Search Results for author:
Found 5 papers, 2 papers with code
M-scan: A Multi-Scenario Causal-driven Adaptive Network for Recommendation
Furthermore, through causal graph analysis, we have discovered that the scenario itself directly influences click behavior, yet existing approaches directly incorporate data from other scenarios during the training of the current scenario, leading to prediction biases when they directly utilize click behaviors from other scenarios to train models.
Variance-Covariance Regularization Improves Representation Learning
In summary, VCReg offers a universally applicable regularization framework that significantly advances transfer learning and highlights the connection between gradient starvation, neural collapse, and feature transferability.
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.
TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning
Similar to other recent self-supervised learning methods, our method is based on maximizing the agreement among embeddings of different distorted versions of the same image, which pushes the encoder to produce transformation invariant representations.
Masked Siamese ConvNets
Self-supervised learning has shown superior performances over supervised methods on various vision benchmarks.
