Self-Supervised Learning from Semantically Imprecise Data
Learning from imprecise labels such as "animal" or "bird", but making precise predictions like "snow bunting" at inference time is an important capability for any classifier when expertly labeled training data is scarce. Contributions by volunteers or results of web crawling lack precision in this manner, but are still valuable. And crucially, these weakly labeled examples are available in larger quantities for lower cost than high-quality bespoke training data. CHILLAX, a recently proposed method to tackle this task, leverages a hierarchical classifier to learn from imprecise labels. However, it has two major limitations. First, it does not learn from examples labeled as the root of the hierarchy, e.g., "object". Second, an extrapolation of annotations to precise labels is only performed at test time, where confident extrapolations could be already used as training data. In this work, we extend CHILLAX with a self-supervised scheme using constrained semantic extrapolation to generate pseudo-labels. This addresses the second concern, which in turn solves the first problem, enabling an even weaker supervision requirement than CHILLAX. We evaluate our approach empirically, showing that our method allows for a consistent accuracy improvement of 0.84 to 1.19 percent points over CHILLAX and is suitable as a drop-in replacement without any negative consequences such as longer training times.
Code (0)
등록된 구현이 없습니다.
Tasks
Self-Supervised LearningSimilar Papers 제목 키워드 기반
Instance-Aware Pseudo-Labeling and Class-Focused Contrastive Learning for Weakly Supervised Domain Adaptive Segmentation of Electron Microscopy
Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (…
Unsupervised Domain AdaptationContrastive LearningSelf-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point representation learning for autonomous drivi…
3D Semantic SegmentationAutonomous DrivingContrastive LearningRepresentation Learning+3Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
Learning with reduced labeling standards, such as noisy label, partial label, and multiple label candidates, which we generically refer to as \textit{imprecise} labels, is a commonplace challenge in machine learning task…
Learning with noisy labelsPartial Label LearningSCOPS: Self-Supervised Co-Part Segmentation
Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely o…
ObjectSegmentationUnsupervised Facial Landmark DetectionUnsupervised Human Pose Estimation+2Self-supervised Visualisation of Medical Image Datasets
Self-supervised learning methods based on data augmentations, such as SimCLR, BYOL, or DINO, allow obtaining semantically meaningful representations of image datasets and are widely used prior to supervised fine-tuning. …
Contrastive LearningSelf-Supervised Learning