Visual Detector Compression via Location-Aware Discriminant Analysis

• URL: http://arxiv.org/abs/2509.17968v1
• Date: Mon, 22 Sep 2025 16:19:00 GMT
• Title: Visual Detector Compression via Location-Aware Discriminant Analysis
• Authors: Qizhen Lan, Jung Im Choi, Qing Tian,
• Abstract summary: We propose a proactive detection-discriminants-based network compression approach for deep visual detectors.<n>Our approach can even beat the original base models with a substantial reduction in complexity.
• Score: 1.0773370323095608
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks are powerful, yet their high complexity greatly limits their potential to be deployed on billions of resource-constrained edge devices. Pruning is a crucial network compression technique, yet most existing methods focus on classification models, with limited attention to detection. Even among those addressing detection, there is a lack of utilization of essential localization information. Also, many pruning methods passively rely on pre-trained models, in which useful and useless components are intertwined, making it difficult to remove the latter without harming the former at the neuron/filter level. To address the above issues, in this paper, we propose a proactive detection-discriminants-based network compression approach for deep visual detectors, which alternates between two steps: (1) maximizing and compressing detection-related discriminants and aligning them with a subset of neurons/filters immediately before the detection head, and (2) tracing the detection-related discriminating power across the layers and discarding features of lower importance. Object location information is exploited in both steps. Extensive experiments, employing four advanced detection models and four state-of-the-art competing methods on the KITTI and COCO datasets, highlight the superiority of our approach. Remarkably, our compressed models can even beat the original base models with a substantial reduction in complexity.

Related papers

• A Benchmark Study of Neural Network Compression Methods for Hyperspectral Image Classification [0.0]
  compression techniques have been proposed to reduce model size and computational cost while maintaining predictive performance.<n>We examine three widely used compression strategies for convolutional neural networks: pruning, quantization, and knowledge distillation.<n>Our results demonstrate that compressed models can significantly reduce model size and computational cost while maintaining competitive classification performance.
  arXiv  Detail & Related papers  (2026-03-05T01:48:30Z)
• A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks [6.537257913467249]
  We present a highly compact run-time monitoring approach for deep computer vision networks. It can efficiently detect silent data corruption originating from both hardware memory and input faults.
  arXiv  Detail & Related papers  (2023-10-31T10:45:55Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Hyperbolic Self-supervised Contrastive Learning Based Network Anomaly Detection [0.0]
  Anomaly detection on the attributed network has recently received increasing attention in many research fields. We propose an efficient anomaly detection framework using hyperbolic self-supervised contrastive learning.
  arXiv  Detail & Related papers  (2022-09-12T07:08:34Z)
• Generalizing Face Forgery Detection with High-frequency Features [63.33397573649408]
  Current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize. We propose to utilize the high-frequency noises for face forgery detection. The first is the multi-scale high-frequency feature extraction module that extracts high-frequency noises at multiple scales. The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective.
  arXiv  Detail & Related papers  (2021-03-23T08:19:21Z)
• Multi-attentional Deepfake Detection [79.80308897734491]
  Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. We propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps.
  arXiv  Detail & Related papers  (2021-03-03T13:56:14Z)
• Video Anomaly Detection Using Pre-Trained Deep Convolutional Neural Nets and Context Mining [2.0646127669654835]
  We show how to use pre-trained convolutional neural net models to perform feature extraction and context mining. We derive contextual properties from the high-level features to further improve the performance of our video anomaly detection method.
  arXiv  Detail & Related papers  (2020-10-06T00:26:14Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)
• Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread [136.2224792151324]
  We propose a new deep learning algorithm for fast salient object detection. The proposed algorithm achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
  arXiv  Detail & Related papers  (2020-01-22T15:23:48Z)

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.