LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving

• URL: http://arxiv.org/abs/2403.08215v1
• Date: Wed, 13 Mar 2024 03:24:36 GMT
• Title: LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving
• Authors: Sicen Guo, Zhiyuan Wu, Qijun Chen, Ioannis Pitas and Rui Fan
• Abstract summary: We introduce the Learning to Infuse "X" (LIX) framework, with novel contributions in both logit distillation and feature distillation aspects. We develop an adaptively-recalibrated feature distillation algorithm, including two technical novelties.
• Score: 26.319489913682574
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the impressive performance achieved by data-fusion networks with duplex encoders for visual semantic segmentation, they become ineffective when spatial geometric data are not available. Implicitly infusing the spatial geometric prior knowledge acquired by a duplex-encoder teacher model into a single-encoder student model is a practical, albeit less explored research avenue. This paper delves into this topic and resorts to knowledge distillation approaches to address this problem. We introduce the Learning to Infuse "X" (LIX) framework, with novel contributions in both logit distillation and feature distillation aspects. We present a mathematical proof that underscores the limitation of using a single fixed weight in decoupled knowledge distillation and introduce a logit-wise dynamic weight controller as a solution to this issue. Furthermore, we develop an adaptively-recalibrated feature distillation algorithm, including two technical novelties: feature recalibration via kernel regression and in-depth feature consistency quantification via centered kernel alignment. Extensive experiments conducted with intermediate-fusion and late-fusion networks across various public datasets provide both quantitative and qualitative evaluations, demonstrating the superior performance of our LIX framework when compared to other state-of-the-art approaches.

Related papers

• On Distilling the Displacement Knowledge for Few-Shot Class-Incremental Learning [17.819582979803286]
  Few-shot Class-Incremental Learning (FSCIL) addresses the challenges of evolving data distributions and the difficulty of data acquisition in real-world scenarios. To counteract the catastrophic forgetting typically encountered in FSCIL, knowledge distillation is employed as a way to maintain the knowledge from learned data distribution.
  arXiv  Detail & Related papers  (2024-12-15T02:10:18Z)
• HSLiNets: Hyperspectral Image and LiDAR Data Fusion Using Efficient Dual Non-Linear Feature Learning Networks [7.06787067270941]
  The integration of hyperspectral imaging (HSI) and LiDAR data within new linear feature spaces offers a promising solution to the challenges posed by the high-dimensionality and redundancy inherent in HSIs. This study introduces a dual linear fused space framework that capitalizes on bidirectional reversed convolutional neural network (CNN) pathways, coupled with a specialized spatial analysis block. The proposed method not only enhances data processing and classification accuracy, but also mitigates the computational burden typically associated with advanced models such as Transformers.
  arXiv  Detail & Related papers  (2024-11-30T01:08:08Z)
• Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
  We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture. We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
  arXiv  Detail & Related papers  (2024-09-20T07:41:47Z)
• A Generalization Theory of Cross-Modality Distillation with Contrastive Learning [49.35244441141323]
  Cross-modality distillation arises as an important topic for data modalities containing limited knowledge. We formulate a general framework of cross-modality contrastive distillation (CMCD), built upon contrastive learning. Our algorithm outperforms existing algorithms consistently by a margin of 2-3% across diverse modalities and tasks.
  arXiv  Detail & Related papers  (2024-05-06T11:05:13Z)
• Fully Differentiable Correlation-driven 2D/3D Registration for X-ray to CT Image Fusion [3.868072865207522]
  Image-based rigid 2D/3D registration is a critical technique for fluoroscopic guided surgical interventions. We propose a novel fully differentiable correlation-driven network using a dual-branch CNN-transformer encoder. A correlation-driven loss is proposed for low-frequency feature and high-frequency feature decomposition based on embedded information.
  arXiv  Detail & Related papers  (2024-02-04T14:12:51Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Generative Model-based Feature Knowledge Distillation for Action Recognition [11.31068233536815]
  Our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model. The efficacy of our approach is demonstrated through comprehensive experiments on diverse popular datasets.
  arXiv  Detail & Related papers  (2023-12-14T03:55:29Z)
• DUCK: Distance-based Unlearning via Centroid Kinematics [40.2428948628001]
  This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK) evaluation of the algorithm's performance is conducted across various benchmark datasets. We also introduce a novel metric, called Adaptive Unlearning Score (AUS), encompassing not only the efficacy of the unlearning process in forgetting target data but also quantifying the performance loss relative to the original model.
  arXiv  Detail & Related papers  (2023-12-04T17:10:25Z)
• AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation [12.92102548320001]
  This paper proposes a novel method called Inter-Class Similarity Distillation (ICSD) for the purpose of knowledge distillation. The proposed method transfers high-order relations from the teacher network to the student network by independently computing intra-class distributions for each class from network outputs. Experiments conducted on two well-known datasets for semantic segmentation, Cityscapes and Pascal VOC 2012, validate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-08-08T13:17:20Z)
• Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems? [56.62372517641597]
  Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range machine learning. This paper develops two novel decentralized minimax optimization algorithms for the non-strongly-nonconcave problem.
  arXiv  Detail & Related papers  (2023-04-24T02:19:39Z)
• EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval [83.79667141681418]
  Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR) We propose a novel distillation approach that leverages the relative geometry among queries and documents learned by the large teacher model. We show that our approach successfully distills from both dual-encoder (DE) and cross-encoder (CE) teacher models to 1/10th size asymmetric students that can retain 95-97% of the teacher performance.
  arXiv  Detail & Related papers  (2023-01-27T22:04:37Z)
• Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation [74.67594286008317]
  This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. We propose the Point-to-Voxel Knowledge Distillation (PVD), which transfers the hidden knowledge from both point level and voxel level.
  arXiv  Detail & Related papers  (2022-06-05T05:28:32Z)
• Bayesian Low-rank Matrix Completion with Dual-graph Embedding: Prior Analysis and Tuning-free Inference [16.82986562533071]
  We propose a novel Bayesian learning algorithm that automatically learns the hyper- parameters associated with dual-graph regularization. A novel prior is devised to promote the low-rankness of the matrix and encode the dual-graph information simultaneously. Experiments using synthetic and real-world datasets demonstrate the state-of-the-art performance of the proposed learning algorithm.
  arXiv  Detail & Related papers  (2022-03-18T16:38:30Z)
• On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
  Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
  arXiv  Detail & Related papers  (2022-03-08T09:57:48Z)
• Optimization-Based Separations for Neural Networks [57.875347246373956]
  We show that gradient descent can efficiently learn ball indicator functions using a depth 2 neural network with two layers of sigmoidal activations. This is the first optimization-based separation result where the approximation benefits of the stronger architecture provably manifest in practice.
  arXiv  Detail & Related papers  (2021-12-04T18:07:47Z)
• Extendable and invertible manifold learning with geometry regularized autoencoders [9.742277703732187]
  A fundamental task in data exploration is to extract simplified low dimensional representations that capture intrinsic geometry in data. Common approaches to this task use kernel methods for manifold learning. We present a new method for integrating both approaches by incorporating a geometric regularization term in the bottleneck of the autoencoder.
  arXiv  Detail & Related papers  (2020-07-14T15:59:10Z)
• One-Shot Object Detection without Fine-Tuning [62.39210447209698]
  We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
  arXiv  Detail & Related papers  (2020-05-08T01:59:23Z)
• Gradient tracking and variance reduction for decentralized optimization and machine learning [19.54092620537586]
  Decentralized methods to solve finite-sum problems are important in many signal processing and machine learning tasks. We provide a unified algorithmic framework that combines variance-reduction with gradient tracking to achieve robust performance.
  arXiv  Detail & Related papers  (2020-02-13T07:17:07Z)

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.