DeepHash: Getting Regularization, Depth and Fine-Tuning Right
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing scheme based on deep networks. Key to making DeepHash work at extremely low bitrates are three important considerations -- regularization, depth and fine-tuning -- each requiring solutions specific to the hashing problem. In-depth evaluation shows that our scheme consistently outperforms state-of-the-art methods across all data sets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 20 percent over other schemes. The retrieval performance with 256-bit hashes is close to that of the uncompressed floating point features -- a remarkable 512 times compression.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
Before sufficient training data is available, fine-tuning neural networks pre-trained on large-scale datasets substantially outperforms training from random initialization. However, fine-tuning methods suffer from two di…
Transfer LearningWhy Fine-Tuning Struggles with Forgetting in Machine Unlearning? Theoretical Insights and a Remedial Approach
Machine Unlearning has emerged as a significant area of research, focusing on 'removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approxima…
Machine UnlearningProxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting
Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuning foundation models on one task often l…
image-classificationImage ClassificationVisual Question Answering (VQA)Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less
Optimizers play an important role in both pretraining and finetuning stages when training large language models (LLMs). In this paper, we present an observation that full finetuning with the same optimizer as in pretrain…
Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
Catastrophic forgetting remains a critical challenge in continual learning for large language models (LLMs), where models struggle to retain performance on historical tasks when fine-tuning on new sequential data without…
Continual Learning