Alert button
Picture for Aude Oliva

Aude Oliva

Alert button

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

Mar 30, 2023
Paola Cascante-Bonilla, Khaled Shehada, James Seale Smith, Sivan Doveh, Donghyun Kim, Rameswar Panda, Gül Varol, Aude Oliva, Vicente Ordonez, Rogerio Feris, Leonid Karlinsky

Figure 1 for Going Beyond Nouns With Vision & Language Models Using Synthetic Data
Figure 2 for Going Beyond Nouns With Vision & Language Models Using Synthetic Data
Figure 3 for Going Beyond Nouns With Vision & Language Models Using Synthetic Data
Figure 4 for Going Beyond Nouns With Vision & Language Models Using Synthetic Data

Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural language prompts. However, recent works have uncovered a fundamental weakness of these models. For example, their difficulty to understand Visual Language Concepts (VLC) that go 'beyond nouns' such as the meaning of non-object words (e.g., attributes, actions, relations, states, etc.), or difficulty in performing compositional reasoning such as understanding the significance of the order of the words in a sentence. In this work, we investigate to which extent purely synthetic data could be leveraged to teach these models to overcome such shortcomings without compromising their zero-shot capabilities. We contribute Synthetic Visual Concepts (SyViC) - a million-scale synthetic dataset and data generation codebase allowing to generate additional suitable data to improve VLC understanding and compositional reasoning of VL models. Additionally, we propose a general VL finetuning strategy for effectively leveraging SyViC towards achieving these improvements. Our extensive experiments and ablations on VL-Checklist, Winoground, and ARO benchmarks demonstrate that it is possible to adapt strong pre-trained VL models with synthetic data significantly enhancing their VLC understanding (e.g. by 9.9% on ARO and 4.3% on VL-Checklist) with under 1% drop in their zero-shot accuracy.

* Project page: https://synthetic-vic.github.io/ 
Viaarxiv icon

Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines

Jun 02, 2022
Camilo Fosco, Emilie Josephs, Alex Andonian, Allen Lee, Xi Wang, Aude Oliva

Figure 1 for Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines
Figure 2 for Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines
Figure 3 for Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines
Figure 4 for Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines

Deepfakes pose a serious threat to our digital society by fueling the spread of misinformation. It is essential to develop techniques that both detect them, and effectively alert the human user to their presence. Here, we introduce a novel deepfake detection framework that meets both of these needs. Our approach learns to generate attention maps of video artifacts, semi-supervised on human annotations. These maps make two contributions. First, they improve the accuracy and generalizability of a deepfake classifier, demonstrated across several deepfake detection datasets. Second, they allow us to generate an intuitive signal for the human user, in the form of "Deepfake Caricatures": transformations of the original deepfake video where attended artifacts are exacerbated to improve human recognition. Our approach, based on a mixture of human and artificial supervision, aims to further the development of countermeasures against fake visual content, and grants humans the ability to make their own judgment when presented with dubious visual media.

* 9 pages, 5 figures, 4 tables 
Viaarxiv icon

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Oct 13, 2021
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik

Figure 1 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 2 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 3 for Ego4D: Around the World in 3,000 Hours of Egocentric Video
Figure 4 for Ego4D: Around the World in 3,000 Hours of Egocentric Video

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,025 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 855 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

Viaarxiv icon

Dynamic Network Quantization for Efficient Video Inference

Aug 23, 2021
Ximeng Sun, Rameswar Panda, Chun-Fu Chen, Aude Oliva, Rogerio Feris, Kate Saenko

Figure 1 for Dynamic Network Quantization for Efficient Video Inference
Figure 2 for Dynamic Network Quantization for Efficient Video Inference
Figure 3 for Dynamic Network Quantization for Efficient Video Inference
Figure 4 for Dynamic Network Quantization for Efficient Video Inference

Deep convolutional networks have recently achieved great success in video recognition, yet their practical realization remains a challenge due to the large amount of computational resources required to achieve robust recognition. Motivated by the effectiveness of quantization for boosting efficiency, in this paper, we propose a dynamic network quantization framework, that selects optimal precision for each frame conditioned on the input for efficient video recognition. Specifically, given a video clip, we train a very lightweight network in parallel with the recognition network, to produce a dynamic policy indicating which numerical precision to be used per frame in recognizing videos. We train both networks effectively using standard backpropagation with a loss to achieve both competitive performance and resource efficiency required for video recognition. Extensive experiments on four challenging diverse benchmark datasets demonstrate that our proposed approach provides significant savings in computation and memory usage while outperforming the existing state-of-the-art methods.

* ICCV 2021 Camera Ready Version 
Viaarxiv icon

IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers

Jun 23, 2021
Bowen Pan, Yifan Jiang, Rameswar Panda, Zhangyang Wang, Rogerio Feris, Aude Oliva

Figure 1 for IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers
Figure 2 for IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers
Figure 3 for IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers
Figure 4 for IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers

The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffers from heavy computation and intensive memory cost. To address this limitation, this paper presents an Interpretability-Aware REDundancy REDuction framework (IA-RED$^2$). We start by observing a large amount of redundant computation, mainly spent on uncorrelated input patches, and then introduce an interpretable module to dynamically and gracefully drop these redundant patches. This novel framework is then extended to a hierarchical structure, where uncorrelated tokens at different stages are gradually removed, resulting in a considerable shrinkage of computational cost. We include extensive experiments on both image and video tasks, where our method could deliver up to 1.4X speed-up for state-of-the-art models like DeiT and TimeSformer, by only sacrificing less than 0.7% accuracy. More importantly, contrary to other acceleration approaches, our method is inherently interpretable with substantial visual evidence, making vision transformer closer to a more human-understandable architecture while being lighter. We demonstrate that the interpretability that naturally emerged in our framework can outperform the raw attention learned by the original visual transformer, as well as those generated by off-the-shelf interpretation methods, with both qualitative and quantitative results. Project Page: http://people.csail.mit.edu/bpan/ia-red/.

Viaarxiv icon

Cross-Modal Discrete Representation Learning

Jun 10, 2021
Alexander H. Liu, SouYoung Jin, Cheng-I Jeff Lai, Andrew Rouditchenko, Aude Oliva, James Glass

Figure 1 for Cross-Modal Discrete Representation Learning
Figure 2 for Cross-Modal Discrete Representation Learning
Figure 3 for Cross-Modal Discrete Representation Learning
Figure 4 for Cross-Modal Discrete Representation Learning

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised learning framework that is able to learn a representation that captures finer levels of granularity across different modalities such as concepts or events represented by visual objects or spoken words. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities. Beyond the shared embedding space, we propose a Cross-Modal Code Matching objective that forces the representations from different views (modalities) to have a similar distribution over the discrete embedding space such that cross-modal objects/actions localization can be performed without direct supervision. In our experiments we show that the proposed discretized multi-modal fine-grained representation (e.g., pixel/word/frame) can complement high-level summary representations (e.g., video/sentence/waveform) for improved performance on cross-modal retrieval tasks. We also observe that the discretized representation uses individual clusters to represent the same semantic concept across modalities.

* Preprint 
Viaarxiv icon

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

May 12, 2021
Rameswar Panda, Chun-Fu Chen, Quanfu Fan, Ximeng Sun, Kate Saenko, Aude Oliva, Rogerio Feris

Figure 1 for AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
Figure 2 for AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
Figure 3 for AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition
Figure 4 for AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational expense limits its impact for many real-world applications. In this paper, we propose an adaptive multi-modal learning framework, called AdaMML, that selects on-the-fly the optimal modalities for each segment conditioned on the input for efficient video recognition. Specifically, given a video segment, a multi-modal policy network is used to decide what modalities should be used for processing by the recognition model, with the goal of improving both accuracy and efficiency. We efficiently train the policy network jointly with the recognition model using standard back-propagation. Extensive experiments on four challenging diverse datasets demonstrate that our proposed adaptive approach yields 35%-55% reduction in computation when compared to the traditional baseline that simply uses all the modalities irrespective of the input, while also achieving consistent improvements in accuracy over the state-of-the-art methods.

Viaarxiv icon

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

May 10, 2021
Mathew Monfort, SouYoung Jin, Alexander Liu, David Harwath, Rogerio Feris, James Glass, Aude Oliva

Figure 1 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Figure 2 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Figure 3 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
Figure 4 for Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

When people observe events, they are able to abstract key information and build concise summaries of what is happening. These summaries include contextual and semantic information describing the important high-level details (what, where, who and how) of the observed event and exclude background information that is deemed unimportant to the observer. With this in mind, the descriptions people generate for videos of different dynamic events can greatly improve our understanding of the key information of interest in each video. These descriptions can be captured in captions that provide expanded attributes for video labeling (e.g. actions/objects/scenes/sentiment/etc.) while allowing us to gain new insight into what people find important or necessary to summarize specific events. Existing caption datasets for video understanding are either small in scale or restricted to a specific domain. To address this, we present the Spoken Moments (S-MiT) dataset of 500k spoken captions each attributed to a unique short video depicting a broad range of different events. We collect our descriptions using audio recordings to ensure that they remain as natural and concise as possible while allowing us to scale the size of a large classification dataset. In order to utilize our proposed dataset, we present a novel Adaptive Mean Margin (AMM) approach to contrastive learning and evaluate our models on video/caption retrieval on multiple datasets. We show that our AMM approach consistently improves our results and that models trained on our Spoken Moments dataset generalize better than those trained on other video-caption datasets.

* To appear at CVPR 2021 
Viaarxiv icon