This image captures an academic poster presented at CVPR 2024, showcasing a research paper titled "Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification" by researchers from Peking University and ByteDance Inc. The poster is neatly divided into several sections explaining various aspects of the research, including an introduction, methodology, experiments, and conclusions.

The **Introduction** section outlines the Lifelong Person Re-identification (L-ReID) problem and emphasizes the necessity for continual updating of person representations to maintain performance over time. It highlights the goal of achieving efficient and accurate person re-indexing without requiring access to historical data.

The **Method** section introduces the Continual Compatible Representation (C²R) scheme, focusing on three main components:
- **Continual Compatible Transfer (CCT):** Updating the old gallery by transferring new features from different domains.
- **Balanced Compatible Distillation (BCD):** Achieving compatibility between transferred features and new features.
- **Anti-forgetting Distillation (BAD):** Elimination of the accumulated forgetting of old knowledge through continual learning.

The **Experiments** section presents empirical results verifying the superiority of C²R using several benchmark datasets, with a detailed table and performance graphs demonstrating the stability and efficacy of the proposed method.

The **Conclusion** summarizes the contributions, stating that C²R proposes a practical solution to lifelong person re-identification challenges by balancing the anti-forgetting of old knowledge with compatibility to new data. The section emphasizes extensive experimental validation of the proposed method's effectiveness.

At the bottom, there are QR codes linking to the Lab homepage, GitHub repository, and WeChat page for further information and access to related works. The poster is framed against the backdrop of a well-lit conference hall, indicating an engaging academic setting.
Text transcribed from the image:
Byte Dance
Introduction:
Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
Zhenyu Cui', Jiahuan Zhou, Xun Wang2, Manyu Zhu², Yuxin Peng1*
"Wangxuan Institute of Computer Technology, Peking University 2ByteDance Inc
Lifelong Person Re-identification (L-ReID): Aims to learn from
sequentially collected data to match a person across different
scenes. Once the model is updated, historical images in the gallery
are re-calculated to obtain new features for testing (Re-indexing).
Feature Replacing
RelD w/Re-indexing
RelD w/o Re-indexing
DO
Privacy
O Gallery Features
Query Fest
• Limitations: Re-indexing is infeasible when raw images in the
gallery are unavailable due to data privacy concerns, resulting in
incompatible retrieval between the query and the gallery features
calculated by different models and limitation on L-ReID performance.
Goal: Achieve effective L-ReID
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.
( Training at Stepe
Continual Compatible Transfer (CCT)
Balanced Compatible Distillation (BCD)
Balanced Anti-forgetting Distillation (BAD)
Experiments:
The CVPR
M SEATTLE, WA JUNE 17-21, 2024
•
Task
Method
mAP
MAP R@I
R@I
Market-1501 CUHK-SYSU DukeMTMC-ReID MSMT17-V2
mAP ROI MAP ROI
The experiment on the benchmark L-ReID datasets verify the
superiority of our proposed C²R.
Joint Train
68.1
85.2
81.4 83.8
60.4
75.7
24.6 48.9
Average
CUHK03
MAP R@1 mAP R@I
42.7 43.6 55.4 67.5
SPD [28]
35.6
61.2
61.7
64.0
27.5
47.1
5.2
15.5
44.3
42.2
34.4 46.4
LwF [11]
563
56.3
77.1
72.9
75.1
29.6
46.5
6.0 16.6
36.1
37.5
40.2
50.6
CRE
CRL [40]
58.0
78.2
72.5
75.1
28.3
45.2
6.0
15.8
37.4
39.8
40.5
50.8
L-ReID
AKATIO
AKA [18]
58.1
77.4
72.5
74.8
28.7
45.2
6.1
38.7
16.2
40.4
40.8 50.8
MEGE [20]
39.0 01.0
61.6
73.3
76.6
16.9
30.3
4.6
13.4
36.4
37.1
34.0
43.8
PatchKD [27] 68.5
85.7
75.6
78.6
33.8
50.4
17.0
6.5
34.1
36.8
43.7
53.7
RFL-ReID
Ours
58.0 40.0
39.1 58.0
LWF [11]
52.2
36.1
AKA [18]
49.0
55.6
38.8
CVS* [30]
78.4 57.8
PatchKD [27] 61.4
Ours 62.7 79.7 64.4
86.8 76.7
69.0
79.5
33.2
48.6
35.6
17.4
6.6
36.2
44.2
53.7
40.7
7.8
15.3
2.6
7.1
23.3 23.9 22.6 29.0
37.6
38.6
7.6
13.8
3.1
8.3
26.5
26.5 22.4
27.7
49.7 19.3
30.0
4.6
20.8
59.0
26.7
66.3
34.4
5.1
41.7
24.7 24.7 27.3
11.5
12.8 36.0 37.6 36.2
6.8 15.7 37.2 37.6 39.5
34.3
44.4
48.2
Our C2R achieves stable SOTA performance at each training stages.
Contal
Compatible
without re-indexing raw images
in the gallery by continuously
updating old features in the
Regrestative
gallery to make it compatible
with new query features.
• Contribution:
日日"
➤Focus on a practical but challenge problem on L-ReID task, called
Re-indexing Free Lifelong Person Re-identification (RFL-ReID).
Propose a Continual Compatible Representation (C2R) scheme to
prevent re-indexing to raw images in the old gallery in L-ReID.
A Continual Compatible Transfer (CCT) and two balanced
distillation modules are proposed to achieve L-ReID without re-
indexing raw images in the gallery.
Transfer at Stage
Pipeline:
(c) Testing at Stage
ID: 112V
Query
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.
Conclusion
•
.
•
We propose C2R for the practical & challenge task, RFL-ReID,
tackling the data privacy issue in lifelong person re-identification.
Two balanced distillation module are designed to balance the anti-
forgetting of old knowledge with the compatibility to the new model.
Extensive experiments on several benchmark L-ReID datasets
demonstrate the effectiveness of our method.
More
Information
Go!
Related
Works
Go!
[Lab homepage]
[GitHub page]
MIPL
[WeChat page]
[1] Zhenyu Cui, et al., "Continual Vision-Language Retrieval via Dynamic Knowledge
Rectification", 8th AAAI Conference on Artificial Intelligence (AAAI), 2024.
[2] Zhenyu Cui, et al., "DMA: Dual Modality-Aware Alignment for Visible-Infrared Person
Re-Identification", IEEE Transactions on Information Forensics and Security (TIFS), 2024.