paper-with-me

홈 › Papers

DSLA: Dynamic smooth label assignment for efficient anchor-free object detection

2022-08-01 · Hu Su, Yonghao He, Rui Jiang, Jiabin Zhang, Wei Zou, Bin Fan

Anchor-free detectors basically formulate object detection as dense classification and regression. For popular anchor-free detectors, it is common to introduce an individual prediction branch to estimate the quality of localization. The following inconsistencies are observed when we delve into the practices of classification and quality estimation. Firstly, for some adjacent samples which are assigned completely different labels, the trained model would produce similar classification scores. This violates the training objective and leads to performance degradation. Secondly, it is found that detected bounding boxes with higher confidences contrarily have smaller overlaps with the corresponding ground-truth. Accurately localized bounding boxes would be suppressed by less accurate ones in the Non-Maximum Suppression (NMS) procedure. To address the inconsistency problems, the Dynamic Smooth Label Assignment (DSLA) method is proposed. Based on the concept of centerness originally developed in FCOS, a smooth assignment strategy is proposed. The label is smoothed to a continuous value in [0, 1] to make a steady transition between positive and negative samples. Intersection-of-Union (IoU) is predicted dynamically during training and is coupled with the smoothed label. The dynamic smooth label is assigned to supervise the classification branch. Under such supervision, quality estimation branch is naturally merged into the classification branch, which simplifies the architecture of anchor-free detector. Comprehensive experiments are conducted on the MS COCO benchmark. It is demonstrated that, DSLA can significantly boost the detection accuracy by alleviating the above inconsistencies for anchor-free detectors. Our codes are released at https://github.com/YonghaoHe/DSLA.

📄 PDF Abstract BibTeX arXiv:2208.00817

Code (1)

yonghaohe/dsla 공식 구현 pytorch

Tasks

Classificationobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

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…
Non Maximum Suppression Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
FPN 설명 없음
FCOS FCOS is an anchor-box free, proposal free, single-stage object detection model. By eliminating the predefined set of anchor boxes, FCOS avoids computation related to anchor…

Similar Papers 제목 키워드 기반

Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs

2022-01-23 · Tianxiao Zhang, Bo Luo, Ajay Sharda, Guanghui Wang

Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. For anchor-based detection models, the Io…

object-detectionObject Detection

DCDet: Dynamic Cross-based 3D Object Detector

2024-01-14 · Shuai Liu, Boyang Li, Zhiyu Fang, Kai Huang

Recently, significant progress has been made in the research of 3D object detection. However, most prior studies have focused on the utilization of center-based or anchor-based label assignment schemes. Alternative label…

3D Object DetectionObjectobject-detectionObject Detection+1

End-to-End Lane detection with One-to-Several Transformer

2023-05-01 · Kunyang Zhou, Rui Zhou

Although lane detection methods have shown impressive performance in real-world scenarios, most of methods require post-processing which is not robust enough. Therefore, end-to-end detectors like DEtection TRansformer(DE…

DecoderLane Detection

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection

2021-01-12 · Zheng Ge, JianFeng Wang, Xin Huang, Songtao Liu 외

Label assignment has been widely studied in general object detection because of its great impact on detectors' performance. However, none of these works focus on label assignment in dense pedestrian detection. In this pa…

object-detectionObject DetectionPedestrian Detection

On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention

2025-06-11 · Yeonju Ro, Zhenyu Zhang, Souvik Kundu, Zhangyang Wang 외

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduc…

Text Summarization