Rethinking The Optimization Of Average Precision: Only Penalizing Negative Instances Before Positive Ones Is Enough

Abstract

Optimizing the approximation of Average Precision (AP) has been widely studied for image retrieval. Limited by the definition of AP, such methods consider both negative and positive instances ranking before each positive instance. However, we claim that only penalizing negative instances before positive ones is enough, because the loss only comes from these negative instances. To this end, we propose a novel loss, namely Penalizing Negative instances before Positive ones (PNP), which can directly minimize the number of negative instances before each positive one. In addition, AP-based methods adopt a fixed and sub-optimal gradient assignment strategy. Therefore, we systematically investigate different gradient assignment solutions via constructing derivative functions of the loss, resulting in PNP-I with increasing derivative functions and PNP-D with decreasing ones. PNP-I focuses more on the hard positive instances by assigning larger gradients to them and tries to make all relevant i

Stats

• citations13
• S2 citations—
• github stars15
• HF likes0
• heat score11.00
• arxiv keyli2021rethinking

Related papers

• Learning With Average Precision: Training Image Retrieval With A Listwise Loss (2019)18.86
• Smooth-ap: Smoothing The Path Towards Large-scale Image Retrieval (2020)15.06
• Hierarchical Average Precision Training For Pertinent Image Retrieval (2022)9.10
• Optimization Of Rank Losses For Image Retrieval (2023)9.43
• Robust And Decomposable Average Precision For Image Retrieval (2021)0.00
• Not All Pairs Are Equal: Hierarchical Learning For Average-precision-oriented Video Retrieval (2024)7.50
• Your Negative May Not Be True Negative: Boosting Image-text Matching With False Negative Elimination (2023)14.32
• Mean Local Group Average Precision (mlgap): A New Performance Metric For Hashing-based Retrieval (2018)0.00