Contrastive Supervised Distillation for Continual Representation Learning

• URL: http://arxiv.org/abs/2205.05476v1
• Date: Wed, 11 May 2022 13:20:47 GMT
• Title: Contrastive Supervised Distillation for Continual Representation Learning
• Authors: Tommaso Barletti, Niccolo' Biondi, Federico Pernici, Matteo Bruni, Alberto Del Bimbo
• Abstract summary: A neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called Contrastive Supervised Distillation (CSD), reduces feature forgetting while learning discriminative features.
• Score: 18.864301420659217
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called Contrastive Supervised Distillation (CSD), reduces feature forgetting while learning discriminative features. This is achieved by leveraging labels information in a distillation setting in which the student model is contrastively learned from the teacher model. Extensive experiments show that CSD performs favorably in mitigating catastrophic forgetting by outperforming current state-of-the-art methods. Our results also provide further evidence that feature forgetting evaluated in visual retrieval tasks is not as catastrophic as in classification tasks. Code at: https://github.com/NiccoBiondi/ContrastiveSupervisedDistillation.

Related papers

• Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task. We name our approach Adaptive Retention & Correction (ARC) ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• CUCL: Codebook for Unsupervised Continual Learning [129.91731617718781]
  The focus of this study is on Unsupervised Continual Learning (UCL), as it presents an alternative to Supervised Continual Learning. We propose a method named Codebook for Unsupervised Continual Learning (CUCL) which promotes the model to learn discriminative features to complete the class boundary. Our method significantly boosts the performances of supervised and unsupervised methods.
  arXiv  Detail & Related papers  (2023-11-25T03:08:50Z)
• Look-Ahead Selective Plasticity for Continual Learning of Visual Tasks [9.82510084910641]
  We propose a new mechanism that takes place during task boundaries, i.e., when one task finishes and another starts. We evaluate the proposed methods on benchmark computer vision datasets including CIFAR10 and TinyImagenet.
  arXiv  Detail & Related papers  (2023-11-02T22:00:23Z)
• Knowledge Diffusion for Distillation [53.908314960324915]
  The representation gap between teacher and student is an emerging topic in knowledge distillation (KD) We state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature. We propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models.
  arXiv  Detail & Related papers  (2023-05-25T04:49:34Z)
• Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models [108.13378788663196]
  We propose Subspace Prompt Tuning (SubPT) to project the gradients in back-propagation onto the low-rank subspace spanned by the early-stage gradient flow eigenvectors during the entire training process. We equip CoOp with Novel Learner Feature (NFL) to enhance the generalization ability of the learned prompts onto novel categories beyond the training set.
  arXiv  Detail & Related papers  (2022-11-04T02:06:22Z)
• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation [46.14545656625703]
  catastrophic forgetting is the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. We propose a novel distillation framework, Uncertainty-aware Contrastive Distillation (method) Our results demonstrate the advantage of the proposed distillation technique, which can be used in synergy with previous IL approaches.
  arXiv  Detail & Related papers  (2022-03-26T15:32:12Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Anomaly Detection via Reverse Distillation from One-Class Embedding [2.715884199292287]
  We propose a novel T-S model consisting of a teacher encoder and a student decoder. Instead of receiving raw images directly, the student network takes teacher model's one-class embedding as input. In addition, we introduce a trainable one-class bottleneck embedding module in our T-S model.
  arXiv  Detail & Related papers  (2022-01-26T01:48:37Z)
• Co$^2$L: Contrastive Continual Learning [69.46643497220586]
  Recent breakthroughs in self-supervised learning show that such algorithms learn visual representations that can be transferred better to unseen tasks. We propose a rehearsal-based continual learning algorithm that focuses on continually learning and maintaining transferable representations.
  arXiv  Detail & Related papers  (2021-06-28T06:14:38Z)
• Unsupervised Class-Incremental Learning Through Confusion [0.4604003661048266]
  We introduce a novelty detection method that leverages network confusion caused by training incoming data as a new class. We found that incorporating a class-imbalance during this detection method substantially enhances performance.
  arXiv  Detail & Related papers  (2021-04-09T15:58:43Z)

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.