Generalising without Forgetting for Lifelong Person Re-Identification

Wu, Guile; Gong, Shaogang

doi:10.1609/aaai.v35i4.16395

Cited by 19 publications

(13 citation statements)

References 18 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(5) Domain generalization methods [27][28][29] which aim to learn from source data and then generalize to target data without access to target data. (6) Lifelong learning methods [30,31] which assumes a continual stream of person Re-ID datasets and avoids catastrophic forgetting in continual training process. Nevertheless, most of them do not fully address the challenge in visible-infrared person Re-ID with enormous modality discrepancy.…”

Section: Visible-visible Person Re-idmentioning

confidence: 99%

Modality Discrepancy Reduction for Visible-Infrared Person Re-Identification under Complete Modality Missing

Zhang,

Ge,

Tang

et al. 2024

Preprint

View full text Add to dashboard Cite

Person re-identification (Re-ID) aims to match person images across non-overlapping camera views. Most of existing methods focus on short-time and small-scale surveillance systems in which each person is captured in multiple camera views of adjacent scenes in a short time span. However, in long-term and large-scale surveillance systems covering larger areas and spanning different time duration, existing methods tend to fail. Specifically, when light condition is extremely dark, the camera automatically switches to infrared mode. Matching across infrared images and RGB images is difficult due to the large appearance difference. Meanwhile, since most pedestrians appear in limited local areas and fixed time, it is difficult to collect training images of the same person under both infrared and RGB mode. Hence, a model is required to match person images cross modality under a complete modality missing condition. In this work, we study intra-modality supervised person re-identification under complete modality missing, which uses cross-modality unpaired data with intra-modality identity labels for training. It is challenging as cross-modality paired data plays an important role for learning modality-invariant representation in most existing Re-ID methods. To learn modality-invariant representation from cross-modality unpaired training data, we first introduce a strong baseline with a dual-head cross-entropy loss and a multi-modality negative loss, aiming to alleviate cross-modality contrast and enhance intra-modality contrast. Then, we propose a residual modality alleviation network and a shape-guided consistency learning loss to further alleviate cross-modality representation discrepancy. The experiments are conducted in the complete modality missing setting on SYSY-MM01 and RegDB datasets. The evaluation results demonstrate the superiority of our method.

show abstract

Section: Visible-visible Person Re-idmentioning

confidence: 99%

Modality Discrepancy Reduction for Visible-Infrared Person Re-Identification under Complete Modality Missing

Zhang,

Ge,

Tang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…This step is focused on how to iteratively leverage human feedback to improve model performance. As mentioned, (He et al 2020) and (Wu and Gong 2021) are two representative incremental learning strategies that work in the online scenario. 3) Online inference: In this stage, human can assist models to accomplish a task together and achieve better performance.…”

Section: Related Workmentioning

confidence: 99%

“…The Thirty-Seventh AAAI Conference on Artificial Intelligence ing the exemplar set. (Wu and Gong 2021) designs a more comprehensive learning objective that incorporates the coherence of classification, distribution and representation in a unified framework. The underlying motivation is to support life-long ReID without forgetting.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human-in-the-Loop Vehicle ReID

Zhang

Shen

et al. 2023

AAAI

View full text Add to dashboard Cite

Vehicle ReID has been an active topic in computer vision, with a substantial number of deep neural models proposed as end-to-end solutions. In this paper, we solve the problem from a new perspective and present an interesting variant called human-in-the-loop vehicle ReID to leverage interactive (and possibly wrong) human feedback signal for performance enhancement. Such human-machine cooperation mode is orthogonal to existing ReID models. To avoid incremental training overhead, we propose an Interaction ReID Network (IRIN) that can directly accept the feedback signal as an input and adjust the embedding of query image in an online fashion. IRIN is offline trained by simulating the human interaction process, with multiple optimization strategies to fully exploit the feedback signal. Experimental results show that even by interacting with flawed feedback generated by non-experts, IRIN still outperforms state-of-the-art ReID models by a considerable margin. If the feedback contains no false positive, IRIN boosts the mAP in Veri776 from 81.6% to 95.2% with only 5 rounds of interaction per query image.

show abstract

“…Similar to other lifelong learning tasks (Liang et al 2022), the challenge of catastrophic forgetting emerges as a critical obstacle due to the discrepancy in knowledge across diverse datasets. To handle this issue, several LReID approaches aim to retain exemplars from the old datasets as the rehearsal of historical knowledge for the learning of new models (Wu and Gong 2021;Ge et al 2022;Yu et al 2023). However, this solution will indeed impede data privacy and suffer from considerable computational overheads.…”

Section: Introductionmentioning

confidence: 99%

LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification

Xu,

Zou,

Zhou

2024

AAAI

View full text Add to dashboard Cite

Lifelong person re-identification (LReID) aims to train a unified model from diverse data sources step by step. The severe domain gaps between different training steps result in catastrophic forgetting in LReID, and existing methods mainly rely on data replay and knowledge distillation techniques to handle this issue. However, the former solution needs to store historical exemplars which inevitably impedes data privacy. The existing knowledge distillation-based models usually retain all the knowledge of the learned old models without any selections, which will inevitably include erroneous and detrimental knowledge that severely impacts the learning performance of the new model. To address these issues, we propose an exemplar-free LReID method named LongShort Term Knowledge Consolidation (LSTKC) that contains a Rectification-based Short-Term Knowledge Transfer module (R-STKT) and an Estimation-based Long-Term Knowledge Consolidation module (E-LTKC). For each learning iteration within one training step, R-STKT aims to filter and rectify the erroneous knowledge contained in the old model and transfer the rectified knowledge to facilitate the short-term learning of the new model. Meanwhile, once one training step is finished, E-LTKC proposes to further consolidate the learned long-term knowledge via adaptively fusing the parameters of models from different steps. Consequently, experimental results show that our LSTKC exceeds the state-of-the-art methods by 6.3%/9.4% and 7.9%/4.5%, 6.4%/8.0% and 9.0%/5.5% average mAP/R@1 on seen and unseen domains under two different training orders of the challenging LReID benchmark respectively.

show abstract

Generalising without Forgetting for Lifelong Person Re-Identification

Cited by 19 publications

References 18 publications

Modality Discrepancy Reduction for Visible-Infrared Person Re-Identification under Complete Modality Missing

Modality Discrepancy Reduction for Visible-Infrared Person Re-Identification under Complete Modality Missing

Human-in-the-Loop Vehicle ReID

LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification

Contact Info

Product

Resources

About