Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation

• URL: http://arxiv.org/abs/2304.01279v2
• Date: Thu, 6 Apr 2023 04:10:59 GMT
• Title: Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation
• Authors: Yan Jin, Mengke Li, Yang Lu, Yiu-ming Cheung, Hanzi Wang
• Abstract summary: We propose a novel MoE-based method called Self-Heterogeneous Integration with Knowledge Excavation (SHIKE) SHIKE achieves the state-of-the-art performance of 56.3%, 60.3%, 75.4%, and 41.9% on CIFAR100-LT (IF100), ImageNet-LT, iNaturalist 2018, and Places-LT, respectively.
• Score: 53.94265240561697
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks have made huge progress in the last few decades. However, as the real-world data often exhibits a long-tailed distribution, vanilla deep models tend to be heavily biased toward the majority classes. To address this problem, state-of-the-art methods usually adopt a mixture of experts (MoE) to focus on different parts of the long-tailed distribution. Experts in these methods are with the same model depth, which neglects the fact that different classes may have different preferences to be fit by models with different depths. To this end, we propose a novel MoE-based method called Self-Heterogeneous Integration with Knowledge Excavation (SHIKE). We first propose Depth-wise Knowledge Fusion (DKF) to fuse features between different shallow parts and the deep part in one network for each expert, which makes experts more diverse in terms of representation. Based on DKF, we further propose Dynamic Knowledge Transfer (DKT) to reduce the influence of the hardest negative class that has a non-negligible impact on the tail classes in our MoE framework. As a result, the classification accuracy of long-tailed data can be significantly improved, especially for the tail classes. SHIKE achieves the state-of-the-art performance of 56.3%, 60.3%, 75.4%, and 41.9% on CIFAR100-LT (IF100), ImageNet-LT, iNaturalist 2018, and Places-LT, respectively.

Related papers

• FedLF: Adaptive Logit Adjustment and Feature Optimization in Federated Long-Tailed Learning [5.23984567704876]
  Federated learning offers a paradigm to the challenge of preserving privacy in distributed machine learning. Traditional approach fails to address the phenomenon of class-wise bias in global long-tailed data. New method FedLF introduces three modifications in the local training phase: adaptive logit adjustment, continuous class centred optimization, and feature decorrelation.
  arXiv  Detail & Related papers  (2024-09-18T16:25:29Z)
• Feature Fusion from Head to Tail for Long-Tailed Visual Recognition [39.86973663532936]
  The biased decision boundary caused by inadequate semantic information in tail classes is one of the key factors contributing to their low recognition accuracy. We propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T) Both theoretical analysis and practical experimentation demonstrate that H2T can contribute to a more optimized solution for the decision boundary.
  arXiv  Detail & Related papers  (2023-06-12T08:50:46Z)
• Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Data [60.64535309016623]
  We build smooth-tail data where the long-tailed distribution of categories decays smoothly to correct the bias towards head classes. We fine-tune the class-agnostic modules of the pre-trained model on the head class dominant replay data. We train a unified model on the tail class dominant replay data while transferring knowledge from the head class expert model to ensure accurate detection of all categories.
  arXiv  Detail & Related papers  (2023-05-22T08:53:50Z)
• Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning [44.947984354108094]
  We propose an innovative long-tailed learning paradigm that breaks the bottleneck by guiding the learning of deep networks with external prior knowledge. The proposed prophetic paradigm acts as a promising solution to the challenge of limited class knowledge in long-tailed datasets.
  arXiv  Detail & Related papers  (2023-04-09T02:02:19Z)
• FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation [54.2658887073461]
  Dealing with non-IID data is one of the most challenging problems for federated learning. This paper studies the joint problem of non-IID and long-tailed data in federated learning and proposes a corresponding solution called Federated Ensemble Distillation with Imbalance (FEDIC) FEDIC uses model ensemble to take advantage of the diversity of models trained on non-IID data.
  arXiv  Detail & Related papers  (2022-04-30T06:17:36Z)
• ResLT: Residual Learning for Long-tailed Recognition [64.19728932445523]
  We propose a more fundamental perspective for long-tailed recognition, i.e., from the aspect of parameter space. We design the effective residual fusion mechanism -- with one main branch optimized to recognize images from all classes, another two residual branches are gradually fused and optimized to enhance images from medium+tail classes and tail classes respectively. We test our method on several benchmarks, i.e., long-tailed version of CIFAR-10, CIFAR-100, Places, ImageNet, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2021-01-26T08:43:50Z)
• Long-tailed Recognition by Routing Diverse Distribution-Aware Experts [64.71102030006422]
  We propose a new long-tailed classifier called RoutIng Diverse Experts (RIDE) It reduces the model variance with multiple experts, reduces the model bias with a distribution-aware diversity loss, reduces the computational cost with a dynamic expert routing module. RIDE outperforms the state-of-the-art by 5% to 7% on CIFAR100-LT, ImageNet-LT and iNaturalist 2018 benchmarks.
  arXiv  Detail & Related papers  (2020-10-05T06:53:44Z)
• Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification [106.08067870620218]
  We propose a self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME) We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. We conduct extensive experiments and demonstrate that our method is able to achieve superior performances compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-06T12:57:36Z)

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.