David Hall

Omar Khattab, Keshav Santhanam, Xiang Lisa Li et al. · stanford

Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM). Existing work has combined these in simple "retrieve-then-read" pipelines in which the RM retrieves passages that are inserted into the LM prompt. To begin to fully realize the potential of frozen LMs and RMs, we propose Demonstrate-Search-Predict (DSP), a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. DSP can express high-level programs that bootstrap pipeline-aware demonstrations, search for relevant passages, and generate grounded predictions, systematically breaking down problems into small transformations that the LM and RM can handle more reliably. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings, establishing in early evaluations new state-of-the-art in-context learning results and delivering 37-120%, 8-39%, and 80-290% relative gains against the vanilla LM (GPT-3.5), a standard retrieve-then-read pipeline, and a contemporaneous self-ask pipeline, respectively. We release DSP at https://github.com/stanfordnlp/dsp

Matt Deitke, Dhruv Batra, Yonatan Bisk et al. · allen-ai, cmu

We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research.

John Thickstun, David Hall, Chris Donahue et al. · stanford

We introduce anticipation: a method for constructing a controllable generative model of a temporal point process (the event process) conditioned asynchronously on realizations of a second, correlated process (the control process). We achieve this by interleaving sequences of events and controls, such that controls appear following stopping times in the event sequence. This work is motivated by problems arising in the control of symbolic music generation. We focus on infilling control tasks, whereby the controls are a subset of the events themselves, and conditional generation completes a sequence of events given the fixed control events. We train anticipatory infilling models using the large and diverse Lakh MIDI music dataset. These models match the performance of autoregressive models for prompted music generation, with the additional capability to perform infilling control tasks, including accompaniment. Human evaluators report that an anticipatory model produces accompaniments with similar musicality to even music composed by humans over a 20-second clip.

Jeffrey Li, Josh Gardner, Doug Kang et al. · utoronto

One of the first pre-processing steps for constructing web-scale LLM pretraining datasets involves extracting text from HTML. Despite the immense diversity of web content, existing open-source datasets predominantly apply a single fixed extractor to all webpages. In this work, we investigate whether this practice leads to suboptimal coverage and utilization of Internet data. We first show that while different extractors may lead to similar model performance on standard language understanding tasks, the pages surviving a fixed filtering pipeline can differ substantially. This suggests a simple intervention: by taking a Union over different extractors, we can increase the token yield of DCLM-Baseline by up to 71% while maintaining benchmark performance. We further show that for structured content such as tables and code blocks, extractor choice can significantly impact downstream task performance, with differences of up to 10 percentage points (p.p.) on WikiTQ and 3 p.p. on HumanEval.

Thorsten Kurth, Shashank Subramanian, Peter Harrington et al.

Extreme weather amplified by climate change is causing increasingly devastating impacts across the globe. The current use of physics-based numerical weather prediction (NWP) limits accuracy due to high computational cost and strict time-to-solution limits. We report that a data-driven deep learning Earth system emulator, FourCastNet, can predict global weather and generate medium-range forecasts five orders-of-magnitude faster than NWP while approaching state-of-the-art accuracy. FourCast-Net is optimized and scales efficiently on three supercomputing systems: Selene, Perlmutter, and JUWELS Booster up to 3,808 NVIDIA A100 GPUs, attaining 140.8 petaFLOPS in mixed precision (11.9%of peak at that scale). The time-to-solution for training FourCastNet measured on JUWELS Booster on 3,072GPUs is 67.4minutes, resulting in an 80,000times faster time-to-solution relative to state-of-the-art NWP, in inference. FourCastNet produces accurate instantaneous weather predictions for a week in advance, enables enormous ensembles that better capture weather extremes, and supports higher global forecast resolutions.

Elliot Bolton, Abhinav Venigalla, Michihiro Yasunaga et al. · stanford

Models such as GPT-4 and Med-PaLM 2 have demonstrated impressive performance on a wide variety of biomedical NLP tasks. However, these models have hundreds of billions of parameters, are computationally expensive to run, require users to send their input data over the internet, and are trained on unknown data sources. Can smaller, more targeted models compete? To address this question, we build and release BioMedLM, a 2.7 billion parameter GPT-style autoregressive model trained exclusively on PubMed abstracts and full articles. When fine-tuned, BioMedLM can produce strong multiple-choice biomedical question-answering results competitive with much larger models, such as achieving a score of 57.3% on MedMCQA (dev) and 69.0% on the MMLU Medical Genetics exam. BioMedLM can also be fine-tuned to produce useful answers to patient questions on medical topics. This demonstrates that smaller models can potentially serve as transparent, privacy-preserving, economical and environmentally friendly foundations for particular NLP applications, such as in biomedicine. The model is available on the Hugging Face Hub: https://huggingface.co/stanford-crfm/BioMedLM.

Eun Chang, Zhuangqun Huang, Yiwei Liao et al.

We introduce WearVQA, the first benchmark specifically designed to evaluate the Visual Question Answering (VQA) capabilities of multi-model AI assistant on wearable devices like smart glasses. Unlike prior benchmarks that focus on high-quality, third-person imagery, WearVQA reflects the unique challenges of ego-centric interaction-where visual inputs may be occluded, poorly lit, unzoomed, or blurry, and questions are grounded in realistic wearable use cases. The benchmark comprises 2,520 carefully curated image-question-answer triplets, spanning 7 diverse image domains including both text-centric and general scenes, 10 cognitive task types ranging from basic recognition to various forms of reasoning, and 6 common wearables-specific image quality issues. All questions are designed to be answerable using only the visual input and common senses. WearVQA is paired with a rigorous LLM-as-a-judge evaluation framework with 96% labeling accuracy. Open-source and proprietary multi-model LLMs achieved a QA accuracy as low as 24-52% on WearVQA, with substantial drops on lower-quality images and reasoning-heavy tasks. These observations position WearVQA as a comprehensive and challenging benchmark for guiding technical advancement towards robust, real-world multi-model wearables AI systems.

Joshua Knights, Joseph Reid, Kaushik Roy et al.

Recent years have seen a significant increase in demand for robotic solutions in unstructured natural environments, alongside growing interest in bridging 2D and 3D scene understanding. However, existing robotics datasets are predominantly captured in structured urban environments, making them inadequate for addressing the challenges posed by complex, unstructured natural settings. To address this gap, we propose WildCross, a cross-modal benchmark for place recognition and metric depth estimation in large-scale natural environments. WildCross comprises over 476K sequential RGB frames with semi-dense depth and surface normal annotations, each aligned with accurate 6DoF poses and synchronized dense lidar submaps. We conduct comprehensive experiments on visual, lidar, and cross-modal place recognition, as well as metric depth estimation, demonstrating the value of WildCross as a challenging benchmark for multi-modal robotic perception tasks. We provide access to the code repository and dataset at https://csiro-robotics.github.io/WildCross.

Kaiyue Wen, David Hall, Tengyu Ma et al.

AdamW has long been the dominant optimizer in language model pretraining, despite numerous claims that alternative optimizers offer 1.4 to 2x speedup. We posit that two methodological shortcomings have obscured fair comparisons and hindered practical adoption: (i) unequal hyperparameter tuning and (ii) limited or misleading evaluation setups. To address these two issues, we conduct a systematic study of ten deep learning optimizers across four model scales (0.1B-1.2B parameters) and data-to-model ratios (1-8x the Chinchilla optimum). We find that fair and informative comparisons require rigorous hyperparameter tuning and evaluations across a range of model scales and data-to-model ratios, performed at the end of training. First, optimal hyperparameters for one optimizer may be suboptimal for another, making blind hyperparameter transfer unfair. Second, the actual speedup of many proposed optimizers over well-tuned baselines is lower than claimed and decreases with model size to only 1.1x for 1.2B parameter models. Thirdly, comparing intermediate checkpoints before reaching the target training budgets can be misleading, as rankings between two optimizers can flip during training due to learning rate decay. Through our thorough investigation, we find that all the fastest optimizers such as Muon and Soap, use matrices as preconditioners -- multiplying gradients with matrices rather than entry-wise scalars. However, the speedup of matrix-based optimizers is inversely proportional to model scale, decreasing from 1.4x over AdamW for 0.1B parameter models to merely 1.1x for 1.2B parameter models.

Anh Tong, Thanh Nguyen-Tang, Dongeun Lee et al.

Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling transformer architectures using highly flexible non-autonomous neural ordinary differential equations (ODEs). Our proposed model parameterizes all weights of attention and feed-forward blocks through neural networks, expressing these weights as functions of a continuous layer index. Through spectral analysis of the model's dynamics, we uncover an increase in eigenvalue magnitude that challenges the weight-sharing assumption prevalent in existing theoretical studies. We also leverage the Lyapunov exponent to examine token-level sensitivity, enhancing model interpretability. Our neural ODE transformer demonstrates performance comparable to or better than vanilla transformers across various configurations and datasets, while offering flexible fine-tuning capabilities that can adapt to different architectural constraints.

Stephen Hausler, David Hall, Sutharsan Mahendren et al.

Neural fields, coordinate-based neural networks, have recently gained popularity for implicitly representing a scene. In contrast to classical methods that are based on explicit representations such as point clouds, neural fields provide a continuous scene representation able to represent 3D geometry and appearance in a way which is compact and ideal for robotics applications. However, limited prior methods have investigated registering multiple neural fields by directly utilising these continuous implicit representations. In this paper, we present Reg-NF, a neural fields-based registration that optimises for the relative 6-DoF transformation between two arbitrary neural fields, even if those two fields have different scale factors. Key components of Reg-NF include a bidirectional registration loss, multi-view surface sampling, and utilisation of volumetric signed distance functions (SDFs). We showcase our approach on a new neural field dataset for evaluating registration problems. We provide an exhaustive set of experiments and ablation studies to identify the performance of our approach, while also discussing limitations to provide future direction to the research community on open challenges in utilizing neural fields in unconstrained environments.

William Held, David Hall, Percy Liang et al. · gatech

Scaling laws describe how language models improve with additional data, parameters, and compute. While widely used, they are typically measured on aggregate test sets. Aggregate evaluations yield clean trends but average over heterogeneous subpopulations, obscuring performance disparities. We introduce relative scaling laws, which track how performance gaps between test distributions evolve with scale rather than focusing solely on absolute error. Using 255 decoder-only Transformers trained under matched-compute (IsoFLOP) budgets from $10^{18}$--$10^{20}$ FLOPs on standard pretraining datasets, we find diverse trajectories: academic domains on MMLU converge toward parity; regional English dialects shift depending on population size; and clusters of AI risk behaviours split, with capability- and influence-related risks increasing during pretraining while adversarial risks do not. These results show that although scaling improves overall performance, it is not a universal equalizer. To support further study, we release all model checkpoints from this work to enable practitioners to measure relative alongside traditional scaling laws, in order to better prioritize robustness challenges in light of the bitter lesson.

Iman Khadir, Shane Stevenson, Henry Li et al.

This paper demonstrates the feasibility of democratizing AI-driven global weather forecasting models among university research groups by leveraging Graphics Processing Units (GPUs) and freely available AI models, such as NVIDIA's FourCastNetv2. FourCastNetv2 is an NVIDIA's advanced neural network for weather prediction and is trained on a 73-channel subset of the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5) dataset at single levels and different pressure levels. Although the training specifications for FourCastNetv2 are not released to the public, the training documentation of the model's first generation, FourCastNet, is available to all users. The training had 64 A100 GPUs and took 16 hours to complete. Although NVIDIA's models offer significant reductions in both time and cost compared to traditional Numerical Weather Prediction (NWP), reproducing published forecasting results presents ongoing challenges for resource-constrained university research groups with limited GPU availability. We demonstrate both (i) leveraging FourCastNetv2 to create predictions through the designated application programming interface (API) and (ii) utilizing NVIDIA hardware to train the original FourCastNet model. Further, this paper demonstrates the capabilities and limitations of NVIDIA A100's for resource-limited research groups in universities. We also explore data management, training efficiency, and model validation, highlighting the advantages and challenges of using limited high-performance computing resources. Consequently, this paper and its corresponding GitHub materials may serve as an initial guide for other university research groups and courses related to machine learning, climate science, and data science to develop research and education programs on AI weather forecasting, and hence help democratize the AI NWP in the digital economy.

David Hall, Stephen Hausler, Sutharsan Mahendren et al.

Neural fields provide a continuous scene representation of 3D geometry and appearance in a way which has great promise for robotics applications. One functionality that unlocks unique use-cases for neural fields in robotics is object 6-DoF registration. In this paper, we provide an expanded analysis of the recent Reg-NF neural field registration method and its use-cases within a robotics context. We showcase the scenario of determining the 6-DoF pose of known objects within a scene using scene and object neural field models. We show how this may be used to better represent objects within imperfectly modelled scenes and generate new scenes by substituting object neural field models into the scene.

Hong Liu, Zhiyuan Li, David Hall et al.

Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training. Adam and its variants have been state-of-the-art for years, and more sophisticated second-order (Hessian-based) optimizers often incur too much per-step overhead. In this paper, we propose Sophia, Second-order Clipped Stochastic Optimization, a simple scalable second-order optimizer that uses a light-weight estimate of the diagonal Hessian as the pre-conditioner. The update is the moving average of the gradients divided by the moving average of the estimated Hessian, followed by element-wise clipping. The clipping controls the worst-case update size and tames the negative impact of non-convexity and rapid change of Hessian along the trajectory. Sophia only estimates the diagonal Hessian every handful of iterations, which has negligible average per-step time and memory overhead. On language modeling with GPT models of sizes ranging from 125M to 1.5B, Sophia achieves a 2x speed-up compared to Adam in the number of steps, total compute, and wall-clock time, achieving the same perplexity with 50% fewer steps, less total compute, and reduced wall-clock time. Theoretically, we show that Sophia, in a much simplified setting, adapts to the heterogeneous curvatures in different parameter dimensions, and thus has a run-time bound that does not depend on the condition number of the loss.

Jaideep Pathak, Shashank Subramanian, Peter Harrington et al.

FourCastNet, short for Fourier Forecasting Neural Network, is a global data-driven weather forecasting model that provides accurate short to medium-range global predictions at $0.25^{\circ}$ resolution. FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor. It has important implications for planning wind energy resources, predicting extreme weather events such as tropical cyclones, extra-tropical cyclones, and atmospheric rivers. FourCastNet matches the forecasting accuracy of the ECMWF Integrated Forecasting System (IFS), a state-of-the-art Numerical Weather Prediction (NWP) model, at short lead times for large-scale variables, while outperforming IFS for variables with complex fine-scale structure, including precipitation. FourCastNet generates a week-long forecast in less than 2 seconds, orders of magnitude faster than IFS. The speed of FourCastNet enables the creation of rapid and inexpensive large-ensemble forecasts with thousands of ensemble-members for improving probabilistic forecasting. We discuss how data-driven deep learning models such as FourCastNet are a valuable addition to the meteorology toolkit to aid and augment NWP models.

Suman Raj Bista, David Hall, Ben Talbot et al.

Recent Semantic SLAM methods combine classical geometry-based estimation with deep learning-based object detection or semantic segmentation. In this paper we evaluate the quality of semantic maps generated by state-of-the-art class- and instance-aware dense semantic SLAM algorithms whose codes are publicly available and explore the impacts both semantic segmentation and pose estimation have on the quality of semantic maps. We obtain these results by providing algorithms with ground-truth pose and/or semantic segmentation data available from simulated environments. We establish that semantic segmentation is the largest source of error through our experiments, dropping mAP and OMQ performance by up to 74.3% and 71.3% respectively.

Fan Zhang, David Hall, Tao Xu et al.

In this paper, we present a workflow for the simulation of drone operations exploiting realistic background environments constructed within Unreal Engine 4 (UE4). Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface. Given the geographical location of the selected area and the camera parameters employed, the scanning strategy and its associated flight parameters are first determined for image capture. Source imagery can be extracted from virtual globe software or obtained through aerial photography of the scene (e.g. using drones). The latter case is clearly more time consuming but can provide enhanced detail, particularly where coverage of virtual globe software is limited. The captured images are then used to generate 3D background environment models employing photogrammetry software. The reconstructed 3D models are then imported into the simulation interface as background environment assets together with appropriate foreground object models as a basis for shot planning and rehearsal. The tool supports both free-flight and parameterisable standard shot types along with programmable scenarios associated with foreground assets and event dynamics. It also supports the exporting of flight plans. Camera shots can also be designed to provide suitable coverage of any landmarks which need to appear in-shot. This simulation tool will contribute to enhanced productivity, improved safety (awareness and mitigations for crowds and buildings), improved confidence of operators and directors and ultimately enhanced quality of viewer experience.

Semantic Machines, Jacob Andreas, John Bufe et al.

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends this graph. Programs include metacomputation operators for reference and revision that reuse dataflow fragments from previous turns. Our graph-based state enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. We introduce a new dataset, SMCalFlow, featuring complex dialogues about events, weather, places, and people. Experiments show that dataflow graphs and metacomputation substantially improve representability and predictability in these natural dialogues. Additional experiments on the MultiWOZ dataset show that our dataflow representation enables an otherwise off-the-shelf sequence-to-sequence model to match the best existing task-specific state tracking model. The SMCalFlow dataset and code for replicating experiments are available at https://www.microsoft.com/en-us/research/project/dataflow-based-dialogue-semantic-machines.

David Hall, Ben Talbot, Suman Raj Bista et al.

Being able to explore an environment and understand the location and type of all objects therein is important for indoor robotic platforms that must interact closely with humans. However, it is difficult to evaluate progress in this area due to a lack of standardized testing which is limited due to the need for active robot agency and perfect object ground-truth. To help provide a standard for testing scene understanding systems, we present a new robot vision scene understanding challenge using simulation to enable repeatable experiments with active robot agency. We provide two challenging task types, three difficulty levels, five simulated environments and a new evaluation measure for evaluating 3D cuboid object maps. Our aim is to drive state-of-the-art research in scene understanding through enabling evaluation and comparison of active robotic vision systems.

Ben Talbot, David Hall, Haoyang Zhang et al.

We introduce BenchBot, a novel software suite for benchmarking the performance of robotics research across both photorealistic 3D simulations and real robot platforms. BenchBot provides a simple interface to the sensorimotor capabilities of a robot when solving robotics research problems; an interface that is consistent regardless of whether the target platform is simulated or a real robot. In this paper we outline the BenchBot system architecture, and explore the parallels between its user-centric design and an ideal research development process devoid of tangential robot engineering challenges. The paper describes the research benefits of using the BenchBot system, including: enhanced capacity to focus solely on research problems, direct quantitative feedback to inform research development, tools for deriving comprehensive performance characteristics, and submission formats which promote sharability and repeatability of research outcomes. BenchBot is publicly available (http://benchbot.org), and we encourage its use in the research community for comprehensively evaluating the simulated and real world performance of novel robotic algorithms.

Christina Kumler-Bonfanti, Jebb Stewart, David Hall et al.

Extracting valuable information from large sets of diverse meteorological data is a time-intensive process. Machine learning methods can help improve both speed and accuracy of this process. Specifically, deep learning image segmentation models using the U-Net structure perform faster and can identify areas missed by more restrictive approaches, such as expert hand-labeling and a priori heuristic methods. This paper discusses four different state-of-the-art U-Net models designed for detection of tropical and extratropical cyclone Regions Of Interest (ROI) from two separate input sources: total precipitable water output from the Global Forecasting System (GFS) model and water vapor radiance images from the Geostationary Operational Environmental Satellite (GOES). These models are referred to as IBTrACS-GFS, Heuristic-GFS, IBTrACS-GOES, and Heuristic-GOES. All four U-Nets are fast information extraction tools and perform with a ROI detection accuracy ranging from 80% to 99%. These are additionally evaluated with the Dice and Tversky Intersection over Union (IoU) metrics, having Dice coefficient scores ranging from 0.51 to 0.76 and Tversky coefficients ranging from 0.56 to 0.74. The extratropical cyclone U-Net model performed 3 times faster than the comparable heuristic model used to detect the same ROI. The U-Nets were specifically selected for their capabilities in detecting cyclone ROI beyond the scope of the training labels. These machine learning models identified more ambiguous and active ROI missed by the heuristic model and hand-labeling methods commonly used in generating real-time weather alerts, having a potentially direct impact on public safety.

Peter Corke, Feras Dayoub, David Hall et al.

The computer vision and robotics research communities are each strong. However progress in computer vision has become turbo-charged in recent years due to big data, GPU computing, novel learning algorithms and a very effective research methodology. By comparison, progress in robotics seems slower. It is true that robotics came later to exploring the potential of learning -- the advantages over the well-established body of knowledge in dynamics, kinematics, planning and control is still being debated, although reinforcement learning seems to offer real potential. However, the rapid development of computer vision compared to robotics cannot be only attributed to the former's adoption of deep learning. In this paper, we argue that the gains in computer vision are due to research methodology -- evaluation under strict constraints versus experiments; bold numbers versus videos.

Steve Branson, Jan Dirk Wegner, David Hall et al.

Up-to-date catalogs of the urban tree population are important for municipalities to monitor and improve quality of life in cities. Despite much research on automation of tree mapping, mainly relying on dedicated airborne LiDAR or hyperspectral campaigns, trees are still mostly mapped manually in practice. We present a fully automated tree detection and species recognition pipeline to process thousands of trees within a few hours using publicly available aerial and street view images of Google MapsTM. These data provide rich information (viewpoints, scales) from global tree shapes to bark textures. Our work-flow is built around a supervised classification that automatically learns the most discriminative features from thousands of trees and corresponding, public tree inventory data. In addition, we introduce a change tracker to keep urban tree inventories up-to-date. Changes of individual trees are recognized at city-scale by comparing street-level images of the same tree location at two different times. Drawing on recent advances in computer vision and machine learning, we apply convolutional neural networks (CNN) for all classification tasks. We propose the following pipeline: download all available panoramas and overhead images of an area of interest, detect trees per image and combine multi-view detections in a probabilistic framework, adding prior knowledge; recognize fine-grained species of detected trees. In a later, separate module, track trees over time and identify the type of change. We believe this is the first work to exploit publicly available image data for fine-grained tree mapping at city-scale, respectively over many thousands of trees. Experiments in the city of Pasadena, California, USA show that we can detect > 70% of the street trees, assign correct species to > 80% for 40 different species, and correctly detect and classify changes in > 90% of the cases.

John Skinner, David Hall, Haoyang Zhang et al.

We introduce a new challenge for computer and robotic vision, the first ACRV Robotic Vision Challenge, Probabilistic Object Detection. Probabilistic object detection is a new variation on traditional object detection tasks, requiring estimates of spatial and semantic uncertainty. We extend the traditional bounding box format of object detection to express spatial uncertainty using gaussian distributions for the box corners. The challenge introduces a new test dataset of video sequences, which are designed to more closely resemble the kind of data available to a robotic system. We evaluate probabilistic detections using a new probability-based detection quality (PDQ) measure. The goal in creating this challenge is to draw the computer and robotic vision communities together, toward applying object detection solutions for practical robotics applications.

David Hall, Feras Dayoub, John Skinner et al.

We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections. Given the lack of methods capable of assessing such probabilistic object detections, we present the new Probability-based Detection Quality measure (PDQ).Unlike AP-based measures, PDQ has no arbitrary thresholds and rewards spatial and label quality, and foreground/background separation quality while explicitly penalising false positive and false negative detections. We contrast PDQ with existing mAP and moLRP measures by evaluating state-of-the-art detectors and a Bayesian object detector based on Monte Carlo Dropout. Our experiments indicate that conventional object detectors tend to be spatially overconfident and thus perform poorly on the task of probabilistic object detection. Our paper aims to encourage the development of new object detection approaches that provide detections with accurately estimated spatial and label uncertainties and are of critical importance for deployment on robots and embodied AI systems in the real world.

David Hall, Feras Dayoub, Tristan Perez et al.

In this work we demonstrate a rapidly deployable weed classification system that uses visual data to enable autonomous precision weeding without making prior assumptions about which weed species are present in a given field. Previous work in this area relies on having prior knowledge of the weed species present in the field. This assumption cannot always hold true for every field, and thus limits the use of weed classification systems based on this assumption. In this work, we obviate this assumption and introduce a rapidly deployable approach able to operate on any field without any weed species assumptions prior to deployment. We present a three stage pipeline for the implementation of our weed classification system consisting of initial field surveillance, offline processing and selective labelling, and automated precision weeding. The key characteristic of our approach is the combination of plant clustering and selective labelling which is what enables our system to operate without prior weed species knowledge. Testing using field data we are able to label 12.3 times fewer images than traditional full labelling whilst reducing classification accuracy by only 14%.

David Hall, Feras Dayoub, Jason Kulk et al.

Weed scouting is an important part of modern integrated weed management but can be time consuming and sparse when performed manually. Automated weed scouting and weed destruction has typically been performed using classification systems able to classify a set group of species known a priori. This greatly limits deployability as classification systems must be retrained for any field with a different set of weed species present within them. In order to overcome this limitation, this paper works towards developing a clustering approach to weed scouting which can be utilized in any field without the need for prior species knowledge. We demonstrate our system using challenging data collected in the field from an agricultural robotics platform. We show that considerable improvements can be made by (i) learning low-dimensional (bottleneck) features using a deep convolutional neural network to represent plants in general and (ii) tying views of the same area (plant) together. Deploying this algorithm on in-field data collected by AgBotII, we are able to successfully cluster cotton plants from grasses without prior knowledge or training for the specific plants in the field.

David Hall, Pietro Perona

A video dataset that is designed to study fine-grained categorisation of pedestrians is introduced. Pedestrians were recorded "in-the-wild" from a moving vehicle. Annotations include bounding boxes, tracks, 14 keypoints with occlusion information and the fine-grained categories of age (5 classes), sex (2 classes), weight (3 classes) and clothing style (4 classes). There are a total of 27,454 bounding box and pose labels across 4222 tracks. This dataset is designed to train and test algorithms for fine-grained categorisation of people, it is also useful for benchmarking tracking, detection and pose estimation of pedestrians. State-of-the-art algorithms for fine-grained classification and pose estimation were tested using the dataset and the results are reported as a useful performance baseline.