Large-Scale Category Structure Aware Image Categorization
Most previous research on image categorization has focused on medium-scale data sets, while large-scale image categorization with millions of images from thousands of categories remains a challenge. With the emergence of structured large-scale dataset such as the ImageNet, rich information about the conceptual relationships between images, such as a tree hierarchy among various image categories, become available. As human cognition of complex visual world benefits from underlying semantic relationships between object classes, we believe a machine learning system can and should leverage such information as well for better performance. In this paper, we employ such semantic relatedness among image categories for large-scale image categorization. Specifically, a category hierarchy is utilized to properly define loss function and select common set of features for related categories. An efficient optimization method based on proximal approximation and accelerated parallel gradient method is introduced. Experimental results on a subset of ImageNet containing 1.2 million images from 1000 categories demonstrate the effectiveness and promise of our proposed approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CategorizationSimilar Papers 제목 키워드 기반
Instance-Aware Hashing for Multi-Label Image Retrieval
Similarity-preserving hashing is a commonly used method for nearest neighbour search in large-scale image retrieval. For image retrieval, deep-networks-based hashing methods are appealing since they can simultaneously le…
Image RetrievalMulti-Label Image RetrievalRetrievalZero-Shot Sketch-Based Image Retrieval with Structure-aware Asymmetric Disentanglement
The goal of Sketch-Based Image Retrieval (SBIR) is using free-hand sketches to retrieve images of the same category from a natural image gallery. However, SBIR requires all test categories to be seen during training, whi…
DisentanglementImage RetrievalRetrievalSketch-Based Image Retrieval+1Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces
Multi-class anomaly detection aims to build unified models across diverse product categories. However, as the number of categories grows, its performance often degrades due to increasingly complex and heterogeneous norma…
Unsupervised Anomaly DetectionMulti-class Anomaly DetectionMultiview Compressive Coding for 3D Reconstruction
A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparati…
3D ReconstructionDecoderSelf-Supervised LearningSingle-View 3D ReconstructionRecurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling,…
Category-Agnostic Pose EstimationPose Estimation