no code implementations • 31 Dec 2024 • Xindi Wu, Mengzhou Xia, Rulin Shao, Zhiwei Deng, Pang Wei Koh, Olga Russakovsky
In this work, we introduce ICONS, a gradient-driven Influence CONsensus approach for vision-language data Selection that selects a compact training dataset for efficient multi-task training.
no code implementations • 22 Oct 2024 • Zhiwei Deng, Tao Li, Yang Li
Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al., 2024).
1 code implementation • 15 Jun 2024 • Tian Qin, Zhiwei Deng, David Alvarez-Melis
Understanding how and why data distillation methods work is vital not only for improving these methods but also for revealing fundamental characteristics of "good" training data.
1 code implementation • 6 Jun 2024 • William Yang, Ye Zhu, Zhiwei Deng, Olga Russakovsky
We reveal distilled data cannot serve as a substitute for real data during training outside the standard evaluation setting for dataset distillation.
no code implementations • 25 May 2024 • Haoyu Wang, Tao Li, Zhiwei Deng, Dan Roth, Yang Li
The experimental results suggest that our introspection-driven approach not only enhances the agent's ability to navigate unanticipated challenges through a robust mechanism of plan execution, but also improves efficiency by reducing the number of trials and plan revisions by 45% needed to achieve a task.
no code implementations • 21 May 2024 • Lujia Zhong, Shuo Huang, Jiaxin Yue, Jianwei Zhang, Zhiwei Deng, Wenhao Chi, Yonggang Shi
By classifying the A4 subjects according to their anomaly map using the SVM trained on ADNI data, we show that our method can successfully group preclinical subjects with significantly different cognitive functions, which further demonstrates the effectiveness of our method in capturing biologically relevant anomaly in tau PET imaging.
1 code implementation • 1 Mar 2024 • Tian Qin, Zhiwei Deng, David Alvarez-Melis
What does a neural network learn when training from a task-specific dataset?
no code implementations • 30 Nov 2023 • Zhiwei Deng, Ting Chen, Yang Li
In this paper, we propose the Perceptual Group Tokenizer, a model that entirely relies on grouping operations to extract visual features and perform self-supervised representation learning, where a series of grouping operations are used to iteratively hypothesize the context for pixels or superpixels to refine feature representations.
Ranked #23 on
Self-Supervised Image Classification
on ImageNet
Representation Learning
Self-Supervised Image Classification
+2
no code implementations • 13 Oct 2023 • Ye Zhu, Yu Wu, Duo Xu, Zhiwei Deng, Yan Yan, Olga Russakovsky
In this work, we study the generalization properties of diffusion models in a few-shot setup, introduce a novel tuning-free paradigm to synthesize the target out-of-domain (OOD) data, and demonstrate its advantages compared to existing methods in data-sparse scenarios with large domain gaps.
no code implementations • 12 Oct 2023 • Tao Li, Gang Li, Zhiwei Deng, Bryan Wang, Yang Li
To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prompting.
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.
1 code implementation • NeurIPS 2023 • Ye Zhu, Yu Wu, Zhiwei Deng, Olga Russakovsky, Yan Yan
Applying pre-trained generative denoising diffusion models (DDMs) for downstream tasks such as image semantic editing usually requires either fine-tuning DDMs or learning auxiliary editing networks in the existing literature.
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.
Ranked #4 on
Dataset Distillation - 1IPC
on CIFAR-10
1 code implementation • 24 Apr 2021 • Mengyao Zhai, Ruizhi Deng, Jiacheng Chen, Lei Chen, Zhiwei Deng, Greg Mori
Hence, we develop an approach based on intermediate representations of poses and appearance: our pose-guided appearance rendering network firstly encodes the targets' poses using an encoder-decoder neural network.
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.
1 code implementation • ACL 2020 • Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha
To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially.
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 • ICLR 2020 • Zhiwei Deng, Greg Mori
A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation process.
no code implementations • 7 Aug 2019 • Zhiwei Deng, Megha Nawhal, Lili Meng, Greg Mori
In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data.
1 code implementation • NeurIPS 2018 • Zhiwei Deng, Jiacheng Chen, Yifang Fu, Greg Mori
In this paper we address the text to scene image generation problem.
1 code implementation • 18 Feb 2018 • Nelson Nauata, Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori
In this paper, we exploit this rich structure for performing graph-based inference in label space for a number of tasks: multi-label image and video classification and action detection in untrimmed videos.
2 code implementations • ECCV 2018 • Ligeng Zhu, Ruizhi Deng, Michael Maire, Zhiwei Deng, Greg Mori, Ping Tan
We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers.
no code implementations • CVPR 2017 • Zhiwei Deng, Rajitha Navarathna, Peter Carr, Stephan Mandt, Yisong Yue, Iain Matthews, Greg Mori
Matrix and tensor factorization methods are often used for finding underlying low-dimensional patterns from noisy data.
no code implementations • 7 Jun 2017 • Mehran Khodabandeh, Zhiwei Deng, Mostafa S. Ibrahim, Shinichi Satoh, Greg Mori
We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video.
no code implementations • 30 May 2017 • Jiawei He, Mostafa S. Ibrahim, Zhiwei Deng, Greg Mori
Our class-independent TPN outperforms other tubelet generation methods, and our unified temporal deep network achieves state-of-the-art localization results on all three datasets.
1 code implementation • 29 Mar 2017 • Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou, Fei Sha, Greg Mori
We advocate that holistic inference of image concepts provides valuable information for detailed pixel labeling.
no code implementations • 24 Nov 2016 • Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou, Fei Sha, Greg Mori
We advocate that high-recall holistic inference of image concepts provides valuable information for detailed pixel labeling.
1 code implementation • 9 Jul 2016 • Mostafa S. Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori
In order to model both person-level and group-level dynamics, we present a 2-stage deep temporal model for the group activity recognition problem.
1 code implementation • CVPR 2016 • Moustafa Ibrahim, Srikanth Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori
In group activity recognition, the temporal dynamics of the whole activity can be inferred based on the dynamics of the individual people representing the activity.
no code implementations • CVPR 2016 • Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori
Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible.
no code implementations • CVPR 2016 • Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori
As a concrete example, group activity recognition involves the interactions and relative spatial relations of a set of people in a scene.
Ranked #6 on
Group Activity Recognition
on Collective Activity
no code implementations • 12 Jun 2015 • Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Javan Roshtkhari, Greg Mori
This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes.