Reconfigurable intelligent surface (RIS) has recently emerged as a promising technology enabling next-generation wireless networks. In this paper, we develop an improved index modulation (IM) scheme by utilizing RIS to convey information. Specifically, we study an RIS-aided multiple-input single-output (MISO) system, in which the information bits are conveyed by reflection patterns of RIS rather than the conventional amplitude-phase constellation. Furthermore, the K-means algorithm is employed to optimize the reflection constellation to improve the error performance. Also, we propose a generalized Gray coding method for mapping information bits to an appropriate reflection constellation and analytically evaluate the error performance of the proposed scheme by deriving a closed-form expression of the average bit error rate (BER). Finally, numerical results verify the accuracy of our theoretical analysis as well as the substantially improved BER performance of the proposed RIS-based IM scheme.
Binary neural network (BNN) is an extreme quantization version of convolutional neural networks (CNNs) with all features and weights mapped to just 1-bit. Although BNN saves a lot of memory and computation demand to make CNN applicable on edge or mobile devices, BNN suffers the drop of network performance due to the reduced representation capability after binarization. In this paper, we propose a new replaceable and easy-to-use convolution module RepConv, which enhances feature maps through replicating input or output along channel dimension by $\beta$ times without extra cost on the number of parameters and convolutional computation. We also define a set of RepTran rules to use RepConv throughout BNN modules like binary convolution, fully connected layer and batch normalization. Experiments demonstrate that after the RepTran transformation, a set of highly cited BNNs have achieved universally better performance than the original BNN versions. For example, the Top-1 accuracy of Rep-ReCU-ResNet-20, i.e., a RepBconv enhanced ReCU-ResNet-20, reaches 88.97% on CIFAR-10, which is 1.47% higher than that of the original network. And Rep-AdamBNN-ReActNet-A achieves 71.342% Top-1 accuracy on ImageNet, a fresh state-of-the-art result of BNNs. Code and models are available at:https://github.com/imfinethanks/Rep_AdamBNN.
Recently, many semi-supervised object detection (SSOD) methods adopt teacher-student framework and have achieved state-of-the-art results. However, the teacher network is tightly coupled with the student network since the teacher is an exponential moving average (EMA) of the student, which causes a performance bottleneck. To address the coupling problem, we propose a Cycle Self-Training (CST) framework for SSOD, which consists of two teachers T1 and T2, two students S1 and S2. Based on these networks, a cycle self-training mechanism is built, i.e., S1${\rightarrow}$T1${\rightarrow}$S2${\rightarrow}$T2${\rightarrow}$S1. For S${\rightarrow}$T, we also utilize the EMA weights of the students to update the teachers. For T${\rightarrow}$S, instead of providing supervision for its own student S1(S2) directly, the teacher T1(T2) generates pseudo-labels for the student S2(S1), which looses the coupling effect. Moreover, owing to the property of EMA, the teacher is most likely to accumulate the biases from the student and make the mistakes irreversible. To mitigate the problem, we also propose a distribution consistency reweighting strategy, where pseudo-labels are reweighted based on distribution consistency across the teachers T1 and T2. With the strategy, the two students S2 and S1 can be trained robustly with noisy pseudo labels to avoid confirmation biases. Extensive experiments prove the superiority of CST by consistently improving the AP over the baseline and outperforming state-of-the-art methods by 2.1% absolute AP improvements with scarce labeled data.
Document Information Extraction (DIE) has attracted increasing attention due to its various advanced applications in the real world. Although recent literature has already achieved competitive results, these approaches usually fail when dealing with complex documents with noisy OCR results or mutative layouts. This paper proposes Generative Multi-modal Network (GMN) for real-world scenarios to address these problems, which is a robust multi-modal generation method without predefined label categories. With the carefully designed spatial encoder and modal-aware mask module, GMN can deal with complex documents that are hard to serialized into sequential order. Moreover, GMN tolerates errors in OCR results and requires no character-level annotation, which is vital because fine-grained annotation of numerous documents is laborious and even requires annotators with specialized domain knowledge. Extensive experiments show that GMN achieves new state-of-the-art performance on several public DIE datasets and surpasses other methods by a large margin, especially in realistic scenes.
Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient robot learning from visual observations. Yet the current approaches typically train a single model end-to-end for learning both visual representations and dynamics, making it difficult to accurately model the interaction between robots and small objects. In this work, we introduce a visual model-based RL framework that decouples visual representation learning and dynamics learning. Specifically, we train an autoencoder with convolutional layers and vision transformers (ViT) to reconstruct pixels given masked convolutional features, and learn a latent dynamics model that operates on the representations from the autoencoder. Moreover, to encode task-relevant information, we introduce an auxiliary reward prediction objective for the autoencoder. We continually update both autoencoder and dynamics model using online samples collected from environment interaction. We demonstrate that our decoupling approach achieves state-of-the-art performance on a variety of visual robotic tasks from Meta-world and RLBench, e.g., we achieve 81.7% success rate on 50 visual robotic manipulation tasks from Meta-world, while the baseline achieves 67.9%. Code is available on the project website: https://sites.google.com/view/mwm-rl.
Modern object detection architectures are moving towards employing self-supervised learning (SSL) to improve performance detection with related pretext tasks. Pretext tasks for monocular 3D object detection have not yet been explored yet in literature. The paper studies the application of established self-supervised bounding box recycling by labeling random windows as the pretext task. The classifier head of the 3D detector is trained to classify random windows containing different proportions of the ground truth objects, thus handling the foreground-background imbalance. We evaluate the pretext task using the RTM3D detection model as baseline, with and without the application of data augmentation. We demonstrate improvements of between 2-3 % in mAP 3D and 0.9-1.5 % BEV scores using SSL over the baseline scores. We propose the inverse class frequency re-weighted (ICFW) mAP score that highlights improvements in detection for low frequency classes in a class imbalanced dataset with long tails. We demonstrate improvements in ICFW both mAP 3D and BEV scores to take into account the class imbalance in the KITTI validation dataset. We see 4-5 % increase in ICFW metric with the pretext task.
Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness. Most existing function approximation theories suggest that with sufficiently many parameters, neural networks can well approximate certain classes of functions in terms of the function value. The neural network themselves, however, can be highly nonsmooth. To bridge this gap, we take convolutional residual networks (ConvResNets) as an example, and prove that large ConvResNets can not only approximate a target function in terms of function value, but also exhibit sufficient first-order smoothness. Moreover, we extend our theory to approximating functions supported on a low-dimensional manifold. Our theory partially justifies the benefits of using deep and wide networks in practice. Numerical experiments on adversarial robust image classification are provided to support our theory.
Implicit feedback is widely leveraged in recommender systems since it is easy to collect and provides weak supervision signals. Recent works reveal a huge gap between the implicit feedback and user-item relevance due to the fact that implicit feedback is also closely related to the item exposure. To bridge this gap, existing approaches explicitly model the exposure and propose unbiased estimators to improve the relevance. Unfortunately, these unbiased estimators suffer from the high gradient variance, especially for long-tail items, leading to inaccurate gradient updates and degraded model performance. To tackle this challenge, we propose a low-variance unbiased estimator from a probabilistic perspective, which effectively bounds the variance of the gradient. Unlike previous works which either estimate the exposure via heuristic-based strategies or use a large biased training set, we propose to estimate the exposure via an unbiased small-scale validation set. Specifically, we first parameterize the user-item exposure by incorporating both user and item information, and then construct an unbiased validation set from the biased training set. By leveraging the unbiased validation set, we adopt bi-level optimization to automatically update exposure-related parameters along with recommendation model parameters during the learning. Experiments on two real-world datasets and two semi-synthetic datasets verify the effectiveness of our method.
Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While effective, contrastive learning approaches introduce sampling bias depending on the data augmentations used, which can degrade performance on downstream tasks. Moreover, these methods are limited to paired image-text data, and cannot leverage widely-available unpaired data. In this paper, we investigate whether a large multimodal model trained purely via masked token prediction, without using modality-specific encoders or contrastive learning, can learn transferable representations for downstream tasks. We propose a simple and scalable network architecture, the Multimodal Masked Autoencoder (M3AE), which learns a unified encoder for both vision and language data via masked token prediction. We provide an empirical study of M3AE trained on a large-scale image-text dataset, and find that M3AE is able to learn generalizable representations that transfer well to downstream tasks. Surprisingly, we find that M3AE benefits from a higher text mask ratio (50-90%), in contrast to BERT whose standard masking ratio is 15%, due to the joint training of two data modalities. We also provide qualitative analysis showing that the learned representation incorporates meaningful information from both image and language. Lastly, we demonstrate the scalability of M3AE with larger model size and training time, and its flexibility to train on both paired image-text data as well as unpaired data.
While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability of models and saliency methods on different tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark at \url{https://xyz} and hope it can facilitate the research in building trustworthy systems.