Soft-NMS — Improving Object Detection with One Line of Code
Navaneeth Bodla,Bharat Singh,Rama Chellappa,Larry S. Davis +3 more
- pp 5562-5570
TLDR
Soft-NMS as mentioned in this paper decays the detection scores of all other objects as a continuous function of their overlap with M. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss.Abstract:
Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant overlap (using a pre-defined threshold) with M are suppressed. This process is recursively applied on the remaining boxes. As per the design of the algorithm, if an object lies within the predefined overlap threshold, it leads to a miss. To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process. Soft-NMS obtains consistent improvements for the coco-style mAP metric on standard datasets like PASCAL VOC2007 (1.7% for both R-FCN and Faster-RCNN) and MS-COCO (1.3% for R-FCN and 1.1% for Faster-RCNN) by just changing the NMS algorithm without any additional hyper-parameters. Using Deformable-RFCN, Soft-NMS improves state-of-the-art in object detection from 39.8% to 40.9% with a single model. Further, the computational complexity of Soft-NMS is the same as traditional NMS and hence it can be efficiently implemented. Since Soft-NMS does not require any extra training and is simple to implement, it can be easily integrated into any object detection pipeline. Code for Soft-NMS is publicly available on GitHub http://bit.ly/2nJLNMu.read more
Citations
More filters
Posted Content
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
TL;DR: Li et al. as mentioned in this paper designed an effective self-supervised semi supervised temporal action proposal (SSTAP) framework, which consists of two crucial branches, i.e., temporal-aware semi supervised branch and relation-aware self supervised branch, to learn the relation of temporal clues.
Journal ArticleDOI
ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities
TL;DR: One-PEACE as mentioned in this paper is a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities, which can capture fine-grained details within modalities concurrently.
Proceedings ArticleDOI
Multi-face detection algorithm suitable for video surveillance
TL;DR: By using data augmentation method, redesigning the detection network structure with deep separable convolution, and optimizing the NMS algorithm, the improved MTCNN algorithm is faster than M TCNN algorithm in the application environment of processing multi-face detection.
Proceedings ArticleDOI
Semi-Supervised Temporal Action Detection with Proposal-Free Masking
TL;DR: A novel Semi-supervised Temporal action detection model based on PropOsal-free Temporal mask (SPOT) with a parallel localization (mask generation) and classification architecture is proposed, which effectively eliminates the dependence between localization and classification by cutting off the route for error propagation in-between.
Journal ArticleDOI
Scene Text Detection Using Attention with Depthwise Separable Convolutions
Ehtesham Hassan,L. L. +1 more
TL;DR: A novel scene text detector using a deep convolutional network which efficiently detects arbitrary oriented and complex-shaped text segments from natural scenes and predicts quadrilateral bounding boxes around text segments.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
A Computational Approach to Edge Detection
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Proceedings ArticleDOI
You Only Look Once: Unified, Real-Time Object Detection
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.