Search Results for author:
Found 4 papers, 1 papers with code
Anything in Any Scene: Photorealistic Video Object Insertion
Our proposed general framework encompasses three key processes: 1) integrating a realistic object into a given scene video with proper placement to ensure geometric realism; 2) estimating the sky and environmental lighting distribution and simulating realistic shadows to enhance the light realism; 3) employing a style transfer network that refines the final video output to maximize photorealism.
Classifier-head Informed Feature Masking and Prototype-based Logit Smoothing for Out-of-Distribution Detection
Logit smoothing computes the cosine similarity between the feature vector of the test sample and the prototype of the predicted ID class at the penultimate layer and uses the similarity as an adaptive temperature factor on the logit to alleviate the network's overconfidence prediction for OOD data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
SATS: Self-Attention Transfer for Continual Semantic Segmentation
Considering that pixels belonging to the same class in each image often share similar visual properties, a class-specific region pooling is applied to provide more efficient relationship information for knowledge transfer.
Ranked #1 on
Overlapped 25-25
on ADE20K
Topic Driven Adaptive Network for Cross-Domain Sentiment Classification
In this vein, most approaches utilized domain adaptation that maps data from different domains into a common feature space.
