Search Results for author:
Found 27 papers, 17 papers with code
PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental Learning
Concretely, we devise modality-specific prompts to compensate for missing information, facilitating the model to maintain a holistic representation of the data.
SegACIL: Solving the Stability-Plasticity Dilemma in Class-Incremental Semantic Segmentation
Extensive experiments on the Pascal VOC2012 dataset show that SegACIL achieves superior performance in the sequential, disjoint, and overlap settings, offering a robust solution to the challenges of class-incremental semantic segmentation.
Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
We innovatively introduce analytic learning into TTA, using the Analytic Classifiers (ACs) to prevent model forgetting.
TS-ACL: A Time Series Analytic Continual Learning Framework for Privacy-Preserving and Class-Incremental Pattern Recognition
A primary challenge in this problem is catastrophic forgetting, where the incorporation of new data samples causes the models to forget previously learned information.
C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets
Conformal prediction, as an emerging uncertainty quantification technique, typically functions as post-hoc processing for the outputs of trained classifiers.
ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning
We introduce a novel Recursive Fusion model, dubbed ReFu, designed to integrate point clouds and meshes for exemplar-free 3D Class-Incremental Learning, where the model learns new 3D classes while retaining knowledge of previously learned ones.
FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Tracking
Specifically, we develop the feature adaptive continual-learning (FAC) module, a neural network that can be trained online to learn features adaptively using all past tracking information during tracking.
AIR: Analytic Imbalance Rectifier for Continual Learning
To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i. e., closed-form) solution for data-imbalanced class-incremental learning (CIL) and generalized CIL scenarios in real-world continual learning.
Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models
In this setting, a CL learner is required to incrementally learn from multiple domains and classify test images from both seen and unseen domains without any domain-identity hint.
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories.
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers.
Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task
One of these scenarios can be formulated as an online continual learning (OCL) problem.
Analytic Federated Learning
In this paper, we introduce analytic federated learning (AFL), a new training paradigm that brings analytical (i. e., closed-form) solutions to the federated learning (FL) community.
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content.
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning
The compensation stream is governed by a Dual-Activation Compensation (DAC) module.
F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
In this paper, we propose an exemplar-free approach--Forward-only Online Analytic Learning (F-OAL).
GACL: Exemplar-Free Generalized Analytic Continual Learning
The GACL adopts analytic learning (a gradient-free training technique) and delivers an analytical (i. e., closed-form) solution to the GCIL scenario.
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
The DS-BPT pretrains model in streams of both supervised learning and self-supervised contrastive learning (SSCL) for base knowledge extraction.
Chimera: A Lossless Decoding Method for Accelerating Large Language Models Inference by Fusing all Tokens
Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words.
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
In this work, we propose a novel method -- Convex-Concave Loss, which enables a high variance of training loss distribution by gradient descent.
ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference
We propose ConsistentEE, an early exiting method that is consistent in training and inference.
GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task
In this paper, we approach the FSCIL by adopting analytic learning, a technique that converts network training into linear problems.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
In the presence of noisy labels, designing robust loss functions is critical for securing the generalization performance of deep neural networks.
ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection
Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively.
Analytic Learning of Convolutional Neural Network For Pattern Recognition
Training convolutional neural networks (CNNs) with back-propagation (BP) is time-consuming and resource-intensive particularly in view of the need to visit the dataset multiple times.
Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization
Decoupled learning is a branch of model parallelism which parallelizes the training of a network by splitting it depth-wise into multiple modules.
Fully Decoupled Neural Network Learning Using Delayed Gradients
Training neural networks with back-propagation (BP) requires a sequential passing of activations and gradients, which forces the network modules to work in a synchronous fashion.
