Search Results for author:
Found 26 papers, 9 papers with code
Multi-Point Positional Insertion Tuning for Small Object Detection
Small object detection aims to localize and classify small objects within images.
HarmonicEval: Multi-modal, Multi-task, Multi-criteria Automatic Evaluation Using a Vision Language Model
Vision-language models (VLMs) have shown impressive abilities in text and image understanding.
HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
Specifically, it incorporates the technique of using MRVQ sub-modules and continues training from a pre-trained LLM-based TTS model.
Formula-Supervised Visual-Geometric Pre-training
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object recognition have tended to process these modalities separately.
Rethinking Image Super-Resolution from Training Data Perspectives
In this work, we investigate the understudied effect of the training data used for image super-resolution (SR).
Scaling Backwards: Minimal Synthetic Pre-training?
To this end, we search for a minimal, purely synthetic pre-training dataset that allows us to achieve performance similar to the 1 million images of ImageNet-1k.
Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering
Visual question answering (VQA) is the task of providing accurate answers to natural language questions based on visual input.
AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering
In the inference phase, given an input question, AdaCoder predicts the question type and chooses the appropriate corresponding compressed preprompt to generate code to answer the question.
ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks
The L-adapters create paths from each encoder layer to the downstream head and help to extract non-linguistic features from lower encoder layers that are effective for speaker verification and emotion recognition.
CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information
The findings are revealing: (i) our aerial agent model trained on human demonstration trajectories, outperform those trained on shortest path trajectories by a large margin; (ii) incorporating 2D spatial map information markedly and robustly enhances navigation performance at a city scale; (iii) despite the use of map information, our challenging CityNav dataset reveals a persistent performance gap between our baseline models and human performance.
CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
To tackle this problem, we introduce the CityRefer dataset for city-level visual grounding.
SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning
SegRCDB has a high potential to contribute to semantic segmentation pre-training and investigation by enabling the creation of large datasets without manual annotation.
Pre-training Vision Transformers with Very Limited Synthesized Images
Prior work on FDSL has shown that pre-training vision transformers on such synthetic datasets can yield competitive accuracy on a wide range of downstream tasks.
Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves
Unlike JFT-300M which is a static dataset, the quality of synthetic datasets will continue to improve, and the current work is a testament to this possibility.
Fixed-Weight Difference Target Propagation
Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work?
PoF: Post-Training of Feature Extractor for Improving Generalization
We developed a training algorithm called PoF: Post-Training of Feature Extractor that updates the feature extractor part of an already-trained deep model to search a flatter minimum.
Replacing Labeled Real-image Datasets with Auto-generated Contours
In the present work, we show that the performance of formula-driven supervised learning (FDSL) can match or even exceed that of ImageNet-21k without the use of real images, human-, and self-supervision during the pre-training of Vision Transformers (ViTs).
Can Vision Transformers Learn without Natural Images?
Moreover, although the ViT pre-trained without natural images produces some different visualizations from ImageNet pre-trained ViT, it can interpret natural image datasets to a large extent.
Pre-training without Natural Images
Is it possible to use convolutional neural networks pre-trained without any natural images to assist natural image understanding?
Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data
Our main idea is to initialize the network parameters by solving an artificial noise classification problem, where the aim is to classify Perlin noise samples into their noise categories.
Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network
We propose a non-invasive and cost-effective method to automatically detect dementia by utilizing solely speech audio data.
Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
Herein, we propose Augmented Cyclic Consistency Regularization (ACCR), a novel regularization method for unpaired I2I translation.
Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition
We investigate the feasibility of sequence-level knowledge distillation of Sequence-to-Sequence (Seq2Seq) models for Large Vocabulary Continuous Speech Recognition (LVSCR).
Few-Shot Adaptation for Multimedia Semantic Indexing
Few-shot adaptation provides robust parameter estimation with few training examples, by optimizing the parameters of zero-shot learning and supervised many-shot learning simultaneously.
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
This paper presents a new framework for human action recognition from a 3D skeleton sequence.
Ranked #111 on
Skeleton Based Action Recognition
on NTU RGB+D
I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification
I-vector based text-independent speaker verification (SV) systems often have poor performance with short utterances, as the biased phonetic distribution in a short utterance makes the extracted i-vector unreliable.
Generative Adversarial Network
Text-Independent Speaker Verification
