Long-Tailed Partial Label Learning via Dynamic Rebalancing

02/10/2023
by   Feng Hong, et al.
0

Real-world data usually couples the label ambiguity and heavy imbalance, challenging the algorithmic robustness of partial label learning (PLL) and long-tailed learning (LT). The straightforward combination of LT and PLL, i.e., LT-PLL, suffers from a fundamental dilemma: LT methods build upon a given class distribution that is unavailable in PLL, and the performance of PLL is severely influenced in long-tailed context. We show that even with the auxiliary of an oracle class prior, the state-of-the-art methods underperform due to an adverse fact that the constant rebalancing in LT is harsh to the label disambiguation in PLL. To overcome this challenge, we thus propose a dynamic rebalancing method, termed as RECORDS, without assuming any prior knowledge about the class distribution. Based on a parametric decomposition of the biased output, our method constructs a dynamic adjustment that is benign to the label disambiguation process and theoretically converges to the oracle class prior. Extensive experiments on three benchmark datasets demonstrate the significant gain of RECORDS compared with a range of baselines. The code is publicly available.

READ FULL TEXT
research
12/01/2020

Disentangling Label Distribution for Long-tailed Visual Recognition

The current evaluation protocol of long-tailed visual recognition trains...
research
08/26/2021

Robust Long-Tailed Learning under Label Noise

Long-tailed learning has attracted much attention recently, with the goa...
research
08/29/2023

Robust Long-Tailed Learning via Label-Aware Bounded CVaR

Data in the real-world classification problems are always imbalanced or ...
research
11/22/2022

Dynamic Loss For Robust Learning

Label noise and class imbalance commonly coexist in real-world data. Pre...
research
11/06/2021

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

Real-world data universally confronts a severe class-imbalance problem a...
research
05/05/2023

Towards Effective Collaborative Learning in Long-Tailed Recognition

Real-world data usually suffers from severe class imbalance and long-tai...
research
06/02/2020

Improved scalability under heavy tails, without strong convexity

Real-world data is laden with outlying values. The challenge for machine...

Please sign up or login with your details

Forgot password? Click here to reset