Progressive Local Filter Pruning for Image Retrieval Acceleration

• URL: http://arxiv.org/abs/2001.08878v1
• Date: Fri, 24 Jan 2020 04:28:44 GMT
• Title: Progressive Local Filter Pruning for Image Retrieval Acceleration
• Authors: Xiaodong Wang, Zhedong Zheng, Yang He, Fei Yan, Zhiqiang Zeng, Yi Yang
• Abstract summary: We propose a new Progressive Local Filter Pruning (PLFP) method for image retrieval acceleration. Specifically, layer by layer, we analyze the local geometric properties of each filter and select the one that can be replaced by the neighbors. In this way, the representation ability of the model is preserved.
• Score: 43.97722250091591
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the model inference, which should be taken into consideration in real-world practice. The challenge of pruning image retrieval models is that the middle-level feature should be preserved as much as possible. Such different requirements of the retrieval and classification model make the traditional pruning methods not that suitable for our task. To solve the problem, we propose a new Progressive Local Filter Pruning (PLFP) method for image retrieval acceleration. Specifically, layer by layer, we analyze the local geometric properties of each filter and select the one that can be replaced by the neighbors. Then we progressively prune the filter by gradually changing the filter weights. In this way, the representation ability of the model is preserved. To verify this, we evaluate our method on two widely-used image retrieval datasets,i.e., Oxford5k and Paris6K, and one person re-identification dataset,i.e., Market-1501. The proposed method arrives with superior performance to the conventional pruning methods, suggesting the effectiveness of the proposed method for image retrieval.

Related papers

• Local Descriptors Weighted Adaptive Threshold Filtering For Few-Shot Learning [0.0]
  Few-shot image classification is a challenging task in the field of machine learning. We propose an innovative weighted adaptive threshold filtering (WATF) strategy for local descriptors. Our method maintains a simple and lightweight design philosophy without additional learnable parameters.
  arXiv  Detail & Related papers  (2024-08-28T16:36:23Z)
• DeepClean: Integrated Distortion Identification and Algorithm Selection for Rectifying Image Corruptions [1.8024397171920883]
  We propose a two-level sequential planning approach for automated image distortion classification and rectification. The advantage of our approach is its dynamic reconfiguration, conditioned on the input image and generalisability to unseen candidate algorithms at inference time.
  arXiv  Detail & Related papers  (2024-07-23T08:57:11Z)
• F$^3$Loc: Fusion and Filtering for Floorplan Localization [63.28504055661646]
  We propose an efficient data-driven solution to self-localization within a floorplan. Our method does not require retraining per map and location or demand a large database of images of the area of interest.
  arXiv  Detail & Related papers  (2024-03-05T23:32:26Z)
• Image Completion via Dual-path Cooperative Filtering [17.62197747945094]
  We propose a predictive filtering method for restoring images based on the input scene. Deep feature-level semantic filtering is introduced to fill in missing information. Experiments on three challenging image completion datasets show that our proposed DCF outperforms state-of-art methods.
  arXiv  Detail & Related papers  (2023-04-30T03:54:53Z)
• PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matching [51.142988196855484]
  We propose PoseMatcher, an accurate model free one-shot object pose estimator. We create a new training pipeline for object to image matching based on a three-view system. To enable PoseMatcher to attend to distinct input modalities, an image and a pointcloud, we introduce IO-Layer.
  arXiv  Detail & Related papers  (2023-04-03T21:14:59Z)
• Pattern Spotting and Image Retrieval in Historical Documents using Deep Hashing [60.67014034968582]
  This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. Deep learning models are used for feature extraction, considering two distinct variants, which provide either real-valued or binary code representations. The proposed approach also reduces the search time by up to 200x and the storage cost up to 6,000x when compared to related works.
  arXiv  Detail & Related papers  (2022-08-04T01:39:37Z)
• Fast Hybrid Image Retargeting [0.0]
  We propose a method that quantifies and limits warping distortions with the use of content-aware cropping. Our method outperforms recent approaches, while running in a fraction of their execution time.
  arXiv  Detail & Related papers  (2022-03-25T11:46:06Z)
• Region-level Active Learning for Cluttered Scenes [60.93811392293329]
  We introduce a new strategy that subsumes previous Image-level and Object-level approaches into a generalized, Region-level approach. We show that this approach significantly decreases labeling effort and improves rare object search on realistic data with inherent class-imbalance and cluttered scenes.
  arXiv  Detail & Related papers  (2021-08-20T14:02:38Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Efficient image retrieval using multi neural hash codes and bloom filters [0.0]
  This paper delivers an efficient and modified approach for image retrieval using multiple neural hash codes. It also limits the number of queries using bloom filters by identifying false positives beforehand.
  arXiv  Detail & Related papers  (2020-11-06T08:46:31Z)

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.