Alert button
Picture for Vasu Sharma

Vasu Sharma

Alert button

FLAP: Fast Language-Audio Pre-training

Nov 02, 2023
Ching-Feng Yeh, Po-Yao Huang, Vasu Sharma, Shang-Wen Li, Gargi Gosh

We propose Fast Language-Audio Pre-training (FLAP), a self-supervised approach that efficiently and effectively learns aligned audio and language representations through masking, contrastive learning and reconstruction. For efficiency, FLAP randomly drops audio spectrogram tokens, focusing solely on the remaining ones for self-supervision. Through inter-modal contrastive learning, FLAP learns to align paired audio and text representations in a shared latent space. Notably, FLAP leverages multiple augmented views via masking for inter-modal contrast and learns to reconstruct the masked portion of audio tokens. Moreover, FLAP leverages large language models (LLMs) to augment the text inputs, contributing to improved performance. These approaches lead to more robust and informative audio-text representations, enabling FLAP to achieve state-of-the-art (SoTA) performance on audio-text retrieval tasks on AudioCaps (achieving 53.0% R@1) and Clotho (achieving 25.5% R@1).

* 6 pages 
Viaarxiv icon

Demystifying CLIP Data

Oct 02, 2023
Hu Xu, Saining Xie, Xiaoqing Ellen Tan, Po-Yao Huang, Russell Howes, Vasu Sharma, Shang-Wen Li, Gargi Ghosh, Luke Zettlemoyer, Christoph Feichtenhofer

Figure 1 for Demystifying CLIP Data
Figure 2 for Demystifying CLIP Data
Figure 3 for Demystifying CLIP Data
Figure 4 for Demystifying CLIP Data

Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative models. We believe that the main ingredient to the success of CLIP is its data and not the model architecture or pre-training objective. However, CLIP only provides very limited information about its data and how it has been collected, leading to works that aim to reproduce CLIP's data by filtering with its model parameters. In this work, we intend to reveal CLIP's data curation approach and in our pursuit of making it open to the community introduce Metadata-Curated Language-Image Pre-training (MetaCLIP). MetaCLIP takes a raw data pool and metadata (derived from CLIP's concepts) and yields a balanced subset over the metadata distribution. Our experimental study rigorously isolates the model and training settings, concentrating solely on data. MetaCLIP applied to CommonCrawl with 400M image-text data pairs outperforms CLIP's data on multiple standard benchmarks. In zero-shot ImageNet classification, MetaCLIP achieves 70.8% accuracy, surpassing CLIP's 68.3% on ViT-B models. Scaling to 1B data, while maintaining the same training budget, attains 72.4%. Our observations hold across various model sizes, exemplified by ViT-H achieving 80.5%, without any bells-and-whistles. Curation code and training data distribution on metadata is made available at https://github.com/facebookresearch/MetaCLIP.

* 17 pages. arXiv admin note: text overlap with arXiv:2103.00020 by other authors 
Viaarxiv icon

Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning

Sep 05, 2023
Lili Yu, Bowen Shi, Ramakanth Pasunuru, Benjamin Muller, Olga Golovneva, Tianlu Wang, Arun Babu, Binh Tang, Brian Karrer, Shelly Sheynin, Candace Ross, Adam Polyak, Russell Howes, Vasu Sharma, Puxin Xu, Hovhannes Tamoyan, Oron Ashual, Uriel Singer, Shang-Wen Li, Susan Zhang, Richard James, Gargi Ghosh, Yaniv Taigman, Maryam Fazel-Zarandi, Asli Celikyilmaz, Luke Zettlemoyer, Armen Aghajanyan

Figure 1 for Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
Figure 2 for Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
Figure 3 for Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
Figure 4 for Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning

We present CM3Leon (pronounced "Chameleon"), a retrieval-augmented, token-based, decoder-only multi-modal language model capable of generating and infilling both text and images. CM3Leon uses the CM3 multi-modal architecture but additionally shows the extreme benefits of scaling up and tuning on more diverse instruction-style data. It is the first multi-modal model trained with a recipe adapted from text-only language models, including a large-scale retrieval-augmented pre-training stage and a second multi-task supervised fine-tuning (SFT) stage. It is also a general-purpose model that can do both text-to-image and image-to-text generation, allowing us to introduce self-contained contrastive decoding methods that produce high-quality outputs. Extensive experiments demonstrate that this recipe is highly effective for multi-modal models. CM3Leon achieves state-of-the-art performance in text-to-image generation with 5x less training compute than comparable methods (zero-shot MS-COCO FID of 4.88). After SFT, CM3Leon can also demonstrate unprecedented levels of controllability in tasks ranging from language-guided image editing to image-controlled generation and segmentation.

Viaarxiv icon

Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI

Aug 09, 2023
Hangjie Shi, Leslie Ball, Govind Thattai, Desheng Zhang, Lucy Hu, Qiaozi Gao, Suhaila Shakiah, Xiaofeng Gao, Aishwarya Padmakumar, Bofei Yang, Cadence Chung, Dinakar Guthy, Gaurav Sukhatme, Karthika Arumugam, Matthew Wen, Osman Ipek, Patrick Lange, Rohan Khanna, Shreyas Pansare, Vasu Sharma, Chao Zhang, Cris Flagg, Daniel Pressel, Lavina Vaz, Luke Dai, Prasoon Goyal, Sattvik Sahai, Shaohua Liu, Yao Lu, Anna Gottardi, Shui Hu, Yang Liu, Dilek Hakkani-Tur, Kate Bland, Heather Rocker, James Jeun, Yadunandana Rao, Michael Johnston, Akshaya Iyengar, Arindam Mandal, Prem Natarajan, Reza Ghanadan

Figure 1 for Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
Figure 2 for Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
Figure 3 for Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
Figure 4 for Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI

The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge. As conversational agents increasingly appear in multimodal and embodied contexts, it is important to explore the affordances of conversational interaction augmented with computer vision and physical embodiment. This paper describes the SimBot Challenge, a new challenge in which university teams compete to build robot assistants that complete tasks in a simulated physical environment. This paper provides an overview of the SimBot Challenge, which included both online and offline challenge phases. We describe the infrastructure and support provided to the teams including Alexa Arena, the simulated environment, and the ML toolkit provided to teams to accelerate their building of vision and language models. We summarize the approaches the participating teams took to overcome research challenges and extract key lessons learned. Finally, we provide analysis of the performance of the competing SimBots during the competition.

Viaarxiv icon

DINOv2: Learning Robust Visual Features without Supervision

Apr 14, 2023
Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski

Figure 1 for DINOv2: Learning Robust Visual Features without Supervision
Figure 2 for DINOv2: Learning Robust Visual Features without Supervision
Figure 3 for DINOv2: Learning Robust Visual Features without Supervision
Figure 4 for DINOv2: Learning Robust Visual Features without Supervision

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques to scale our pretraining in terms of data and model size. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature. In terms of models, we train a ViT model (Dosovitskiy et al., 2020) with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP (Ilharco et al., 2021) on most of the benchmarks at image and pixel levels.

Viaarxiv icon

Alexa Arena: A User-Centric Interactive Platform for Embodied AI

Mar 02, 2023
Qiaozi Gao, Govind Thattai, Xiaofeng Gao, Suhaila Shakiah, Shreyas Pansare, Vasu Sharma, Gaurav Sukhatme, Hangjie Shi, Bofei Yang, Desheng Zheng, Lucy Hu, Karthika Arumugam, Shui Hu, Matthew Wen, Dinakar Guthy, Cadence Chung, Rohan Khanna, Osman Ipek, Leslie Ball, Kate Bland, Heather Rocker, Yadunandana Rao, Michael Johnston, Reza Ghanadan, Arindam Mandal, Dilek Hakkani Tur, Prem Natarajan

Figure 1 for Alexa Arena: A User-Centric Interactive Platform for Embodied AI
Figure 2 for Alexa Arena: A User-Centric Interactive Platform for Embodied AI
Figure 3 for Alexa Arena: A User-Centric Interactive Platform for Embodied AI
Figure 4 for Alexa Arena: A User-Centric Interactive Platform for Embodied AI

We introduce Alexa Arena, a user-centric simulation platform for Embodied AI (EAI) research. Alexa Arena provides a variety of multi-room layouts and interactable objects, for the creation of human-robot interaction (HRI) missions. With user-friendly graphics and control mechanisms, Alexa Arena supports the development of gamified robotic tasks readily accessible to general human users, thus opening a new venue for high-efficiency HRI data collection and EAI system evaluation. Along with the platform, we introduce a dialog-enabled instruction-following benchmark and provide baseline results for it. We make Alexa Arena publicly available to facilitate research in building generalizable and assistive embodied agents.

Viaarxiv icon

MAViL: Masked Audio-Video Learners

Dec 15, 2022
Po-Yao Huang, Vasu Sharma, Hu Xu, Chaitanya Ryali, Haoqi Fan, Yanghao Li, Shang-Wen Li, Gargi Ghosh, Jitendra Malik, Christoph Feichtenhofer

Figure 1 for MAViL: Masked Audio-Video Learners
Figure 2 for MAViL: Masked Audio-Video Learners
Figure 3 for MAViL: Masked Audio-Video Learners
Figure 4 for MAViL: Masked Audio-Video Learners

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks. Code will be available soon.

* Technical report 
Viaarxiv icon

CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning

Aug 26, 2022
Vasu Sharma, Prasoon Goyal, Kaixiang Lin, Govind Thattai, Qiaozi Gao, Gaurav S. Sukhatme

Figure 1 for CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning
Figure 2 for CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning
Figure 3 for CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning
Figure 4 for CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning

We propose a multimodal (vision-and-language) benchmark for cooperative and heterogeneous multi-agent learning. We introduce a benchmark multimodal dataset with tasks involving collaboration between multiple simulated heterogeneous robots in a rich multi-room home environment. We provide an integrated learning framework, multimodal implementations of state-of-the-art multi-agent reinforcement learning techniques, and a consistent evaluation protocol. Our experiments investigate the impact of different modalities on multi-agent learning performance. We also introduce a simple message passing method between agents. The results suggest that multimodality introduces unique challenges for cooperative multi-agent learning and there is significant room for advancing multi-agent reinforcement learning methods in such settings.

Viaarxiv icon

Community Regularization of Visually-Grounded Dialog

Sep 06, 2018
Akshat Agarwal, Swaminathan Gurumurthy, Vasu Sharma, Mike Lewis, Katia Sycara

Figure 1 for Community Regularization of Visually-Grounded Dialog
Figure 2 for Community Regularization of Visually-Grounded Dialog
Figure 3 for Community Regularization of Visually-Grounded Dialog
Figure 4 for Community Regularization of Visually-Grounded Dialog

The task of conducting visually grounded dialog involves learning goal-oriented cooperative dialog between autonomous agents who exchange information about a scene through several rounds of questions and answers in natural language. We posit that requiring artificial agents to adhere to the rules of human language, while also requiring them to maximize information exchange through dialog is an ill-posed problem. We observe that humans do not stray from a common language because they are social creatures who live in communities, and have to communicate with many people everyday, so it is far easier to stick to a common language even at the cost of some efficiency loss. Using this as inspiration, we propose and evaluate a multi-agent community-based dialog framework where each agent interacts with, and learns from, multiple agents, and show that this community-enforced regularization results in more relevant and coherent dialog (as judged by human evaluators) without sacrificing task performance (as judged by quantitative metrics).

* 7 pages, ICML/AAMAS Adaptive Learning Agents Workshop 2018 and CVPR Visual Dialog Workshop 2018. Code available at https://github.com/agakshat/visualdialog-pytorch 
Viaarxiv icon