The YOLO community has been in high spirits since our first two releases! By the advent of Chinese New Year 2023, which sees the Year of the Rabbit, we refurnish YOLOv6 with numerous novel enhancements on the network architecture and the training scheme. This release is identified as YOLOv6 v3.0. For a glimpse of performance, our YOLOv6-N hits 37.5% AP on the COCO dataset at a throughput of 1187 FPS tested with an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 45.0% AP at 484 FPS, outperforming other mainstream detectors at the same scale (YOLOv5-S, YOLOv8-S, YOLOX-S and PPYOLOE-S). Whereas, YOLOv6-M/L also achieve better accuracy performance (50.0%/52.8% respectively) than other detectors at a similar inference speed. Additionally, with an extended backbone and neck design, our YOLOv6-L6 achieves the state-of-the-art accuracy in real-time. Extensive experiments are carefully conducted to validate the effectiveness of each improving component. Our code is made available at https://github.com/meituan/YOLOv6.
Ever since the invention of Bell Laboratories Layer Space-Time (BLAST) in mid 1990s, the focus of MIMO research and development has been largely on pushing the limit of spectral efficiency. While massive MIMO technologies laid the foundation of high throughput in 5G and beyond, energy efficiency of the associated radio system leaves much room for improvement. With the substantial negative implications of climate change looming ever closer, enabling sustainability is of paramount importance for any future technology, and minimizing energy use is a key dimension of achieving sustainability. Thus, every aspect of 6G design, implementation, and operation will be scrutinized to maximize energy efficiency. An analysis of the massive MIMO 5G radio energy consumption at different loads reveals under what specific conditions 6G should outperform 5G, setting qualitative energy efficiency design goals for 6G. Following this, we propose some design principles for the 6G, focusing on novel operational, component technology, and architecture innovations to minimize energy consumption.
While language models have become more capable of producing compelling language, we find there are still gaps in maintaining consistency, especially when describing events in a dynamically changing world. We study the setting of generating narratives in an open world text adventure game, where a graph representation of the underlying game state can be used to train models that consume and output both grounded graph representations and natural language descriptions and actions. We build a large set of tasks by combining crowdsourced and simulated gameplays with a novel dataset of complex actions in order to to construct such models. We find it is possible to improve the consistency of action narration models by training on graph contexts and targets, even if graphs are not present at test time. This is shown both in automatic metrics and human evaluations. We plan to release our code, the new set of tasks, and best performing models.
The purpose of this work was to tackle practical issues which arise when using a tendon-driven robotic manipulator with a long, passive, flexible proximal section in medical applications. A separable robot which overcomes difficulties in actuation and sterilization is introduced, in which the body containing the electronics is reusable and the remainder is disposable. A control input which resolves the redundancy in the kinematics and a physical interpretation of this redundancy are provided. The effect of a static change in the proximal section angle on bending angle error was explored under four testing conditions for a sinusoidal input. Bending angle error increased for increasing proximal section angle for all testing conditions with an average error reduction of 41.48% for retension, 4.28% for hysteresis, and 52.35% for re-tension + hysteresis compensation relative to the baseline case. Two major sources of error in tracking the bending angle were identified: time delay from hysteresis and DC offset from the proximal section angle. Examination of these error sources revealed that the simple hysteresis compensation was most effective for removing time delay and re-tension compensation for removing DC offset, which was the primary source of increasing error. The re-tension compensation was also tested for dynamic changes in the proximal section and reduced error in the final configuration of the tip by 89.14% relative to the baseline case.
The ability to monitor the evolution of topics over time is extremely valuable for businesses. Currently, all existing topic tracking methods use lexical information by matching word usage. However, no studies has ever experimented with the use of semantic information for tracking topics. Hence, we explore a novel semantic-based method using word embeddings. Our results show that a semantic-based approach to topic tracking is on par with the lexical approach but makes different mistakes. This suggest that both methods may complement each other.
Urban air mobility is the new mode of transportation aiming to provide a fast and secure way of travel by utilizing the low-altitude airspace. This goal cannot be achieved without the implementation of new flight regulations which can assure safe and efficient allocation of flight paths to a large number of vertical takeoff/landing aerial vehicles. Such rules should also allow estimating the effective capacity of the low-altitude airspace for planning purposes. Path planning is a vital subject in urban air mobility which could enable a large number of UAVs to fly simultaneously in the airspace without facing the risk of collision. Since urban air mobility is a novel concept, authorities are still working on the redaction of new flight rules applicable to urban air mobility. In this study, an autonomous UAV path planning framework is proposed using a deep reinforcement learning approach and a deep deterministic policy gradient algorithm. The objective is to employ a self-trained UAV to reach its destination in the shortest possible time in any arbitrary environment by adjusting its acceleration. It should avoid collisions with any dynamic or static obstacles and avoid entering prior permission zones existing on its path. The reward function is the determinant factor in the training process. Thus, two different reward function compositions are compared and the chosen composition is deployed to train the UAV by coding the RL algorithm in python. Finally, numerical simulations investigated the success rate of UAVs in different scenarios providing an estimate of the effective airspace capacity.
Background: Deep learning (DL) can extract predictive and prognostic biomarkers from routine pathology slides in colorectal cancer. For example, a DL test for the diagnosis of microsatellite instability (MSI) in CRC has been approved in 2022. Current approaches rely on convolutional neural networks (CNNs). Transformer networks are outperforming CNNs and are replacing them in many applications, but have not been used for biomarker prediction in cancer at a large scale. In addition, most DL approaches have been trained on small patient cohorts, which limits their clinical utility. Methods: In this study, we developed a new fully transformer-based pipeline for end-to-end biomarker prediction from pathology slides. We combine a pre-trained transformer encoder and a transformer network for patch aggregation, capable of yielding single and multi-target prediction at patient level. We train our pipeline on over 9,000 patients from 10 colorectal cancer cohorts. Results: A fully transformer-based approach massively improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training on a large multicenter cohort, we achieve a sensitivity of 0.97 with a negative predictive value of 0.99 for MSI prediction on surgical resection specimens. We demonstrate for the first time that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem. Interpretation: A fully transformer-based end-to-end pipeline trained on thousands of pathology slides yields clinical-grade performance for biomarker prediction on surgical resections and biopsies. Our new methods are freely available under an open source license.
$\textbf{Purpose:}$ The MRI $k$-space acquisition is time consuming. Traditional techniques aim to acquire accelerated data, which in conjunction with recent DL methods, aid in producing high-fidelity images in truncated times. Conventionally, subsampling the $k$-space is performed by utilizing Cartesian-rectilinear trajectories, which even with the use of DL, provide imprecise reconstructions, though, a plethora of non-rectilinear or non-Cartesian trajectories can be implemented in modern MRI scanners. This work investigates the effect of the $k$-space subsampling scheme on the quality of reconstructed accelerated MRI measurements produced by trained DL models. $\textbf{Methods:}$ The RecurrentVarNet was used as the DL-based MRI-reconstruction architecture. Cartesian fully-sampled multi-coil $k$-space measurements from three datasets with different accelerations were retrospectively subsampled using eight distinct subsampling schemes (four Cartesian-rectilinear, two Cartesian non-rectilinear, two non-Cartesian). Experiments were conducted in two frameworks: Scheme-specific, where a distinct model was trained and evaluated for each dataset-subsampling scheme pair, and multi-scheme, where for each dataset a single model was trained on data randomly subsampled by any of the eight schemes and evaluated on data subsampled by all schemes. $\textbf{Results:}$ In the scheme-specific setting RecurrentVarNets trained and evaluated on non-rectilinearly subsampled data demonstrated superior performance especially for high accelerations, whilst in the multi-scheme setting, reconstruction performance on rectilinearly subsampled data improved when compared to the scheme-specific experiments. $\textbf{Conclusion:}$ Training DL-based MRI reconstruction algorithms on non-rectilinearly subsampled measurements can produce more faithful reconstructions.
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data. Recent works for image compression indicate that compression of images based on SMoE models can provide competitive performance to the state-of-the-art. Unfortunately, the iterative model-building process at the encoder comes with excessive computational demands. In this paper we introduce a novel edge-aware Autoencoder (AE) strategy designed to avoid the time-consuming iterative optimization of SMoE models. This is done by directly mapping pixel blocks to model parameters for compression, in spirit similar to recent works on "unfolding" of algorithms, while maintaining full compatibility to the established SMoE framework. With our plug-in AE encoder, we achieve a quantum-leap in performance with encoder run-time savings by a factor of 500 to 1000 with even improved image reconstruction quality. For image compression the plug-in AE encoder has real-time properties and improves RD-performance compared to our previous works.
Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on pushing their accuracy to the state-of-the-art level. However, their latency lags behind sparse convolution-based models (3x slower), hindering their usage in resource-constrained, latency-sensitive applications (such as autonomous driving). This inefficiency comes from point clouds' sparse and irregular nature, whereas transformers are designed for dense, regular workloads. This paper presents FlatFormer to close this latency gap by trading spatial proximity for better computational regularity. We first flatten the point cloud with window-based sorting and partition points into groups of equal sizes rather than windows of equal shapes. This effectively avoids expensive structuring and padding overheads. We then apply self-attention within groups to extract local features, alternate sorting axis to gather features from different directions, and shift windows to exchange features across groups. FlatFormer delivers state-of-the-art accuracy on Waymo Open Dataset with 4.6x speedup over (transformer-based) SST and 1.4x speedup over (sparse convolutional) CenterPoint. This is the first point cloud transformer that achieves real-time performance on edge GPUs and is faster than sparse convolutional methods while achieving on-par or even superior accuracy on large-scale benchmarks. Code to reproduce our results will be made publicly available.