Search

With a growing number of facilities able to monitor the entire sky and produce light curves with a cadence of days, in recent years there has been an increased rate of detection of sources whose variability deviates from standard behavior, revealing a variety of exotic nuclear transients. The aim of the present study is to disentangle the nature of the transient AT 2021hdr, whose optical light curve used to be consistent with a classic Seyfert 1 nucleus, which was also confirmed by its optical spectrum and high-energy properties. From late 2021, AT 2021hdr started to present sudden brightening episodes in the form of oscillating peaks in the Zwicky Transient Facility (ZTF) alert stream, and the same shape is observed in X-rays and UV from Swift data. The oscillations occur every about 60-90 days with amplitudes of around 0.2 mag in the g and r bands. Very Long Baseline Array (VLBA) observations show no radio emission at milliarcseconds scale. It is argued that these findings are inconsistent with a standard tidal disruption event (TDE), a binary supermassive black hole (BSMBH), or a changing-look active galactic nucleus (AGN); neither does this object resemble previous observed AGN flares, and disk or jet instabilities are an unlikely scenario. Here, we propose that the behavior of AT 2021hdr might be due to the tidal disruption of a gas cloud by a BSMBH. In this scenario, we estimate that the putative binary has a separation of about 0.83 mpc and would merge in about 70000 years. This galaxy is located at 9 kpc from a companion galaxy, and in this work we report this merger for the first time. The oscillations are not related to the companion galaxy., Comment: 11 pages, 5 figures, 2 tables, plus appendices. Accepted for publication in Astronomy & Astrophysics. NASA press release available at https://science.nasa.gov/missions/swift/nasas-swift-studies-gas-churning-monster-black-holes/ doi: 10.1051/0004-6361/202451305

3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce a framework for quantifying uncertainty in 3D object detection by leveraging an evidential learning loss on Bird's Eye View representations in the 3D detector. These uncertainty estimates require minimal computational overhead and are generalizable across different architectures. We demonstrate both the efficacy and importance of these uncertainty estimates on identifying out-of-distribution scenes, poorly localized objects, and missing (false negative) detections; our framework consistently improves over baselines by 10-20% on average. Finally, we integrate this suite of tasks into a system where a 3D object detector auto-labels driving scenes and our uncertainty estimates verify label correctness before the labels are used to train a second model. Here, our uncertainty-driven verification results in a 1% improvement in mAP and a 1-2% improvement in NDS.

The flat spectrum radio quasar PKS 1510-089 is one of the most active blazars in $\gamma$-rays, exhibiting phases of very high activity. This study investigates its variability over a decade across a wide range of wavelengths, from radio to $\gamma$-rays. Utilizing the non-thermal dominance parameter, we analyze the H$\beta$, H$\gamma$, and $\lambda5100\text{ \AA}$ continuum light curves to discern the primary source of continuum emission, either from the accretion disk or the jet, during different activity phases. Our findings underscore the dominance of jet emission in the continuum during flare-like events. We observed an approximately 80-day delay between the H$\beta$ and continuum emissions, which we attribute to the spatial separation between the optical emission zone and the broad-line region. Near-zero delays between optical and near-infrared emissions suggest that the emitting regions within the jet are co-spatial. Synchrotron self-Compton was identified as the primary mechanism for $\gamma$-ray emission during flares, supported by the minimal delay observed between optical/near-infrared emissions and $\gamma$-rays. Additionally, we found a delay of about 60 days between the leading optical/near-infrared emissions and X-rays, indicating that inverse Compton scattering within the jet predominantly drives X-ray emission. However, distinguishing between synchrotron self-Compton and external inverse Compton mechanism was not feasible. Shifts in the spectral index across the 15-230 GHz range corresponded with ejections from the radio core, suggesting changes in the physical conditions of the jet., Comment: 22 pages, 13 figures, 4 tables. Accepted for publication in ApJ

In recent years, the data collected for artificial intelligence has grown to an unmanageable amount. Particularly within industrial applications, such as autonomous vehicles, model training computation budgets are being exceeded while model performance is saturating -- and yet more data continues to pour in. To navigate the flood of data, we propose a framework to select the most semantically diverse and important dataset portion. Then, we further semantically enrich it by discovering meaningful new data from a massive unlabeled data pool. Importantly, we can provide explainability by leveraging foundation models to generate semantics for every data point. We quantitatively show that our Semantic Selection and Enrichment framework (SSE) can a) successfully maintain model performance with a smaller training dataset and b) improve model performance by enriching the smaller dataset without exceeding the original dataset size. Consequently, we demonstrate that semantic diversity is imperative for optimal data selection and model performance.

The cornerstone of autonomous vehicles (AV) is a solid perception system, where camera encoders play a crucial role. Existing works usually leverage pre-trained Convolutional Neural Networks (CNN) or Vision Transformers (ViTs) designed for general vision tasks, such as image classification, segmentation, and 2D detection. Although those well-known architectures have achieved state-of-the-art accuracy in AV-related tasks, e.g., 3D Object Detection, there remains significant potential for improvement in network design due to the nuanced complexities of industrial-level AV dataset. Moreover, existing public AV benchmarks usually contain insufficient data, which might lead to inaccurate evaluation of those architectures.To reveal the AV-specific model insights, we start from a standard general-purpose encoder, ConvNeXt and progressively transform the design. We adjust different design parameters including width and depth of the model, stage compute ratio, attention mechanisms, and input resolution, supported by systematic analysis to each modifications. This customization yields an architecture optimized for AV camera encoder achieving 8.79% mAP improvement over the baseline. We believe our effort could become a sweet cookbook of image encoders for AV and pave the way to the next-level drive system.

We propose Hydra-MDP, a novel paradigm employing multiple teachers in a teacher-student model. This approach uses knowledge distillation from both human and rule-based teachers to train the student model, which features a multi-head decoder to learn diverse trajectory candidates tailored to various evaluation metrics. With the knowledge of rule-based teachers, Hydra-MDP learns how the environment influences the planning in an end-to-end manner instead of resorting to non-differentiable post-processing. This method achieves the $1^{st}$ place in the Navsim challenge, demonstrating significant improvements in generalization across diverse driving environments and conditions. More details by visiting \url{https://github.com/NVlabs/Hydra-MDP}., Comment: The 1st place solution of End-to-end Driving at Scale at the CVPR 2024 Autonomous Grand Challenge

The Ground-based Observational Support of the Fermi Gamma-ray Space Telescope is conducted by the University of Arizona using the 2.3m Bok and 1.54m Kuiper telescopes operated by the Steward Observatory (SO). This program monitors blazar sources with spectroscopic (among others) observations. Yet, the instrumental broadenings for the different slit widths used in the spectra, are unavailable (the widths range from 2.0 to 12.7 arcsec). Using quasi-simultaneous spectroscopic observations of the blazar 3C 273 between the SO, Observatorio Astrof\'isico Guillermo Haro (OAGH), and Observatorio Astron\'omico Nacional San Pedro M\'artir (OAN-SPM), we can provide an estimation of the instrumental profile for two of the slit widths. Since the instrumental broadening and the slit width are directly proportional, we were able to estimate the instrumental broadening for all six slit widths used at the SO. We found significant variations between the instrumental profiles, emphasizing the need to correct the instrumental broadening for each aperture., Comment: 9 pages, 2 figures, 1 table. Accepted on Revista Mexicana de Astronom\'ia y Astrof\'isica, to appear on Vol. 60, N{\deg}2, October 2024

Data often arrives in sequence over time in real-world deep learning applications such as autonomous driving. When new training data is available, training the model from scratch undermines the benefit of leveraging the learned knowledge, leading to significant training costs. Warm-starting from a previously trained checkpoint is the most intuitive way to retain knowledge and advance learning. However, existing literature suggests that this warm-starting degrades generalization. In this paper, we advocate for warm-starting but stepping out of the previous converging point, thus allowing a better adaptation to new data without compromising previous knowledge. We propose Knowledge Consolidation and Acquisition (CKCA), a continuous model improvement algorithm with two novel components. First, a novel feature regularization (FeatReg) to retain and refine knowledge from existing checkpoints; Second, we propose adaptive knowledge distillation (AdaKD), a novel approach to forget mitigation and knowledge transfer. We tested our method on ImageNet using multiple splits of the training data. Our approach achieves up to $8.39\%$ higher top1 accuracy than the vanilla warm-starting and consistently outperforms the prior art with a large margin.

Humans naturally retain memories of permanent elements, while ephemeral moments often slip through the cracks of memory. This selective retention is crucial for robotic perception, localization, and mapping. To endow robots with this capability, we introduce 3D Gaussian Mapping (3DGM), a self-supervised, camera-only offline mapping framework grounded in 3D Gaussian Splatting. 3DGM converts multitraverse RGB videos from the same region into a Gaussian-based environmental map while concurrently performing 2D ephemeral object segmentation. Our key observation is that the environment remains consistent across traversals, while objects frequently change. This allows us to exploit self-supervision from repeated traversals to achieve environment-object decomposition. More specifically, 3DGM formulates multitraverse environmental mapping as a robust differentiable rendering problem, treating pixels of the environment and objects as inliers and outliers, respectively. Using robust feature distillation, feature residuals mining, and robust optimization, 3DGM jointly performs 2D segmentation and 3D mapping without human intervention. We build the Mapverse benchmark, sourced from the Ithaca365 and nuPlan datasets, to evaluate our method in unsupervised 2D segmentation, 3D reconstruction, and neural rendering. Extensive results verify the effectiveness and potential of our method for self-driving and robotics., Comment: Project page: https://3d-gaussian-mapping.github.io; Code and data: https://github.com/NVlabs/3DGM

Testing for discrimination consists of deriving a profile, known as the comparator, similar to the profile making the discrimination claim, known as the complainant, and comparing the outcomes of these two profiles. An important aspect for establishing discrimination is evidence, often obtained via discrimination testing tools that implement the complainant-comparator pair. In this work, we revisit the role of the comparator in discrimination testing. We argue for the causal modeling nature of deriving the comparator, and introduce a two-kinds classification for the comparator: the ceteris paribus (CP), and mutatis mutandis (MM) comparators. The CP comparator is the standard one among discrimination testing, representing an idealized comparison as it aims for having a complainant-comparator pair that only differs on membership to the protected attribute. As an alternative to it, we define the MM comparator, which requires that the comparator represents what would have been of the complainant without the effects of the protected attribute on the non-protected attributes. The complainant-comparator pair, in that case, may also be dissimilar in terms of all attributes. We illustrate these two comparators and their impact on discrimination testing using a real illustrative example. Importantly, we position generative models and, overall, machine learning methods as useful tools for constructing the MM comparator and, in turn, achieving more complex and realistic comparisons when testing for discrimination.

The advances in multimodal large language models (MLLMs) have led to growing interests in LLM-based autonomous driving agents to leverage their strong reasoning capabilities. However, capitalizing on MLLMs' strong reasoning capabilities for improved planning behavior is challenging since planning requires full 3D situational awareness beyond 2D reasoning. To address this challenge, our work proposes a holistic framework for strong alignment between agent models and 3D driving tasks. Our framework starts with a novel 3D MLLM architecture that uses sparse queries to lift and compress visual representations into 3D before feeding them into an LLM. This query-based representation allows us to jointly encode dynamic objects and static map elements (e.g., traffic lanes), providing a condensed world model for perception-action alignment in 3D. We further propose OmniDrive-nuScenes, a new visual question-answering dataset challenging the true 3D situational awareness of a model with comprehensive visual question-answering (VQA) tasks, including scene description, traffic regulation, 3D grounding, counterfactual reasoning, decision making and planning. Extensive studies show the effectiveness of the proposed architecture as well as the importance of the VQA tasks for reasoning and planning in complex 3D scenes.

To accelerate the scale-up of gaseous CO2 fermentation reactors, computational models need to predict gas-to-liquid mass transfer which requires capturing the bubble size dynamics, i.e. bubble breakup and coalescence. However, the applicability of existing models beyond air-water mixtures remains to be established. Here, an inverse modeling approach, accelerated with a neural network surrogate, calibrates the breakup and coalescence closure models, that are used in the Multiple-Size-Group (MUSIG) population balance modeling (PBM). The calibration is performed based on experimental results obtained in a CO2-air-water-coflowing bubble column reactor. Bayesian inference is used to account for noise in the experimental dataset and bias in the simulation results. To accurately capture gas holdup and interphase mass transfer, the results show that the breakage rate needs to be increased by one order of magnitude. The inferred model parameters are then used on a separate configuration and shown to also improve bubble size distribution predictions.

This paper focuses on self-supervised monocular depth estimation in dynamic scenes trained on monocular videos. Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1 remain a critical challenge for these methods due to the inherent ambiguity in depth and motion estimation, resulting in inaccurate depth estimation. This paper proposes a self-supervised training framework exploiting pseudo depth labels for dynamic regions from training data. The key contribution of our framework is to decouple depth estimation for static and dynamic regions of images in the training data. We start with an unsupervised depth estimation approach, which provides reliable depth estimates for static regions and motion cues for dynamic regions and allows us to extract moving object information at the instance level. In the next stage, we use an object network to estimate the depth of those moving objects assuming rigid motions. Then, we propose a new scale alignment module to address the scale ambiguity between estimated depths for static and dynamic regions. We can then use the depth labels generated to train an end-to-end depth estimation network and improve its performance. Extensive experiments on the Cityscapes and KITTI datasets show that our self-training strategy consistently outperforms existing self/unsupervised depth estimation methods., Comment: Accepted to CVPR2024

BoLD is a new dispute resolution protocol that is designed to replace the originally deployed Arbitrum dispute resolution protocol. Unlike that protocol, BoLD is resistant to delay attacks. It achieves this resistance without a significant increase in onchain computation costs and with reduced staking costs.

Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annotations. Comprehensive experiments on three VIS benchmarks demonstrate competitive performance of the proposed framework, nearly matching fully supervised methods.

Improving the detection of distant 3d objects is an important yet challenging task. For camera-based 3D perception, the annotation of 3d bounding relies heavily on LiDAR for accurate depth information. As such, the distance of annotation is often limited due to the sparsity of LiDAR points on distant objects, which hampers the capability of existing detectors for long-range scenarios. We address this challenge by considering only 2D box supervision for distant objects since they are easy to annotate. We propose LR3D, a framework that learns to recover the missing depth of distant objects. LR3D adopts an implicit projection head to learn the generation of mapping between 2D boxes and depth using the 3D supervision on close objects. This mapping allows the depth estimation of distant objects conditioned on their 2D boxes, making long-range 3D detection with 2D supervision feasible. Experiments show that without distant 3D annotations, LR3D allows camera-based methods to detect distant objects (over 200m) with comparable accuracy to full 3D supervision. Our framework is general, and could widely benefit 3D detection methods to a large extent., Comment: Accepted by CVPR 2024

Perception occurs when two individuals interpret the same information differently. Despite being a known phenomenon with implications for bias in decision-making, as individual experience determines interpretation, perception remains largely overlooked in machine learning (ML) research. Modern decision flows, whether partially or fully automated, involve human experts interacting with ML applications. How might we then, e.g., account for two experts that interpret differently a deferred instance or an explanation from a ML model? To account for perception, we first need to formulate it. In this work, we define perception under causal reasoning using structural causal models (SCM). Our framework formalizes individual experience as additional causal knowledge that comes with and is used by a human expert (read, decision maker). We present two kinds of causal perception, unfaithful and inconsistent, based on the SCM properties of faithfulness and consistency. Further, we motivate the importance of perception within fairness problems. We illustrate our framework through a series of decision flow examples involving ML applications and human experts., Comment: arXiv admin note: text overlap with arXiv:2305.09535 by other authors

Recent studies indicate that Vision Transformers (ViTs) are robust against out-of-distribution scenarios. In particular, the Fully Attentional Network (FAN) - a family of ViT backbones, has achieved state-of-the-art robustness. In this paper, we revisit the FAN models and improve their pre-training with a self-emerging token labeling (STL) framework. Our method contains a two-stage training framework. Specifically, we first train a FAN token labeler (FAN-TL) to generate semantically meaningful patch token labels, followed by a FAN student model training stage that uses both the token labels and the original class label. With the proposed STL framework, our best model based on FAN-L-Hybrid (77.3M parameters) achieves 84.8% Top-1 accuracy and 42.1% mCE on ImageNet-1K and ImageNet-C, and sets a new state-of-the-art for ImageNet-A (46.1%) and ImageNet-R (56.6%) without using extra data, outperforming the original FAN counterpart by significant margins. The proposed framework also demonstrates significantly enhanced performance on downstream tasks such as semantic segmentation, with up to 1.7% improvement in robustness over the counterpart model. Code is available at https://github.com/NVlabs/STL.

End-to-end autonomous driving recently emerged as a promising research direction to target autonomy from a full-stack perspective. Along this line, many of the latest works follow an open-loop evaluation setting on nuScenes to study the planning behavior. In this paper, we delve deeper into the problem by conducting thorough analyses and demystifying more devils in the details. We initially observed that the nuScenes dataset, characterized by relatively simple driving scenarios, leads to an under-utilization of perception information in end-to-end models incorporating ego status, such as the ego vehicle's velocity. These models tend to rely predominantly on the ego vehicle's status for future path planning. Beyond the limitations of the dataset, we also note that current metrics do not comprehensively assess the planning quality, leading to potentially biased conclusions drawn from existing benchmarks. To address this issue, we introduce a new metric to evaluate whether the predicted trajectories adhere to the road. We further propose a simple baseline able to achieve competitive results without relying on perception annotations. Given the current limitations on the benchmark and metrics, we suggest the community reassess relevant prevailing research and be cautious whether the continued pursuit of state-of-the-art would yield convincing and universal conclusions. Code and models are available at \url{https://github.com/NVlabs/BEV-Planner}, Comment: Accept to cvpr 2024

Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their outstanding abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set. Code will be available at \url{https://github.com/woxihuanjiangguo/BEVNeXt}.

In-context segmentation aims at segmenting novel images using a few labeled example images, termed as "in-context examples", exploring content similarities between examples and the target. The resulting models can be generalized seamlessly to novel segmentation tasks, significantly reducing the labeling and training costs compared with conventional pipelines. However, in-context segmentation is more challenging than classic ones requiring the model to learn segmentation rules conditioned on a few samples. Unlike previous work with ad-hoc or non-end-to-end designs, we propose SEGIC, an end-to-end segment-in-context framework built upon a single vision foundation model (VFM). In particular, SEGIC leverages the emergent correspondence within VFM to capture dense relationships between target images and in-context samples. As such, information from in-context samples is then extracted into three types of instructions, i.e. geometric, visual, and meta instructions, serving as explicit conditions for the final mask prediction. SEGIC is a straightforward yet effective approach that yields state-of-the-art performance on one-shot segmentation benchmarks. Notably, SEGIC can be easily generalized to diverse tasks, including video object segmentation and open-vocabulary segmentation. Code will be available at https://github.com/MengLcool/SEGIC., Comment: ECCV-24 camera-ready

Vision Transformers (ViTs) have attracted a lot of popularity in recent years, due to their exceptional capabilities in modeling long-range spatial dependencies and scalability for large scale training. Although the training parallelism of self-attention mechanism plays an important role in retaining great performance, its quadratic complexity baffles the application of ViTs in many scenarios which demand fast inference. This effect is even more pronounced in applications in which autoregressive modeling of input features is required. In Natural Language Processing (NLP), a new stream of efforts has proposed parallelizable models with recurrent formulation that allows for efficient inference in generative applications. Inspired by this trend, we propose a new class of computer vision models, dubbed Vision Retention Networks (ViR), with dual parallel and recurrent formulations, which strike an optimal balance between fast inference and parallel training with competitive performance. In particular, ViR scales favorably for image throughput and memory consumption in tasks that require higher-resolution images due to its flexible formulation in processing large sequence lengths. The ViR is the first attempt to realize dual parallel and recurrent equivalency in a general vision backbone for recognition tasks. We have validated the effectiveness of ViR through extensive experiments with different dataset sizes and various image resolutions and achieved competitive performance. Code: https://github.com/NVlabs/ViR, Comment: Introduction of Vision Retention Networks (ViR) for Efficient Visual Modeling

Autonomous vehicles (AV) require that neural networks used for perception be robust to different viewpoints if they are to be deployed across many types of vehicles without the repeated cost of data collection and labeling for each. AV companies typically focus on collecting data from diverse scenarios and locations, but not camera rig configurations, due to cost. As a result, only a small number of rig variations exist across most fleets. In this paper, we study how AV perception models are affected by changes in camera viewpoint and propose a way to scale them across vehicle types without repeated data collection and labeling. Using bird's eye view (BEV) segmentation as a motivating task, we find through extensive experiments that existing perception models are surprisingly sensitive to changes in camera viewpoint. When trained with data from one camera rig, small changes to pitch, yaw, depth, or height of the camera at inference time lead to large drops in performance. We introduce a technique for novel view synthesis and use it to transform collected data to the viewpoint of target rigs, allowing us to train BEV segmentation models for diverse target rigs without any additional data collection or labeling cost. To analyze the impact of viewpoint changes, we leverage synthetic data to mitigate other gaps (content, ISP, etc). Our approach is then trained on real data and evaluated on synthetic data, enabling evaluation on diverse target rigs. We release all data for use in future work. Our method is able to recover an average of 14.7% of the IoU that is otherwise lost when deploying to new rigs., Comment: ICCV 2023. Project Page: https://nvlabs.github.io/viewpoint-robustness

View Transformation Module (VTM), where transformations happen between multi-view image features and Bird-Eye-View (BEV) representation, is a crucial step in camera-based BEV perception systems. Currently, the two most prominent VTM paradigms are forward projection and backward projection. Forward projection, represented by Lift-Splat-Shoot, leads to sparsely projected BEV features without post-processing. Backward projection, with BEVFormer being an example, tends to generate false-positive BEV features from incorrect projections due to the lack of utilization on depth. To address the above limitations, we propose a novel forward-backward view transformation module. Our approach compensates for the deficiencies in both existing methods, allowing them to enhance each other to obtain higher quality BEV representations mutually. We instantiate the proposed module with FB-BEV, which achieves a new state-of-the-art result of 62.4% NDS on the nuScenes test set. Code and models are available at https://github.com/NVlabs/FB-BEV., Comment: Accept to ICCV 2023, camera-ready version

We investigate the role of the initial screening order (ISO) in candidate screening tasks, such as employee hiring and academic admissions, in which a screener is tasked with selecting $k$ candidates from a candidate pool. The ISO refers to the order in which the screener searches the candidate pool. Today, it is common for the ISO to be the product of an information access system, such as an online platform or a database query. The ISO has been largely overlooked in the literature, despite its potential impact on the optimality and fairness of the chosen $k$ candidates, especially under a human screener. We define two problem formulations describing the search behavior of the screener under the ISO: the best-$k$, where the screener selects the $k$ best candidates; and the good-$k$, where the screener selects the $k$ first good-enough candidates. To study the impact of the ISO, we introduce a human-like screener and compare it to its algorithmic counterpart, where the human-like screener is conceived to be inconsistent over time due to fatigue. In particular, our analysis shows that the ISO, under a human-like screener solving for the good-$k$ problem, hinders individual fairness despite meeting group level fairness, and hampers the optimality of the selected $k$ candidates. This is due to position bias, where a candidate's evaluation is affected by its position within the ISO. We report extensive simulated experiments exploring the parameters of the best-$k$ and good-$k$ problems for the algorithmic and human-like screeners. The simulation framework is flexible enough to account for multiple screening settings, being an alternative to running real-world candidate screening procedures. This work is motivated by a real-world candidate screening problem studied in collaboration with an European company.

Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the main bottleneck of these methods is transforming image features into the BEV coordinate frame. This paper focuses on leveraging geometry information, such as depth, to model such feature transformation. Existing works rely on non-parametric depth distribution modeling leading to significant memory consumption, or ignore the geometry information to address this problem. In contrast, we propose to use parametric depth distribution modeling for feature transformation. We first lift the 2D image features to the 3D space defined for the ego vehicle via a predicted parametric depth distribution for each pixel in each view. Then, we aggregate the 3D feature volume based on the 3D space occupancy derived from depth to the BEV frame. Finally, we use the transformed features for downstream tasks such as object detection and semantic segmentation. Existing semantic segmentation methods do also suffer from an hallucination problem as they do not take visibility information into account. This hallucination can be particularly problematic for subsequent modules such as control and planning. To mitigate the issue, our method provides depth uncertainty and reliable visibility-aware estimations. We further leverage our parametric depth modeling to present a novel visibility-aware evaluation metric that, when taken into account, can mitigate the hallucination problem. Extensive experiments on object detection and semantic segmentation on the nuScenes datasets demonstrate that our method outperforms existing methods on both tasks.

This technical report summarizes the winning solution for the 3D Occupancy Prediction Challenge, which is held in conjunction with the CVPR 2023 Workshop on End-to-End Autonomous Driving and CVPR 23 Workshop on Vision-Centric Autonomous Driving Workshop. Our proposed solution FB-OCC builds upon FB-BEV, a cutting-edge camera-based bird's-eye view perception design using forward-backward projection. On top of FB-BEV, we further study novel designs and optimization tailored to the 3D occupancy prediction task, including joint depth-semantic pre-training, joint voxel-BEV representation, model scaling up, and effective post-processing strategies. These designs and optimization result in a state-of-the-art mIoU score of 54.19% on the nuScenes dataset, ranking the 1st place in the challenge track. Code and models will be released at: https://github.com/NVlabs/FB-BEV., Comment: Outstanding Champion and Innovation Award in the 3D Occupancy Prediction Challenge (CVPR23)

We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global representation learning. At a high level, global self-attentions enable the efficient cross-window communication at lower costs. FasterViT achieves a SOTA Pareto-front in terms of accuracy and image throughput. We have extensively validated its effectiveness on various CV tasks including classification, object detection and segmentation. We also show that HAT can be used as a plug-and-play module for existing networks and enhance them. We further demonstrate significantly faster and more accurate performance than competitive counterparts for images with high resolution. Code is available at https://github.com/NVlabs/FasterViT., Comment: ICLR'24 Accepted Paper

We describe a setup that is used for high-frequency electrical sample excitation in a cathode lens electron microscope with the sample stage at high voltage as used in many synchrotron light sources. Electrical signals are transmitted by dedicated high-frequency components to the printed circuit board supporting the sample. Sub-miniature push-on connectors (SMP) are used to realize the connection in the ultra-high vacuum chamber, bypassing the standard feedthrough. A bandwidth up to 4 GHz with -6 dB attenuation was measured at the sample position, which allows to apply sub-nanosecond pulses. We describe different electronic sample excitation schemes and demonstrate a spatial resolution of 56 nm employing the new setup.

PBC J2333.9-2343 is a giant radio galaxy at z = 0.047 with a bright central core associated to a blazar nucleus. If the nuclear blazar jet is a new phase of the jet activity, then the small orientation angle suggest a dramatic change of the jet direction. We present observations obtained between September 2018 and January 2019 (cadence larger than three days) with Effeslberg, SMARTS-1.3m, ZTF, ATLAS, Swift, and Fermi-LAT, and between April-July 2019 (daily cadence) with SMARTS-1.3m and ATLAS. Large (>2x) flux increases are observed on timescales shorter than a month, which are interpreted as flaring events. The cross correlation between the SMARTS-1.3m monitoring in the NIR and optical shows that these data do not show significant time lag within the measured errors. A comparison of the optical variability properties between non-blazars and blazars AGN shows that PBC J2333.9-2343 has properties more comparable to the latter. The SED of the nucleus shows two peaks, that were fitted with a one zone leptonic model. Our data and modelling shows that the high energy peak is dominated by External Compton from the dusty torus with mild contribution from Inverse Compton from the jet. The derived jet angle of 3 degrees is also typical of a blazar. Therefore, we confirm the presence of a blazar-like core in the center of this giant radio galaxy, likely a Flat Spectrum Radio Quasar with peculiar properties., Comment: Accepted for publication in MNRAS. 15 pages, 6 figures, 2 appendix including tables and figures

In uses of pre-trained machine learning models, it is a known issue that the target population in which the model is being deployed may not have been reflected in the source population with which the model was trained. This can result in a biased model when deployed, leading to a reduction in model performance. One risk is that, as the population changes, certain demographic groups will be under-served or otherwise disadvantaged by the model, even as they become more represented in the target population. The field of domain adaptation proposes techniques for a situation where label data for the target population does not exist, but some information about the target distribution does exist. In this paper we contribute to the domain adaptation literature by introducing domain-adaptive decision trees (DADT). We focus on decision trees given their growing popularity due to their interpretability and performance relative to other more complex models. With DADT we aim to improve the accuracy of models trained in a source domain (or training data) that differs from the target domain (or test data). We propose an in-processing step that adjusts the information gain split criterion with outside information corresponding to the distribution of the target population. We demonstrate DADT on real data and find that it improves accuracy over a standard decision tree when testing in a shifted target population. We also study the change in fairness under demographic parity and equal opportunity. Results show an improvement in fairness with the use of DADT., Comment: *Both authors contributed equally to this work. Accepted at FAccT '23

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This appealing ability is vital for recognition and understanding. To enable such capability in AI systems, we propose VoxFormer, a Transformer-based semantic scene completion framework that can output complete 3D volumetric semantics from only 2D images. Our framework adopts a two-stage design where we start from a sparse set of visible and occupied voxel queries from depth estimation, followed by a densification stage that generates dense 3D voxels from the sparse ones. A key idea of this design is that the visual features on 2D images correspond only to the visible scene structures rather than the occluded or empty spaces. Therefore, starting with the featurization and prediction of the visible structures is more reliable. Once we obtain the set of sparse queries, we apply a masked autoencoder design to propagate the information to all the voxels by self-attention. Experiments on SemanticKITTI show that VoxFormer outperforms the state of the art with a relative improvement of 20.0% in geometry and 18.1% in semantics and reduces GPU memory during training to less than 16GB. Our code is available on https://github.com/NVlabs/VoxFormer., Comment: CVPR 2023 Highlight (10% of accepted papers, 2.5% of submissions)

We present counterfactual situation testing (CST), a causal data mining framework for detecting discrimination in classifiers. CST aims to answer in an actionable and meaningful way the intuitive question "what would have been the model outcome had the individual, or complainant, been of a different protected status?" It extends the legally-grounded situation testing of Thanh et al. (2011) by operationalizing the notion of fairness given the difference using counterfactual reasoning. For any complainant, we find and compare similar protected and non-protected instances in the dataset used by the classifier to construct a control and test group, where a difference between the decision outcomes of the two groups implies potential individual discrimination. Unlike situation testing, which builds both groups around the complainant, we build the test group on the complainant's counterfactual generated using causal knowledge. The counterfactual is intended to reflect how the protected attribute when changed affects the seemingly neutral attributes used by the classifier, which is taken for granted in many frameworks for discrimination. Under CST, we compare similar individuals within each group but dissimilar individuals across both groups due to the possible difference between the complainant and its counterfactual. Evaluating our framework on two classification scenarios, we show that it uncovers a greater number of cases than situation testing, even when the classifier satisfies the counterfactual fairness condition of Kusner et al. (2017).

We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask auto-labeling framework for instance segmentation using only box annotations. MAL takes box-cropped images as inputs and conditionally generates their mask pseudo-labels.We show that Vision Transformers are good mask auto-labelers. Our method significantly reduces the gap between auto-labeling and human annotation regarding mask quality. Instance segmentation models trained using the MAL-generated masks can nearly match the performance of their fully-supervised counterparts, retaining up to 97.4\% performance of fully supervised models. The best model achieves 44.1\% mAP on COCO instance segmentation (test-dev 2017), outperforming state-of-the-art box-supervised methods by significant margins. Qualitative results indicate that masks produced by MAL are, in some cases, even better than human annotations.

Structured channel pruning has been shown to significantly accelerate inference time for convolution neural networks (CNNs) on modern hardware, with a relatively minor loss of network accuracy. Recent works permanently zero these channels during training, which we observe to significantly hamper final accuracy, particularly as the fraction of the network being pruned increases. We propose Soft Masking for cost-constrained Channel Pruning (SMCP) to allow pruned channels to adaptively return to the network while simultaneously pruning towards a target cost constraint. By adding a soft mask re-parameterization of the weights and channel pruning from the perspective of removing input channels, we allow gradient updates to previously pruned channels and the opportunity for the channels to later return to the network. We then formulate input channel pruning as a global resource allocation problem. Our method outperforms prior works on both the ImageNet classification and PASCAL VOC detection datasets., Comment: Accepted by ECCV 2022

Structural pruning can simplify network architecture and improve inference speed. We propose Hardware-Aware Latency Pruning (HALP) that formulates structural pruning as a global resource allocation optimization problem, aiming at maximizing the accuracy while constraining latency under a predefined budget on targeting device. For filter importance ranking, HALP leverages latency lookup table to track latency reduction potential and global saliency score to gauge accuracy drop. Both metrics can be evaluated very efficiently during pruning, allowing us to reformulate global structural pruning under a reward maximization problem given target constraint. This makes the problem solvable via our augmented knapsack solver, enabling HALP to surpass prior work in pruning efficacy and accuracy-efficiency trade-off. We examine HALP on both classification and detection tasks, over varying networks, on ImageNet and VOC datasets, on different platforms. In particular, for ResNet-50/-101 pruning on ImageNet, HALP improves network throughput by $1.60\times$/$1.90\times$ with $+0.3\%$/$-0.2\%$ top-1 accuracy changes, respectively. For SSD pruning on VOC, HALP improves throughput by $1.94\times$ with only a $0.56$ mAP drop. HALP consistently outperforms prior art, sometimes by large margins. Project page at https://halp-neurips.github.io/., Comment: Accepted by NeurIPS 2022. arXiv admin note: substantial text overlap with arXiv:2110.10811

Modern deep learning systems require huge data sets to achieve impressive performance, but there is little guidance on how much or what kind of data to collect. Over-collecting data incurs unnecessary present costs, while under-collecting may incur future costs and delay workflows. We propose a new paradigm for modeling the data collection workflow as a formal optimal data collection problem that allows designers to specify performance targets, collection costs, a time horizon, and penalties for failing to meet the targets. Additionally, this formulation generalizes to tasks requiring multiple data sources, such as labeled and unlabeled data used in semi-supervised learning. To solve our problem, we develop Learn-Optimize-Collect (LOC), which minimizes expected future collection costs. Finally, we numerically compare our framework to the conventional baseline of estimating data requirements by extrapolating from neural scaling laws. We significantly reduce the risks of failing to meet desired performance targets on several classification, segmentation, and detection tasks, while maintaining low total collection costs., Comment: Accepted to NeurIPS 2022