Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
cs.CV, cs.LG
Submitted: 2026-03-05
Updated: 2026-03-05
Comments: Accepted to CVPR2026
Journal ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, pp. 39659-39668
Code: https://github.com/RyanZhaoIc/CAD
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Improved Baselines with Momentum Contrastive Learning
- AutoAugment: Learning Augmentation Policies from Data
- Improved Regularization of Convolutional Neural Networks with Cutout
- Prompt-to-Prompt Image Editing with Cross Attention Control
- Diffusion Model-Based Image Editing: A Survey
- Diffusion Models already have a Semantic Latent Space
- Learning Causal Transition Matrix for Instance-dependent Label Noise
- MoEController: Instruction-based Arbitrary Image Manipulation with Mixture-of-Expert Controllers
- Representation Learning with Contrastive Predictive Coding
- Decompositional Generation Process for Instance-Dependent Partial Label Learning
- Realistic Evaluation of Deep Partial-Label Learning Algorithms
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
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