Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are continually being ...developed, we have found two research topics that have spawned when dealing with these latest state-of-the-art methods. To address the topics, we propose a trainable bag-of-freebies oriented solution. We combine the flexible and efficient training tools with the proposed architecture and the compound scaling method. YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 120 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. Source code is released in https://github.com/WongKinYiu/yolov7.
Algorithms for Big Data Bast, Hannah; Korzen, Claudius; Meyer, Ulrich ...
2022, 2023, 2023-01-17, Volume:
13201
eBook
Open access
This open access book surveys the progress in addressing selected challenges related to the growth of big data in combination with increasingly complicated hardware. It emerged from a research ...program established by the German Research Foundation (DFG) as priority program SPP 1736 on Algorithmics for Big Data where researchers from theoretical computer science worked together with application experts in order to tackle problems in domains such as networking, genomics research, and information retrieval. Such domains are unthinkable without substantial hardware and software support, and these systems acquire, process, exchange, and store data at an exponential rate. The chapters of this volume summarize the results of projects realized within the program and survey-related work. This is an open access book.
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks. With the broader deployment of DNNs on ...various applications, the concerns over their safety and trustworthiness have been raised in public, especially after the widely reported fatal incidents involving self-driving cars. Research to address these concerns is particularly active, with a significant number of papers released in the past few years. This survey paper conducts a review of the current research effort into making DNNs safe and trustworthy, by focusing on four aspects: verification, testing, adversarial attack and defence, and interpretability. In total, we survey 202 papers, most of which were published after 2017.
Inspired by a
width
invariant defined on permutations by Guillemot and Marx SODA’14, we introduce the notion of twin-width on graphs and on matrices. Proper minor-closed classes, bounded rank-width ...graphs, map graphs,
K
t
-free unit
d
-dimensional ball graphs, posets with antichains of bounded size, and proper subclasses of dimension-2 posets all have bounded twin-width. On all these classes (except map graphs without geometric embedding) we show how to compute in polynomial time a
sequence of
d
-contractions
, witness that the twin-width is at most
d
. We show that FO model checking, that is deciding if a given first-order formula ϕ evaluates to true for a given binary structure
G
on a domain
D
, is FPT in |ϕ| on classes of bounded twin-width, provided the witness is given. More precisely, being given a
d
-contraction sequence for
G
, our algorithm runs in time
f
(
d
,|ϕ |) · |D| where
f
is a computable but non-elementary function. We also prove that bounded twin-width is preserved under FO interpretations and transductions (allowing operations such as squaring or complementing a graph). This unifies and significantly extends the knowledge on fixed-parameter tractability of FO model checking on non-monotone classes, such as the FPT algorithm on bounded-width posets by Gajarský et al. FOCS’15.
This article shows how to solve linear programs of the form min
Ax
=
b
,
x
≥ 0
c
⊤
x
with
n
variables in time
O
*
((
n
ω
+
n
2.5−α/2
+
n
2+1/6
) log (
n
/δ)), where ω is the exponent of matrix ...multiplication, α is the dual exponent of matrix multiplication, and δ is the relative accuracy. For the current value of ω δ 2.37 and α δ 0.31, our algorithm takes
O
*
(
n
ω
log (
n
/δ)) time. When ω = 2, our algorithm takes
O
*
(
n
2+1/6
log (
n
/δ)) time.
Our algorithm utilizes several new concepts that we believe may be of independent interest:
• We define a stochastic central path method.
• We show how to maintain a projection matrix √
W
A
⊤
(
AWA
⊤
)
−1
A
√
W
in sub-quadratic time under \ell
2
multiplicative changes in the diagonal matrix
W
.
This open access book constitutes the thoroughly refereed post-conference proceedings of the 6th International Workshop on Graph Structures for Knowledge Representation and Reasoning, GKR 2020, held ...virtually in September 2020, associated with ECAI 2020, the 24th European Conference on Artificial Intelligence.The 7 revised full papers presented together with 2 invited contributions were reviewed and selected from 9 submissions. The contributions address various issues for knowledge representation and reasoning and the common graph-theoretic background, which allows to bridge the gap between the different communities.
Object Detection With Deep Learning: A Review Zhao, Zhong-Qiu; Zheng, Peng; Xu, Shou-Tao ...
IEEE transaction on neural networks and learning systems,
2019-Nov., 2019-11-00, 20191101, Volume:
30, Issue:
11
Journal Article
Open access
Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on ...handcrafted features and shallow trainable architectures. Their performance easily stagnates by constructing complex ensembles that combine multiple low-level image features with high-level context from object detectors and scene classifiers. With the rapid development in deep learning, more powerful tools, which are able to learn semantic, high-level, deeper features, are introduced to address the problems existing in traditional architectures. These models behave differently in network architecture, training strategy, and optimization function. In this paper, we provide a review of deep learning-based object detection frameworks. Our review begins with a brief introduction on the history of deep learning and its representative tool, namely, the convolutional neural network. Then, we focus on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. As distinct specific detection tasks exhibit different characteristics, we also briefly survey several specific tasks, including salient object detection, face detection, and pedestrian detection. Experimental analyses are also provided to compare various methods and draw some meaningful conclusions. Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network-based learning systems.