亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Recent advances in large-scale vision-language models have achieved very impressive performance in various zero-shot image classification tasks. While prior studies have demonstrated significant improvements by introducing few-shot labelled target samples, they still require labelling of target samples, which greatly degrades their scalability while handling various visual recognition tasks. We design NtUA, a Noise-tolerant Unsupervised Adapter that allows learning superior target models with few-shot unlabelled target samples. NtUA works as a key-value cache that formulates visual features and predicted pseudo-labels of the few-shot unlabelled target samples as key-value pairs. It consists of two complementary designs. The first is adaptive cache formation that combats pseudo-label noises by weighting the key-value pairs according to their prediction confidence. The second is pseudo-label rectification, which corrects both pair values (i.e., pseudo-labels) and cache weights by leveraging knowledge distillation from large-scale vision language models. Extensive experiments show that NtUA achieves superior performance consistently across multiple widely adopted benchmarks.

The range of robot activities is expanding from industries with fixed environments to diverse and changing environments, such as nursing care support and daily life support. In particular, autonomous construction of robots that are personalized for each user and task is required. Therefore, we develop an actuator module that can be reconfigured to various link configurations, can carry heavy objects using a locking mechanism, and can be easily operated by human teaching using a releasing mechanism. Given multiple target coordinates, a modular robot configuration that satisfies these coordinates and minimizes the required torque is automatically generated by Tree-structured Parzen Estimator (TPE), a type of black-box optimization. Based on the obtained results, we show that the robot can be reconfigured to perform various functions such as moving monitors and lights, serving food, and so on.

Learning-based approaches to autonomous vehicle planners have the potential to scale to many complicated real-world driving scenarios by leveraging huge amounts of driver demonstrations. However, prior work only learns to estimate a single planning trajectory, while there may be multiple acceptable plans in real-world scenarios. To solve the problem, we propose an interpretable neural planner to regress a heatmap, which effectively represents multiple potential goals in the bird's-eye view of an autonomous vehicle. The planner employs an adaptive Gaussian kernel and relaxed hourglass loss to better capture the uncertainty of planning problems. We also use a negative Gaussian kernel to add supervision to the heatmap regression, enabling the model to learn collision avoidance effectively. Our systematic evaluation on the Lyft Open Dataset across a diverse range of real-world driving scenarios shows that our model achieves a safer and more flexible driving performance than prior works.

We investigate the use of transformer sequence models as dynamics models (TDMs) for control. We find that TDMs exhibit strong generalization capabilities to unseen environments, both in a few-shot setting, where a generalist TDM is fine-tuned with small amounts of data from the target environment, and in a zero-shot setting, where a generalist TDM is applied to an unseen environment without any further training. Here, we demonstrate that generalizing system dynamics can work much better than generalizing optimal behavior directly as a policy. Additional results show that TDMs also perform well in a single-environment learning setting when compared to a number of baseline models. These properties make TDMs a promising ingredient for a foundation model of control.

Nonlinear model predictive control (NMPC) is typically restricted to short, finite horizons to limit the computational burden of online optimization. This makes a global planner necessary to avoid local minima when using NMPC for navigation in complex environments. For this reason, the performance of NMPC approaches are often limited by that of the global planner. While control policies trained with reinforcement learning (RL) can theoretically learn to avoid such local minima, they are usually unable to guarantee enforcement of general state constraints. In this paper, we augment a sampling-based stochastic NMPC (SNMPC) approach with an RL trained perception-informed value function. This allows the system to avoid observable local minima in the environment by reasoning about perception information beyond the finite planning horizon. By using Probably Approximately Correct NMPC (PAC-NMPC) as our base controller, we are also able to generate statistical guarantees of performance and safety. We demonstrate our approach in simulation and on hardware using a 1/10th scale rally car with lidar.

The standard vector autoregressive (VAR) models suffer from overparameterization which is a serious issue for high-dimensional time series data as it restricts the number of variables and lags that can be incorporated into the model. Several statistical methods, such as the reduced-rank model for multivariate (multiple) time series (Velu et al., 1986; Reinsel and Velu, 1998; Reinsel et al., 2022) and the Envelope VAR model (Wang and Ding, 2018), provide solutions for achieving dimension reduction of the parameter space of the VAR model. However, these methods can be inefficient in extracting relevant information from complex data, as they fail to distinguish between relevant and irrelevant information, or they are inefficient in addressing the rank deficiency problem. We put together the idea of envelope models into the reduced-rank VAR model to simultaneously tackle these challenges, and propose a new parsimonious version of the classical VAR model called the reduced-rank envelope VAR (REVAR) model. Our proposed REVAR model incorporates the strengths of both reduced-rank VAR and envelope VAR models and leads to significant gains in efficiency and accuracy. The asymptotic properties of the proposed estimators are established under different error assumptions. Simulation studies and real data analysis are conducted to evaluate and illustrate the proposed method.

High-speed autonomous driving in off-road environments has immense potential for various applications, but it also presents challenges due to the complexity of vehicle-terrain interactions. In such environments, it is crucial for the vehicle to predict its motion and adjust its controls proactively in response to environmental changes, such as variations in terrain elevation. To this end, we propose a method for learning terrain-aware kinodynamic model which is conditioned on both proprioceptive and exteroceptive information. The proposed model generates reliable predictions of 6-degree-of-freedom motion and can even estimate contact interactions without requiring ground truth force data during training. This enables the design of a safe and robust model predictive controller through appropriate cost function design which penalizes sampled trajectories with unstable motion, unsafe interactions, and high levels of uncertainty derived from the model. We demonstrate the effectiveness of our approach through experiments on a simulated off-road track, showing that our proposed model-controller pair outperforms the baseline and ensures robust high-speed driving performance without control failure.

Intelligent reflecting surface (IRS) has emerged as a promising technique to extend the wireless signal coverage of access point (AP) and improve the communication performance cost-effectively. In order to reduce the path-loss of the cascaded user-IRS-AP channels, the IRS-integrated AP architecture has been proposed to deploy the IRSs and the antenna array of the AP within the same antenna radome. To reduce the pilot overhead for estimating all IRS-involved channels, in this paper, we propose a novel codebook-based IRS reflection design for the IRS-integrated AP to enhance the coverage performance in a given area. In particular, the codebook consisting of a small number of codewords is designed offline by employing an efficient sector division strategy based on the azimuth angle. To ensure the performance of each sector, we optimize its corresponding codeword for IRS reflection pattern to maximize the sector-min-average-effective-channel-power (SMAECP) by applying the alternating optimization (AO) and semidefinite relaxation (SDR) methods. With the designed codebook, the AP performs the IRS reflection training by sequentially applying all codewords and selects the one achieving the best communication performance for data transmission. Numerical results show that our proposed codebook design can enhance the average channel power of the whole coverage area, as compared to the system without IRS. Moreover, our proposed codebook-based IRS reflection design is shown to achieve significant performance gain over other benchmark schemes in both single-user and multi-user transmissions.

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) introduces the concept of prompt learning -- a recent trend in NLP -- to the vision domain for adapting pre-trained vision-language models. Specifically, CoOp turns context words in a prompt into a set of learnable vectors and, with only a few labeled images for learning, can achieve huge improvements over intensively-tuned manual prompts. In our study we identify a critical problem of CoOp: the learned context is not generalizable to wider unseen classes within the same dataset, suggesting that CoOp overfits base classes observed during training. To address the problem, we propose Conditional Context Optimization (CoCoOp), which extends CoOp by further learning a lightweight neural network to generate for each image an input-conditional token (vector). Compared to CoOp's static prompts, our dynamic prompts adapt to each instance and are thus less sensitive to class shift. Extensive experiments show that CoCoOp generalizes much better than CoOp to unseen classes, even showing promising transferability beyond a single dataset; and yields stronger domain generalization performance as well. Code is available at //github.com/KaiyangZhou/CoOp.

This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.