Unified Generator-Classifier for Efficient Zero-Shot Learning
This work addresses the efficiency and performance issues in zero-shot learning for computer vision, offering a practical solution for handling new object categories without incremental retraining.
The authors tackled the problem of zero-shot learning by proposing GenClass, a unified generator-classifier framework that eliminates the need for retraining classifiers for new categories, achieving state-of-the-art performance on standard object classification datasets like AWA, CUB, and SUN, and demonstrating generalizability to zero-shot action classification.
Generative models have achieved state-of-the-art performance for the zero-shot learning problem, but they require re-training the classifier every time a new object category is encountered. The traditional semantic embedding approaches, though very elegant, usually do not perform at par with their generative counterparts. In this work, we propose an unified framework termed GenClass, which integrates the generator with the classifier for efficient zero-shot learning, thus combining the representative power of the generative approaches and the elegance of the embedding approaches. End-to-end training of the unified framework not only eliminates the requirement of additional classifier for new object categories as in the generative approaches, but also facilitates the generation of more discriminative and useful features. Extensive evaluation on three standard zero-shot object classification datasets, namely AWA, CUB and SUN shows the effectiveness of the proposed approach. The approach without any modification, also gives state-of-the-art performance for zero-shot action classification, thus showing its generalizability to other domains.