目前，神经网络模型的量化方法主要分为训练后量化（PTQ）和量化意识培训（QAT）。培训后量化仅需要一小部分数据即可完成量化过程，但是其定量模型的性能不如量化意识培训。本文提出了一种新颖的量化方法，称为注意弹。该方法给出了参数w有机会映射到所有可能的量化值，而不仅仅是在量化过程中w附近的两个量化值。被映射到不同量化值的概率与量化值和W之间的距离负相关，并随高斯函数衰减。此外，本文使用有损耗的编码长度作为衡量标准，将位宽度分配给模型的不同层以解决混合精度量化的问题，从而有效避免了解决组合优化问题。本文还对不同模型进行了定量实验，结果证实了该方法的有效性。对于RESNET18和MOBILENETV2，本文提出的后培训量化仅需要1,024个培训数据和10分钟即可完成量化过程，这可以在量化意识培训的情况下实现量化性能。

Molecular representation learning is crucial for the problem of molecular property prediction, where graph neural networks (GNNs) serve as an effective solution due to their structure modeling capabilities. Since labeled data is often scarce and expensive to obtain, it is a great challenge for GNNs to generalize in the extensive molecular space. Recently, the training paradigm of "pre-train, fine-tune" has been leveraged to improve the generalization capabilities of GNNs. It uses self-supervised information to pre-train the GNN, and then performs fine-tuning to optimize the downstream task with just a few labels. However, pre-training does not always yield statistically significant improvement, especially for self-supervised learning with random structural masking. In fact, the molecular structure is characterized by motif subgraphs, which are frequently occurring and influence molecular properties. To leverage the task-related motifs, we propose a novel paradigm of "pre-train, prompt, fine-tune" for molecular representation learning, named molecule continuous prompt tuning (MolCPT). MolCPT defines a motif prompting function that uses the pre-trained model to project the standalone input into an expressive prompt. The prompt effectively augments the molecular graph with meaningful motifs in the continuous representation space; this provides more structural patterns to aid the downstream classifier in identifying molecular properties. Extensive experiments on several benchmark datasets show that MolCPT efficiently generalizes pre-trained GNNs for molecular property prediction, with or without a few fine-tuning steps.

Adder Neural Network (AdderNet) provides a new way for developing energy-efficient neural networks by replacing the expensive multiplications in convolution with cheaper additions (i.e.l1-norm). To achieve higher hardware efficiency, it is necessary to further study the low-bit quantization of AdderNet. Due to the limitation that the commutative law in multiplication does not hold in l1-norm, the well-established quantization methods on convolutional networks cannot be applied on AdderNets. Thus, the existing AdderNet quantization techniques propose to use only one shared scale to quantize both the weights and activations simultaneously. Admittedly, such an approach can keep the commutative law in the l1-norm quantization process, while the accuracy drop after low-bit quantization cannot be ignored. To this end, we first thoroughly analyze the difference on distributions of weights and activations in AdderNet and then propose a new quantization algorithm by redistributing the weights and the activations. Specifically, the pre-trained full-precision weights in different kernels are clustered into different groups, then the intra-group sharing and inter-group independent scales can be adopted. To further compensate the accuracy drop caused by the distribution difference, we then develop a lossless range clamp scheme for weights and a simple yet effective outliers clamp strategy for activations. Thus, the functionality of full-precision weights and the representation ability of full-precision activations can be fully preserved. The effectiveness of the proposed quantization method for AdderNet is well verified on several benchmarks, e.g., our 4-bit post-training quantized adder ResNet-18 achieves an 66.5% top-1 accuracy on the ImageNet with comparable energy efficiency, which is about 8.5% higher than that of the previous AdderNet quantization methods.

Recognition of facial expression is a challenge when it comes to computer vision. The primary reasons are class imbalance due to data collection and uncertainty due to inherent noise such as fuzzy facial expressions and inconsistent labels. However, current research has focused either on the problem of class imbalance or on the problem of uncertainty, ignoring the intersection of how to address these two problems. Therefore, in this paper, we propose a framework based on Resnet and Attention to solve the above problems. We design weight for each class. Through the penalty mechanism, our model will pay more attention to the learning of small samples during training, and the resulting decrease in model accuracy can be improved by a Convolutional Block Attention Module (CBAM). Meanwhile, our backbone network will also learn an uncertain feature for each sample. By mixing uncertain features between samples, the model can better learn those features that can be used for classification, thus suppressing uncertainty. Experiments show that our method surpasses most basic methods in terms of accuracy on facial expression data sets (e.g., AffectNet, RAF-DB), and it also solves the problem of class imbalance well.

We discuss two kinds of semantics relevant to Computer Vision (CV) systems - Visual Semantics and Lexical Semantics. While visual semantics focus on how humans build concepts when using vision to perceive a target reality, lexical semantics focus on how humans build concepts of the same target reality through the use of language. The lack of coincidence between visual and lexical semantics, in turn, has a major impact on CV systems in the form of the Semantic Gap Problem (SGP). The paper, while extensively exemplifying the lack of coincidence as above, introduces a general, domain-agnostic methodology to enforce alignment between visual and lexical semantics.

Recently, the self-supervised pre-training paradigm has shown great potential in leveraging large-scale unlabeled data to improve downstream task performance. However, increasing the scale of unlabeled pre-training data in real-world scenarios requires prohibitive computational costs and faces the challenge of uncurated samples. To address these issues, we build a task-specific self-supervised pre-training framework from a data selection perspective based on a simple hypothesis that pre-training on the unlabeled samples with similar distribution to the target task can bring substantial performance gains. Buttressed by the hypothesis, we propose the first yet novel framework for Scalable and Efficient visual Pre-Training (SEPT) by introducing a retrieval pipeline for data selection. SEPT first leverage a self-supervised pre-trained model to extract the features of the entire unlabeled dataset for retrieval pipeline initialization. Then, for a specific target task, SEPT retrievals the most similar samples from the unlabeled dataset based on feature similarity for each target instance for pre-training. Finally, SEPT pre-trains the target model with the selected unlabeled samples in a self-supervised manner for target data finetuning. By decoupling the scale of pre-training and available upstream data for a target task, SEPT achieves high scalability of the upstream dataset and high efficiency of pre-training, resulting in high model architecture flexibility. Results on various downstream tasks demonstrate that SEPT can achieve competitive or even better performance compared with ImageNet pre-training while reducing the size of training samples by one magnitude without resorting to any extra annotations.

In this paper, we present ExtremeBERT, a toolkit for accelerating and customizing BERT pretraining. Our goal is to provide an easy-to-use BERT pretraining toolkit for the research community and industry. Thus, the pretraining of popular language models on customized datasets is affordable with limited resources. Experiments show that, to achieve the same or better GLUE scores, the time cost of our toolkit is over $6\times$ times less for BERT Base and $9\times$ times less for BERT Large when compared with the original BERT paper. The documentation and code are released at https://github.com/extreme-bert/extreme-bert under the Apache-2.0 license.

机载激光扫描（ALS）点云的分类是遥感和摄影测量场的关键任务。尽管最近基于深度学习的方法取得了令人满意的表现，但他们忽略了接受场的统一性，这使得ALS点云分类对于区分具有复杂结构和极端规模变化的区域仍然具有挑战性。在本文中，为了配置多受感受性的场特征，我们提出了一个新型的接受场融合和分层网络（RFFS-NET）。以新颖的扩张图卷积（DGCONV）及其扩展环形扩张卷积（ADCONV）作为基本的构建块，使用扩张和环形图融合（Dagfusion）模块实现了接受场融合过程，该模块获得了多受感染的场特征代表通过捕获带有各种接收区域的扩张和环形图。随着计算碱基的计算基础，使用嵌套在RFFS-NET中的多级解码器进行的接收场的分层，并由多层接受场聚集损失（MRFALOSS）驱动，以驱动网络驱动网络以学习在具有不同分辨率的监督标签的方向。通过接受场融合和分层，RFFS-NET更适应大型ALS点云中具有复杂结构和极端尺度变化区域的分类。在ISPRS Vaihingen 3D数据集上进行了评估，我们的RFFS-NET显着优于MF1的基线方法5.3％，而MIOU的基线方法的总体准确性为82.1％，MF1的总准确度为71.6％，MIOU的MF1和MIOU为58.2％。此外，LASDU数据集和2019 IEEE-GRSS数据融合竞赛数据集的实验显示，RFFS-NET可以实现新的最新分类性能。

几次动作识别中面临的主要挑战是培训视频数据不足。为了解决此问题，该领域中的当前方法主要集中于在功能级别上设计算法，而对处理输入视频数据的关注很少。此外，现有的框架采样策略可能会省略时间和空间维度的关键行动信息，从而进一步影响视频利用效率。在本文中，我们提出了一个新颖的视频框架采样器，以进行几次动作识别以解决此问题，其中特定于任务的空间框架采样是通过时间选择器（TS）和空间放大器（SA）实现的。具体而言，我们的采样器首先以较小的计算成本扫描整个视频，以获得对视频帧的全球感知。 TS在选择最显着，随后的贡献的顶级框架方面发挥了作用。 SA通过使用显着图的指导来扩大关键区域来强调每个框架的歧视性信息。我们进一步采用任务自适应学习，根据手头的情节任务动态调整采样策略。 TS和SA的实现均可以端到端的优化为基础，从而通过大多数少数发动的动作识别方法促进了我们所提出的采样器的无缝集成。广泛的实验表明，在包括长期视频在内的各种基准测试中的表演都有显着提高。

降解的图像通常存在于字符图像的一般来源中，从而导致特征识别结果不令人满意。现有的方法有专门的努力来恢复降级的角色图像。但是，这些方法获得的降解结果似乎并不能提高字符识别性能。这主要是因为当前方法仅着眼于像素级信息，而忽略了角色的关键特征，例如其字形，从而在脱索过程中导致字符标志性损害。在本文中，我们介绍了一个基于字形融合和注意力机制（即Churformer）的新型通用框架，以精确地恢复角色图像而不改变其固有的字形。与现有的框架不同，Charformer引入了一个并行目标任务，用于捕获其他信息并将其注入DICONISE骨架的图像，这将在字符图像DeNoising期间保持角色字形的一致性。此外，我们利用基于注意力的网络进行全局本地特征交互，这将有助于处理盲目的denoising和增强deNoSising绩效。我们将Charformer与多个数据集上的最新方法进行比较。实验结果表明了杂形和质量上的优势。