paper-with-me

Papers

Bag of Tricks and A Strong baseline for Image Copy Detection

2021-11-13 · Wenhao Wang, Weipu Zhang, Yifan Sun, Yi Yang

Image copy detection is of great importance in real-life social media. In this paper, a bag of tricks and a strong baseline are proposed for image copy detection. Unsupervised pre-training substitutes the commonly-used supervised one. Beyond that, we design a descriptor stretching strategy to stabilize the scores of different queries. Experiments demonstrate that the proposed method is effective. The proposed baseline ranks third out of 526 participants on the Facebook AI Image Similarity Challenge: Descriptor Track. The code and trained models are available at https://github.com/WangWenhao0716/ISC-Track2-Submission.

📄 PDF Abstract BibTeX arXiv:2111.08004

Code (1)

wangwenhao0716/isc-track2-submission 공식 구현 pytorch

Tasks

Copy DetectionUnsupervised Pre-training

Similar Papers 제목 키워드 기반

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

2019-03-17 · Hao Luo, Youzhi Gu, Xingyu Liao, Shenqi Lai 외

This paper explores a simple and efficient baseline for person re-identification (ReID). Person re-identification (ReID) with deep neural networks has made progress and achieved high performance in recent years. However,…

Person Re-Identification

A Strong Baseline and Batch Normalization Neck for Deep Person Re-identification

2019-06-19 · Hao Luo, Wei Jiang, Youzhi Gu, Fuxu Liu 외

This study explores a simple but strong baseline for person re-identification (ReID). Person ReID with deep neural networks has progressed and achieved high performance in recent years. However, many state-of-the-art met…

Person Re-Identification

Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directions

2022-09-21 · Dong Zhang, Yi Lin, Hao Chen, Zhuotao Tian 외

Over the past few years, the rapid development of deep learning technologies for computer vision has significantly improved the performance of medical image segmentation (MedISeg). However, the diverse implementation str…

Data AugmentationDomain AdaptationImage SegmentationMedical Image Segmentation+1

TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection

2026-02-03 · Alireza Salehi, Ehsan Karami, Sepehr Noey, Sahand Noey 외 arxiv

Anomaly detection identifies departures from expected behavior in safety-critical settings. When target-domain normal data are unavailable, zero-shot anomaly detection (ZSAD) leverages vision-language models (VLMs). Howe…

Anomaly Detection

Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection

2023-10-09 · ICCV 2023 1 · Xinzhu Ma, Yongtao Wang, Yinmin Zhang, Zhiyi Xia 외

In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object detection. In particular, different from oth…

2D Object Detection3D Object DetectionObjectobject-detection+1