Search Results for author:
Found 22 papers, 9 papers with code
Sentiment Interpretable Logic Tensor Network for Aspect-Term Sentiment Analysis
SILTN is interpretable because it is a neurosymbolic formalism and a computational model that supports learning and reasoning about data with a differentiable first-order logic language (FOL).
Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text
To tackle two challenges, we propose to split the long text into multiple granularities for encoding, i. e., word, phrase, and sentence, so that the long text can be fully encoded without losing any key semantic knowledge.
AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation Nowcasting
Inspired by the fact that in the frequency domain, phase variations are shown to correspond to changes in the position of precipitation, while amplitude variations are linked to intensity changes, we propose an amplitude-phase disentanglement model called AlphaPre, which separately learn the position and intensity changes of precipitation.
Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation
In this paper, we find that the distribution of sensitive parameters is not chaotic, but concentrates in a small number of rows or columns in each parameter matrix.
AsyncDSB: Schedule-Asynchronous Diffusion Schrödinger Bridge for Image Inpainting
Although these methods have shown superior performance, in this paper, we find that 1) existing methods suffer from a schedule-restoration mismatching issue, i. e., the theoretical schedule and practical restoration processes usually exist a large discrepancy, which theoretically results in the schedule not fully leveraged for restoring images; and 2) the key reason causing such issue is that the restoration process of all pixels are actually asynchronous but existing methods set a synchronous noise schedule to them, i. e., all pixels shares the same noise schedule.
Prototype Optimization with Neural ODE for Few-Shot Learning
To address this issue, in this paper, we regard the gradient and its flow as meta-knowledge and then propose a novel Neural Ordinary Differential Equation (ODE)-based meta-optimizer to optimize prototypes, called MetaNODE.
LG-VQ: Language-Guided Codebook Learning
Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner.
MCSDNet: Mesoscale Convective System Detection Network via Multi-scale Spatiotemporal Information
Different from the previous models, MCSDNet targets on multi-frames detection and leverages multi-scale spatiotemporal information for the detection of MCS regions in remote sensing imagery(RSI).
A Challenge Dataset and Effective Models for Conversational Stance Detection
Previous stance detection studies typically concentrate on evaluating stances within individual instances, thereby exhibiting limitations in effectively modeling multi-party discussions concerning the same specific topic, as naturally transpire in authentic social media interactions.
Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modeling
To this end, we propose a novel codebook transfer framework with part-of-speech, called VQCT, which aims to transfer a well-trained codebook from pretrained language models to VQIM for robust codebook learning.
DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting
A unified and flexible framework that can equip any type of spatio-temporal models is proposed based on residual diffusion, which effectively tackles the shortcomings of previous methods.
HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning
Our previous work proposes a novel replay-based method called proxy-based contrastive replay (PCR), which handles the shortcomings by achieving complementary advantages of both replay manners.
UER: A Heuristic Bias Addressing Approach for Online Continual Learning
By decomposing the dot-product logits into an angle factor and a norm factor, we empirically find that the bias problem mainly occurs in the angle factor, which can be used to learn novel knowledge as cosine logits.
MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning
Its key idea is learning a deep model in a bi-level optimization manner, where the outer-loop process learns a shared gradient descent algorithm (i. e., its hyperparameters), while the inner-loop process leverage it to optimize a task-specific model by using only few labeled data.
Knowledge-enhanced Prompt-tuning for Stance Detection
However, conducting prompt-tuning methods for stance detection in real-world remains a challenge for several reasons: (1) The text form of stance detection is usually short and informal, which makes it difficult to design label words for the verbalizer.
PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning
It aims to continuously learn new classes from data stream and the samples of data stream are seen only once, which suffers from the catastrophic forgetting issue, i. e., forgetting historical knowledge of old classes.
MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning
Then, resorting to the prior, we split each few-shot task to a set of subtasks with different concept levels and then perform class prediction via a model of decision tree.
SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification
In this framework, a scene graph construction module is carefully designed to represent each test remote sensing image or each scene class as a scene graph, where the nodes reflect these co-occurrence objects meanwhile the edges capture the spatial correlations between these co-occurrence objects.
Prototype Completion for Few-Shot Learning
In this paper, 1) we figure out the reason, i. e., in the pre-trained feature space, the base classes already form compact clusters while novel classes spread as groups with large variances, which implies that fine-tuning feature extractor is less meaningful; 2) instead of fine-tuning feature extractor, we focus on estimating more representative prototypes.
MetaNODE: Prototype Optimization as a Neural ODE for Few-Shot Learning
Although the existing meta-optimizers can also be adapted to our framework, they all overlook a crucial gradient bias issue, \emph{i. e.}, the mean-based gradient estimation is also biased on sparse data.
Prototype Completion with Primitive Knowledge for Few-Shot Learning
To avoid the prototype completion error caused by primitive knowledge noises or class differences, we further develop a Gaussian based prototype fusion strategy that combines the mean-based and completed prototypes by exploiting the unlabeled samples.
MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning
To this end, we propose a novel meta-learning framework, called MetaConcept, which learns to abstract concepts via the concept graph.
