Aug 23, 2020 · We propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors.

Seesaw Loss can easily cooperates with object detection and instance segmentation frameworks for the long-tailed datasets. Long-Tailed Recognition. Long-tailed ...

Seesaw Loss is a loss function for long-tailed instance segmentation. It dynamically re-balances the gradients of positive and negative samples on a tail class.

Seesaw Loss can easily cooperates with object detection and instance segmentation frameworks for the long-tailed datasets. Long-Tailed Recognition. Long-tailed ...

This work proposes Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors, i.e., ...

We propose Seesaw Loss that dynamically rebalances the penalty between different categories for long-tailed instance segmentation. 2. We propose HTC-Lite, a ...

We propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category, with two complementary factors.

In this work, we propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category. Specifically, Seesaw Loss ...

Seesaw Loss improves the strong baseline by 6.9% AP on LVIS v1 val split. With a single model, and without using external data and annotations except for ...

In this paper, we propose Seesaw Loss for long-tailed instance segmentation. Seesaw Loss dynamically re-balances gradients of positive and negative samples ...