Search Results for author:
Found 11 papers, 5 papers with code
Diffusion Prior Interpolation for Flexibility Real-World Face Super-Resolution
In this paper, we propose a masking strategy with strong and weak constraints and iterative refinement for real-world FSR, termed Diffusion Prior Interpolation (DPI).
EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance
However, these approaches often produce biased distributions of important tokens due to the influence of accumulated attention scores or positional encoding.
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP).
MambaVC: Learned Visual Compression with Selective State Spaces
Learned visual compression is an important and active task in multimedia.
Theoretically Principled Federated Learning for Balancing Privacy and Utility
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility.
PILC: Practical Image Lossless Compression with an End-to-end GPU Oriented Neural Framework
Generative model based image lossless compression algorithms have seen a great success in improving compression ratio.
WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
In this work, we propose an effective weakly-supervised video semantic segmentation pipeline with click annotations, called WeClick, for saving laborious annotating effort by segmenting an instance of the semantic class with only a single click.
Energy Aligning for Biased Models
Training on class-imbalanced data usually results in biased models that tend to predict samples into the majority classes, which is a common and notorious problem.
Towards a category-extended object detector with limited data
Object detectors are typically learned on fully-annotated training data with fixed predefined categories.
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown.
