A large academic poster displayed at a conference, detailing research from Peking University titled "Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification." The poster features an extensive introduction and method section, highlighting novel approaches to lifelong person re-identification. Graphs, charts, and diagrams illustrate the research's methodologies, including topics such as Instance-level Distribution Modeling and Distribution-aware Knowledge Transfer. The poster is attributed to Kunlun Xu, Xu Zou, Yuxin Peng, and Jiahuan Zhou from the School of Artificial Intelligence at Peking University and Huazhong University of Science and Technology. A hand is pointing towards the "Experiments" section, emphasizing the detailed results and performance metrics obtained from the experiments conducted. The layout is organized, facilitating a comprehensive understanding of the research findings showcased. The environment appears to be an academic or professional conference setting, evidenced by the visible booth structures and lighting.
Text transcribed from the image:
9
北京大學
PEKING UNIVERSITY
Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification
Kunlun Xu, Xu Zou², Yuxin Peng, Jiahuan Zhou
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, 430074, China?
Wangxuan Institute of Computer Technology, Peking University, Beijing 100871, China
ction
suffers from
g person re-identification (LReID)
Ophic forgetting when learning continually. Exemplar
owledge distillation-based LReID methods encounter
vacy and limited acquisition capacity respectively.
e-based works set the prototypes as discrete points or
al distributions, either discarding the distribution
ion or omitting instance-level diversity which are
ne-grained clues for LReID.
pose Distribution-aware Knowledge Prototyping (DKP)
stance-level diversity of each sample is modeled to
comprehensive fine-grained knowledge for prototyping.
Identity Feature
Identity Center
Distribution Boundary
New
Identity
Step t-1
Step t
ty feature center A
as prototype
A
Method
SEATTLE
Step t-1.
Dt-1
-Step t.
Experiments
Pt-1
Dt
Pt
-Step t+1
D+1
Peti
The experiments on the LReID benchmark
Method
Marke
MTMC MSMT17
mAP Re
(a) Overall Model
Instance center Prototype of step t-1
(b) Instance-level Distribution Modeling (IDM)
Instance center
Joint-Train
75.3 91
316 57
L&F (21
CIL SPD [31]
56.3 77
35.6 6
Pt-10
0
Lee-d
PRAKA 12 374 61
PKT
Pooling
IDM
He-d
Lproto-di
Liri-di
Xn
X1 X2
Backbone
H
DPG
.....
Liri-d
CRL (42)
N(CV)
Conv
Linear
Pt
Model Mt
Instance variance Prototype of step t
Instance variance
Sampler
m candidates per age
Feature candidate
(d) Distribution-oriented Prototype Generation (DPG)
PRD [2] 73 180
580 782 725 75.1
AKA [24] 512 720 475 451 187 33.1
LReID AKA [24] 581 714 72.5 748 287 452 61
PatchKD [25] 68.5 85.7 75.6 78.6 33.8 504 65
MEGE [26] 390 616 73.3 76.5 16.9 30.3 49
DKP(Ours) 603 805 83.6 85.4 51.6 68.4 10
Our DKP achieves better balance between learning
> Performance tendency on seen and unse
(c) Prototype-based Knowledge Transfer (PKT)
91 1
2
92 proto-d
Instances Identity i
UN₁-1
Prototype Pt-1
Sampler Prototype sample
Instance center Instances of identity k
Eq. (4) and Eq. (5) Prototype P
Overview: Our model is built upon a dual branch convolution network where the instance-specific
distribution center and variance are predicted, respectively. Furthermore, three modules PKT,
IDM and DPG are designed to accomplish the lifelong learning procedure.
IDM: Model the distribution for each input instance based on the sampling strategy and the
proposed distribution-aware losses ce-d and Ltri-d
Lce-d
1
m
==
m+1
j=1
Taining stop
+a+D
+4
<+-LNE
(a) Anti-
Ltri-d = log(1+ exp(c-fp-f
Ou
th
I learning via enhancing the discriminant of new identity features with
I on the prototype-aware knowledge transfer loss proto-d
=LKL (P(CC/2)p(FF/2))
a multiva