Object-Extent Pooling for Weakly Supervised Single-Shot Localization
In the face of scarcity in detailed training annotations, the ability to perform object localization tasks in real-time with weak-supervision is very valuable. However, the computational cost of generating and evaluating region proposals is heavy. We adapt the concept of Class Activation Maps (CAM) into the very first weakly-supervised 'single-shot' detector that does not require the use of region proposals. To facilitate this, we propose a novel global pooling technique called Spatial Pyramid Averaged Max (SPAM) pooling for training this CAM-based network for object extent localisation with only weak image-level supervision. We show this global pooling layer possesses a near ideal flow of gradients for extent localization, that offers a good trade-off between the extremes of max and average pooling. Our approach only requires a single network pass and uses a fast-backprojection technique, completely omitting any region proposal steps. To the best of our knowledge, this is the first approach to do so. Due to this, we are able to perform inference in real-time at 35fps, which is an order of magnitude faster than all previous weakly supervised object localization frameworks.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectObject LocalizationRegion ProposalWeakly-Supervised Object LocalizationSimilar Papers 제목 키워드 기반
Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling
Weakly-Supervised Semantic Segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, cur…
ClassificationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationImproving weakly supervised sound event detection with self-supervised auxiliary tasks
While multitask and transfer learning has shown to improve the performance of neural networks in limited data settings, they require pretraining of the model on large datasets beforehand. In this paper, we focus on impro…
DecoderEvent DetectionSound Event DetectionTask 2+1Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentation
We address the problem of weakly-supervised semantic segmentation (WSSS) using bounding box annotations. Although object bounding boxes are good indicators to segment corresponding objects, they do not specify object bou…
ObjectSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1DANet: Divergent Activation for Weakly Supervised Object Localization
Weakly supervised object localization remains a challenge when learning object localization models from image category labels. Optimizing image classification tends to activate object parts and ignore the full object ext…
ClassificationGeneral Classificationimage-classificationImage Classification+3C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) is a challenging task when provided with image category supervision but required to simultaneously learn object locations and object detectors. Many WSOD approaches adopt multipl…
Multiple Instance LearningObjectobject-detectionObject Detection+3