Learning to Rank Proposals for Object Detection

By Zhiyu Tan, Xuecheng Nie, Qi Qian, Nan Li, Hao Li. 2019

53 citations recorded by the source corpus.

Non-Maximum Suppression (NMS) is an essential step of modern object detection models for removing duplicated candidates. The efficacy of NMS heavily affects the final detection results. Prior works exploit suppression criterions relying on either the objectiveness derived from classification or the overlapness produced by regression, both of which are heuristically designed and fail to explicitly link with the suppression rank. To address this issue, in this paper, we propose a novel Learning-to-Rank (LTR) model to produce the suppression rank via a learning procedure, thus facilitating the candidate generation and lifting the detection performance. In particular, we define a ranking score based on IoU to indicate the ranks of candidates during the NMS step, where candidates with high ranking score will be reserved and the ones with low ranking score will be eliminated. We design a lightweight network to predict the ranking score. We introduce a ranking loss to supervise the generation of these ranking scores, which encourages candidates with IoU to the ground-truth to rank higher. To facilitate the training procedure, we design a novel sampling strategy via dividing candidates into different levels and select hard pairs to adopt in the training. During the inference phase, this module can be exploited as a plugin to the current object detector. The training and inference of the overall framework is end-to-end. Comprehensive experiments on benchmarks PASCAL VOC and MS COCO demonstrate the generality and effectiveness of our model for facilitating existing object detectors to state-of-the-art accuracy.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, methodology): “After that, lots of algorithms are proposed to improve its performance, including architecture redesign and reform [4, 9, 5, 28, 30], context and attention mechanism [2, 51, 38, 7, 44], multiscale training and testing [54, 41], training strategy and loss function [40, 52, 61, 17], feature fusion and”
VarifocalNet: An IoU-aware Dense Object Detector (2020, background): “Fitness NMS [29], IoU-aware RetinaNet [11] and [30] are similar to IoU-Net in essence, except that they multiply the predicted IoU or IoU-based ranking scores and the classification score as the ranking basis.”
Object Detection in 20 Years: A Survey (2019, unknown): “Learning-Based NMS: A recent group of NMS improvements that have recently received much attention is learning-based NMS [85], [93], [109], [110], [111], [122].”
Rethinking Classification and Localization for Object Detection (2019, background): “Learning-to-Rank [39] utilizes an extra head to produce a rank value of a proposal for Non-Maximum Suppression (NMS).”
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training (2020, background): “esides, various improvements have been witnessed in recent studies [18,44,26,27,52]. Classication in object detection. Recent researches focus on improving object classier from various perspectives [29,19,34,42,25,49,6,17]. The classication scores in detection not only determine the semantic categor”
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation (2021, background): “…neural network have achieved remarkable success in a wide range of application scenarios (Wang et al., 2022; Qian et al., 2021; Yiqi Jiang, 2022; Tan et al., 2019; Chen et al., 2021b; Jiang et al., 2021; Chen et al., 2017) but it still suffers poor generalization performance to other new domain…”
Imbalance Problems in Object Detection: A Review (2019, methodology): “The idea is similar to the networks with an additional localization confidence associated prediction branch [89], [125], [126], [127], [128], besides classification and regression, in order to use the predicted confidence during inference.”