Search Results for author:
Found 10 papers, 3 papers with code
Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency
In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps.
Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep
We propose a novel stereo-confidence that can be measured externally to various stereo-matching networks, offering an alternative input modality choice of the cost volume for learning-based approaches, especially in safety-critical systems.
Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representations
Anomaly detection is a critical and challenging task that aims to identify data points deviating from normal patterns and distributions within a dataset.
Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning
Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain translation and text-guided image manipulation.
Deep Cross-Modal Steganography Using Neural Representations
The proposed framework employs INRs to represent the secret data, which can handle data of various modalities and resolutions.
Reinforcement Learning-Based Black-Box Model Inversion Attacks
Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model.
Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
This allows our method to smoothly control the degree to which it preserves source features while generating images from an entirely new domain using only a single model.
I See-Through You: A Framework for Removing Foreground Occlusion in Both Sparse and Dense Light Field Images
To apply LF-DeOcc in both LF datasets, we propose a framework, ISTY, which is defined and divided into three roles: (1) extract LF features, (2) define the occlusion, and (3) inpaint occluded regions.
Data Poisoning Attack Aiming the Vulnerability of Continual Learning
Training data generated by the proposed attack causes performance degradation on a specific task targeted by the attacker.
Fix the Noise: Disentangling Source Feature for Transfer Learning of StyleGAN
Owing to the disentangled feature space, our method can smoothly control the degree of the source features in a single model.
