Search Results for author:
Found 5 papers, 1 papers with code
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
We identify a critical bias in contemporary CLIP-based models, which we denote as single tag bias.
Ranked #1 on
Open Vocabulary Semantic Segmentation
on COCO-Stuff-171
(mIoU metric)
Multi-Label Text Classification
Open Vocabulary Semantic Segmentation
+3
Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel
Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks.
Bias Decay Matters : Improving Large Batch Optimization with Connectivity Sharpness
To mitigate this issue, we propose simple bias decay methods including a novel adaptive one and found that this simple remedy can fill a large portion of the performance gaps that occur in large batch optimization.
Reliable Estimation of Individual Treatment Effect with Causal Information Bottleneck
We also introduce an additional form of a regularizer from the perspective of understanding ITE in the semi-supervised learning framework to ensure more reliable representations.
Ranked #1 on
Causal Inference
on IDHP
Tsallis Reinforcement Learning: A Unified Framework for Maximum Entropy Reinforcement Learning
By controlling the entropic index, we can generate various types of entropy, including the SG entropy, and a different entropy results in a different class of the optimal policy in Tsallis MDPs.
