Saliency Regularization for Self-Training with Partial Annotations
Partially annotated images are easy to obtain in multi-label classification. However, unknown labels in partially annotated images exacerbate the positive-negative imbalance inherent in multi-label classification, which affects supervised learning of known labels. Most current methods require sufficient image annotations, and do not focus on the imbalance of the labels in the supervised training phase. In this paper, we propose saliency regularization (SR) for a novel self-training framework. In particular, we model saliency on the class-specific maps, and strengthen the saliency of object regions corresponding to the present labels. Besides, we introduce consistency regularization to mine unlabeled information to complement unknown labels with the help of SR. It is verified to alleviate the negative dominance caused by the imbalance, and achieve state-of-the-art performance on Pascal VOC 2007, MS-COCO, VG-200, and OpenImages V3.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-label Image Recognition with Partial LabelsSimilar Papers 제목 키워드 기반
To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection
Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency n…
object-detectionObject DetectionSalient Object DetectionWeakly-supervised LearningNew Definitions and Evaluations for Saliency Methods: Staying Intrinsic and Sound
Saliency methods seek to provide human-interpretable explanations for the output of machine learning model on a given input. A plethora of saliency methods exist, as well as an extensive literature on their justificati…
Salient Objects in Clutter
This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets, which unrealistically assume that each image should contain at least one clear and uncluttered salient object…
Image AugmentationObjectobject-detectionObject Detection+2Energy-Based Generative Cooperative Saliency Prediction
Conventional saliency prediction models typically learn a deterministic mapping from an image to its saliency map, and thus fail to explain the subjective nature of human attention. In this paper, to model the uncertaint…
PredictionSaliency PredictionAutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
AutoFocus-IL is a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rather than distractors and spurious correl…
Robot Manipulation