paper-with-me

Papers

RankDetNet: Delving Into Ranking Constraints for Object Detection

2021-06-19 · CVPR 2021 1 · Ji Liu, Dong Li, Rongzhang Zheng, Lu Tian, Yi Shan

Modern object detection approaches cast detecting objects as optimizing two subtasks of classification and localization simultaneously. Existing methods often learn the classification task by optimizing each proposal separately and neglect the relationship among different proposals. Such detection paradigm also encounters the mismatch between classification and localization due to the inherent discrepancy of their optimization targets. In this work, we propose a ranking-based optimization algorithm for harmoniously learning to rank and localize proposals in lieu of the classification task. To this end, we comprehensively investigate three types of ranking constraints, i.e., global ranking, class-specific ranking and IoU-guided ranking losses. The global ranking loss encourages foreground samples to rank higher than background. The class-specific ranking loss ensures that positive samples rank higher than negative ones for each specific class. The IoU-guided ranking loss aims to align each pair of confidence scores with the associated pair of IoU overlap between two positive samples of a specific class. Our ranking constraints can sufficiently explore the relationships between samples from three different perspectives. They are easy-to-implement, compatible with mainstream detection frameworks and computation-free for inference. Experiments demonstrate that our RankDetNet consistently surpasses prior anchor-based and anchor-free baselines, e.g., improving RetinaNet baseline by 2.5% AP on the COCO test-dev set without bells and whistles. We also apply the proposed ranking constraints for 3D object detection and achieve improved performance, which further validates the superiority and generality of our method.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionClassificationLearning-To-RankObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

FPN 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Focal Loss A Focal Loss function addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to…
RetinaNet RetinaNet is a one-stage object detection model that utilizes a focal loss function to address class imbalance during training.…

Similar Papers 제목 키워드 기반

RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss

2021-10-09 · Trung Q. Tran, Mingu Kang, Daeyoung Kim

Semi-supervised learning (SSL) has played an important role in leveraging unlabeled data when labeled data is limited. One of the most successful SSL approaches is based on consistency regularization, which encourages th…

Computational EfficiencyTriplet

Pillars of Grammatical Error Correction: Comprehensive Inspection Of Contemporary Approaches In The Era of Large Language Models

2024-04-23 · Kostiantyn Omelianchuk, Andrii Liubonko, Oleksandr Skurzhanskyi, Artem Chernodub 외

In this paper, we carry out experimental research on Grammatical Error Correction, delving into the nuances of single-model systems, comparing the efficiency of ensembling and ranking methods, and exploring the applicati…

Grammatical Error Correction

Multi-objective Learning to Rank by Model Distillation

2024-07-09 · Jie Tang, Huiji Gao, Liwei He, Sanjeev Katariya

In online marketplaces, search ranking's objective is not only to purchase or conversion (primary objective), but to also the purchase outcomes(secondary objectives), e.g. order cancellation(or return), review rating, cu…

Learning-To-Rankmodel

Learning with Privileged Information for Multi-Label Classification

2017-03-29 · Shiyu Chen, Shangfei Wang, Tanfang Chen, Xiaoxiao Shi

In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available informati…

Action Unit DetectionClassificationFacial Action Unit DetectionGeneral Classification+4

Elo Uncovered: Robustness and Best Practices in Language Model Evaluation

2023-11-29 · Meriem Boubdir, Edward Kim, Beyza Ermis, Sara Hooker 외

In Natural Language Processing (NLP), the Elo rating system, originally designed for ranking players in dynamic games such as chess, is increasingly being used to evaluate Large Language Models (LLMs) through "A vs B" pa…

Language Model EvaluationLanguage ModelingLanguage Modelling