Osamu Yoshie

Label assignment has been widely studied in general object detection because of its great impact on detectors’ performance. In the field of dense pedestrian detection, human bodies are often heavily entangled, making label assignment more important. However, none of the existing label assignment method focuses on crowd scenarios. Motivated by this, we propose Loss-aware Label Assignment (LLA) to boost the performance of pedestrian detectors in crowd scenarios. Concretely, LLA first calculates cl

Imbalance issue is a major yet unsolved bottleneck for the current object detection models. In this work, we observe two crucial yet never discussed imbalance issues. The first imbalance lies in the large number of low-quality RPN proposals, which makes the R-CNN module (i.e., post-classification layers) become highly biased towards the negative proposals in the early training stage. The second imbalance stems from the unbalanced ground-truth numbers across different testing images, resulting in

The inefficiency of manual inspections in substations struggles to meet increasing workloads amid power grid expansion, necessitating intelligent solutions for equipment monitoring. This study addresses two key challenges: detecting diverse equipment under scale variations, occlusions, and real-time constraints, and ensuring data privacy given geographically dispersed, sensitive substation data. We propose CWA-YOLO, a detection framework integrating multi-scale feature fusion and an enhanced sma

Searching for the nearest neighbor is a fundamental problem in the computer vision field, and deep hashing has become one of the most representative and widely used methods, which learns to generate compact binary codes for visual data. In this paper, we first delve into the representation learning of deep hashing and surprisingly find that deep hashing could be a double-edged sword, i.e., deep hashing can accelerate the query speed and decrease the storage cost in the nearest neighbor search pr