OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
cs.CV
Submitted: 2026-09-29
Updated: 2026-09-29
Project page: https://ofbd-neurips2026-longtail-learning.github.io
Terminology
Sources
- Layer Normalization
- Reframing Long-Tailed Learning via Loss Landscape Geometry
- BAM: Bottleneck Attention Module
- ResizeMix: Mixing Data with Preserved Object Information and True Labels
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Vision Transformers Need More Than Registers
- SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
- Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models