HAMBox: Delving Into Mining High-Quality Anchors on Face Detection
Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under large pose and scale variations. However, we observe that, more than 80% correctly predicted bounding boxes are regressed from the unmatched anchors (the IoUs between anchors and target faces are lower than a threshold) in the inference phase. It indicates that these unmatched anchors perform excellent regression ability, but the existing methods neglect to learn from them. In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors. Our proposed HAMBox method could be a general strategy for anchor-based single-stage face detection. Experiments on various datasets, including WIDER FACE, FDDB, AFW and PASCAL Face, demonstrate the superiority of the proposed method.
Code (0)
등록된 구현이 없습니다.
Tasks
Face DetectionMulti-Task LearningregressionVocal Bursts Intensity PredictionSimilar Papers 제목 키워드 기반
HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to local…
Face DetectionMulti-Task LearningregressionVocal Bursts Intensity PredictionGMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection
Depth perception is a crucial component of monoc-ular 3D detection tasks that typically involve ill-posed problems. In light of the success of sample mining techniques in 2D object detection, we propose a simple yet effe…
2D Object Detection3D Object DetectionDepth EstimationDepth Prediction+3Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge
Recent research has explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks. This study expands on this work by examining the effec…
knowledge editingNovel Deep Neural Network Classifier Characterization Metrics with Applications to Dataless Evaluation
The mainstream AI community has seen a rise in large-scale open-source classifiers, often pre-trained on vast datasets and tested on standard benchmarks; however, users facing diverse needs and limited, expensive test da…
The Acquisition of Semantic Relationships between words
The study of semantic relationships has revealed a close connection between these relationships and the morphological characteristics of a language. Morphology, as a subfield of linguistics, investigates the internal str…