Representation Learning with Adaptive Superpixel Coding
Deep learning vision models are typically tailored for specific modalities and often rely on domain-specific assumptions, such as the grid structures used by nearly all existing vision models. In this work, we propose a self-supervised model based on Transformers, which we call Adaptive Superpixel Coding (ASC). The key insight of our model is to overcome the limitations of traditional Vision Transformers, which depend on fixed-size and non-adaptive patch partitioning. Instead, ASC employs adaptive superpixel layers that dynamically adjust to the underlying image content. We analyze key properties of the approach that make it effective, and find that our method outperforms widely-used alternatives on standard image downstream task benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Is an Image Also Worth 16x16=256 Superpixels? A Framework for Attentional Image Classification
Superpixel-based image classification has traditionally leveraged graph neural networks (GNNs) for processing irregular image representations. Recent advances in computer vision, driven by Vision Transformers (ViTs), hav…
Superpixel Image ClassificationDomain GeneralizationBayesian Adaptive Superpixel Segmentation
Superpixels provide a useful intermediate image representation. Existing superpixel methods, however, suffer from at least some of the following drawbacks: 1) topology is handled heuristically; 2) the number of superpixe…
Face DetectionGPUSegmentationSuperpixelsAdaptive Superpixel for Active Learning in Semantic Segmentation
Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dom…
Active LearningSegmentationSemantic SegmentationSuperpixelsSquare Superpixel Generation and Representation Learning via Granular Ball Computing
Superpixels provide a compact region-based representation that preserves object boundaries and local structures, and have therefore been widely used in a variety of vision tasks to reduce computational cost. However, mos…
Representation LearningHERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation
Superpixels serve as a powerful preprocessing tool in numerous computer vision tasks. By using superpixel representation, the number of image primitives can be largely reduced by orders of magnitudes. With the rise of de…
Superpixels