Parity Partition Coding for Sharp Multi-Label Classification
The problem of efficiently training and evaluating image classifiers that can distinguish between a large number of object categories is considered. A novel metric, sharpness, is proposed which is defined as the fraction of object categories that are above a threshold accuracy. To estimate sharpness (along with a confidence value), a technique called fraction-accurate estimation is introduced which samples categories and samples instances from these categories. In addition, a technique called parity partition coding, a special type of error correcting output code, is introduced, increasing sharpness, while reducing the multi-class problem to a multi-label one with exponentially fewer outputs. We demonstrate that this approach outperforms the baseline model for both MultiMNIST and CelebA, while requiring fewer parameters and exceeding state of the art accuracy on individual labels.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONObjectSimilar Papers 제목 키워드 기반
DeepQTMT: A Deep Learning Approach for Fast QTMT-based CU Partition of Intra-mode VVC
Versatile Video Coding (VVC), as the latest standard, significantly improves the coding efficiency over its ancestor standard High Efficiency Video Coding (HEVC), but at the expense of sharply increased complexity. In VV…
Optimization With Parity Constraints: From Binary Codes to Discrete Integration
Many probabilistic inference tasks involve summations over exponentially large sets. Recently, it has been shown that these problems can be reduced to solving a polynomial number of MAP inference queries for a model augm…
Region-Adaptive Video Sharpening via Rate-Perception Optimization
Sharpening is a widely adopted video enhancement technique. However, uniform sharpening intensity ignores texture variations, degrading video quality. Sharpening also increases bitrate, and there's a lack of techniques t…
Video EnhancementAn Automatic ICD Coding Network Using Partition-Based Label Attention
International Classification of Diseases (ICD) is a global medical classification system which provides unique codes for diagnoses and procedures appropriate to a patient's clinical record. However, manual coding by huma…
Multi-Label ClassificationMUlTI-LABEL-ClASSIFICATIONThe Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
Transformers consist of diverse building blocks, such as embedding layers, normalization layers, self-attention mechanisms, and point-wise feedforward networks. Thus, understanding the differences and interactions among …
Language ModelingLanguage ModellingLarge Language Model