Learning from Reduced Labels for Long-Tailed Data
This work addresses the labor-intensive annotation process for long-tailed data in classification tasks, offering a practical solution to reduce costs while maintaining accuracy for tail classes, though it is incremental in improving weakly supervised learning methods.
The paper tackles the problem of high labeling costs for long-tailed classification data by introducing a novel weakly supervised labeling setting called Reduced Label, which preserves supervised information for tail samples and reduces labeling costs, achieving superior performance over state-of-the-art weakly supervised methods on benchmark datasets like ImageNet.
Long-tailed data is prevalent in real-world classification tasks and heavily relies on supervised information, which makes the annotation process exceptionally labor-intensive and time-consuming. Unfortunately, despite being a common approach to mitigate labeling costs, existing weakly supervised learning methods struggle to adequately preserve supervised information for tail samples, resulting in a decline in accuracy for the tail classes. To alleviate this problem, we introduce a novel weakly supervised labeling setting called Reduced Label. The proposed labeling setting not only avoids the decline of supervised information for the tail samples, but also decreases the labeling costs associated with long-tailed data. Additionally, we propose an straightforward and highly efficient unbiased framework with strong theoretical guarantees to learn from these Reduced Labels. Extensive experiments conducted on benchmark datasets including ImageNet validate the effectiveness of our approach, surpassing the performance of state-of-the-art weakly supervised methods.