For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing. In various computer perception tasks for AVs, it may be helpful to match landmark patches taken by an onboard camera with other landmark patches captured at a different time or saved in a street scene image database. To perform matching under challenging driving environments caused by changing seasons, weather, and illumination, we utilize the spatial neighborhood information of each patch. We propose an approach, named RobustMat, which derives its robustness to perturbations from neural differential equations. A convolutional neural ODE diffusion module is used to learn the feature representation for the landmark patches. A graph neural PDE diffusion module then aggregates information from neighboring landmark patches in the street scene. Finally, feature similarity learning outputs the final matching score. Our approach is evaluated on several street scene datasets and demonstrated to achieve state-of-the-art matching results under environmental perturbations.
相關內容
Despite the current surge of interest in autonomous robotic systems, robot activity recognition within restricted indoor environments remains a formidable challenge. Conventional methods for detecting and recognizing robotic arms' activities often rely on vision-based or light detection and ranging (LiDAR) sensors, which require line-of-sight (LoS) access and may raise privacy concerns, for example, in nursing facilities. This research pioneers an innovative approach harnessing channel state information (CSI) measured from WiFi signals, subtly influenced by the activity of robotic arms. We developed an attention-based network to classify eight distinct activities performed by a Franka Emika robotic arm in different situations. Our proposed bidirectional vision transformer-concatenated (BiVTC) methodology aspires to predict robotic arm activities accurately, even when trained on activities with different velocities, all without dependency on external or internal sensors or visual aids. Considering the high dependency of CSI data to the environment, motivated us to study the problem of sniffer location selection, by systematically changing the sniffer's location and collecting different sets of data. Finally, this paper also marks the first publication of the CSI data of eight distinct robotic arm activities, collectively referred to as RoboFiSense. This initiative aims to provide a benchmark dataset and baselines to the research community, fostering advancements in the field of robotics sensing.
Recent work demonstrates that, after being fine-tuned on a high-quality instruction dataset, the resulting model can obtain impressive capabilities to address a wide range of tasks. However, existing methods for instruction data generation often produce duplicate data and are not controllable enough on data quality. In this paper, we extend the generalization of instruction tuning by classifying the instruction data to 4 code-related tasks and propose a LLM-based Generator-Discriminator data process framework to generate diverse, high-quality instruction data from open source code. Hence, we introduce CodeOcean, a dataset comprising 20,000 instruction instances across 4 universal code-related tasks,which is aimed at augmenting the effectiveness of instruction tuning and improving the generalization ability of fine-tuned model. Subsequently, we present WaveCoder, a fine-tuned Code LLM with Widespread And Versatile Enhanced instruction tuning. This model is specifically designed for enhancing instruction tuning of Code Language Models (LLMs). Our experiments demonstrate that Wavecoder models outperform other open-source models in terms of generalization ability across different code-related tasks at the same level of fine-tuning scale. Moreover, Wavecoder exhibits high efficiency in previous code generation tasks. This paper thus offers a significant contribution to the field of instruction data generation and fine-tuning models, providing new insights and tools for enhancing performance in code-related tasks.
Unsupervised depth completion methods are trained by minimizing sparse depth and image reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data augmentation schemes that affect image reconstruction quality, and thus the training signal. Hence, typical augmentations on images viewed as essential to training pipelines in other vision tasks have seen limited use beyond small image intensity changes and flipping. The sparse depth modality have seen even less as intensity transformations alter the scale of the 3D scene, and geometric transformations may decimate the sparse points during resampling. We propose a method that unlocks a wide range of previously-infeasible geometric augmentations for unsupervised depth completion. This is achieved by reversing, or ``undo"-ing, geometric transformations to the coordinates of the output depth, warping the depth map back to the original reference frame. This enables computing the reconstruction losses using the original images and sparse depth maps, eliminating the pitfalls of naive loss computation on the augmented inputs. This simple yet effective strategy allows us to scale up augmentations to boost performance. We demonstrate our method on indoor (VOID) and outdoor (KITTI) datasets where we improve upon three existing methods by an average of 11.75% across both datasets.
The accelerated proliferation of visual content and the rapid development of machine vision technologies bring significant challenges in delivering visual data on a gigantic scale, which shall be effectively represented to satisfy both human and machine requirements. In this work, we investigate how hierarchical representations derived from the advanced generative prior facilitate constructing an efficient scalable coding paradigm for human-machine collaborative vision. Our key insight is that by exploiting the StyleGAN prior, we can learn three-layered representations encoding hierarchical semantics, which are elaborately designed into the basic, middle, and enhanced layers, supporting machine intelligence and human visual perception in a progressive fashion. With the aim of achieving efficient compression, we propose the layer-wise scalable entropy transformer to reduce the redundancy between layers. Based on the multi-task scalable rate-distortion objective, the proposed scheme is jointly optimized to achieve optimal machine analysis performance, human perception experience, and compression ratio. We validate the proposed paradigm's feasibility in face image compression. Extensive qualitative and quantitative experimental results demonstrate the superiority of the proposed paradigm over the latest compression standard Versatile Video Coding (VVC) in terms of both machine analysis as well as human perception at extremely low bitrates ($<0.01$ bpp), offering new insights for human-machine collaborative compression.
MARS: Multi-Scale Adaptive Robotics Vision for Underwater Object Detection and Domain Generalization
Underwater robotic vision encounters significant challenges, necessitating advanced solutions to enhance performance and adaptability. This paper presents MARS (Multi-Scale Adaptive Robotics Vision), a novel approach to underwater object detection tailored for diverse underwater scenarios. MARS integrates Residual Attention YOLOv3 with Domain-Adaptive Multi-Scale Attention (DAMSA) to enhance detection accuracy and adapt to different domains. During training, DAMSA introduces domain class-based attention, enabling the model to emphasize domain-specific features. Our comprehensive evaluation across various underwater datasets demonstrates MARS's performance. On the original dataset, MARS achieves a mean Average Precision (mAP) of 58.57\%, showcasing its proficiency in detecting critical underwater objects like echinus, starfish, holothurian, scallop, and waterweeds. This capability holds promise for applications in marine robotics, marine biology research, and environmental monitoring. Furthermore, MARS excels at mitigating domain shifts. On the augmented dataset, which incorporates all enhancements (+Domain +Residual+Channel Attention+Multi-Scale Attention), MARS achieves an mAP of 36.16\%. This result underscores its robustness and adaptability in recognizing objects and performing well across a range of underwater conditions. The source code for MARS is publicly available on GitHub at //github.com/LyesSaadSaoud/MARS-Object-Detection/
This paper introduces Hardcaml, an embedded hardware design domain specific language (DSL) implemented in the OCaml programming language. Unlike high level synthesis (HLS), Hardcaml allows for low level control of the underlying hardware for maximum productivity, while abstracting away many of the tedious aspects of traditional hardware definition languages (HDLs) such as Verilog or VHDL. The richness of OCaml's type system combined with Hardcaml's fast circuit elaboration checks reduces the chance of user-introduced bugs and erroneous connections with features like custom type defining, type-safe parameterized modules and elaboration-time bit-width inference and validation. Hardcaml tooling emphasizes fast feedback through simulation, testing, and verification. It includes both a native OCaml cycle-accurate and an event-driven simulator. Unit tests can live in the source code and include digital ASCII waveforms representing the simulator's output. Hardcaml also provides tools for SAT proving and formal verification. Hardcaml is industrially proven, and has been used at Jane Street internally for many large FPGA designs. As a case study we highlight several aspects of our recent Hardcaml submission to the 2022 ZPrize cryptography competition which won 1st place in the FPGA track.
In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIESCORE, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIESCORE leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIESCORE on seven prominent tasks in conditional image tasks and found: (1) VIESCORE (GPT4-v) achieves a high Spearman correlation of 0.3 with human evaluations, while the human-to-human correlation is 0.45. (2) VIESCORE (with open-source MLLM) is significantly weaker than GPT-4v in evaluating synthetic images. (3) VIESCORE achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIESCORE shows its great potential to replace human judges in evaluating image synthesis tasks.
This paper addresses the need for automatic and efficient generation of host driver code for arbitrary custom AXI-based accelerators targeting linear algebra algorithms, an important workload in various applications, including machine learning and scientific computing. While existing tools have focused on automating accelerator prototyping, little attention has been paid to the host-accelerator interaction. This paper introduces AXI4MLIR, an extension of the MLIR compiler framework designed to facilitate the automated generation of host-accelerator driver code. With new MLIR attributes and transformations, AXI4MLIR empowers users to specify accelerator features (including their instructions) and communication patterns and exploit the host memory hierarchy. We demonstrate AXI4MLIR's versatility across different types of accelerators and problems, showcasing significant CPU cache reference reductions (up to 56%) and up to a 1.65x speedup compared to manually optimized driver code implementations. AXI4MLIR implementation is open-source and available at: //github.com/AXI4MLIR/axi4mlir.
With the extremely rapid advances in remote sensing (RS) technology, a great quantity of Earth observation (EO) data featuring considerable and complicated heterogeneity is readily available nowadays, which renders researchers an opportunity to tackle current geoscience applications in a fresh way. With the joint utilization of EO data, much research on multimodal RS data fusion has made tremendous progress in recent years, yet these developed traditional algorithms inevitably meet the performance bottleneck due to the lack of the ability to comprehensively analyse and interpret these strongly heterogeneous data. Hence, this non-negligible limitation further arouses an intense demand for an alternative tool with powerful processing competence. Deep learning (DL), as a cutting-edge technology, has witnessed remarkable breakthroughs in numerous computer vision tasks owing to its impressive ability in data representation and reconstruction. Naturally, it has been successfully applied to the field of multimodal RS data fusion, yielding great improvement compared with traditional methods. This survey aims to present a systematic overview in DL-based multimodal RS data fusion. More specifically, some essential knowledge about this topic is first given. Subsequently, a literature survey is conducted to analyse the trends of this field. Some prevalent sub-fields in the multimodal RS data fusion are then reviewed in terms of the to-be-fused data modalities, i.e., spatiospectral, spatiotemporal, light detection and ranging-optical, synthetic aperture radar-optical, and RS-Geospatial Big Data fusion. Furthermore, We collect and summarize some valuable resources for the sake of the development in multimodal RS data fusion. Finally, the remaining challenges and potential future directions are highlighted.
We present Emu, a system that semantically enhances multilingual sentence embeddings. Our framework fine-tunes pre-trained multilingual sentence embeddings using two main components: a semantic classifier and a language discriminator. The semantic classifier improves the semantic similarity of related sentences, whereas the language discriminator enhances the multilinguality of the embeddings via multilingual adversarial training. Our experimental results based on several language pairs show that our specialized embeddings outperform the state-of-the-art multilingual sentence embedding model on the task of cross-lingual intent classification using only monolingual labeled data.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191