Minimizing Embedding Distortion for Robust Out-of-Distribution Performance

• URL: http://arxiv.org/abs/2409.07582v1
• Date: Wed, 11 Sep 2024 19:22:52 GMT
• Title: Minimizing Embedding Distortion for Robust Out-of-Distribution Performance
• Authors: Tom Shaked, Yuval Goldman, Oran Shayer,
• Abstract summary: We introduce a novel approach we call "similarity loss", which can be incorporated into the fine-tuning process of any task. We evaluate our approach on two diverse tasks: image classification on satellite imagery and face recognition.
• Score: 1.0923877073891446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundational models, trained on vast and diverse datasets, have demonstrated remarkable capabilities in generalizing across different domains and distributions for various zero-shot tasks. Our work addresses the challenge of retaining these powerful generalization capabilities when adapting foundational models to specific downstream tasks through fine-tuning. To this end, we introduce a novel approach we call "similarity loss", which can be incorporated into the fine-tuning process of any task. By minimizing the distortion of fine-tuned embeddings from the pre-trained embeddings, our method strikes a balance between task-specific adaptation and preserving broad generalization abilities. We evaluate our approach on two diverse tasks: image classification on satellite imagery and face recognition, focusing on open-class and domain shift scenarios to assess out-of-distribution (OOD) performance. We demonstrate that this approach significantly improves OOD performance while maintaining strong in-distribution (ID) performance.

Related papers

• InvFussion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems [76.39776789410088]
  This work introduces a framework that combines the strong performance of supervised approaches and the flexibility of zero-shot methods. A novel architectural design seamlessly integrates the degradation operator directly into the denoiser. Experimental results on the FFHQ and ImageNet datasets demonstrate state-of-the-art posterior-sampling performance.
  arXiv  Detail & Related papers  (2025-04-02T12:40:57Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective [17.394732703591462]
  We propose a framework to jointly optimize the pruning mask and weight update processes with fairness constraints. This framework is engineered to compress models that maintain performance while ensuring fairness in a single execution. Our empirical analysis contrasts our framework with several mainstream pruning strategies, emphasizing our method's superiority in maintaining model fairness, performance, and efficiency.
  arXiv  Detail & Related papers  (2023-12-15T20:08:53Z)
• ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation [23.621454800084724]
  We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.
  arXiv  Detail & Related papers  (2023-02-20T05:15:23Z)
• Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification [0.0]
  This paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. We put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-25T10:10:48Z)
• Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks [73.63892022944198]
  We present a generic perception architecture named Uni-Perceiver. It processes a variety of modalities and tasks with unified modeling and shared parameters. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks.
  arXiv  Detail & Related papers  (2021-12-02T18:59:50Z)
• Variational Disentanglement for Domain Generalization [68.85458536180437]
  We propose to tackle the problem of domain generalization by delivering an effective framework named Variational Disentanglement Network (VDN) VDN is capable of disentangling the domain-specific features and task-specific features, where the task-specific features are expected to be better generalized to unseen but related test data.
  arXiv  Detail & Related papers  (2021-09-13T09:55:32Z)
• Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning [6.247939901619901]
  We show that in certain settings, the available data can be dramatically increased through a form of multi-task learning. We provide a theoretical performance bound for the gain in sample efficiency under this setting. This motivates a new approach to multi-task learning, which involves the design of an appropriate neural network architecture and a prioritized task-sampling strategy.
  arXiv  Detail & Related papers  (2021-02-18T14:13:02Z)
• Style Normalization and Restitution for DomainGeneralization and Adaptation [88.86865069583149]
  An effective domain generalizable model is expected to learn feature representations that are both generalizable and discriminative. In this paper, we design a novel Style Normalization and Restitution module (SNR) to ensure both high generalization and discrimination capability of the networks.
  arXiv  Detail & Related papers  (2021-01-03T09:01:39Z)
• Spectrum-Guided Adversarial Disparity Learning [52.293230153385124]
  We propose a novel end-to-end knowledge directed adversarial learning framework. It portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity. The experiments on four HAR benchmark datasets demonstrate the robustness and generalization of our proposed methods over a set of state-of-the-art.
  arXiv  Detail & Related papers  (2020-07-14T05:46:27Z)
• Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
  We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
  arXiv  Detail & Related papers  (2020-06-12T12:23:50Z)

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.