pipeline of the proposed framework consists of the following steps: image preprocessing, face normalization, color transformation, morphological erosion, heat-map generation and abnormality scoring. Heatmaps that finely discern anatomic anomalies are proposed by exploiting the features of the considered framework. The proposed framework is validated through computer simulations and surveys containing human ratings. The anomaly scores yielded by the proposed computer model correlate closely with the human ratings of facial differences, leading to 0.942 Pearson's r score.