DSLA: Dynamic smooth label assignment for efficient anchor-free object detection
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.
Code (1)
Tasks
Classificationobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs
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 DetectionDCDet: Dynamic Cross-based 3D Object Detector
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+1End-to-End Lane detection with One-to-Several Transformer
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 DetectionLLA: Loss-aware Label Assignment for Dense Pedestrian Detection
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 DetectionOn-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention
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