Long-tail Recognition via Compositional Knowledge Transfer
- URL: http://arxiv.org/abs/2112.06741v1
- Date: Mon, 13 Dec 2021 15:48:59 GMT
- Title: Long-tail Recognition via Compositional Knowledge Transfer
- Authors: Sarah Parisot, Pedro M. Esperanca, Steven McDonagh, Tamas J. Madarasz,
Yongxin Yang, Zhenguo Li
- Abstract summary: We introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem.
Our objective is to transfer knowledge acquired from information-rich common classes to semantically similar, and yet data-hungry, rare classes.
Experiments show that our approach can achieve significant performance boosts on rare classes while maintaining robust common class performance.
- Score: 60.03764547406601
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this work, we introduce a novel strategy for long-tail recognition that
addresses the tail classes' few-shot problem via training-free knowledge
transfer. Our objective is to transfer knowledge acquired from information-rich
common classes to semantically similar, and yet data-hungry, rare classes in
order to obtain stronger tail class representations. We leverage the fact that
class prototypes and learned cosine classifiers provide two different,
complementary representations of class cluster centres in feature space, and
use an attention mechanism to select and recompose learned classifier features
from common classes to obtain higher quality rare class representations. Our
knowledge transfer process is training free, reducing overfitting risks, and
can afford continual extension of classifiers to new classes. Experiments show
that our approach can achieve significant performance boosts on rare classes
while maintaining robust common class performance, outperforming directly
comparable state-of-the-art models.
Related papers
- Granularity Matters in Long-Tail Learning [62.30734737735273]
We offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance.
We introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes.
To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss.
arXiv Detail & Related papers (2024-10-21T13:06:21Z) - Self-Cooperation Knowledge Distillation for Novel Class Discovery [8.984031974257274]
Novel Class Discovery (NCD) aims to discover unknown and novel classes in an unlabeled set by leveraging knowledge already learned about known classes.
We propose a Self-Cooperation Knowledge Distillation (SCKD) method to utilize each training sample (whether known or novel, labeled or unlabeled) for both review and discovery.
arXiv Detail & Related papers (2024-07-02T03:49:48Z) - Subclass-balancing Contrastive Learning for Long-tailed Recognition [38.31221755013738]
Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications.
We propose a novel subclass-balancing contrastive learning'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes.
We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance.
arXiv Detail & Related papers (2023-06-28T05:08:43Z) - Cross-Class Feature Augmentation for Class Incremental Learning [45.91253737682168]
We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks.
The proposed approach has a unique perspective to utilize the previous knowledge in class incremental learning since it augments features of arbitrary target classes.
Our method consistently outperforms existing class incremental learning methods by significant margins in various scenarios.
arXiv Detail & Related papers (2023-04-04T15:48:09Z) - Generalization Bounds for Few-Shot Transfer Learning with Pretrained
Classifiers [26.844410679685424]
We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes.
We show that the few-shot error of the learned feature map on new classes is small in case of class-feature-variability collapse.
arXiv Detail & Related papers (2022-12-23T18:46:05Z) - SATS: Self-Attention Transfer for Continual Semantic Segmentation [50.51525791240729]
continual semantic segmentation suffers from the same catastrophic forgetting issue as in continual classification learning.
This study proposes to transfer a new type of information relevant to knowledge, i.e. the relationships between elements within each image.
The relationship information can be effectively obtained from the self-attention maps in a Transformer-style segmentation model.
arXiv Detail & Related papers (2022-03-15T06:09:28Z) - Learning to Generate Novel Classes for Deep Metric Learning [24.048915378172012]
We introduce a new data augmentation approach that synthesizes novel classes and their embedding vectors.
We implement this idea by learning and exploiting a conditional generative model, which, given a class label and a noise, produces a random embedding vector of the class.
Our proposed generator allows the loss to use richer class relations by augmenting realistic and diverse classes, resulting in better generalization to unseen samples.
arXiv Detail & Related papers (2022-01-04T06:55:19Z) - Class-Balanced Distillation for Long-Tailed Visual Recognition [100.10293372607222]
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions.
In this work, we introduce a new framework, by making the key observation that a feature representation learned with instance sampling is far from optimal in a long-tailed setting.
Our main contribution is a new training method, that leverages knowledge distillation to enhance feature representations.
arXiv Detail & Related papers (2021-04-12T08:21:03Z) - Learning and Evaluating Representations for Deep One-class
Classification [59.095144932794646]
We present a two-stage framework for deep one-class classification.
We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations.
In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
arXiv Detail & Related papers (2020-11-04T23:33:41Z) - Transferring Dense Pose to Proximal Animal Classes [83.84439508978126]
We show that it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes.
We do this by establishing a DensePose model for the new animal which is also geometrically aligned to humans.
We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach.
arXiv Detail & Related papers (2020-02-28T21:43:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.