Generative Adversarial Networks (GAN) is a model for data synthesis, which creates plausible data through the competition of generator and discriminator. Although GAN application to image synthesis is extensively studied, it has inherent limitations to natural language generation. Because natural language is composed of discrete tokens, a generator has difficulty updating its gradient through backpropagation; therefore, most text-GAN studies generate sentences starting with a random token based on a reward system. Thus, the generators of previous studies are pre-trained in an autoregressive way before adversarial training, causing data memorization that synthesized sentences reproduce the training data. In this paper, we synthesize sentences using a framework similar to the original GAN. More specifically, we propose Text Embedding Space Generative Adversarial Networks (TESGAN) which generate continuous text embedding spaces instead of discrete tokens to solve the gradient backpropagation problem. Furthermore, TESGAN conducts unsupervised learning which does not directly refer to the text of the training data to overcome the data memorization issue. By adopting this novel method, TESGAN can synthesize new sentences, showing the potential of unsupervised learning for text synthesis. We expect to see extended research combining Large Language Models with a new perspective of viewing text as an continuous space.

Most contributions on Few-Shot Object Detection (FSOD) evaluate their methods on natural images only, yet the transferability of the announced performance is not guaranteed for applications on other kinds of images. We demonstrate this with an in-depth analysis of existing FSOD methods on aerial images and observed a large performance gap compared to natural images. Small objects, more numerous in aerial images, are the cause for the apparent performance gap between natural and aerial images. As a consequence, we improve FSOD performance on small objects with a carefully designed attention mechanism. In addition, we also propose a scale-adaptive box similarity criterion, that improves the training and evaluation of FSOD methods, particularly for small objects. We also contribute to generic FSOD with two distinct approaches based on metric learning and fine-tuning. Impressive results are achieved with the fine-tuning method, which encourages tackling more complex scenarios such as Cross-Domain FSOD. We conduct preliminary experiments in this direction and obtain promising results. Finally, we address the deployment of the detection models inside COSE's systems. Detection must be done in real-time in extremely large images (more than 100 megapixels), with limited computation power. Leveraging existing optimization tools such as TensorRT, we successfully tackle this engineering challenge.

Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetting with task priors, \ie using task identity or a subset of previously seen samples for model training. However, these methods would be infeasible when such priors are unknown in real-world applications. To address this fundamental but seldom-studied problem, we propose a Prior-Free Continual Learning (PFCL) method, which learns new tasks without knowing the task identity or any previous data. First, based on a fixed single-head architecture, we eliminate the need for task identity to select the task-specific output head. Second, we employ a regularization-based strategy for consistent predictions between the new and old models, avoiding revisiting previous samples. However, using this strategy alone often performs poorly in class-incremental scenarios, particularly for a long sequence of tasks. By analyzing the effectiveness and limitations of conventional regularization-based methods, we propose enhancing model consistency with an auxiliary unlabeled dataset additionally. Moreover, since some auxiliary data may degrade the performance, we further develop a reliable sample selection strategy to obtain consistent performance improvement. Extensive experiments on multiple image classification benchmark datasets show that our PFCL method significantly mitigates forgetting in all three learning scenarios. Furthermore, when compared to the most recent rehearsal-based methods that replay a limited number of previous samples, PFCL achieves competitive accuracy. Our code is available at: https://github.com/visiontao/pfcl

In the domain of semi-supervised learning, the current approaches insufficiently exploit the potential of considering inter-instance relationships among (un)labeled data. In this work, we address this limitation by providing an approach for inferring latent graphs that capture the intrinsic data relationships. By leveraging graph-based representations, our approach facilitates the seamless propagation of information throughout the graph, effectively incorporating global and local knowledge. Through evaluations on biomedical tabular datasets, we compare the capabilities of our approach to other contemporary methods. Our work demonstrates the significance of inter-instance relationship discovery as practical means for constructing robust latent graphs to enhance semi-supervised learning techniques. The experiments show that the proposed methodology outperforms contemporary state-of-the-art methods for (semi-)supervised learning on three biomedical datasets.

Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks. However, the self-supervised task knowledge could not be aligned or sometimes conflicted with what the predictions needed. In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model. We use a diffusion model to fully utilize the unlabeled graphs and design two new objectives to guide the model's denoising process with each task's labeled data to generate task-specific graph examples and their labels. Experiments demonstrate that our data-centric approach performs significantly better than fifteen existing various methods on fifteen tasks. The performance improvement brought by unlabeled data is visible as the generated labeled examples unlike the self-supervised learning.

Satellite-based remote sensing missions have revolutionized our understanding of the Ocean state and dynamics. Among them, spaceborne altimetry provides valuable measurements of Sea Surface Height (SSH), which is used to estimate surface geostrophic currents. However, due to the sensor technology employed, important gaps occur in SSH observations. Complete SSH maps are produced by the altimetry community using linear Optimal Interpolations (OI) such as the widely-used Data Unification and Altimeter Combination System (DUACS). However, OI is known for producing overly smooth fields and thus misses some mesostructures and eddies. On the other hand, Sea Surface Temperature (SST) products have much higher data coverage and SST is physically linked to geostrophic currents through advection. We design a realistic twin experiment to emulate the satellite observations of SSH and SST to evaluate interpolation methods. We introduce a deep learning network able to use SST information, and a trainable in two settings: one where we have no access to ground truth during training and one where it is accessible. Our investigation involves a comparative analysis of the aforementioned network when trained using either supervised or unsupervised loss functions. We assess the quality of SSH reconstructions and further evaluate the network's performance in terms of eddy detection and physical properties. We find that it is possible, even in an unsupervised setting to use SST to improve reconstruction performance compared to SST-agnostic interpolations. We compare our reconstructions to DUACS's and report a decrease of 41\% in terms of root mean squared error.

In this paper, we tackle the problem of video alignment, the process of matching the frames of a pair of videos containing similar actions. The main challenge in video alignment is that accurate correspondence should be established despite the differences in the execution processes and appearances between the two videos. We introduce an unsupervised method for alignment that uses global and local features of the frames. In particular, we introduce effective features for each video frame using three machine vision tools: person detection, pose estimation, and VGG network. Then, the features are processed and combined to construct a multidimensional time series that represents the video. The resulting time series are used to align videos of the same actions using a novel version of dynamic time warping named Diagonalized Dynamic Time Warping(DDTW). The main advantage of our approach is that no training is required, which makes it applicable for any new type of action without any need to collect training samples for it. For evaluation, we considered video synchronization and phase classification tasks on the Penn action dataset. Also, for an effective evaluation of the video synchronization task, we present a new metric called Enclosed Area Error(EAE). The results show that our method outperforms previous state-of-the-art methods, such as TCC, and other self-supervised and weakly supervised methods.

Multimodal magnetic resonance imaging (MRI) can reveal different patterns of human tissue and is crucial for clinical diagnosis. However, limited by cost, noise and manual labeling, obtaining diverse and reliable multimodal MR images remains a challenge. For the same lesion, different MRI manifestations have great differences in background information, coarse positioning and fine structure. In order to obtain better generation and segmentation performance, a coordination-spatial attention generation adversarial network (CASP-GAN) based on the cycle-consistent generative adversarial network (CycleGAN) is proposed. The performance of the generator is optimized by introducing the Coordinate Attention (CA) module and the Spatial Attention (SA) module. The two modules can make full use of the captured location information, accurately locating the interested region, and enhancing the generator model network structure. The ability to extract the structure information and the detailed information of the original medical image can help generate the desired image with higher quality. There exist some problems in the original CycleGAN that the training time is long, the parameter amount is too large, and it is difficult to converge. In response to this problem, we introduce the Coordinate Attention (CA) module to replace the Res Block to reduce the number of parameters, and cooperate with the spatial information extraction network above to strengthen the information extraction ability. On the basis of CASP-GAN, an attentional generative cross-modality segmentation (AGCMS) method is further proposed. This method inputs the modalities generated by CASP-GAN and the real modalities into the segmentation network for brain tumor segmentation. Experimental results show that CASP-GAN outperforms CycleGAN and some state-of-the-art methods in PSNR, SSMI and RMSE in most tasks.

We propose XVO, a semi-supervised learning method for training generalized monocular Visual Odometry (VO) models with robust off-the-self operation across diverse datasets and settings. In contrast to standard monocular VO approaches which often study a known calibration within a single dataset, XVO efficiently learns to recover relative pose with real-world scale from visual scene semantics, i.e., without relying on any known camera parameters. We optimize the motion estimation model via self-training from large amounts of unconstrained and heterogeneous dash camera videos available on YouTube. Our key contribution is twofold. First, we empirically demonstrate the benefits of semi-supervised training for learning a general-purpose direct VO regression network. Second, we demonstrate multi-modal supervision, including segmentation, flow, depth, and audio auxiliary prediction tasks, to facilitate generalized representations for the VO task. Specifically, we find audio prediction task to significantly enhance the semi-supervised learning process while alleviating noisy pseudo-labels, particularly in highly dynamic and out-of-domain video data. Our proposed teacher network achieves state-of-the-art performance on the commonly used KITTI benchmark despite no multi-frame optimization or knowledge of camera parameters. Combined with the proposed semi-supervised step, XVO demonstrates off-the-shelf knowledge transfer across diverse conditions on KITTI, nuScenes, and Argoverse without fine-tuning.

Amidst the evolving landscape of artificial intelligence, the convergence of visual and textual information has surfaced as a crucial frontier, leading to the advent of image-text multimodal models. This paper provides a comprehensive review of the evolution and current state of image-text multimodal models, exploring their application value, challenges, and potential research trajectories. Initially, we revisit the basic concepts and developmental milestones of these models, introducing a novel classification that segments their evolution into three distinct phases, based on their time of introduction and subsequent impact on the discipline. Furthermore, based on the tasks' significance and prevalence in the academic landscape, we propose a categorization of the tasks associated with image-text multimodal models into five major types, elucidating the recent progress and key technologies within each category. Despite the remarkable accomplishments of these models, numerous challenges and issues persist. This paper delves into the inherent challenges and limitations of image-text multimodal models, fostering the exploration of prospective research directions. Our objective is to offer an exhaustive overview of the present research landscape of image-text multimodal models and to serve as a valuable reference for future scholarly endeavors. We extend an invitation to the broader community to collaborate in enhancing the image-text multimodal model community, accessible at: \href{https://github.com/i2vec/A-survey-on-image-text-multimodal-models}{https://github.com/i2vec/A-survey-on-image-text-multimodal-models}.