Search Results for author:
Found 17 papers, 8 papers with code
LLM meets Vision-Language Models for Zero-Shot One-Class Classification
In this setting, only the label of the target class is available, and the goal is to discriminate between positive and negative query samples without requiring any validation example from the target task.
A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models
In recent years, the rapid evolution of computer vision has seen the emergence of various foundation models, each tailored to specific data types and tasks.
Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning
In this paper, we present a novel approach that leverages text-derived statistics to predict the mean and covariance of the visual feature distribution for each class.
DBsurf: A Discrepancy Based Method for Discrete Stochastic Gradient Estimation
Computing gradients of an expectation with respect to the distributional parameters of a discrete distribution is a problem arising in many fields of science and engineering.
Towards Robust FastSpeech 2 by Modelling Residual Multimodality
State-of-the-art non-autoregressive text-to-speech (TTS) models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech.
A Statistical Model for Predicting Generalization in Few-Shot Classification
Such a set is hardly available in few-shot learning scenarios, a highly disregarded shortcoming in the field.
A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps
We also achieve low memory footprint for weights and activations by means of mixed precision quantization-at-training techniques.
AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling
Using this differentiable duration method, we introduce AutoTTS, a direct text-to-waveform speech synthesis model.
NVC-Net: End-to-End Adversarial Voice Conversion
By disentangling the speaker identity from the speech content, NVC-Net is able to perform non-parallel traditional many-to-many voice conversion as well as zero-shot voice conversion from a short utterance of an unseen target speaker.
DNN Quantization with Attention
We call this procedure \textit{DNN Quantization with Attention} (DQA).
Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives
While there exist a plethora of deep learning tools and frameworks, the fast-growing complexity of the field brings new demands and challenges, such as more flexible network design, speedy computation on distributed setting, and compatibility between different tools.
Efficient Sampling for Predictor-Based Neural Architecture Search
Usually, we compute the proxy for all DNNs in the network search space and pick those that maximize the proxy as candidates for optimization.
Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency
This procedure bears the problem that the generated magnitude spectrogram may not be consistent, which is required for finding a phase such that the full spectrogram has a natural-sounding speech waveform.
Iteratively Training Look-Up Tables for Network Quantization
For each layer, we learn a value dictionary and an assignment matrix to represent the network weights.
Mixed Precision DNNs: All you need is a good parametrization
Since choosing the optimal bitwidths is not straight forward, training methods, which can learn them, are desirable.
Iteratively Training Look-Up Tables for Network Quantization
In this paper we introduce a training method, called look-up table quantization, LUT-Q, which learns a dictionary and assigns each weight to one of the dictionary's values.
Improving DNN-based Music Source Separation using Phase Features
Music source separation with deep neural networks typically relies only on amplitude features.
