时间序列数据的积累和标签的不存在使时间序列异常检测（AD）是自我监督的深度学习任务。基于单拟合的方法只能触及整个正态性的某些方面，不足以检测各种异常。其中，AD采用的对比度学习方法总是选择正常的负面对，这是反对AD任务的目的。现有的基于多促进的方法通常是两阶段的，首先应用了训练过程，其目标可能与AD不同，因此性能受到预训练的表示的限制。本文提出了一种深层对比的单级异常检测方法（COCA），该方法结合了对比度学习和一级分类的正态性假设。关键思想是将表示和重建表示形式视为无阴性对比度学习的积极对，我们将其命名为序列对比。然后，我们应用了由不变性和方差项组成的对比度损失函数，前者同时优化了这两个假设的损失，后者则防止了超晶体崩溃。在四个现实世界中的时间序列数据集上进行的广泛实验表明，所提出的方法的卓越性能达到了最新。该代码可在https://github.com/ruiking04/coca上公开获得。

Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of description where the sentences describe different segments of the video, by matching all sentence-clip pairs, the paragraph and the full video are aligned implicitly. However, such unit-level similarity measure may ignore the global temporal context over a long time span, which inevitably limits the generalization ability. In this paper, we propose a contrastive learning framework TempCLR to compare the full video and the paragraph explicitly. As the video/paragraph is formulated as a sequence of clips/sentences, under the constraint of their temporal order, we use dynamic time warping to compute the minimum cumulative cost over sentence-clip pairs as the sequence-level distance. To explore the temporal dynamics, we break the consistency of temporal order by shuffling the video clips or sentences according to the temporal granularity. In this way, we obtain the representations for clips/sentences, which perceive the temporal information and thus facilitate the sequence alignment. In addition to pre-training on the video and paragraph, our approach can also generalize on the matching between different video instances. We evaluate our approach on video retrieval, action step localization, and few-shot action recognition, and achieve consistent performance gain over all three tasks. Detailed ablation studies are provided to justify the approach design.

Semi-supervised learning (SSL) has made significant strides in the field of remote sensing. Finding a large number of labeled datasets for SSL methods is uncommon, and manually labeling datasets is expensive and time-consuming. Furthermore, accurately identifying remote sensing satellite images is more complicated than it is for conventional images. Class-imbalanced datasets are another prevalent phenomenon, and models trained on these become biased towards the majority classes. This becomes a critical issue with an SSL model's subpar performance. We aim to address the issue of labeling unlabeled data and also solve the model bias problem due to imbalanced datasets while achieving better accuracy. To accomplish this, we create "artificial" labels and train a model to have reasonable accuracy. We iteratively redistribute the classes through resampling using a distribution alignment technique. We use a variety of class imbalanced satellite image datasets: EuroSAT, UCM, and WHU-RS19. On UCM balanced dataset, our method outperforms previous methods MSMatch and FixMatch by 1.21% and 0.6%, respectively. For imbalanced EuroSAT, our method outperforms MSMatch and FixMatch by 1.08% and 1%, respectively. Our approach significantly lessens the requirement for labeled data, consistently outperforms alternative approaches, and resolves the issue of model bias caused by class imbalance in datasets.

Using a Bayesian network to analyze the causal relationship between nodes is a hot spot. The existing network learning algorithms are mainly constraint-based and score-based network generation methods. The constraint-based method is mainly the application of conditional independence (CI) tests, but the inaccuracy of CI tests in the case of high dimensionality and small samples has always been a problem for the constraint-based method. The score-based method uses the scoring function and search strategy to find the optimal candidate network structure, but the search space increases too much with the increase of the number of nodes, and the learning efficiency is very low. This paper presents a new hybrid algorithm, MCME (multiple compound memory erasing). This method retains the advantages of the first two methods, solves the shortcomings of the above CI tests, and makes innovations in the scoring function in the direction discrimination stage. A large number of experiments show that MCME has better or similar performance than some existing algorithms.

End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on handcrafted composition models. However, existing generative methods still have plenty of room for improvement in quantitative performance. More crucially, these methods are considered black boxes due to weak interpretability and there is rarely a theory trying to explain their mechanism and learning process. In this study, we try to re-interpret these generative methods for image restoration tasks using information theory. Different from conventional understanding, we analyzed the information flow of these methods and identified three sources of information (extracted high-level information, retained low-level information, and external information that is absent from the source inputs) are involved and optimized respectively in generating the restoration results. We further derived their learning behaviors, optimization objectives, and the corresponding information boundaries by extending the information bottleneck principle. Based on this theoretic framework, we found that many existing generative methods tend to be direct applications of the general models designed for conventional generation tasks, which may suffer from problems including over-invested abstraction processes, inherent details loss, and vanishing gradients or imbalance in training. We analyzed these issues with both intuitive and theoretical explanations and proved them with empirical evidence respectively. Ultimately, we proposed general solutions or ideas to address the above issue and validated these approaches with performance boosts on six datasets of three different image restoration tasks.

This work focuses on 3D Radar imaging inverse problems. Current methods obtain undifferentiated results that suffer task-depended information retrieval loss and thus don't meet the task's specific demands well. For example, biased scattering energy may be acceptable for screen imaging but not for scattering diagnosis. To address this issue, we propose a new task-oriented imaging framework. The imaging principle is task-oriented through an analysis phase to obtain task's demands. The imaging model is multi-cognition regularized to embed and fulfill demands. The imaging method is designed to be general-ized, where couplings between cognitions are decoupled and solved individually with approximation and variable-splitting techniques. Tasks include scattering diagnosis, person screen imaging, and parcel screening imaging are given as examples. Experiments on data from two systems indicate that the pro-posed framework outperforms the current ones in task-depended information retrieval.

Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

In massive multiple-input multiple-output (MIMO) systems, the user equipment (UE) needs to feed the channel state information (CSI) back to the base station (BS) for the following beamforming. But the large scale of antennas in massive MIMO systems causes huge feedback overhead. Deep learning (DL) based methods can compress the CSI at the UE and recover it at the BS, which reduces the feedback cost significantly. But the compressed CSI must be quantized into bit streams for transmission. In this paper, we propose an adaptor-assisted quantization strategy for bit-level DL-based CSI feedback. First, we design a network-aided adaptor and an advanced training scheme to adaptively improve the quantization and reconstruction accuracy. Moreover, for easy practical employment, we introduce the expert knowledge of data distribution and propose a pluggable and cost-free adaptor scheme. Experiments show that compared with the state-of-the-art feedback quantization method, this adaptor-aided quantization strategy can achieve better quantization accuracy and reconstruction performance with less or no additional cost. The open-source codes are available at https://github.com/zhangxd18/QCRNet.

We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. This flash-only image is visually reflection-free and thus can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR. We extend our approach to handheld photography to address the misalignment between the flash and no-flash pair. With misaligned training data and the alignment module, our aligned model outperforms our previous version by more than 3.19dB in PSNR on a misaligned dataset. We also study using linear RGB images as training data. Our source code and dataset are publicly available at https://github.com/ChenyangLEI/flash-reflection-removal.

Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles. Existing methods focus on capturing the overall visual scene of each frame, ignoring fine-grained argument-level information. Inspired by the definition of events as changes of states, we propose a novel framework to detect video events by tracking the changes in the visual states of all involved arguments, which are expected to provide the most informative evidence for the extraction of video events. In order to capture the visual state changes of arguments, we decompose them into changes in pixels within objects, displacements of objects, and interactions among multiple arguments. We further propose Object State Embedding, Object Motion-aware Embedding and Argument Interaction Embedding to encode and track these changes respectively. Experiments on various video event extraction tasks demonstrate significant improvements compared to state-of-the-art models. In particular, on verb classification, we achieve 3.49% absolute gains (19.53% relative gains) in F1@5 on Video Situation Recognition.