Search Results for author:
Found 10 papers, 4 papers with code
CAVM: Conditional Autoregressive Vision Model for Contrast-Enhanced Brain Tumor MRI Synthesis
As the enhancement of image intensity grows with a higher dose of contrast agents, we assume that it is less challenging to synthesize a virtual image with a lower dose, where the difference between the contrast-enhanced and non-contrast images is smaller.
Monotonic Paraphrasing Improves Generalization of Language Model Prompting
In this paper, we propose monotonic paraphrasing (MonoPara), an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt (or instruction) rewriting, and a target LM (i. e. the prompt or instruction executor) that constrains the generation for lower perplexity.
Multi-task Collaborative Pre-training and Individual-adaptive-tokens Fine-tuning: A Unified Framework for Brain Representation Learning
Structural magnetic resonance imaging (sMRI) provides accurate estimates of the brain's structural organization and learning invariant brain representations from sMRI is an enduring issue in neuroscience.
Connectional-Style-Guided Contextual Representation Learning for Brain Disease Diagnosis
In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis.
Robust Natural Language Understanding with Residual Attention Debiasing
However, previous ensemble-based debiasing methods typically apply debiasing on top-level logits without directly addressing biased attention patterns.
Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain adaptive (UDA) person re-identification (Re-ID).
PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
PASS learns to match the output of the local views and global views on the same [PART].
Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization
In summary, the EOQ framework is specially designed for reducing the high cost of convolution and BN in network training, demonstrating a broad application prospect of online training in resource-limited devices.
Kronecker CP Decomposition with Fast Multiplication for Compressing RNNs
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition.
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.
