Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection

• URL: http://arxiv.org/abs/2207.12042v1
• Date: Mon, 25 Jul 2022 10:33:06 GMT
• Title: Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection
• Authors: Dongli Xu, Jinhong Deng, Wen Li
• Abstract summary: In this work, we revisit the average precision (AP)loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. We propose two strategies to improve the AP loss. The first is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Experiments conducted on the MSCOCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss.
• Score: 19.940491797959407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Average precision (AP) loss has recently shown promising performance on the dense object detection task. However,a deep understanding of how AP loss affects the detector from a pairwise ranking perspective has not yet been developed.In this work, we revisit the average precision (AP)loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples.Based on this observation, we propose two strategies to improve the AP loss. The first of these is a novel Adaptive Pairwise Error (APE) loss that focusing on ranking pairs in both positive and negative samples. Moreover,we select more accurate ranking pairs by exploiting the normalized ranking scores and localization scores with a clustering algorithm. Experiments conducted on the MSCOCO dataset support our analysis and demonstrate the superiority of our proposed method compared with current classification and ranking loss. The code is available at https://github.com/Xudangliatiger/APE-Loss.

Related papers

• Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval [80.09819072780193]
  Average Precision (AP) assesses the overall rankings of relevant videos at the top list. Recent video retrieval methods utilize pair-wise losses that treat all sample pairs equally.
  arXiv  Detail & Related papers  (2024-07-22T11:52:04Z)
• Rank-DETR for High Quality Object Detection [52.82810762221516]
  A highly performant object detector requires accurate ranking for the bounding box predictions. In this work, we introduce a simple and highly performant DETR-based object detector by proposing a series of rank-oriented designs.
  arXiv  Detail & Related papers  (2023-10-13T04:48:32Z)
• Ranking-Based Siamese Visual Tracking [31.2428211299895]
  Siamese-based trackers mainly formulate the visual tracking into two independent subtasks, including classification and localization. This paper proposes a ranking-based optimization algorithm to explore the relationship among different proposals. The proposed two ranking losses are compatible with most Siamese trackers and incur no additional computation for inference.
  arXiv  Detail & Related papers  (2022-05-24T03:46:40Z)
• Disentangle Your Dense Object Detector [82.22771433419727]
  Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. We propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art detectors.
  arXiv  Detail & Related papers  (2021-07-07T00:52:16Z)
• Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details [107.2722027807328]
  We find that the default implementation of AP is neither category independent, nor does it directly reward properly calibrated detectors. We show that the default implementation produces a gameable metric, where a simple, nonsensical re-ranking policy can improve AP by a large margin. We benchmark recent advances in large-vocabulary detection and find that many reported gains do not translate to improvements under our new per-class independent evaluation.
  arXiv  Detail & Related papers  (2021-02-01T18:56:02Z)
• Optimized Loss Functions for Object detection: A Case Study on Nighttime Vehicle Detection [0.0]
  In this paper, we optimize both two loss functions for classification and localization simultaneously. Compared to the existing studies, in which the correlation is only applied to improve the localization accuracy for positive samples, this paper utilizes the correlation to obtain the really hard negative samples. A novel localization loss named MIoU is proposed by incorporating a Mahalanobis distance between predicted box and target box, which eliminate the gradients inconsistency problem in the DIoU loss.
  arXiv  Detail & Related papers  (2020-11-11T03:00:49Z)
• AP-Loss for Accurate One-Stage Object Detection [49.13608882885456]
  One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously. The former suffers much from extreme foreground-background imbalance due to the large number of anchors. This paper proposes a novel framework to replace the classification task in one-stage detectors with a ranking task.
  arXiv  Detail & Related papers  (2020-08-17T13:22:01Z)
• Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval [94.73459295405507]
  Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks. We apply Smooth-AP to standard retrieval benchmarks: Stanford Online products and VehicleID. We also evaluate on larger-scale datasets: INaturalist for fine-grained category retrieval, VGGFace2 and IJB-C for face retrieval.
  arXiv  Detail & Related papers  (2020-07-23T17:52:03Z)

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.