Visually Analyzing and Steering Zero Shot Learning
We propose a visual analytics system to help a user analyze and steer zero-shot learning models. Zero-shot learning has emerged as a viable scenario for categorizing data that consists of no labeled examples, and thus a promising approach to minimize data annotation from humans. However, it is challenging to understand where zero-shot learning fails, the cause of such failures, and how a user can modify the model to prevent such failures. Our visualization system is designed to help users diagnose and understand mispredictions in such models, so that they may gain insight on the behavior of a model when applied to data associated with categories not seen during training. Through usage scenarios, we highlight how our system can help a user improve performance in zero-shot learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Zero-Shot LearningSimilar Papers 제목 키워드 기반
SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors
Speech-aware large language models often generalize poorly to out-of-domain settings. We propose SALSA (Speech-Aware LLM Adaptation via Learned Steering Activations), a lightweight adaptation method that learns layer-wis…
Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation
Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approa…
Synthetic Data GenerationVGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning
Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., w…
Transfer LearningWord EmbeddingsZero-Shot LearningMulti-Modal Decentralized Reinforcement Learning for Modular Reconfigurable Lunar Robots
Modular reconfigurable robots suit task-specific space operations, but the combinatorial growth of morphologies hinders unified control. We propose a decentralized reinforcement learning (Dec-RL) scheme where each module…
Zero-shot GeneralizationReinforcement LearningLearning Visually Consistent Label Embeddings for Zero-Shot Learning
In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The ma…
Transfer LearningZero-Shot Learning