Search Results for author: Jian Ding

Found 32 papers, 18 papers with code

Efficiently matching random inhomogeneous graphs via degree profiles

no code implementations16 Oct 2023 Jian Ding, Yumou Fei, Yuanzheng Wang

In this paper, we study the problem of recovering the latent vertex correspondence between two correlated random graphs with vastly inhomogeneous and unknown edge probabilities between different pairs of vertices.

Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer

1 code implementation13 Sep 2023 Yaoting Wang, Weisong Liu, Guangyao Li, Jian Ding, Di Hu, Xi Li

Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio?

CoLA Visual Localization

On the Robustness of Object Detection Models in Aerial Images

1 code implementation29 Aug 2023 Haodong He, Jian Ding, Gui-Song Xia

The robustness of object detection models is a major concern when applied to real-world scenarios.

Data Augmentation Object +3

Towards Generic and Controllable Attacks Against Object Detection

1 code implementation23 Jul 2023 Guopeng Li, Yue Xu, Jian Ding, Gui-Song Xia

To this end, we propose a generic white-box attack, LGP (local perturbations with adaptively global attacks), to blind mainstream object detectors with controllable perturbations.

Object object-detection +1

A polynomial-time iterative algorithm for random graph matching with non-vanishing correlation

no code implementations1 Jun 2023 Jian Ding, Zhangsong Li

We propose an efficient algorithm for matching two correlated Erd\H{o}s--R\'enyi graphs with $n$ vertices whose edges are correlated through a latent vertex correspondence.

Graph Matching

HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

1 code implementation CVPR 2023 Jian Ding, Nan Xue, Gui-Song Xia, Bernt Schiele, Dengxin Dai

This work studies semantic segmentation under the domain generalization setting, where a model is trained only on the source domain and tested on the unseen target domain.

Domain Generalization Segmentation +1

FreePoint: Unsupervised Point Cloud Instance Segmentation

no code implementations11 May 2023 Zhikai Zhang, Jian Ding, Li Jiang, Dengxin Dai, Gui-Song Xia

Based on the point features, we perform a multicut algorithm to segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.

Instance Segmentation Segmentation +2

Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection

1 code implementation CVPR 2023 Chang Xu, Jian Ding, Jinwang Wang, Wen Yang, Huai Yu, Lei Yu, Gui-Song Xia

Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues.

object-detection Object Detection +3

Few-Shot Object Detection via Variational Feature Aggregation

1 code implementation31 Jan 2023 Jiaming Han, Yuqiang Ren, Jian Ding, Ke Yan, Gui-Song Xia

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples, the learned models are usually biased to base classes and sensitive to the variance of novel examples.

Few-Shot Object Detection Meta-Learning +3

Detecting Building Changes with Off-Nadir Aerial Images

1 code implementation26 Jan 2023 Chao Pang, Jiang Wu, Jian Ding, Can Song, Gui-Song Xia

The tilted viewing nature of the off-nadir aerial images brings severe challenges to the building change detection (BCD) problem: the mismatch of the nearby buildings and the semantic ambiguity of the building facades.

Building change detection for remote sensing images Change Detection

A polynomial time iterative algorithm for matching Gaussian matrices with non-vanishing correlation

no code implementations28 Dec 2022 Jian Ding, Zhangsong Li

Motivated by the problem of matching vertices in two correlated Erd\H{o}s-R\'enyi graphs, we study the problem of matching two correlated Gaussian Wigner matrices.

Graph Matching

Matching recovery threshold for correlated random graphs

no code implementations29 May 2022 Jian Ding, Hang Du

For two correlated graphs which are independently sub-sampled from a common Erd\H{o}s-R\'enyi graph $\mathbf{G}(n, p)$, we wish to recover their \emph{latent} vertex matching from the observation of these two graphs \emph{without labels}.

Detection threshold for correlated Erdős-Rényi graphs via densest subgraphs

no code implementations28 Mar 2022 Jian Ding, Hang Du

The problem of detecting edge correlation between two Erd\H{o}s-R\'enyi random graphs on $n$ unlabeled nodes can be formulated as a hypothesis testing problem: under the null hypothesis, the two graphs are sampled independently; under the alternative, the two graphs are independently sub-sampled from a parent graph which is Erd\H{o}s-R\'enyi $\mathbf{G}(n, p)$ (so that their marginal distributions are the same as the null).

The planted matching problem: Sharp threshold and infinite-order phase transition

no code implementations17 Mar 2021 Jian Ding, Yihong Wu, Jiaming Xu, Dana Yang

Conversely, if $\sqrt{d} B(\mathcal{P},\mathcal{Q}) \ge 1+\epsilon$ for an arbitrarily small constant $\epsilon>0$, the reconstruction error for any estimator is shown to be bounded away from $0$ under both the sparse and dense model, resolving the conjecture in [Moharrami et al. 2019, Semerjian et al. 2020].

ReDet: A Rotation-equivariant Detector for Aerial Object Detection

3 code implementations CVPR 2021 Jiaming Han, Jian Ding, Nan Xue, Gui-Song Xia

More precisely, we incorporate rotation-equivariant networks into the detector to extract rotation-equivariant features, which can accurately predict the orientation and lead to a huge reduction of model size.

Ranked #15 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +1

DetCo: Unsupervised Contrastive Learning for Object Detection

2 code implementations ICCV 2021 Enze Xie, Jian Ding, Wenhai Wang, Xiaohang Zhan, Hang Xu, Peize Sun, Zhenguo Li, Ping Luo

Unlike most recent methods that focused on improving accuracy of image classification, we present a novel contrastive learning approach, named DetCo, which fully explores the contrasts between global image and local image patches to learn discriminative representations for object detection.

Contrastive Learning Image Classification +2

Align Deep Features for Oriented Object Detection

3 code implementations21 Aug 2020 Jiaming Han, Jian Ding, Jie Li, Gui-Song Xia

However most of existing methods rely on heuristically defined anchors with different scales, angles and aspect ratios and usually suffer from severe misalignment between anchor boxes and axis-aligned convolutional features, which leads to the common inconsistency between the classification score and localization accuracy.

Ranked #19 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +2

Consistent recovery threshold of hidden nearest neighbor graphs

no code implementations18 Nov 2019 Jian Ding, Yihong Wu, Jiaming Xu, Dana Yang

Motivated by applications such as discovering strong ties in social networks and assembling genome subsequences in biology, we study the problem of recovering a hidden $2k$-nearest neighbor (NN) graph in an $n$-vertex complete graph, whose edge weights are independent and distributed according to $P_n$ for edges in the hidden $2k$-NN graph and $Q_n$ otherwise.

Learning RoI Transformer for Oriented Object Detection in Aerial Images

2 code implementations CVPR 2019 Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, Qikai Lu

Object detection in aerial images is an active yet challenging task in computer vision because of the bird's-eye view perspective, the highly complex backgrounds, and the variant appearances of objects.

Object object-detection +2

Learning RoI Transformer for Detecting Oriented Objects in Aerial Images

1 code implementation1 Dec 2018 Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, Qikai Lu

Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects.

Ranked #45 on Object Detection In Aerial Images on DOTA (using extra training data)

General Classification Object +4

Efficient random graph matching via degree profiles

1 code implementation19 Nov 2018 Jian Ding, Zongming Ma, Yihong Wu, Jiaming Xu

This work develops an $\tilde{O}(n d^2+n^2)$-time algorithm which perfectly recovers the true vertex correspondence with high probability, provided that the average degree is at least $d = \Omega(\log^2 n)$ and the two graphs differ by at most $\delta = O( \log^{-2}(n) )$ fraction of edges.

Graph Matching

Hidden Hamiltonian Cycle Recovery via Linear Programming

no code implementations15 Apr 2018 Vivek Bagaria, Jian Ding, David Tse, Yihong Wu, Jiaming Xu

Represented as bicolored multi-graphs, these extreme points are further decomposed into simpler "blossom-type" structures for the large deviation analysis and counting arguments.

Traveling Salesman Problem

Online Learning with Composite Loss Functions

no code implementations18 May 2014 Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres

This class includes problems where the algorithm's loss is the minimum over the recent adversarial values, the maximum over the recent values, or a linear combination of the recent values.

Bandits with Switching Costs: T^{2/3} Regret

no code implementations11 Oct 2013 Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres

We prove that the player's $T$-round minimax regret in this setting is $\widetilde{\Theta}(T^{2/3})$, thereby closing a fundamental gap in our understanding of learning with bandit feedback.

Cannot find the paper you are looking for? You can Submit a new open access paper.