1 code implementation • 20 Dec 2023 • Hongtao Wu, Ya Jing, Chilam Cheang, Guangzeng Chen, Jiafeng Xu, Xinghang Li, Minghuan Liu, Hang Li, Tao Kong
In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation can significantly benefit from large-scale video generative pre-training.
Ranked #2 on Zero-shot Generalization on CALVIN (using extra training data)
no code implementations • 2 Nov 2023 • Xinghang Li, Minghuan Liu, Hanbo Zhang, Cunjun Yu, Jie Xu, Hongtao Wu, Chilam Cheang, Ya Jing, Weinan Zhang, Huaping Liu, Hang Li, Tao Kong
We believe RoboFlamingo has the potential to be a cost-effective and easy-to-use solution for robotics manipulation, empowering everyone with the ability to fine-tune their own robotics policy.
1 code implementation • 18 Oct 2023 • Hanbo Zhang, Jie Xu, Yuchen Mo, Tao Kong
Ambiguity is ubiquitous in human communication.
no code implementations • 7 Aug 2023 • Taozheng Yang, Ya Jing, Hongtao Wu, Jiafeng Xu, Kuankuan Sima, Guangzeng Chen, Qie Sima, Tao Kong
In this paper, we present a novel method for mobile manipulators to perform multiple contact-rich manipulation tasks.
no code implementations • 7 Aug 2023 • Ya Jing, Xuelin Zhu, Xingbin Liu, Qie Sima, Taozheng Yang, Yunhai Feng, Tao Kong
However, the recipes of visual pre-training for robot manipulation tasks are yet to be built.
no code implementations • 19 Jul 2023 • Leyao Liu, Tao Kong, Minzhao Zhu, Jiashuo Fan, Lu Fang
Instead of directly using the model inference way, i. e., mean-shift clustering, to generate the pseudo labels, we propose to use k-means with fixed initial seeds: the annotated points.
2 code implementations • 5 Jul 2023 • Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong
However, the performance of these models heavily relies on design choices such as network structures, training data, and training strategies, and these choices have not been extensively discussed in the literature, making it difficult to quantify progress in this field.
no code implementations • 20 Mar 2023 • Ya Jing, Tao Kong
Unlike static perception methods trained on pre-collected images, the embodied agent can move around in the environment and obtain images of objects from any viewpoints.
1 code implementation • 24 Oct 2022 • Duo Zheng, Tao Kong, Ya Jing, Jiaan Wang, Xiaojie Wang
Additionally, IRTF could generate pseudo input regions for the REC task to enable a uniform way for sharing the identical representation space across the REC and REG.
1 code implementation • 3 Oct 2022 • Guanglin Li, Yifeng Li, Zhichao Ye, Qihang Zhang, Tao Kong, Zhaopeng Cui, Guofeng Zhang
Then, by using a SIM(3)-invariant shape descriptor, we gracefully decouple the shape and pose of an object, thus supporting latent shape optimization of target objects in arbitrary poses.
Ranked #2 on 6D Pose Estimation using RGBD on REAL275
1 code implementation • 8 Sep 2022 • Xingbin Liu, Jinghao Zhou, Tao Kong, Xianming Lin, Rongrong Ji
Masked autoencoders have become popular training paradigms for self-supervised visual representation learning.
no code implementations • 5 Jul 2022 • Rufeng Zhang, Tao Kong, WeiHao Wang, Xuan Han, Mingyu You
It is desirable to enable robots capable of automatic assembly.
1 code implementation • 12 Apr 2022 • Yunfei Li, Tao Kong, Lei LI, Yi Wu
Can a robot autonomously learn to design and construct a bridge from varying-sized blocks without a blueprint?
no code implementations • 8 Feb 2022 • Minzhao Zhu, Binglei Zhao, Tao Kong
With the estimated distance map, the agent could simultaneously explore the environment and navigate to the target objects based on a simple human-designed strategy.
1 code implementation • 15 Nov 2021 • Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, Tao Kong
We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer.
Ranked #1 on Unsupervised Image Classification on ImageNet
2 code implementations • 14 Oct 2021 • Feng Wang, Tao Kong, Rufeng Zhang, Huaping Liu, Hang Li
To solve this problem, we propose to maximize the mutual information between the input and the class predictions.
Ranked #1 on Image Classification on Oxford-IIIT Pet Dataset
Fine-Grained Image Classification Representation Learning +5
no code implementations • ICLR 2022 • Jinghao Zhou, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille, Tao Kong
The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces.
no code implementations • 26 Aug 2021 • Ruihang Chu, Yukang Chen, Tao Kong, Lu Qi, Lei LI
Separating 3D point clouds into individual instances is an important task for 3D vision.
no code implementations • 5 Aug 2021 • Yiming Li, Tao Kong, Ruihang Chu, Yifeng Li, Peng Wang, Lei LI
In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information.
no code implementations • 5 Aug 2021 • Yunfei Li, Tao Kong, Lei LI, Yifeng Li, Yi Wu
In this task, the robot needs to first design a feasible bridge architecture for arbitrarily wide cliffs and then manipulate the blocks reliably to construct a stable bridge according to the proposed design.
no code implementations • 30 Jun 2021 • Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei LI
Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation.
1 code implementation • 10 Jun 2021 • Mingxuan Jing, Wenbing Huang, Fuchun Sun, Xiaojian Ma, Tao Kong, Chuang Gan, Lei LI
In particular, we propose an Expectation-Maximization(EM)-style algorithm: an E-step that samples the options of expert conditioned on the current learned policy, and an M-step that updates the low- and high-level policies of agent simultaneously to minimize the newly proposed option-occupancy measurement between the expert and the agent.
1 code implementation • CVPR 2021 • Yukang Chen, Yanwei Li, Tao Kong, Lu Qi, Ruihang Chu, Lei LI, Jiaya Jia
We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
no code implementations • CVPR 2021 • Ya Jing, Tao Kong, Wei Wang, Liang Wang, Lei LI, Tieniu Tan
Referring image segmentation aims to segment the objects referred by a natural language expression.
Generalized Referring Expression Segmentation Image Segmentation +2
6 code implementations • CVPR 2021 • Peize Sun, Rufeng Zhang, Yi Jiang, Tao Kong, Chenfeng Xu, Wei Zhan, Masayoshi Tomizuka, Lei LI, Zehuan Yuan, Changhu Wang, Ping Luo
In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location.
Ranked #5 on 2D Object Detection on CeyMo
6 code implementations • CVPR 2021 • Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei LI
Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin.
18 code implementations • NeurIPS 2020 • Xinlong Wang, Rufeng Zhang, Tao Kong, Lei LI, Chunhua Shen
Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location.
Ranked #10 on Real-time Instance Segmentation on MSCOCO
no code implementations • ICLR 2020 • Tao Kong, Fuchun Sun, Huaping Liu, Yuning Jiang, Lei LI, Jianbo Shi
While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors.
24 code implementations • ECCV 2020 • Xinlong Wang, Tao Kong, Chunhua Shen, Yuning Jiang, Lei LI
We present a new, embarrassingly simple approach to instance segmentation in images.
Ranked #67 on Instance Segmentation on COCO test-dev
1 code implementation • 17 Sep 2019 • Xinlong Wang, Wei Yin, Tao Kong, Yuning Jiang, Lei LI, Chunhua Shen
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
1 code implementation • 17 Sep 2019 • Luxuan Li, Tao Kong, Fuchun Sun, Huaping Liu
Detecting actions in videos is an important yet challenging task.
no code implementations • 25 Apr 2019 • Chuanqi Tan, Fuchun Sun, Tao Kong, Bin Fang, Wenchang Zhang
Different functional areas of the human brain play different roles in brain activity, which has not been paid sufficient research attention in the brain-computer interface (BCI) field.
7 code implementations • 8 Apr 2019 • Tao Kong, Fuchun Sun, Huaping Liu, Yuning Jiang, Lei LI, Jianbo Shi
In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate. We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis.
Ranked #89 on Object Detection on COCO test-dev (APM metric)
no code implementations • 19 Jan 2019 • Tao Kong, Fuchun Sun, Huaping Liu, Yuning Jiang, Jianbo Shi
We present consistent optimization for single stage object detection.
no code implementations • CVPR 2019 • Liangzhe Yuan, Yibo Chen, Hantian Liu, Tao Kong, Jianbo Shi
We propose a light-weight video frame interpolation algorithm.
no code implementations • ECCV 2018 • Tao Kong, Fuchun Sun, Wenbing Huang, Huaping Liu
In this paper, we begin by investigating current feature pyramids solutions, and then reformulate the feature pyramid construction as the feature reconfiguration process.
no code implementations • 6 Aug 2018 • Chuanqi Tan, Fuchun Sun, Tao Kong, Wenchang Zhang, Chao Yang, Chunfang Liu
As a new classification platform, deep learning has recently received increasing attention from researchers and has been successfully applied to many domains.
1 code implementation • CVPR 2017 • Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Ming Lu, Yurong Chen
To address (a), we design the reverse connection, which enables the network to detect objects on multi-levels of CNNs.
no code implementations • CVPR 2016 • Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun
Almost all of the current top-performing object detection networks employ region proposals to guide the search for object instances.