Improving Person Re-identification with Iterative Impression Aggregation

• URL: http://arxiv.org/abs/2009.10066v1
• Date: Mon, 21 Sep 2020 17:59:04 GMT
• Title: Improving Person Re-identification with Iterative Impression Aggregation
• Authors: Dengpan Fu and Bo Xin and Jingdong Wang and Dongdong Chen and Jianmin Bao and Gang Hua and Houqiang Li
• Abstract summary: We formulate such an intuition into the problem of person re-identification (re-ID) We propose a simple attentional aggregation formulation to instantiate this idea and showcase that such a pipeline achieves competitive performance on standard benchmarks.
• Score: 115.28738095583228
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Our impression about one person often updates after we see more aspects of him/her and this process keeps iterating given more meetings. We formulate such an intuition into the problem of person re-identification (re-ID), where the representation of a query (probe) image is iteratively updated with new information from the candidates in the gallery. Specifically, we propose a simple attentional aggregation formulation to instantiate this idea and showcase that such a pipeline achieves competitive performance on standard benchmarks including CUHK03, Market-1501 and DukeMTMC. Not only does such a simple method improve the performance of the baseline models, it also achieves comparable performance with latest advanced re-ranking methods. Another advantage of this proposal is its flexibility to incorporate different representations and similarity metrics. By utilizing stronger representations and metrics, we further demonstrate state-of-the-art person re-ID performance, which also validates the general applicability of the proposed method.

Related papers

• Neighbor-Based Feature and Index Enhancement for Person Re-Identification [11.268034456071542]
  Person re-identification (Re-ID) aims to match the same pedestrian in a large gallery with different cameras and views. Existing methods usually improve feature representation by improving model architecture. We propose a novel model DMON-ARO that leverages latent neighborhood information to enhance both feature representation and index performance.
  arXiv  Detail & Related papers  (2025-04-16T06:13:20Z)
• Breaking the Clusters: Uniformity-Optimization for Text-Based Sequential Recommendation [17.042627742322427]
  Traditional sequential recommendation methods rely on explicit item IDs to capture user preferences over time. Recent studies have shifted towards leveraging text-only information for recommendation. We propose UniT, a framework that employs three pairwise item sampling strategies.
  arXiv  Detail & Related papers  (2025-02-19T08:35:28Z)
• Interactive Visualization Recommendation with Hier-SUCB [52.11209329270573]
  We propose an interactive personalized visualization recommendation (PVisRec) system that learns on user feedback from previous interactions. For more interactive and accurate recommendations, we propose Hier-SUCB, a contextual semi-bandit in the PVisRec setting.
  arXiv  Detail & Related papers  (2025-02-05T17:14:45Z)
• Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training [51.87027943520492]
  We present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities. Benefiting from our proposed paradigm, we first create a new large-scale person Re-ID dataset Diff-Person, which consists of over 777K images from 5,183 identities.
  arXiv  Detail & Related papers  (2024-06-10T06:26:03Z)
• Rethinking Person Re-identification from a Projection-on-Prototypes Perspective [84.24742313520811]
  Person Re-IDentification (Re-ID) as a retrieval task, has achieved tremendous development over the past decade. We propose a new baseline ProNet, which innovatively reserves the function of the classifier at the inference stage. Experiments on four benchmarks demonstrate that our proposed ProNet is simple yet effective, and significantly beats previous baselines.
  arXiv  Detail & Related papers  (2023-08-21T13:38:10Z)
• A Model-Agnostic Framework for Recommendation via Interest-aware Item Embeddings [4.989653738257287]
  Interest-aware Capsule network (IaCN) is a model-agnostic framework that directly learns interest-oriented item representations. IaCN serves as an auxiliary task, enabling the joint learning of both item-based and interest-based representations. We evaluate the proposed approach on benchmark datasets, exploring various scenarios involving different deep neural networks.
  arXiv  Detail & Related papers  (2023-08-17T22:40:59Z)
• Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs [7.923088041693465]
  We present an ensemble of lightweight VAEs to learn posteriors over subsets of the feature-space, which get aggregated into a joint posterior in a novel divide-and-conquer approach. We show that our approach is robust to partial features at inference, exhibiting little performance degradation even with most features missing.
  arXiv  Detail & Related papers  (2023-06-27T17:55:31Z)
• FedAvg with Fine Tuning: Local Updates Lead to Representation Learning [54.65133770989836]
  Federated Averaging (FedAvg) algorithm consists of alternating between a few local gradient updates at client nodes, followed by a model averaging update at the server. We show that the reason behind generalizability of the FedAvg's output is its power in learning the common data representation among the clients' tasks. We also provide empirical evidence demonstrating FedAvg's representation learning ability in federated image classification with heterogeneous data.
  arXiv  Detail & Related papers  (2022-05-27T00:55:24Z)
• Contextual Similarity Aggregation with Self-attention for Visual Re-ranking [96.55393026011811]
  We propose a visual re-ranking method by contextual similarity aggregation with self-attention. We conduct comprehensive experiments on four benchmark datasets to demonstrate the generality and effectiveness of our proposed visual re-ranking method.
  arXiv  Detail & Related papers  (2021-10-26T06:20:31Z)
• Instance and Pair-Aware Dynamic Networks for Re-Identification [16.32740680438257]
  Re-identification (ReID) is to identify the same instance across different cameras. We propose a novel end-to-end trainable dynamic convolution framework named Instance and Pair-Aware Dynamic Networks. In some datasets our algorithm outperforms state-of-the-art methods and in others, our algorithm achieves a comparable performance.
  arXiv  Detail & Related papers  (2021-03-09T12:34:41Z)
• Intra-Camera Supervised Person Re-Identification [87.88852321309433]
  We propose a novel person re-identification paradigm based on an idea of independent per-camera identity annotation. This eliminates the most time-consuming and tedious inter-camera identity labelling process. We formulate a Multi-tAsk mulTi-labEl (MATE) deep learning method for Intra-Camera Supervised (ICS) person re-id.
  arXiv  Detail & Related papers  (2020-02-12T15:26:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.