Search Results for author:
Found 30 papers, 25 papers with code
Generative Multi-modal Models are Good Class-Incremental Learners
In class-incremental learning (CIL) scenarios, the phenomenon of catastrophic forgetting caused by the classifier's bias towards the current task has long posed a significant challenge.
GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Specifically, our TES leverages the property that CLIP can generate aligned vision-language features, converting visual embeddings into tokens of the CLIP's text encoder to generate pseudo text embeddings.
Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
Considering this challenge, we propose a novel framework of fine-grained knowledge selection and restoration.
Class Incremental Learning with Pre-trained Vision-Language Models
We also propose a method for parameter retention in the adapter layers that uses a measure of parameter importance to better maintain stability and plasticity during incremental learning.
Masked Autoencoders are Efficient Class Incremental Learners
Moreover, MAEs can reliably reconstruct original input images from randomly selected patches, which we use to store exemplars from past tasks more efficiently for CIL.
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
However, these methods are impeded by several critical limitations: a) the explicit calibration process is both labor- and time-intensive, b) challenge exists in transferring denoisers across different camera models, and c) the disparity between synthetic and real noise is exacerbated by digital gain.
Ranked #1 on
Image Denoising
on SID SonyA7S2 x300
Endpoints Weight Fusion for Class Incremental Semantic Segmentation
In our method, the model containing old knowledge is fused with the model retaining new knowledge in a dynamic fusion manner, strengthening the memory of old classes in ever-changing distributions.
Class-Incremental Semantic Segmentation
Incremental Learning
+1
Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
EFCIL is of interest because it mitigates concerns about privacy and long-term storage of data, while at the same time alleviating the problem of catastrophic forgetting in incremental learning.
Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification
Lifelong object re-identification incrementally learns from a stream of re-identification tasks.
Long-Tailed Class Incremental Learning
However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of long-tailed distributions in the real world.
Universal Representations: A Unified Look at Multiple Task and Domain Learning
We propose a unified look at jointly learning multiple vision tasks and visual domains through universal representations, a single deep neural network.
Representation Compensation Networks for Continual Semantic Segmentation
In this work, we study the continual semantic segmentation problem, where the deep neural networks are required to incorporate new classes continually without catastrophic forgetting.
Ranked #1 on
Domain 1-1
on Cityscapes
Class Incremental Learning
Continual Semantic Segmentation
+16
Learning Multiple Dense Prediction Tasks from Partially Annotated Data
Despite the recent advances in multi-task learning of dense prediction problems, most methods rely on expensive labelled datasets.
Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition
We propose an approach to IML, which we call Episodic Replay Distillation (ERD), that mixes classes from the current task with class exemplars from previous tasks when sampling episodes for meta-learning.
HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods.
Cross-domain Few-shot Learning with Task-specific Adapters
In this paper, we look at the problem of cross-domain few-shot classification that aims to learn a classifier from previously unseen classes and domains with few labeled samples.
Ranked #2 on
Few-Shot Image Classification
on Meta-Dataset
cross-domain few-shot learning
Few-Shot Image Classification
Universal Representation Learning from Multiple Domains for Few-shot Classification
In this paper, we look at the problem of few-shot classification that aims to learn a classifier for previously unseen classes and domains from few labeled samples.
Ranked #4 on
Few-Shot Image Classification
on Meta-Dataset
Self-Training for Class-Incremental Semantic Segmentation
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks.
Class-Incremental Semantic Segmentation
Incremental Learning
Class-incremental learning: survey and performance evaluation on image classification
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning.
Learning to Rank for Active Learning: A Listwise Approach
Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.).
Generative Feature Replay For Class-Incremental Learning
To prevent forgetting, we combine generative feature replay in the classifier with feature distillation in the feature extractor.
Semantic Drift Compensation for Class-Incremental Learning
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
Multi-Task Incremental Learning for Object Detection
For the difficult cases, where the domain gaps and especially category differences are large, we explore three different exemplar sampling methods and show the proposed adaptive sampling method is effective to select diverse and informative samples from entire datasets, to further prevent forgetting.
Learning Metrics from Teachers: Compact Networks for Image Embedding
In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks.
Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting.
Memory Replay GANs: Learning to Generate New Categories without Forgetting
In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion.
Memory Replay GANs: learning to generate images from new categories without forgetting
In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion.
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework.
Ranked #18 on
Crowd Counting
on UCF CC 50
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios.
RankIQA: Learning from Rankings for No-reference Image Quality Assessment
Furthermore, on the LIVE benchmark we show that our approach is superior to existing NR-IQA techniques and that we even outperform the state-of-the-art in full-reference IQA (FR-IQA) methods without having to resort to high-quality reference images to infer IQA.
