Search Results for author:
Found 7 papers, 4 papers with code
Debiasing Text-to-Image Diffusion Models
Despite its simplicity, we show that IDA shows efficiency and fast convergence in resolving the social bias in TTI diffusion models.
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference
Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width.
LUMix: Improving Mixup by Better Modelling Label Uncertainty
LUMix is simple as it can be implemented in just a few lines of code and can be universally applied to any deep networks \eg CNNs and Vision Transformers, with minimal computational cost.
Is synthetic data from generative models ready for image recognition?
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images.
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability
Large-scale pre-training has been proven to be crucial for various computer vision tasks.
Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data.
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods.
Ranked #2 on
Optical Flow Estimation
on KITTI 2012 unsupervised
