VLDB 2026 Research / reviewers in the wild / expert

Ilija Radosavovic

dblp:211/6740 · DBLP profile ↗
← Back
12ranked-venue papers
5as first author
8since 2021 · last 2025
0009-0004-9200-5980ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 12 · 5 first-author · 8 since 2021Graphics, computer vision, multimedia, augmented reality and games · 8 · 3 first-author · 4 since 2021Systems, architecture and hardware · 2 · 1 first-author · 2 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
11 papers
Video understanding and tracking · 27% Motion planning and robot control · 19% 3D vision · 17%
Computer graphics and multimedia
1 paper
Multimedia analysis and retrieval · 100%

Topics — the 28 heaviest of 31, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Robotics › Motion planning and robot control
robot learning		 1.522024
Humanoid Locomotion as Next Token Prediction · NeurIPS 2024
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration · ICRA 2024
Computer vision › Video understanding and tracking
egocentric video understanding		 1.422025
Ego4D: Around the World in 3,600 Hours of Egocentric Video · IEEE Trans. Pattern Anal. Mach. Intell. 2025
Ego4D: Around the World in 3, 000 Hours of Egocentric Video · CVPR 2022
Computer vision › Video understanding and tracking
activity prediction		 0.912025
Ego4D: Around the World in 3,600 Hours of Egocentric Video · IEEE Trans. Pattern Anal. Mach. Intell. 2025
Computer vision › Video understanding and tracking
video representation learning		 0.912025
An Empirical Study of Autoregressive Pre-Training from Videos · ICCV 2025
Robotics › Motion planning and robot control › robot learning › robot policy learning
generalist robot policy		 0.812024
Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration · ICRA 2024
Computer vision › 3D vision › 3d human reconstruction
hand mesh reconstruction		 0.812024
Reconstructing Hands in 3D with Transformers · CVPR 2024
Computer vision › 3D vision
human mesh recovery		 0.812024
Reconstructing Hands in 3D with Transformers · CVPR 2024
Robotics › Legged, aerial and field robots › legged robots
humanoid locomotion		 0.812024
Humanoid Locomotion as Next Token Prediction · NeurIPS 2024
Robotics › Motion planning and robot control
humanoid robot control		 0.812024
Humanoid Locomotion as Next Token Prediction · NeurIPS 2024
Computer vision › Video understanding and tracking
activity understanding		 0.612022
Ego4D: Around the World in 3, 000 Hours of Egocentric Video · CVPR 2022
Computer vision › Video understanding and tracking › egocentric video understanding
first-person activity recognition		 0.612022
Ego4D: Around the World in 3, 000 Hours of Egocentric Video · CVPR 2022
Computer vision › 3D vision › 3d human reconstruction
hand-object interaction reconstruction		 0.512021
Reconstructing Hand-Object Interactions in the Wild · ICCV 2021
Computer vision › 3D vision › 3d reconstruction
image-based 3d reconstruction		 0.512021
Reconstructing Hand-Object Interactions in the Wild · ICCV 2021
Machine learning › Learning paradigms
multi-task learning		 0.412019
Attentive Single-Tasking of Multiple Tasks · CVPR 2019
Machine learning › Efficient and distributed learning › automated machine learning
neural architecture search		 0.412019
On Network Design Spaces for Visual Recognition · ICCV 2019
Computer vision › Segmentation and scene understanding › dense prediction
pixel labeling		 0.412019
Attentive Single-Tasking of Multiple Tasks · CVPR 2019
Machine learning › Learning paradigms › multi-task learning
task conflict mitigation		 0.412019
Attentive Single-Tasking of Multiple Tasks · CVPR 2019
Computer vision › Image recognition and object detection
visual recognition		 0.412019
On Network Design Spaces for Visual Recognition · ICCV 2019
Machine learning › Efficient and distributed learning
dataset distillation		 0.312018
Data Distillation: Towards Omni-Supervised Learning · CVPR 2018
Machine learning › Learning paradigms › semi-supervised learning
omni-supervised learning		 0.312018
Data Distillation: Towards Omni-Supervised Learning · CVPR 2018
Machine learning › Deep learning architectures and training › data-centric deep learning
self-training with unlabeled data		 0.312018
Data Distillation: Towards Omni-Supervised Learning · CVPR 2018
Machine learning › Learning paradigms
semi-supervised learning		 0.312018
Data Distillation: Towards Omni-Supervised Learning · CVPR 2018
Computer vision › 3D vision
3d scene reconstruction		 0.312025
Ego4D: Around the World in 3,600 Hours of Egocentric Video · IEEE Trans. Pattern Anal. Mach. Intell. 2025
Machine learning › Generative modeling › autoregressive model
autoregressive sequence modeling		 0.312025
An Empirical Study of Autoregressive Pre-Training from Videos · ICCV 2025
Machine learning › Generative modeling
autoregressive model		 0.212024
Humanoid Locomotion as Next Token Prediction · NeurIPS 2024
Computer vision › Face, body and person analysis › human pose estimation › articulated pose estimation
hand pose estimation		 0.212024
Reconstructing Hands in 3D with Transformers · CVPR 2024
Machine learning › Generative modeling › autoregressive model
next-token prediction		 0.212024
Humanoid Locomotion as Next Token Prediction · NeurIPS 2024
Multimedia analysis and retrieval › video dataset
video dataset benchmark		 0.212022
Ego4D: Around the World in 3, 000 Hours of Egocentric Video · CVPR 2022

Methods — techniques the papers use, named apart from their topics

visual tokenization · 0.9autoregressive transformer · 0.9vision transformer · 0.8transformer policy · 0.8scaling · 0.8large-scale pretraining · 0.8causal transformer · 0.8autoregressive prediction · 0.8image cue integration · 0.53d contact priors · 0.5
YearPublicationVenuePosition
2025 An Empirical Study of Autoregressive Pre-Training from Videos
abstract
We empirically study autoregressive pre-training from videos. To perform our study, we construct a series of autoregressive video models, called Toto. We treat videos as sequences of visual tokens and train transformer models to autoregressively predict future tokens. Our models are pre-trained on a diverse dataset of videos and images comprising over 1 trillion visual tokens. We explore different architectural, training, and inference design choices. We evaluate the learned visual representations on a range of downstream tasks including image recognition, video classification, object tracking, and robotics. Our results demonstrate that, despite minimal inductive biases, autoregressive pre-training leads to competitive performance across all benchmarks. Finally, we find that scaling our video models results in similar scaling curves to those seen in language models, albeit with a different rate. More details at https://brjathu.github.io/toto/
Jathushan Rajasegaran, Ilija Radosavovic, Rahul Ravishankar, Yossi Gandelsman, Christoph Feichtenhofer, Jitendra Malik
 ICCV2
2025 Ego4D: Around the World in 3,600 Hours of Egocentric Video
abstract
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 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.
Kristen Grauman, Andrew Westbury, Eugene Byrne, Vincent Cartillier, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang 0007, Devansh Kukreja, Miao Liu 0007, Xingyu Liu 0001, Tushar Nagarajan, Ilija Radosavovic, Santhosh K. Ramakrishnan, Fiona Ryan, Jayant Sharma 0002, Michael Wray, Mengmeng Xu 0006, Eric Zhongcong Xu, Chen Zhao 0002, Siddhant Bansal, Dhruv Batra, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Abrham Gebreselasie, Cristina González, James Hillis, Xuhua Huang, Yifei Huang 0002, Wenqi Jia 0001, Weslie Khoo, Jáchym Kolár, Satwik Kottur, Anurag Kumar 0003, Federico Landini, Yanghao Li, Zhenqiang Li 0002, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran K. Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Xindi Wu, Takuma Yagi, Ziwei Zhao 0003, Yunyi Zhu, Pablo Andrés Arbeláez, David Crandall, Dima Damen, Giovanni Maria Farinella, Christian Fügen, Bernard Ghanem, Vamsi K. Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Makoto Kitani, Haizhou Li 0001, Richard A. Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato 0001, Jianbo Shi, Zheng Shou 0001, Antonio Torralba 0001, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
 IEEE Trans. Pattern Anal. Mach. Intell.15
2024 Reconstructing Hands in 3D with Transformers
abstract
We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data, we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model, we use a large scale Vision Transformer architecture. Our final model consistently outperforms the previous baselines on popular 3D hand pose benchmarks. To further evaluate the effect of our design in non-controlled settings, we annotate existing in-the-wild datasets with 2D hand keypoint annotations. On this newly collected dataset of annotations, HInt, we demonstrate significant improvements over existing baselines. We will make our code, data and models publicly available upon publication. We make our code, data and models available on the project website: https://geopavlakos.github.io/hamer/. “It is because of his being armed with hands that man is the most intelligent animal.” Anaxagoras
Georgios Pavlakos, Dandan Shan, Ilija Radosavovic, Angjoo Kanazawa, David F. Fouhey, Jitendra Malik
 CVPR3
2024 Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration
abstract
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io.
Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin
 ICRA85
2024 Humanoid Locomotion as Next Token Prediction
abstract
We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor sequences. To account for the multi-modal nature of the data, we perform prediction in a modality-aligned way, and for each input token predict the next token from the same modality. This general formulation enables us to leverage data with missing modalities, such as videos without actions. We train our model on a dataset of sequences from a prior neural network policy, a model-based controller, motion capture, and YouTube videos of humans. We show that our model enables a real humanoid robot to walk in San Francisco zero-shot. Our model can transfer to the real world even when trained on only 27 hours of walking data, and can generalize to commands not seen during training. These findings suggest a promising path toward learning challenging real-world control tasks by generative modeling of sensorimotor sequences.
Ilija Radosavovic, Bike Zhang, Baifeng Shi, Jathushan Rajasegaran, Sarthak Kamat, Trevor Darrell, Koushil Sreenath, Jitendra Malik
 NeurIPS1
2022 Ego4D: Around the World in 3, 000 Hours of Egocentric Video
abstract
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 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/
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang 0007, Miao Liu 0007, Xingyu Liu 0001, Tushar Nagarajan, Ilija Radosavovic, Santhosh K. Ramakrishnan, Fiona Ryan, Jayant Sharma 0002, Michael Wray, Mengmeng Xu 0006, Eric Zhongcong Xu, Chen Zhao 0002, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Abrham Gebreselasie, Cristina González, James Hillis, Xuhua Huang, Yifei Huang 0002, Wenqi Jia 0001, Weslie Khoo, Jáchym Kolár, Satwik Kottur, Anurag Kumar 0003, Federico Landini, Yanghao Li, Zhenqiang Li 0002, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran K. Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Xindi Wu, Takuma Yagi, Ziwei Zhao 0003, Yunyi Zhu, Pablo Andrés Arbeláez, David Crandall, Dima Damen, Giovanni Maria Farinella, Christian Fügen, Bernard Ghanem, Vamsi K. Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Makoto Kitani, Haizhou Li 0001, Richard A. Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato 0001, Jianbo Shi, Zheng Shou 0001, Antonio Torralba 0001, Lorenzo Torresani, Mingfei Yan, Jitendra Malik
 CVPR13
2021 Reconstructing Hand-Object Interactions in the Wild
abstract
We study the problem of understanding hand-object interactions from 2D images in the wild. This requires reconstructing both the hand and the object in 3D, which is challenging because of the mutual occlusion between the hand and the object. In this paper we make two main contributions: (1) a novel reconstruction technique, RHO (Reconstructing Hands and Objects), which reconstructs 3D models of both the hand and the object leveraging the 2D image cues and 3D contact priors; (2) a dataset MOW (Manipulating Objects in the Wild) of 500 examples of hand-object interaction images that have been "3Dfied" with the help of the RHO technique. Overall our dataset contains 121 distinct object categories, with a much greater diversity of manipulation actions, than in previous datasets.
Zhe Cao 0003, Ilija Radosavovic, Angjoo Kanazawa, Jitendra Malik
 ICCV2
2021 State-Only Imitation Learning for Dexterous Manipulation
abstract
Modern model-free reinforcement learning methods have recently demonstrated impressive results on a number of problems. However, complex domains like dexterous manipulation remain a challenge due to the high sample complexity. To address this, current approaches employ expert demonstrations in the form of state-action pairs, which are difficult to obtain for real-world settings such as learning from videos. In this paper, we move toward a more realistic setting and explore state-only imitation learning. To tackle this setting, we train an inverse dynamics model and use it to predict actions for state-only demonstrations. The inverse dynamics model and the policy are trained jointly. Our method performs on par with state-action approaches and considerably outperforms RL alone. By not relying on expert actions, we are able to learn from demonstrations with different dynamics, morphologies, and objects. Videos available on the ${\text{project page}}$.
Ilija Radosavovic, Xiaolong Wang 0004, Lerrel Pinto, Jitendra Malik
 IROS1
2020 Designing Network Design Spaces
abstract
In this work, we present a new network design paradigm. Our goal is to help advance the understanding of network design and discover design principles that generalize across settings. Instead of focusing on designing individual network instances, we design network design spaces that parametrize populations of networks. The overall process is analogous to classic manual design of networks, but elevated to the design space level. Using our methodology we explore the structure aspect of network design and arrive at a low-dimensional design space consisting of simple, regular networks that we call RegNet. The core insight of the RegNet parametrization is surprisingly simple: widths and depths of good networks can be explained by a quantized linear function. We analyze the RegNet design space and arrive at interesting findings that do not match the current practice of network design. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. Under comparable training settings and flops, the RegNet models outperform the popular EfficientNet models while being up to 5x faster on GPUs.
Ilija Radosavovic, Raj Prateek Kosaraju, Ross B. Girshick, Kaiming He, Piotr Dollár
 CVPR1
2019 Attentive Single-Tasking of Multiple Tasks
abstract
In this work we address task interference in universal networks by considering that a network is trained on multiple tasks, but performs one task at a time, an approach we refer to as “single-tasking multiple tasks”. The network thus modifies its behaviour through task-dependent feature adaptation, or task attention. This gives the network the ability to accentuate the features that are adapted to a task, while shunning irrelevant ones. We further reduce task interference by forcing the task gradients to be statistically indistinguishable through adversarial training, ensuring that the common backbone architecture serving all tasks is not dominated by any of the task-specific gradients. Results in three multi-task dense labelling problems consistently show: (i) a large reduction in the number of parameters while preserving, or even improving performance and (ii) a smooth trade-off between computation and multi-task accuracy. We provide our system's code and pre-trained models at https://github. com/facebookresearch/astmt.
Kevis-Kokitsi Maninis, Ilija Radosavovic, Iasonas Kokkinos
 CVPR2
2019 On Network Design Spaces for Visual Recognition
abstract
Over the past several years progress in designing better neural network architectures for visual recognition has been substantial. To help sustain this rate of progress, in this work we propose to reexamine the methodology for comparing network architectures. In particular, we introduce a new comparison paradigm of distribution estimates, in which network design spaces are compared by applying statistical techniques to populations of sampled models, while controlling for confounding factors like network complexity. Compared to current methodologies of comparing point and curve estimates of model families, distribution estimates paint a more complete picture of the entire design landscape. As a case study, we examine design spaces used in neural architecture search (NAS). We find significant statistical differences between recent NAS design space variants that have been largely overlooked. Furthermore, our analysis reveals that the design spaces for standard model families like ResNeXt can be comparable to the more complex ones used in recent NAS work. We hope these insights into distribution analysis will enable more robust progress toward discovering better networks for visual recognition.
Ilija Radosavovic, Justin Johnson 0001, Saining Xie, Wan-Yen Lo, Piotr Dollár
 ICCV1
2018 Data Distillation: Towards Omni-Supervised Learning
abstract
We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data. Omni-supervised learning is lower-bounded by performance on existing labeled datasets, offering the potential to surpass state-of-the-art fully supervised methods. To exploit the omni-supervised setting, we propose data distillation, a method that ensembles predictions from multiple transformations of unlabeled data, using a single model, to automatically generate new training annotations. We argue that visual recognition models have recently become accurate enough that it is now possible to apply classic ideas about self-training to challenging real-world data. Our experimental results show that in the cases of human keypoint detection and general object detection, state-of-the-art models trained with data distillation surpass the performance of using labeled data from the COCO dataset alone.
Ilija Radosavovic, Piotr Dollár, Ross B. Girshick, Georgia Gkioxari, Kaiming He
 CVPR1