This image appears to be a photo of an academic poster titled "Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification." The research is presented by Zhenyu Cui, Jiahua Zhou, Xun Wang, Manyu Zhu, and Yuxin Peng from the Wangxuan Institute of Computer Technology, Peking University, and ByteDance Inc. The poster outlines their proposed method for person re-identification without the need for re-indexing old data in a gallery, making it compatible with new query features.

### Key Components of the Poster:

#### Method:
- **Overview**: Describes a scheme called Continual Compatible Representation (C2R) for the RFL-ReID task.
- **Continual Compatible Transfer (CCT)**: Updates old gallery features and transfers them to a new feature space.
- **Balanced Compatible Distillation (BCD)**: Ensures compatibility between transferred and new features, maintaining relevance.
- **Balanced Anti-forgetting Distillation (BAD)**: Prevents the loss of old knowledge while balancing old and new information.

#### Pipeline:
- **Training Stage**: Joint optimization of CCT, BCD, and BAD.
- **Transferring Stage**: Updates old feature sets for each training stage.
- **Testing Stage**: Uses calculated query features to match updated gallery features for lifelong person re-identification.

#### Experiments:
- Provides results from various experiments showcasing the effectiveness of the proposed method compared to existing techniques.

#### Conclusion:
- Summarizes the benefits of the proposed method, including its capability to tackle challenges in lifelong person re-identification without the need for re-indexing old data.

### Additional Elements:
- **Diagrams**: Visual representations of the pipeline stages and transfer processes.
- **QR Codes**: Links to more information and related works.

The poster is displayed under ceiling lights with a background structure of intersecting beams, indicative of an exhibition or conference setting.
Text transcribed from the image:
Continual Compatible Representation for Re-indexing Free Lifelong Person Re-ident
Zhenyu Cui¹, Jiahuan Zhou1, Xun Wang2, Manyu Zhu², Yuxin Peng1*
1Wangxuan Institute of Computer Technology, Peking University 2ByteDance Inc
ReID): Aims to learn from
a person across different
orical images in the gallery
or testing (Re-indexing).
Data
Privacy
ReID w/o Re-indexing
New Model
QQ
ID:3
ID:5
Old Gallery Features
Query Features
when raw images in the
acy concerns, resulting in
and the gallery features
on L-ReID performance.
100
Continual
Compatible
Representation
New Model
ID:3 ID:5
Old Gallery Features
Method:
Overview: A Continual Compatible Representation (C2R) scheme is
proposed for RFL-ReID to continuously update old features in the
gallery to make it compatible with new query features.
➤ Continual Compatible Transfer (CCT): Update old gallery
features continuously and transfer old feature to the new feature
space, adaptively capturing the knowledge from different domains.
➤ Balanced Compatible Distillation (BCD): Achieve the
compatibility between the transferred features and the new ones,
preserving the relationship between the old and the transferred
features in a unified feature space.
Balanced Anti-forgetting Distillation (BAD): Eliminate the
accumulated forgetting of old knowledge during the continuous
transfer, balancing the old and the new discriminative information.
(a) Training at s Stage
Old data
New data
Old Model
New Mode
(b) Transfer at s Stage
F
ID:1 ID:2
Updated Features
Query Features
Continual Compatible Transfer (CCT)
Balanced Compatible Distillation (BCD)
Multiply
20
Forward Mapping Module (FMM))
Softmax
Sum
Balanced Anti-forgetting Distillation (BAD)
MLP
H
FC
Knowledge Capturing Module (KCM)
Multiply
00-1-1-0000-1
ID:
New Gallery Feature Set
ID:
ID:
Old Gallery
Feature Set
Transferred
Feature Set
Experiments:
The experiment o
superiority of our pr
Mark
Task
Method
mAE
Joint Train
68.1
SPD [28]
35.0
LWF [11]
56.
CRL [40]
58.
L-ReID
AKA [18]
58
MEGE [20] 39
RFL-ReID
PatchKD [27] 68
Ours 69
LwF* [11] 39
AKA* [18] 3-
CVS* [30] 3
PatchKD* [27] 6
Ours
Our C2R achieve
Conclusion
We propose
tackling the d
• Two balance
forgetting of
•
H
(c) Testing at s Stage
ID: N
ID: N+1 ID: M
ID: 1
•
Extensive e
Extracted
Features:
ID: 182
Query
demonstrate
m on L-ReID task, called
tification (RFL-ReID).
ntation (C2R) scheme to
d gallery in L-ReID.
T) and two balanced
eve L-ReID without re-
Pipeline:
Training Stage: CCT, BCD, and BAD are jointly optimized.
Transferring Stage: CCT network is employed to update the old
feature set after each training stage in L-ReID.
Testing Stage: Query features calculated by the new model is
used to directly match the updated gallery features to achieve re-
indexing free lifelong person re-identification.
➤ Three stages are executed sequentially when facing new data.
More
Information
Go!
Related
Works
Go!
回回
[Lab
[1] Zhenyu
Rectificatio
[2] Zhenyu
Re-Identific