Decoupled and Memory-Reinforced Networks: Towards Effective Feature
Learning for One-Step Person Search
- URL: http://arxiv.org/abs/2102.10795v1
- Date: Mon, 22 Feb 2021 06:19:45 GMT
- Title: Decoupled and Memory-Reinforced Networks: Towards Effective Feature
Learning for One-Step Person Search
- Authors: Chuchu Han, Zhedong Zheng, Changxin Gao, Nong Sang, Yi Yang
- Abstract summary: One-step methods have been developed to handle pedestrian detection and identification sub-tasks using a single network.
There are two major challenges in the current one-step approaches.
We propose a decoupled and memory-reinforced network (DMRNet) to overcome these problems.
- Score: 65.51181219410763
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The goal of person search is to localize and match query persons from scene
images. For high efficiency, one-step methods have been developed to jointly
handle the pedestrian detection and identification sub-tasks using a single
network. There are two major challenges in the current one-step approaches. One
is the mutual interference between the optimization objectives of multiple
sub-tasks. The other is the sub-optimal identification feature learning caused
by small batch size when end-to-end training. To overcome these problems, we
propose a decoupled and memory-reinforced network (DMRNet). Specifically, to
reconcile the conflicts of multiple objectives, we simplify the standard
tightly coupled pipelines and establish a deeply decoupled multi-task learning
framework. Further, we build a memory-reinforced mechanism to boost the
identification feature learning. By queuing the identification features of
recently accessed instances into a memory bank, the mechanism augments the
similarity pair construction for pairwise metric learning. For better encoding
consistency of the stored features, a slow-moving average of the network is
applied for extracting these features. In this way, the dual networks reinforce
each other and converge to robust solution states. Experimentally, the proposed
method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds
all the existing one-step methods.
Related papers
- GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning [51.677086019209554]
We propose a Generalized Structural Sparse to capture powerful relationships across modalities for pair-wise similarity learning.
The distance metric delicately encapsulates two formats of diagonal and block-diagonal terms.
Experiments on cross-modal and two extra uni-modal retrieval tasks have validated its superiority and flexibility.
arXiv Detail & Related papers (2024-10-20T03:45:50Z) - AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection [23.91870504363899]
Double-stream networks in multispectral detection employ two separate feature extraction branches for multi-modal data.
This has hindered the widespread employment of multispectral pedestrian detection in embedded devices for autonomous systems.
We introduce the Adaptive Modal Fusion Distillation (AMFD) framework, which can fully utilize the original modal features of the teacher network.
arXiv Detail & Related papers (2024-05-21T17:17:17Z) - Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features.
Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
arXiv Detail & Related papers (2023-05-17T14:30:11Z) - Learning to Learn with Indispensable Connections [6.040904021861969]
We propose a novel meta-learning method called Meta-LTH that includes indispensible (necessary) connections.
Our method improves the classification accuracy by approximately 2% (20-way 1-shot task setting) for omniglot dataset.
arXiv Detail & Related papers (2023-04-06T04:53:13Z) - OFA$^2$: A Multi-Objective Perspective for the Once-for-All Neural
Architecture Search [79.36688444492405]
Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints.
We aim to give one step further in the search for efficiency by explicitly conceiving the search stage as a multi-objective optimization problem.
arXiv Detail & Related papers (2023-03-23T21:30:29Z) - Transformer-based assignment decision network for multiple object
tracking [0.0]
We introduce Transformer-based Assignment Decision Network (TADN) that tackles data association without the need of explicit optimization during inference.
Our proposed approach outperforms the state-of-the-art in most evaluation metrics despite its simple nature as a tracker.
arXiv Detail & Related papers (2022-08-06T19:47:32Z) - Multi-object Tracking with a Hierarchical Single-branch Network [31.680667324595557]
We propose an online multi-object tracking framework based on a hierarchical single-branch network.
Our novel iHOIM loss function unifies the objectives of the two sub-tasks and encourages better detection performance.
Experimental results on MOT16 and MOT20 datasets show that we can achieve state-of-the-art tracking performance.
arXiv Detail & Related papers (2021-01-06T12:14:58Z) - Diverse Knowledge Distillation for End-to-End Person Search [81.4926655119318]
Person search aims to localize and identify a specific person from a gallery of images.
Recent methods can be categorized into two groups, i.e., two-step and end-to-end approaches.
We propose a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck.
arXiv Detail & Related papers (2020-12-21T09:04:27Z) - MetaGater: Fast Learning of Conditional Channel Gated Networks via
Federated Meta-Learning [46.79356071007187]
We propose a holistic approach to jointly train the backbone network and the channel gating.
We develop a federated meta-learning approach to jointly learn good meta-initializations for both backbone networks and gating modules.
arXiv Detail & Related papers (2020-11-25T04:26:23Z) - FairMOT: On the Fairness of Detection and Re-Identification in Multiple
Object Tracking [92.48078680697311]
Multi-object tracking (MOT) is an important problem in computer vision.
We present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet.
The approach achieves high accuracy for both detection and tracking.
arXiv Detail & Related papers (2020-04-04T08:18:00Z)
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.