Distilling Channels for Efficient Deep Tracking

• URL: http://arxiv.org/abs/2409.11785v1
• Date: Wed, 18 Sep 2024 08:09:20 GMT
• Title: Distilling Channels for Efficient Deep Tracking
• Authors: Shiming Ge, Zhao Luo, Chunhui Zhang, Yingying Hua, Dacheng Tao,
• Abstract summary: This paper presents a novel framework termed channel distillation to facilitate deep trackers. We show that an integrated formulation can turn feature compression, response map generation, and model update into a unified energy minimization problem. The resulting deep tracker is accurate, fast, and has low memory requirements.
• Score: 68.13422829310835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep trackers have proven success in visual tracking. Typically, these trackers employ optimally pre-trained deep networks to represent all diverse objects with multi-channel features from some fixed layers. The deep networks employed are usually trained to extract rich knowledge from massive data used in object classification and so they are capable to represent generic objects very well. However, these networks are too complex to represent a specific moving object, leading to poor generalization as well as high computational and memory costs. This paper presents a novel and general framework termed channel distillation to facilitate deep trackers. To validate the effectiveness of channel distillation, we take discriminative correlation filter (DCF) and ECO for example. We demonstrate that an integrated formulation can turn feature compression, response map generation, and model update into a unified energy minimization problem to adaptively select informative feature channels that improve the efficacy of tracking moving objects on the fly. Channel distillation can accurately extract good channels, alleviating the influence of noisy channels and generally reducing the number of channels, as well as adaptively generalizing to different channels and networks. The resulting deep tracker is accurate, fast, and has low memory requirements. Extensive experimental evaluations on popular benchmarks clearly demonstrate the effectiveness and generalizability of our framework.

Related papers

• Joint Channel Estimation and Feedback with Masked Token Transformers in Massive MIMO Systems [74.52117784544758]
  This paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix. The entire encoder-decoder network is utilized for channel compression. Our method outperforms state-of-the-art channel estimation and feedback techniques in joint tasks.
  arXiv  Detail & Related papers  (2023-06-08T06:15:17Z)
• CATRO: Channel Pruning via Class-Aware Trace Ratio Optimization [61.71504948770445]
  We propose a novel channel pruning method via Class-Aware Trace Ratio Optimization (CATRO) to reduce the computational burden and accelerate the model inference. We show that CATRO achieves higher accuracy with similar cost or lower cost with similar accuracy than other state-of-the-art channel pruning algorithms. Because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.
  arXiv  Detail & Related papers  (2021-10-21T06:26:31Z)
• Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs [36.479195100553085]
  Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret. We analyze theoretically channel-wise non-negative kernel (CW-NNK) regression graphs to quantify the overlap between channels. We find that redundancy between channels is significant and varies with the layer depth and the level of regularization.
  arXiv  Detail & Related papers  (2021-10-18T22:50:07Z)
• Robust MIMO Detection using Hypernetworks with Learned Regularizers [28.917679125825]
  We propose a method that tries to strike a balance between symbol error rate (SER) performance and generality of channels. Our method is based on hypernetworks that generate the parameters of a neural network-based detector that works well on a specific channel.
  arXiv  Detail & Related papers  (2021-10-13T22:07:13Z)
• Group Fisher Pruning for Practical Network Compression [58.25776612812883]
  We present a general channel pruning approach that can be applied to various complicated structures. We derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Our method can be used to prune any structures including those with coupled channels.
  arXiv  Detail & Related papers  (2021-08-02T08:21:44Z)
• Channel-wise Knowledge Distillation for Dense Prediction [73.99057249472735]
  We propose to align features channel-wise between the student and teacher networks. We consistently achieve superior performance on three benchmarks with various network structures.
  arXiv  Detail & Related papers  (2020-11-26T12:00:38Z)
• Operation-Aware Soft Channel Pruning using Differentiable Masks [51.04085547997066]
  We propose a data-driven algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. We perform extensive experiments and achieve outstanding performance in terms of the accuracy of output networks.
  arXiv  Detail & Related papers  (2020-07-08T07:44:00Z)
• Hybrid Channel Based Pedestrian Detection [15.696919306737321]
  We propose a new pedestrian detection framework, which extends the successful RPN+BF framework to combine handcrafted features and CNN features. Our experiments show that the developed handcrafted features can reach better detection accuracy than the CNN features extracted from the VGG-16 net.
  arXiv  Detail & Related papers  (2019-12-28T09:55:35Z)

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.