Abstract: We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual 'foundation models' for Embodied AI. First, we curate CortexBench, consisting of 17 different tasks spanning locomotion, navigation, dexterous, and mobile manipulation. Next, we systematically evaluate existing PVRs and find that none are universally dominant. To study the effect of pre-training data scale and diversity, we combine over 4,000 hours of egocentric videos from 7 different sources (over 5.6M images) and ImageNet to train different-sized vision transformers using Masked Auto-Encoding (MAE) on slices of this data. Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average). Our largest model, named VC-1, outperforms all prior PVRs on average but does not universally dominate either. Finally, we show that task or domain-specific adaptation of VC-1 leads to substantial gains, with VC-1 (adapted) achieving competitive or superior performance than the best known results on all of the benchmarks in CortexBench. These models required over 10,000 GPU-hours to train and can be found on our website for the benefit of the research community.

Abstract: We present a single neural network architecture composed of task-agnostic components (ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav ("go to location in this picture") and ObjectNav ("find a chair") tasks without any task-specific modules like object detection, segmentation, mapping, or planning modules. Such general-purpose methods offer advantages of simplicity in design, positive scaling with available compute, and versatile applicability to multiple tasks.

Our work builds upon the recent success of self-supervised learning (SSL) for pre-training vision transformers (ViT). However, while the training recipes for convolutional networks are mature and robust, the recipes for ViTs are contingent and brittle, and in the case of ViTs for visual navigation, yet to be fully discovered. Specifically, we find that vanilla ViTs do not outperform ResNets on visual navigation. We propose the use of a compression layer operating over ViT patch representations to preserve spatial information along with policy training improvements. These improvements allow us to demonstrate positive scaling laws for the first time in visual navigation tasks. Consequently, our model advances state-of-the-art performance on ImageNav from 54.2% to 82.0% success and performs competitively against concurrent state-of-art on ObjectNav with success rate of 64.0% vs. 65.0%.

Overall, this work does not present a fundamentally new approach, but rather recommendations for training a general-purpose architecture that achieves state-of-art performance today and could serve as a strong baseline for future methods.

Abstract: We present a scalable approach for learning open-world object-goal navigation (ObjectNav) -- the task of asking a virtual robot (agent) to find any instance of an object in an unexplored environment (e.g., "find a sink"). Our approach is entirely zero-shot -- i.e., it does not require ObjectNav rewards or demonstrations of any kind. Instead, we train on the image-goal navigation (ImageNav) task, in which agents find the location where a picture (i.e., goal image) was captured. Specifically, we encode goal images into a multimodal, semantic embedding space to enable training semantic-goal navigation (SemanticNav) agents at scale in unannotated 3D environments (e.g., HM3D). After training, SemanticNav agents can be instructed to find objects described in free-form natural language (e.g., "sink", "bathroom sink", etc.) by projecting language goals into the same multimodal, semantic embedding space. As a result, our approach enables open-world ObjectNav. We extensively evaluate our agents on three ObjectNav datasets (Gibson, HM3D, and MP3D) and observe absolute improvements in success of 4.2% - 20.0% over existing zero-shot methods. For reference, these gains are similar or better than the 5% improvement in success between the Habitat 2020 and 2021 ObjectNav challenge winners. In an open-world setting, we discover that our agents can generalize to compound instructions with a room explicitly mentioned (e.g., "Find a kitchen sink") and when the target room can be inferred (e.g., "Find a sink and a stove").

Abstract: How should we learn visual representations for embodied agents that must see and move? The status quo is tabula rasa in vivo, i.e. learning visual representations from scratch while also learning to move, potentially augmented with auxiliary tasks (e.g. predicting the action taken between two successive observations). In this paper, we show that an alternative 2-stage strategy is far more effective: (1) offline pretraining of visual representations with self-supervised learning (SSL) using large-scale pre-rendered images of indoor environments (Omnidata), and (2) online finetuning of visuomotor representations on specific tasks with image augmentations under long learning schedules. We call this method Offline Visual Representation Learning (OVRL). We conduct large-scale experiments - on 3 different 3D datasets (Gibson, HM3D, MP3D), 2 tasks (ImageNav, ObjectNav), and 2 policy learning algorithms (RL, IL) - and find that the OVRL representations lead to significant across-the-board improvements in state of art, on ImageNav from 29.2% to 54.2% (+25% absolute, 86% relative) and on ObjectNav from 18.1% to 23.2% (+5.1% absolute, 28% relative). Importantly, both results were achieved by the same visual encoder generalizing to datasets that were not seen during pretraining. While the benefits of pretraining sometimes diminish (or entirely disappear) with long finetuning schedules, we find that OVRL's performance gains continue to increase (not decrease) as the agent is trained for 2 billion frames of experience.

Abstract: Natural language instructions for visual navigation often use scene descriptions (e.g., "bedroom") and object references (e.g., "green chairs") to provide a breadcrumb trail to a goal location. This work presents a transformer-based vision-and-language navigation (VLN) agent that uses two different visual encoders -- a scene classification network and an object detector -- which produce features that match these two distinct types of visual cues. In our method, scene features contribute high-level contextual information that supports object-level processing. With this design, our model is able to use vision-and-language pretraining (i.e., learning the alignment between images and text from large-scale web data) to substantially improve performance on the Room-to-Room (R2R) and Room-Across-Room (RxR) benchmarks. Specifically, our approach leads to improvements of 1.8% absolute in SPL on R2R and 3.7% absolute in SR on RxR. Our analysis reveals even larger gains for navigation instructions that contain six or more object references, which further suggests that our approach is better able to use object features and align them to references in the instructions.

Abstract: We study the challenging problem of releasing a robot in a previously unseen environment, and having it follow unconstrained natural language navigation instructions. Recent work on the task of Vision-and-Language Navigation (VLN) has achieved significant progress in simulation. To assess the implications of this work for robotics, we transfer a VLN agent trained in simulation to a physical robot. To bridge the gap between the high-level discrete action space learned by the VLN agent, and the robot’s low-level continuous action space, we propose a subgoal model to identify nearby waypoints, and use domain randomization to mitigate visual domain differences. For accurate sim and real comparisons in parallel environments, we annotate a 325m2 office space with 1.3km of navigation instructions, and create a digitized replica in simulation. We find that sim-to-real transfer to an environment not seen in training is successful if an occupancy map and navigation graph can be collected and annotated in advance (success rate of 46.8% vs. 55.9% in sim), but much more challenging in the hardest setting with no prior mapping at all (success rate of 22.5%).

Abstract: Following a navigation instruction such as 'Walk down the stairs and stop at the brown sofa' requires embodied AI agents to ground scene elements referenced via language (e.g. 'stairs') to visual content in the environment (pixels corresponding to 'stairs').

We ask the following question -- Can we leverage abundant 'disembodied' web-scraped vision-and-language corpora (e.g. Conceptual Captions) to learn visual groundings (what do 'stairs' look like?) that improve performance on a relatively data-starved embodied perception task (Vision-and-Language Navigation)? Specifically, we develop VLN-BERT, a visiolinguistic transformer-based model for scoring the compatibility between an instruction ('...stop at the brown sofa') and a sequence of panoramic RGB images captured by the agent. We demonstrate that pretraining VLN-BERT on image-text pairs from the web before fine-tuning on embodied path-instruction data significantly improves performance on VLN -- outperforming the prior state-of-the-art in the fully-observed setting by 4 absolute percentage points on success rate. Ablations of our pretraining curriculum show each stage to be impactful -- with their combination resulting in further positive synergistic effects.

Abstract: We develop a language-guided navigation task set in a continuous 3D environment where agents must execute low-level actions to follow natural language navigation directions. By being situated in continuous environments, this setting lifts a number of assumptions implicit in prior work that represents environments as a sparse graph of panoramas with edges corresponding to navigability. Specifically, our setting drops the presumptions of known environment topologies, short-range oracle navigation, and perfect agent localization. To contextualize this new task, we develop models that mirror many of the advances made in prior settings as well as single-modality baselines. While some of these techniques transfer, we find significantly lower absolute performance in the continuous setting -- suggesting that performance in prior `navigation-graph' settings may be inflated by the strong implicit assumptions.

Abstract: Visual question answering requires high-order reasoning about an image, which is a fundamental capability needed by machine systems to follow complex directives. Recently, modular networks have been shown to be an effective framework for performing visual reasoning tasks. While modular networks were initially designed with a degree of model transparency, their performance on complex visual reasoning benchmarks was lacking. Current state-of-the-art approaches do not provide an effective mechanism for understanding the reasoning process. In this paper, we close the performance gap between interpretable models and state-of-the-art visual reasoning methods. We propose a set of visual-reasoning primitives which, when composed, manifest as a model capable of performing complex reasoning tasks in an explicitly-interpretable manner. The fidelity and interpretability of the primitives’ outputs enable an unparalleled ability to diagnose the strengths and weaknesses of the resulting model. Critically, we show that these primitives are highly performant, achieving state-of-the-art accuracy of 99.1% on the CLEVR dataset. We also show that our model is able to effectively learn generalized representations when provided a small amount of data containing novel object attributes. Using the CoGenT generalization task, we show more than a 20 percentage point improvement over the current state of the art.

Abstract: Initial results are reported on automated detection of intracranial hemorrhage from CT, which would be valuable in a computer-aided diagnosis system to help the radiologist detect subtle hemorrhages. Previous work has taken a classic approach involving multiple steps of alignment, image processing, image corrections, handcrafted feature extraction, and classification. Our current work instead uses a deep convolutional neural network to simultaneously learn features and classification, eliminating the multiple hand-tuned steps. Performance is improved by computing the mean output for rotations of the input image. Postprocessing is additionally applied to the CNN output to significantly improve specificity. The database consists of 134 CT cases (4,300 images), divided into 60, 5, and 69 cases for training, validation, and test. Each case typically includes multiple hemorrhages. Performance on the test set was 81% sensitivity per lesion (34/42 lesions) and 98% specificity per case (45/46 cases). The sensitivity is comparable to previous results (on different datasets), but with a significantly higher specificity. In addition, insights are shared to improve performance as the database is expanded.

Abstract: In recent years, convolutional neural networks (CNNs) have been successfully applied for automatic target recognition (ATR) in synthetic aperture radar (SAR) data. However, it is challenging to train a CNN with high classification accuracy when labeled data is limited. This is often the case with SAR ATR in practice, because collecting large amounts of labeled SAR data is both difficult and expensive. Using a simulator to generate SAR images offers a possible solution. Unfortunately, CNNs trained on simulated data may not be directly transferable to real data. In this paper, we introduce a method to refine simulated SAR data based on deep residual networks. We learn a refinement function from simulated to real SAR data through a residual learning framework, and use the function to refine simulated images. Using the MSTAR dataset, we demonstrate that a CNN-based SAR ATR system trained on simulated data under residual network refinements can yield much higher classification accuracy as compared to a system trained on simulated images, and so can training on real data augmented with these simulated data under refinements compared to training with real data alone.