6 code implementations • 18 Apr 2019 • Hei Law, Yun Teng, Olga Russakovsky, Jia Deng
Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency.
Ranked #137 on Object Detection on COCO minival
2 code implementations • 6 Jun 2022 • Zhiwei Deng, Olga Russakovsky
We propose an algorithm that compresses the critical information of a large dataset into compact addressable memories.
2 code implementations • 15 Aug 2023 • Xindi Wu, Byron Zhang, Zhiwei Deng, Olga Russakovsky
In this work, we design the first vision-language dataset distillation method, building on the idea of trajectory matching.
12 code implementations • 1 Sep 2014 • Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, Li Fei-Fei
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images.
2 code implementations • ECCV 2020 • Angelina Wang, Alexander Liu, Ryan Zhang, Anat Kleiman, Leslie Kim, Dora Zhao, Iroha Shirai, Arvind Narayanan, Olga Russakovsky
Machine learning models are known to perpetuate and even amplify the biases present in the data.
1 code implementation • CVPR 2016 • Serena Yeung, Olga Russakovsky, Greg Mori, Li Fei-Fei
In this work we introduce a fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions.
Ranked #9 on Temporal Action Localization on THUMOS’14 (mAP IOU@0.2 metric)
1 code implementation • ICCV 2017 • Gunnar A. Sigurdsson, Olga Russakovsky, Abhinav Gupta
We present the many kinds of information that will be needed to achieve substantial gains in activity understanding: objects, verbs, intent, and sequential reasoning.
3 code implementations • CVPR 2020 • Zeyu Wang, Klint Qinami, Ioannis Christos Karakozis, Kyle Genova, Prem Nair, Kenji Hata, Olga Russakovsky
We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation.
Ranked #1 on Out-of-Distribution Generalization on UrbanCars
1 code implementation • CVPR 2021 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Olga Russakovsky
Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world.
1 code implementation • ICCV 2019 • Kaiyu Yang, Olga Russakovsky, Jia Deng
Understanding the spatial relations between objects in images is a surprisingly challenging task.
1 code implementation • CVPR 2017 • Siddha Ganju, Olga Russakovsky, Abhinav Gupta
For instance, the question "what is the breed of the dog?"
1 code implementation • 10 Mar 2021 • Kaiyu Yang, Jacqueline Yau, Li Fei-Fei, Jia Deng, Olga Russakovsky
In this paper, we explore the effects of face obfuscation on the popular ImageNet challenge visual recognition benchmark.
1 code implementation • 6 Jun 2015 • Amy Bearman, Olga Russakovsky, Vittorio Ferrari, Li Fei-Fei
The semantic image segmentation task presents a trade-off between test time accuracy and training-time annotation cost.
1 code implementation • 10 Jan 2022 • Zeyu Wang, Yu Wu, Karthik Narasimhan, Olga Russakovsky
Retrieving target videos based on text descriptions is a task of great practical value and has received increasing attention over the past few years.
1 code implementation • RC 2020 • Sunnie S. Y. Kim, Sharon Zhang, Nicole Meister, Olga Russakovsky
The implementation of most (7 of 10) methods was straightforward, especially after we received additional details from the original authors.
1 code implementation • 6 Dec 2021 • Sunnie S. Y. Kim, Nicole Meister, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable.
1 code implementation • 27 Nov 2020 • Arjun Mani, Nobline Yoo, Will Hinthorn, Olga Russakovsky
Concretely, we (1) introduce and motivate point-input questions as an extension of VQA, (2) define three novel classes of questions within this space, and (3) for each class, introduce both a benchmark dataset and a series of baseline models to handle its unique challenges.
1 code implementation • 24 Feb 2021 • Angelina Wang, Olga Russakovsky
We introduce and analyze a new, decoupled metric for measuring bias amplification, $\text{BiasAmp}_{\rightarrow}$ (Directional Bias Amplification).
1 code implementation • ECCV 2020 • Zeyu Wang, Berthy Feng, Karthik Narasimhan, Olga Russakovsky
We find that modern captioning systems return higher likelihoods for incorrect distractor sentences compared to ground truth captions, and that evaluation metrics like SPICE can be 'topped' using simple captioning systems relying on object detectors.
1 code implementation • ICCV 2021 • Dora Zhao, Angelina Wang, Olga Russakovsky
Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments.
1 code implementation • CVPR 2023 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky
Second, we find that concepts in the probe dataset are often less salient and harder to learn than the classes they claim to explain, calling into question the correctness of the explanations.
1 code implementation • ACL 2022 • Carlos E. Jimenez, Olga Russakovsky, Karthik Narasimhan
We introduce CARETS, a systematic test suite to measure consistency and robustness of modern VQA models through a series of six fine-grained capability tests.
1 code implementation • 27 Jul 2022 • Mengxue Qu, Yu Wu, Wu Liu, Qiqi Gong, Xiaodan Liang, Olga Russakovsky, Yao Zhao, Yunchao Wei
Particularly, SiRi conveys a significant principle to the research of visual grounding, i. e., a better initialized vision-language encoder would help the model converge to a better local minimum, advancing the performance accordingly.
1 code implementation • ICCV 2023 • Angelina Wang, Olga Russakovsky
Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets.
1 code implementation • 6 Nov 2023 • Nobline Yoo, Olga Russakovsky
We (1) analyze the relationship between reconstruction quality and pose estimation accuracy, (2) develop a model pipeline that outperforms the baseline which inspired our work, using less than one-third the amount of training data, and (3) offer a new metric suitable for self-supervised settings that measures the consistency of predicted body part length proportions.
no code implementations • CVPR 2017 • Achal Dave, Olga Russakovsky, Deva Ramanan
While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing.
1 code implementation • 21 Jul 2015 • Serena Yeung, Olga Russakovsky, Ning Jin, Mykhaylo Andriluka, Greg Mori, Li Fei-Fei
Every moment counts in action recognition.
Ranked #7 on Action Detection on Multi-THUMOS
no code implementations • CVPR 2017 • Serena Yeung, Vignesh Ramanathan, Olga Russakovsky, Liyue Shen, Greg Mori, Li Fei-Fei
Our method uses Q-learning to learn a data labeling policy on a small labeled training dataset, and then uses this to automatically label noisy web data for new visual concepts.
no code implementations • 7 Nov 2016 • Adriana Kovashka, Olga Russakovsky, Li Fei-Fei, Kristen Grauman
Computer vision systems require large amounts of manually annotated data to properly learn challenging visual concepts.
no code implementations • 25 Jul 2016 • Gunnar A. Sigurdsson, Olga Russakovsky, Ali Farhadi, Ivan Laptev, Abhinav Gupta
We conclude that the optimal strategy is to ask as many questions as possible in a HIT (up to 52 binary questions after watching a 30-second video clip in our experiments).
no code implementations • CVPR 2015 • Davide Modolo, Alexander Vezhnevets, Olga Russakovsky, Vittorio Ferrari
We formulate joint calibration as a constrained optimization problem and devise an efficient optimization algorithm to find its global optimum.
no code implementations • CVPR 2015 • Olga Russakovsky, Li-Jia Li, Li Fei-Fei
This paper brings together the latest advancements in object detection and in crowd engineering into a principled framework for accurately and efficiently localizing objects in images.
no code implementations • ICCV 2019 • Joshua C. Peterson, Ruairidh M. Battleday, Thomas L. Griffiths, Olga Russakovsky
We then show that, while contemporary classifiers fail to exhibit human-like uncertainty on their own, explicit training on our dataset closes this gap, supports improved generalization to increasingly out-of-training-distribution test datasets, and confers robustness to adversarial attacks.
no code implementations • 4 Dec 2019 • Jonathan C. Stroud, Ryan McCaffrey, Rada Mihalcea, Jia Deng, Olga Russakovsky
Temporal grounding entails establishing a correspondence between natural language event descriptions and their visual depictions.
no code implementations • 16 Dec 2019 • Kaiyu Yang, Klint Qinami, Li Fei-Fei, Jia Deng, Olga Russakovsky
Computer vision technology is being used by many but remains representative of only a few.
no code implementations • 31 Mar 2020 • Felix Yu, Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky
In the Vision-and-Language Navigation (VLN) task, an agent with egocentric vision navigates to a destination given natural language instructions.
no code implementations • NeurIPS 2020 • Zhiwei Deng, Karthik Narasimhan, Olga Russakovsky
The ability to perform effective planning is crucial for building an instruction-following agent.
no code implementations • 1 Jan 2021 • Angelina Wang, Olga Russakovsky
The conversation around the fairness of machine learning models is growing and evolving.
no code implementations • 29 Sep 2021 • Eric Zhao, De-An Huang, Hao liu, Zhiding Yu, Anqi Liu, Olga Russakovsky, Anima Anandkumar
In real-world applications, however, there are multiple protected attributes yielding a large number of intersectional protected groups.
1 code implementation • 10 May 2022 • Angelina Wang, Vikram V. Ramaswamy, Olga Russakovsky
In this work, we grapple with questions that arise along three stages of the machine learning pipeline when incorporating intersectionality as multiple demographic attributes: (1) which demographic attributes to include as dataset labels, (2) how to handle the progressively smaller size of subgroups during model training, and (3) how to move beyond existing evaluation metrics when benchmarking model fairness for more subgroups.
no code implementations • 15 Jun 2022 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Nicole Meister, Ruth Fong, Olga Russakovsky
Specifically, we develop a novel explanation framework ELUDE (Explanation via Labelled and Unlabelled DEcomposition) that decomposes a model's prediction into two parts: one that is explainable through a linear combination of the semantic attributes, and another that is dependent on the set of uninterpretable features.
no code implementations • ICCV 2023 • Nicole Meister, Dora Zhao, Angelina Wang, Vikram V. Ramaswamy, Ruth Fong, Olga Russakovsky
Gender biases are known to exist within large-scale visual datasets and can be reflected or even amplified in downstream models.
no code implementations • 7 Jul 2022 • Sunayana Rane, Mira L. Nencheva, Zeyu Wang, Casey Lew-Williams, Olga Russakovsky, Thomas L. Griffiths
The performance of the computer vision systems is correlated with human judgments of the concreteness of words, which are in turn a predictor of children's word learning, suggesting that these models are capturing the relationship between words and visual phenomena.
no code implementations • 2 Oct 2022 • Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández
Despite the proliferation of explainable AI (XAI) methods, little is understood about end-users' explainability needs and behaviors around XAI explanations.
no code implementations • 27 Mar 2023 • Vikram V. Ramaswamy, Sunnie S. Y. Kim, Ruth Fong, Olga Russakovsky
In this work, we propose UFO, a unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations.
no code implementations • 15 May 2023 • Sunnie S. Y. Kim, Elizabeth Anne Watkins, Olga Russakovsky, Ruth Fong, Andrés Monroy-Hernández
Trust is an important factor in people's interactions with AI systems.
no code implementations • 7 Jun 2023 • Ziv Epstein, Aaron Hertzmann, Laura Herman, Robert Mahari, Morgan R. Frank, Matthew Groh, Hope Schroeder, Amy Smith, Memo Akten, Jessica Fjeld, Hany Farid, Neil Leach, Alex Pentland, Olga Russakovsky
A new class of tools, colloquially called generative AI, can produce high-quality artistic media for visual arts, concept art, music, fiction, literature, video, and animation.
no code implementations • 7 Jun 2023 • Sruthi Sudhakar, Viraj Prabhu, Olga Russakovsky, Judy Hoffman
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising.
1 code implementation • 3 Oct 2023 • William Yang, Byron Zhang, Olga Russakovsky
Through comprehensive experiments, we show that OOD detectors are more sensitive to covariate shift than to semantic shift, and the benefits of recent OOD detection algorithms on semantic shift detection is minimal.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 13 Oct 2023 • Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan
While the current trend in the generative field is scaling up towards larger models and more training data for generalized domain representations, we go the opposite direction in this work by synthesizing unseen domain images without additional training.
no code implementations • 16 Dec 2023 • Sai Wang, Ye Zhu, Ruoyu Wang, Amaya Dharmasiri, Olga Russakovsky, Yu Wu
While face swapping and attribute editing are performed on similar face regions such as eyes and nose, the inpainting operation can be performed on random image regions, removing the spurious correlations of previous datasets.
no code implementations • 15 Feb 2024 • Allison Chen, Ilia Sucholutsky, Olga Russakovsky, Thomas L. Griffiths
Does language help make sense of the visual world?