Search Results for author:
Found 33 papers, 18 papers with code
MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens
This paper introduces MiniGPT4-Video, a multimodal Large Language Model (LLM) designed specifically for video understanding.
Uni3DL: Unified Model for 3D and Language Understanding
In this work, we present Uni3DL, a unified model for 3D and Language understanding.
Efficiently matching random inhomogeneous graphs via degree profiles
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
Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio?
On the Robustness of Object Detection Models in Aerial Images
The robustness of object detection models is a major concern when applied to real-world scenarios.
Towards Generic and Controllable Attacks Against Object Detection
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.
A polynomial-time iterative algorithm for random graph matching with non-vanishing correlation
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.
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation
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.
FreePoint: Unsupervised Point Cloud Instance Segmentation
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.
Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
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.
Ranked #4 on
Oriented Object Detection
on DOTA 2.0
Few-Shot Object Detection via Variational Feature Aggregation
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.
Detecting Building Changes with Off-Nadir Aerial Images
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
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.
Matching recovery threshold for correlated random graphs
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
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).
Expanding Low-Density Latent Regions for Open-Set Object Detection
Thus, unknown objects in low-density regions can be easily identified with the learned unknown probability.
Decoupling Zero-Shot Semantic Segmentation
2) a zero-shot classification task on segments.
LUAI Challenge 2021 on Learning to Understand Aerial Images
This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images.
The planted matching problem: Sharp threshold and infinite-order phase transition
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
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 #18 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks.
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
In this paper, we present a large-scale Dataset of Object deTection in Aerial images (DOTA) and comprehensive baselines for ODAI.
DetCo: Unsupervised Contrastive Learning for Object Detection
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.
Align Deep Features for Oriented Object Detection
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 #22 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Modeling the Control of COVID-19: Impact of Policy Interventions and Meteorological Factors
Home quarantine is the most important one to prevent the spread of COVID-19.
Consistent recovery threshold of hidden nearest neighbor graphs
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
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.
Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
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 #48 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Efficient random graph matching via degree profiles
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.
Hidden Hamiltonian Cycle Recovery via Linear Programming
Represented as bicolored multi-graphs, these extreme points are further decomposed into simpler "blossom-type" structures for the large deviation analysis and counting arguments.
DOTA: A Large-scale Dataset for Object Detection in Aerial Images
The fully annotated DOTA images contains $188, 282$ instances, each of which is labeled by an arbitrary (8 d. o. f.)
Ranked #52 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Online Learning with Composite Loss Functions
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
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.
