Search Results for author:
Found 37 papers, 13 papers with code
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning
Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.
Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendations
Fashion, deeply rooted in sociocultural dynamics, evolves as individuals emulate styles popularized by influencers and iconic figures.
Measuring Large Language Models Capacity to Annotate Journalistic Sourcing
Since the launch of ChatGPT in late 2022, the capacities of Large Language Models and their evaluation have been in constant discussion and evaluation both in academic research and in the industry.
UdeerLID+: Integrating LiDAR, Image, and Relative Depth with Semi-Supervised
The integration of multiple data sources in road segmentation presents both opportunities and challenges.
MV-DETR: Multi-modality indoor object detection by Multi-View DEtecton TRansformers
Unfortunately, single RGBD dataset with thousands of data is not enough for training an discriminating filter for visual texture feature extraction.
Ranked #4 on
3D Object Detection
on ScanNetV2
Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization
In this paper, we propose a ``Multi-stage Face-voice Association Learning with Keynote Speaker Diarization''~(MFV-KSD) framework.
MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes.
Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy.
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Through a series of experiments, we have uncovered two critical insights that shed light on the training and parameter inefficiency of LoRA.
Voice Conversion Augmentation for Speaker Recognition on Defective Datasets
Our experimental results on three created datasets demonstrated that VCA-NN effectively mitigates these dataset problems, which provides a new direction for handling the speaker recognition problems from the data aspect.
Integrative Graph-Transformer Framework for Histopathology Whole Slide Image Representation and Classification
In digital pathology, the multiple instance learning (MIL) strategy is widely used in the weakly supervised histopathology whole slide image (WSI) classification task where giga-pixel WSIs are only labeled at the slide level.
PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
Large Language Models (LLMs) have succeeded remarkably in understanding long-form contents.
Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning
Secondly, we develop a series of affinity learning methods that equip the selfexpressive framework with ℓp-norm to construct an intrinsic affinity matrix with an adaptive extension.
Aperture Diffraction for Compact Snapshot Spectral Imaging
We demonstrate a compact, cost-effective snapshot spectral imaging system named Aperture Diffraction Imaging Spectrometer (ADIS), which consists only of an imaging lens with an ultra-thin orthogonal aperture mask and a mosaic filter sensor, requiring no additional physical footprint compared to common RGB cameras.
Regression-Oriented Knowledge Distillation for Lightweight Ship Orientation Angle Prediction with Optical Remote Sensing Images
Four tiny SOAP models are also created by replacing the convolutional blocks in Mobile-SOAP with four small-scale networks, respectively.
Speaker recognition with two-step multi-modal deep cleansing
However, noisy samples (i. e., with wrong labels) in the training set induce confusion and cause the network to learn the incorrect representation.
Visual Semantic Parsing: From Images to Abstract Meaning Representation
The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e. g., image) into a structured representation, where entities (people and objects) are nodes connected by edges specifying their relations.
Graph-based Active Learning for Semi-supervised Classification of SAR Data
We use a Convolutional Neural Network Variational Autoencoder (CNNVAE) to embed SAR data into a feature space, and then construct a similarity graph from the embedded data and apply graph-based semi-supervised learning techniques.
Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
There have been two lines of approaches that can be used to further address the limitation: (1) unsupervised pretraining can leverage knowledge in much larger unstructured text data; (2) structured (often human-curated) knowledge has started to be considered in neural-network-based models for NLI.
Unsupervised Conversation Disentanglement through Co-Training
For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier.
Enhancing Descriptive Image Captioning with Natural Language Inference
In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions.
An infinite-dimensional representation of the Ray-Knight theorems
The classical Ray-Knight theorems for Brownian motion determine the law of its local time process either at the first hitting time of a given value a by the local time at the origin, or at the first hitting time of a given position b by Brownian motion.
Probability
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks
Graph convolution networks (GCNs) have become effective models for graph classification.
Learned Hardware/Software Co-Design of Neural Accelerators
The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning.
Improving Image Captioning with Better Use of Caption
Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community.
Improving Image Captioning with Better Use of Captions
Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community.
Generalised Lipschitz Regularisation Equals Distributional Robustness
The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximators.
Certifying Distributional Robustness using Lipschitz Regularisation
Distributional robust risk (DRR) minimisation has arisen as a flexible and effective framework for machine learning.
Learning Execution through Neural Code Fusion
In this work, we propose a new approach to use GNNs to learn fused representations of general source code and its execution.
Exploring Unsupervised Pretraining and Sentence Structure Modelling for Winograd Schema Challenge
Winograd Schema Challenge (WSC) was proposed as an AI-hard problem in testing computers' intelligence on common sense representation and reasoning.
Lipschitz Networks and Distributional Robustness
Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation.
Inductive Two-Layer Modeling with Parametric Bregman Transfer
Latent prediction models, exemplified by multi-layer networks, employ hidden variables that automate abstract feature discovery.
Monge blunts Bayes: Hardness Results for Adversarial Training
A key feature of our result is that it holds for all proper losses, and for a popular subset of these, the optimisation of this central measure appears to be independent of the loss.
Toward Diverse Text Generation with Inverse Reinforcement Learning
Similar to the adversarial models, the reward and policy function in IRL are optimized alternately.
Bregman Divergence for Stochastic Variance Reduction: Saddle-Point and Adversarial Prediction
Adversarial machines, where a learner competes against an adversary, have regained much recent interest in machine learning.
DAG-based Long Short-Term Memory for Neural Word Segmentation
In this paper, we propose a new neural model to incorporate the word-level information for Chinese word segmentation.
Adversarial Multi-Criteria Learning for Chinese Word Segmentation
Different linguistic perspectives causes many diverse segmentation criteria for Chinese word segmentation (CWS).
