Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and hence poor performance on tail classes with only a few samples. Owing to this paucity of samples, learning on the tail classes is especially challenging for the fine-tuning when transferring a pretrained model to a downstream task. In this work, we present a simple modification of standard fine-tuning to cope with these challenges. Specifically, we propose a two-stage fine-tuning: we first fine-tune the final layer of the pretrained model with class-balanced reweighting loss, and then we perform the standard fine-tuning. Our modification has several benefits: (1) it leverages pretrained representations by only fine-tuning a small portion of the model parameters while keeping the rest untouched; (2) it allows the model to learn an initial representation of the specific task; and importantly (3) it protects the learning of tail classes from being at a disadvantage during the model updating. We conduct extensive experiments on synthetic datasets of both two-class and multi-class tasks of text classification as well as a real-world application to ADME (i.e., absorption, distribution, metabolism, and excretion) semantic labeling. The experimental results show that the proposed two-stage fine-tuning outperforms both fine-tuning with conventional loss and fine-tuning with a reweighting loss on the above datasets.
Vision-Language Pre-training (VLP) models have achieved state-of-the-art performance in numerous cross-modal tasks. Since they are optimized to capture the statistical properties of intra- and inter-modality, there remains risk to learn social biases presented in the data as well. In this work, we (1) introduce a counterfactual-based bias measurement \emph{CounterBias} to quantify the social bias in VLP models by comparing the [MASK]ed prediction probabilities of factual and counterfactual samples; (2) construct a novel VL-Bias dataset including 24K image-text pairs for measuring gender bias in VLP models, from which we observed that significant gender bias is prevalent in VLP models; and (3) propose a VLP debiasing method \emph{FairVLP} to minimize the difference in the [MASK]ed prediction probabilities between factual and counterfactual image-text pairs for VLP debiasing. Although CounterBias and FairVLP focus on social bias, they are generalizable to serve as tools and provide new insights to probe and regularize more knowledge in VLP models.
In this paper, we develop algorithms for joint user scheduling and three types of mmWave link configuration: relay selection, codebook optimization, and beam tracking in millimeter wave (mmWave) networks. Our goal is to design an online controller that dynamically schedules users and configures their links to minimize the system delay. To solve this complex scheduling problem, we model it as a dynamic decision-making process and develop two reinforcement learning-based solutions. The first solution is based on deep reinforcement learning (DRL), which leverages the proximal policy optimization to train a neural network-based solution. Due to the potential high sample complexity of DRL, we also propose an empirical multi-armed bandit (MAB)-based solution, which decomposes the decision-making process into a sequential of sub-actions and exploits classic maxweight scheduling and Thompson sampling to decide those sub-actions. Our evaluation of the proposed solutions confirms their effectiveness in providing acceptable system delay. It also shows that the DRL-based solution has better delay performance while the MAB-based solution has a faster training process.
In this work, we propose PolarBEV for vision-based uneven BEV representation learning. To adapt to the foreshortening effect of camera imaging, we rasterize the BEV space both angularly and radially, and introduce polar embedding decomposition to model the associations among polar grids. Polar grids are rearranged to an array-like regular representation for efficient processing. Besides, to determine the 2D-to-3D correspondence, we iteratively update the BEV surface based on a hypothetical plane, and adopt height-based feature transformation. PolarBEV keeps real-time inference speed on a single 2080Ti GPU, and outperforms other methods for both BEV semantic segmentation and BEV instance segmentation. Thorough ablations are presented to validate the design. The code will be released at \url{https://github.com/SuperZ-Liu/PolarBEV}.
By virtue of the message-passing that implicitly injects collaborative effect into the embedding process, Graph Neural Networks (GNNs) have been successfully adopted in recommendation systems. Nevertheless, most of existing message-passing mechanisms in recommendation are directly inherited from GNNs without any recommendation-tailored modification. Although some efforts have been made towards simplifying GNNs to improve the performance/efficiency of recommendation, no study has comprehensively scrutinized how message-passing captures collaborative effect and whether the captured effect would benefit the prediction of user preferences over items. Therefore, in this work we aim to demystify the collaborative effect captured by message-passing in GNNs and develop new insights towards customizing message-passing for recommendation. First, we theoretically analyze how message-passing captures and leverages the collaborative effect in predicting user preferences. Then, to determine whether the captured collaborative effect would benefit the prediction of user preferences, we propose a recommendation-oriented topological metric, Common Interacted Ratio (CIR), which measures the level of interaction between a specific neighbor of a node with the rest of its neighborhood set. Inspired by our theoretical and empirical analysis, we propose a recommendation-tailored GNN, Augmented Collaboration-Aware Graph Convolutional Network (CAGCN*), that extends upon the LightGCN framework and is able to selectively pass information of neighbors based on their CIR via the Collaboration-Aware Graph Convolution. Experimental results on six benchmark datasets show that CAGCN* outperforms the most representative GNN-based recommendation model, LightGCN, by 9% in Recall@20 and also achieves more than 79% speedup. Our code is publicly available at https://github.com/YuWVandy/CAGCN.
With the rapid development of eXplainable Artificial Intelligence (XAI), a long line of past work has shown concerns about the Out-of-Distribution (OOD) problem in perturbation-based post-hoc XAI models and explanations are socially misaligned. We explore the limitations of post-hoc explanation methods that use approximators to mimic the behavior of black-box models. Then we propose eXplanation-based Counterfactual Retraining (XCR), which extracts feature importance fastly. XCR applies the explanations generated by the XAI model as counterfactual input to retrain the black-box model to address OOD and social misalignment problems. Evaluation of popular image datasets shows that XCR can improve model performance when only retaining 12.5% of the most crucial features without changing the black-box model structure. Furthermore, the evaluation of the benchmark of corruption datasets shows that the XCR is very helpful for improving model robustness and positively impacts the calibration of OOD problems. Even though not calibrated in the validation set like some OOD calibration methods, the corrupted data metric outperforms existing methods. Our method also beats current OOD calibration methods on the OOD calibration metric if calibration on the validation set is applied.
Video restoration, aiming at restoring clear frames from degraded videos, has been attracting increasing attention. Video restoration is required to establish the temporal correspondences from multiple misaligned frames. To achieve that end, existing deep methods generally adopt complicated network architectures, such as integrating optical flow, deformable convolution, cross-frame or cross-pixel self-attention layers, resulting in expensive computational cost. We argue that with proper design, temporal information utilization in video restoration can be much more efficient and effective. In this study, we propose a simple, fast yet effective framework for video restoration. The key of our framework is the grouped spatial-temporal shift, which is simple and lightweight, but can implicitly establish inter-frame correspondences and achieve multi-frame aggregation. Coupled with basic 2D U-Nets for frame-wise encoding and decoding, such an efficient spatial-temporal shift module can effectively tackle the challenges in video restoration. Extensive experiments show that our framework surpasses previous state-of-the-art method with 43% of its computational cost on both video deblurring and video denoising.
Vision transformers have shown great success on numerous computer vision tasks. However, its central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Although linear attention was introduced in natural language processing (NLP) tasks to mitigate a similar issue, directly applying existing linear attention to vision transformers may not lead to satisfactory results. We investigate this problem and find that computer vision tasks focus more on local information compared with NLP tasks. Based on this observation, we present a Vicinity Attention that introduces a locality bias to vision transformers with linear complexity. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance measured by its neighbouring patches. In this case, the neighbouring patches will receive stronger attention than far-away patches. Moreover, since our Vicinity Attention requires the token length to be much larger than the feature dimension to show its efficiency advantages, we further propose a new Vicinity Vision Transformer (VVT) structure to reduce the feature dimension without degenerating the accuracy. We perform extensive experiments on the CIFAR100, ImageNet1K, and ADE20K datasets to validate the effectiveness of our method. Our method has a slower growth rate of GFlops than previous transformer-based and convolution-based networks when the input resolution increases. In particular, our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous methods.
With the rapid development of wireless communication technology, wireless access points (AP) and internet of things (IoT) devices have been widely deployed in our surroundings. Various types of wireless signals (e.g., Wi-Fi, LoRa, LTE) are filling out our living and working spaces. Previous researches reveal the fact that radio waves are modulated by the spatial structure during the propagation process (e.g., reflection, diffraction, and scattering) and superimposed on the receiver. This observation allows us to reconstruct the surrounding environment based on received wireless signals, called "wireless sensing". Wireless sensing is an emerging technology that enables a wide range of applications, such as gesture recognition for human-computer interaction, vital signs monitoring for health care, and intrusion detection for security management. Compared with other sensing paradigms, such as vision-based and IMU-based sensing, wireless sensing solutions have unique advantages such as high coverage, pervasiveness, low cost, and robustness under adverse light and texture scenarios. Besides, wireless sensing solutions are generally lightweight in terms of both computation overhead and device size. This tutorial takes Wi-Fi sensing as an example. It introduces both the theoretical principles and the code implementation of data collection, signal processing, features extraction, and model design. In addition, this tutorial highlights state-of-the-art deep learning models (e.g., CNN, RNN, and adversarial learning models) and their applications in wireless sensing systems. We hope this tutorial will help people in other research fields to break into wireless sensing research and learn more about its theories, designs, and implementation skills, promoting prosperity in the wireless sensing research field.