Search Results for author:
Found 17 papers, 4 papers with code
Fine-grained Text to Image Synthesis
In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different subclasses, and there may be linguistic discrepancy among texts describing the same image.
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
To gain deeper insights into this trend, we study over 1500 quantized LLM checkpoints of various sizes and at different training levels (undertrained or fully trained) in a controlled setting, deriving scaling laws for understanding the relationship between QiD and factors such as the number of training tokens, model size and bit width.
Secure and Effective Data Appraisal for Machine Learning
Essential for an unfettered data market is the ability to discreetly select and evaluate training data before finalizing a transaction between the data owner and model owner.
Efficient NLP Model Finetuning via Multistage Data Filtering
To this end, we set to filter training examples in a streaming fashion, in tandem with training the target model.
e-G2C: A 0.14-to-8.31 $μ$J/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM
This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation.
SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
In this paper, we discover for the first time that both efficient DNNs and their lottery subnetworks (i. e., lottery tickets) can be directly identified from a supernet, which we term as SuperTickets, via a two-in-one training scheme with jointly architecture searching and parameter pruning.
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i. e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions.
Semi-supervised Domain Adaptation for Semantic Segmentation
We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks.
Contrastive Quant: Quantization Makes Stronger Contrastive Learning
Contrastive learning, which learns visual representations by enforcing feature consistency under different augmented views, has emerged as one of the most effective unsupervised learning methods.
D$^2$-GCN: Data-Dependent GCNs for Boosting Both Efficiency and Scalability
Graph Convolutional Networks (GCNs) have gained an increasing attention thanks to their state-of-the-art (SOTA) performance in graph-based learning tasks.
"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle for the efficient implementation of BNN training.
Ranked #178 on
Image Classification
on CIFAR-100
Mask-based Data Augmentation for Semi-supervised Semantic Segmentation
Training a CNN to perform semantic segmentation requires a large amount of labeled data, where the production of such labeled data is both costly and labor intensive.
Domain Adaptation on Semantic Segmentation for Aerial Images
In this paper, we propose a novel unsupervised domain adaptation framework to address domain shift in the context of aerial semantic image segmentation.
Accelerated WGAN update strategy with loss change rate balancing
Optimizing the discriminator in Generative Adversarial Networks (GANs) to completion in the inner training loop is computationally prohibitive, and on finite datasets would result in overfitting.
Generating Image Sequence from Description with LSTM Conditional GAN
Generating images from word descriptions is a challenging task.
Layered Optical Flow Estimation Using a Deep Neural Network with a Soft Mask
We show that by using masks the motion estimate results in a quadratic function of input features in the output layer.
Lecture video indexing using boosted margin maximizing neural networks
This paper presents a novel approach for lecture video indexing using a boosted deep convolutional neural network system.
