Search Results for author:
Found 23 papers, 8 papers with code
Confidence Self-Calibration for Multi-Label Class-Incremental Learning
The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unavailable.
Variational Continual Test-Time Adaptation
At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model.
Elastic Multi-Gradient Descent for Parallel Continual Learning
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.
Long-Tailed Learning as Multi-Objective Optimization
Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes.
Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning
Moreover, we design a multi-stage strategy for training S2C model, which mitigates the training challenges posed by limited data in the incremental process.
Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision
Vehicle-to-everything (V2X) perception is an innovative technology that enhances vehicle perception accuracy, thereby elevating the security and reliability of autonomous systems.
Two-level Graph Network for Few-Shot Class-Incremental Learning
Class-level graph network aims to mitigate the semantic conflict between prototype features of new classes and old classes.
Centroid Distance Distillation for Effective Rehearsal in Continual Learning
Rehearsal, retraining on a stored small data subset of old tasks, has been proven effective in solving catastrophic forgetting in continual learning.
Measuring Asymmetric Gradient Discrepancy in Parallel Continual Learning
In Parallel Continual Learning (PCL), the parallel multiple tasks start and end training unpredictably, thus suffering from training conflict and catastrophic forgetting issues.
Multi-Label Continual Learning using Augmented Graph Convolutional Network
In contrast, the inter-task relationships leverage hard and soft labels from data and a constructed expert network.
Exploring Example Influence in Continual Learning
Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks).
Class-Incremental Lifelong Learning in Multi-Label Classification
This paper studies Lifelong Multi-Label (LML) classification, which builds an online class-incremental classifier in a sequential multi-label classification data stream.
AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition
The key challenges of LML image recognition are the construction of label relationships on Partial Labels of training data and the Catastrophic Forgetting on old classes, resulting in poor generalization.
Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing
Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image.
Rethinking Rehearsal in Lifelong Learning: Does An Example Contribute the Plasticity or Stability?
Traditionally, the primary goal of LL is to achieve the trade-off between the Stability (remembering past tasks) and Plasticity (adapting to new tasks).
Disentangling Semantic-to-visual Confusion for Zero-shot Learning
However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL.
Coarse to Fine: Multi-label Image Classification with Global/Local Attention
Since multi-label image classification is very complicated, people seek to use the attention mechanism to guide the classification process.
Multi-Domain Multi-Task Rehearsal for Lifelong Learning
Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i. e., biased forgetting of previous knowledge when moving to new tasks.
Associating Multi-Scale Receptive Fields for Fine-grained Recognition
First, CNL computes correlations between features of a query layer and all response layers.
Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition
Paired egocentric interaction recognition (PEIR) is the task to collaboratively recognize the interactions between two persons with the videos in their corresponding views.
MUTATT: Visual-Textual Mutual Guidance for Referring Expression Comprehension
In this paper, we argue that for REC the referring expression and the target region are semantically correlated and subject, location and relationship consistency exist between vision and language. On top of this, we propose a novel approach called MutAtt to construct mutual guidance between vision and language, which treat vision and language equally thus yield compact information matching.
SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
First, we pre-train a Semantic Rectifying Network (SRN) to rectify semantic space with a semantic loss and a rectifying loss.
Visual Grounding via Accumulated Attention
There are three main challenges in VG: 1) what is the main focus in a query; 2) how to understand an image; 3) how to locate an object.
