Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning

• URL: http://arxiv.org/abs/2503.14824v1
• Date: Wed, 19 Mar 2025 01:45:48 GMT
• Title: Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning
• Authors: Zikun Zhou, Yushuai Sun, Wenjie Pei, Xin Li, Yaowei Wang,
• Abstract summary: We develop two approaches for calculating the perturbations: Neighbor-Driven Prototype Perturbation (NDPP) and Optimization-Driven Prototype Perturbation (ODPP)<n>Our approaches perform favorably against state-of-the-art BCL algorithms.
• Score: 43.8412077229831
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The traditional paradigm to update retrieval models requires re-computing the embeddings of the gallery data, a time-consuming and computationally intensive process known as backfilling. To circumvent backfilling, Backward-Compatible Learning (BCL) has been widely explored, which aims to train a new model compatible with the old one. Many previous works focus on effectively aligning the embeddings of the new model with those of the old one to enhance the backward-compatibility. Nevertheless, such strong alignment constraints would compromise the discriminative ability of the new model, particularly when different classes are closely clustered and hard to distinguish in the old feature space. To address this issue, we propose to relax the constraints by introducing perturbations to the old feature prototypes. This allows us to align the new feature space with a pseudo-old feature space defined by these perturbed prototypes, thereby preserving the discriminative ability of the new model in backward-compatible learning. We have developed two approaches for calculating the perturbations: Neighbor-Driven Prototype Perturbation (NDPP) and Optimization-Driven Prototype Perturbation (ODPP). Particularly, they take into account the feature distributions of not only the old but also the new models to obtain proper perturbations along with new model updating. Extensive experiments on the landmark and commodity datasets demonstrate that our approaches perform favorably against state-of-the-art BCL algorithms.

Related papers

• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer [20.96380700548786]
  Visual retrieval systems face challenges when updating models with improved representations due to misalignment between the old and new representations. Prior research has explored backward-compatible training methods that enable direct comparisons between new and old representations without backfilling. In this paper, we address achieving a balance between backward compatibility and the performance of independently trained models.
  arXiv  Detail & Related papers  (2024-08-16T15:05:28Z)
• Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation [56.1776710527814]
  Weakly Incremental Learning for Semantic (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed areas for each new class, serving as a form of pixel-level supervision. We propose an innovative, tendency-driven relationship of mutual exclusivity, meticulously tailored to govern the behavior of the seed areas.
  arXiv  Detail & Related papers  (2024-04-18T08:23:24Z)
• Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning [65.57123249246358]
  We propose ExpAndable Subspace Ensemble (EASE) for PTM-based CIL. We train a distinct lightweight adapter module for each new task, aiming to create task-specific subspaces. Our prototype complement strategy synthesizes old classes' new features without using any old class instance.
  arXiv  Detail & Related papers  (2024-03-18T17:58:13Z)
• MixBCT: Towards Self-Adapting Backward-Compatible Training [66.52766344751635]
  We propose MixBCT, a simple yet highly effective backward-compatible training method. We conduct experiments on the large-scale face recognition datasets MS1Mv3 and IJB-C.
  arXiv  Detail & Related papers  (2023-08-14T05:55:38Z)
• Darwinian Model Upgrades: Model Evolving with Selective Compatibility [29.920204547961696]
  BCT presents the first step towards backward-compatible model upgrades to get rid of backfilling. We propose Darwinian Model Upgrades (DMU) which disentangle the inheritance and variation in the model evolving with selective backward compatibility and forward adaptation. DMU effectively alleviates the new-to-new degradation and improves new-to-old compatibility, rendering a more proper model upgrading paradigm in large-scale retrieval systems.
  arXiv  Detail & Related papers  (2022-10-13T12:28:48Z)
• Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation [46.86784621137665]
  backward-compatible representation is proposed to enable the "new" features compatible with "old"' features. We propose a Neighborhood Consensus Contrastive Learning (NCCL) method, which learns backward-compatible representation from a neighborhood consensus perspective. Our method ensures backward compatibility without impairing the accuracy of the new model.
  arXiv  Detail & Related papers  (2021-08-07T05:50:47Z)

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.