IQDet: Instance-wise Quality Distribution Sampling for Object Detection
We propose a dense object detector with an instance-wise sampling strategy, named IQDet. Instead of using human prior sampling strategies, we first extract the regional feature of each ground-truth to estimate the instance-wise quality distribution. According to a mixture model in spatial dimensions, the distribution is more noise-robust and adapted to the semantic pattern of each instance. Based on the distribution, we propose a quality sampling strategy, which automatically selects training samples in a probabilistic manner and trains with more high-quality samples. Extensive experiments on MS COCO show that our method steadily improves baseline by nearly 2.4 AP without bells and whistles. Moreover, our best model achieves 51.6 AP, outperforming all existing state-of-the-art one-stage detectors and it is completely cost-free in inference time.
Code (0)
등록된 구현이 없습니다.
Tasks
object-detectionObject DetectionSimilar Papers 제목 키워드 기반
DiverseAR: Boosting Diversity in Bitwise Autoregressive Image Generation
In this paper, we investigate the underexplored challenge of sample diversity in autoregressive (AR) generative models with bitwise visual tokenizers. We first analyze the factors that limit diversity in bitwise AR model…
Binary ClassificationImage GenerationFairly Adaptive Negative Sampling for Recommendations
Pairwise learning strategies are prevalent for optimizing recommendation models on implicit feedback data, which usually learns user preference by discriminating between positive (i.e., clicked by a user) and negative it…
AttributeFairnessInstance-Wise Adaptive Sampling for Dataset Construction in Approximating Inverse Problem Solutions
We propose an instance-wise adaptive sampling framework for constructing compact and informative training datasets for supervised learning of inverse problem solutions. Typical learning-based approaches aim to learn a ge…
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature py…
Instance SegmentationSemantic SegmentationVocal Bursts Intensity PredictionSampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Energy-Based Models (EBMs) allow for extremely flexible specifications of probability distributions. However, they do not provide a mechanism for obtaining exact samples from these distributions. Monte Carlo techniques c…
Paraphrase GenerationText Generation