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.
Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA), a modular framework for zero-shot VQA. In contrast to most existing works, which require substantial adaptation of pretrained language models (PLMs) for the vision modality, PNP-VQA requires no additional training of the PLMs. Instead, we propose to use natural language and network interpretation as an intermediate representation that glues pretrained models together. We first generate question-guided informative image captions, and pass the captions to a PLM as context for question answering. Surpassing end-to-end trained baselines, PNP-VQA achieves state-of-the-art results on zero-shot VQAv2 and GQA. With 11B parameters, it outperforms the 80B-parameter Flamingo model by 8.5% on VQAv2. With 738M PLM parameters, PNP-VQA achieves an improvement of 9.1% on GQA over FewVLM with 740M PLM parameters. Code is released at https://github.com/salesforce/LAVIS/tree/main/projects/pnp-vqa
We introduce LAVIS, an open-source deep learning library for LAnguage-VISion research and applications. LAVIS aims to serve as a one-stop comprehensive library that brings recent advancements in the language-vision field accessible for researchers and practitioners, as well as fertilizing future research and development. It features a unified interface to easily access state-of-the-art image-language, video-language models and common datasets. LAVIS supports training, evaluation and benchmarking on a rich variety of tasks, including multimodal classification, retrieval, captioning, visual question answering, dialogue and pre-training. In the meantime, the library is also highly extensible and configurable, facilitating future development and customization. In this technical report, we describe design principles, key components and functionalities of the library, and also present benchmarking results across common language-vision tasks. The library is available at: https://github.com/salesforce/LAVIS.
Recent research in multi-task learning reveals the benefit of solving related problems in a single neural network. 3D object detection and multi-object tracking (MOT) are two heavily intertwined problems predicting and associating an object instance location across time. However, most previous works in 3D MOT treat the detector as a preceding separated pipeline, disjointly taking the output of the detector as an input to the tracker. In this work, we present Minkowski Tracker, a sparse spatio-temporal R-CNN that jointly solves object detection and tracking. Inspired by region-based CNN (R-CNN), we propose to solve tracking as a second stage of the object detector R-CNN that predicts assignment probability to tracks. First, Minkowski Tracker takes 4D point clouds as input to generate a spatio-temporal Bird's-eye-view (BEV) feature map through a 4D sparse convolutional encoder network. Then, our proposed TrackAlign aggregates the track region-of-interest (ROI) features from the BEV features. Finally, Minkowski Tracker updates the track and its confidence score based on the detection-to-track match probability predicted from the ROI features. We show in large-scale experiments that the overall performance gain of our method is due to four factors: 1. The temporal reasoning of the 4D encoder improves the detection performance 2. The multi-task learning of object detection and MOT jointly enhances each other 3. The detection-to-track match score learns implicit motion model to enhance track assignment 4. The detection-to-track match score improves the quality of the track confidence score. As a result, Minkowski Tracker achieved the state-of-the-art performance on Nuscenes dataset tracking task without hand-designed motion models.
Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.
We introduce OmniXAI (short for Omni eXplainable AI), an open-source Python library of eXplainable AI (XAI), which offers omni-way explainable AI capabilities and various interpretable machine learning techniques to address the pain points of understanding and interpreting the decisions made by machine learning (ML) in practice. OmniXAI aims to be a one-stop comprehensive library that makes explainable AI easy for data scientists, ML researchers and practitioners who need explanation for various types of data, models and explanation methods at different stages of ML process (data exploration, feature engineering, model development, evaluation, and decision-making, etc). In particular, our library includes a rich family of explanation methods integrated in a unified interface, which supports multiple data types (tabular data, images, texts, time-series), multiple types of ML models (traditional ML in Scikit-learn and deep learning models in PyTorch/TensorFlow), and a range of diverse explanation methods including "model-specific" and "model-agnostic" ones (such as feature-attribution explanation, counterfactual explanation, gradient-based explanation, etc). For practitioners, the library provides an easy-to-use unified interface to generate the explanations for their applications by only writing a few lines of codes, and also a GUI dashboard for visualization of different explanations for more insights about decisions. In this technical report, we present OmniXAI's design principles, system architectures, and major functionalities, and also demonstrate several example use cases across different types of data, tasks, and models.
State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved impressive progress, it still requires a second stage of finetuning on labeled data. On the other hand, models pre-trained with large-scale text-image supervision (e.g., CLIP) have enabled zero-shot transfer to downstream image classification tasks. However, the zero-shot performance of CLIP-like models are often insufficient for real-world adoption. In this paper, we aim to leverage the abundant unlabeled data to improve the performance of a pre-trained zero-shot classifier on downstream tasks. We propose Masked Unsupervised Self-Training (MUST), a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST jointly optimizes three objectives to learn both class-level global feature and pixel-level local feature and enforces a regularization between the two. We demonstrate the efficacy of MUST on 8 downstream tasks across a variety of domains, where it improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification. For instance, MUST achieves a zero-shot top-1 accuracy of 77.7% on ImageNet using ViT-B, +9.4% higher than CLIP. Our code is available at https://github.com/salesforce/MUST.
Program synthesis strives to generate a computer program as a solution to a given problem specification. We propose a conversational program synthesis approach via large language models, which addresses the challenges of searching over a vast program space and user intent specification faced in prior approaches. Our new approach casts the process of writing a specification and program as a multi-turn conversation between a user and a system. It treats program synthesis as a sequence prediction problem, in which the specification is expressed in natural language and the desired program is conditionally sampled. We train a family of large language models, called CodeGen, on natural language and programming language data. With weak supervision in the data and the scaling up of data size and model size, conversational capacities emerge from the simple autoregressive language modeling. To study the model behavior on conversational program synthesis, we develop a multi-turn programming benchmark (MTPB), where solving each problem requires multi-step synthesis via multi-turn conversation between the user and the model. Our findings show the emergence of conversational capabilities and the effectiveness of the proposed conversational program synthesis paradigm. In addition, our model CodeGen (with up to 16B parameters trained on TPU-v4) outperforms OpenAI's Codex on the HumanEval benchmark. We make the training library JaxFormer including checkpoints available as open source contribution: https://github.com/salesforce/CodeGen.
Text summarization aims to condense long documents and retain key information. Critical to the success of a summarization model is the faithful inference of latent representations of words or tokens in the source documents. Most recent models infer the latent representations with a transformer encoder, which is purely bottom-up. Also, self-attention-based inference models face the challenge of quadratic complexity with respect to sequence length. We propose a principled inference framework to improve summarization models on these two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency at a coarser time scale and the bottom token level preserves the details. Critically, this hierarchical structure enables token representations to be updated in both a bottom-up and top-down manner. In the bottom-up pass, token representations are inferred with local self-attention to leverage its efficiency. Top-down correction is then applied to allow tokens to capture long-range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets, including narrative, conversational, scientific documents and news. Our model achieves (1) competitive or better performance on short documents with higher memory and compute efficiency, compared to full attention transformers, and (2) state-of-the-art performance on a wide range of long document summarization benchmarks, compared to recent efficient transformers. We also show that our model can summarize an entire book and achieve competitive performance using $0.27\%$ parameters (464M vs. 175B) and much less training data, compared to a recent GPT-3-based model. These results indicate the general applicability and benefits of the proposed framework.