Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation

• URL: http://arxiv.org/abs/2006.03708v5
• Date: Wed, 19 Jan 2022 13:12:50 GMT
• Title: Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
• Abstract summary: Dilated convolutions are widely used in deep semantic segmentation models. However, dilated convolutional filters do not possess positional knowledge about the pixels on semantically meaningful contours. We propose the dilated convolution with lateral inhibitions (LI-Convs) to overcome these limitations.
• Score: 47.15129679400581
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dilated convolutions are widely used in deep semantic segmentation models as they can enlarge the filters' receptive field without adding additional weights nor sacrificing spatial resolution. However, as dilated convolutional filters do not possess positional knowledge about the pixels on semantically meaningful contours, they could lead to ambiguous predictions on object boundaries. In addition, although dilating the filter can expand its receptive field, the total number of sampled pixels remains unchanged, which usually comprises a small fraction of the receptive field's total area. Inspired by the Lateral Inhibition (LI) mechanisms in human visual systems, we propose the dilated convolution with lateral inhibitions (LI-Convs) to overcome these limitations. Introducing LI mechanisms improves the convolutional filter's sensitivity to semantic object boundaries. Moreover, since LI-Convs also implicitly take the pixels from the laterally inhibited zones into consideration, they can also extract features at a denser scale. By integrating LI-Convs into the Deeplabv3+ architecture, we propose the Lateral Inhibited Atrous Spatial Pyramid Pooling (LI-ASPP), the Lateral Inhibited MobileNet-V2 (LI-MNV2) and the Lateral Inhibited ResNet (LI-ResNet). Experimental results on three benchmark datasets (PASCAL VOC 2012, CelebAMask-HQ and ADE20K) show that our LI-based segmentation models outperform the baseline on all of them, thus verify the effectiveness and generality of the proposed LI-Convs.

Related papers

• VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement [14.35890716158584]
  VCAR is a training-free coarse-to-fine segmentation strategy based on View Completeness and Axis-aware Boundary Refinement.<n>VCAR achieves state-of-the-art segmentation accuracy and efficiency without training.
  arXiv  Detail & Related papers  (2026-08-31T14:32:26Z)
• PXDepth: Pixel-Space Modeling for Structure Preserving Monocular Depth Estimation [102.98521307122452]
  We propose PXDepth, a discriminative monocular depth model that separates global context modeling from pixel-level depth prediction.<n>Specifically, a large-patch ViT captures global scene context, while a pixel-space predictor composed of Context-Modulated Pixel Transformer blocks maintains high-resolution spatial representations.<n>This design preserves fine structures and sharp boundaries without sacrificing global depth consistency.
  arXiv  Detail & Related papers  (2026-08-17T18:00:02Z)
• FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction [63.738631229597274]
  Vision-based 3D occupancy prediction fundamentally relies on the 2D-to-3D view transformation.<n>Current paradigms predominantly utilize explicit physical projection, which artificially restricts the routing matrix to strict, sparse camera rays.<n>We propose Factorized Dense Routing (FDR) to break this bottleneck.<n>Our framework achieves state-the-art performance on the Occ3D-nuScenes and Occ3D-Waymo benchmarks.
  arXiv  Detail & Related papers  (2026-07-04T11:12:42Z)
• LACE: Loss-Adaptive Capacity Expansion for Continual Learning [0.0]
  LACE (Loss-Adaptive Capacity Expansion) is an online mechanism that expands a model's representational capacity during training.<n>LACE requires no labels, no replay buffers, and no external controllers, making it suitable for on-device continual learning under resource constraints.
  arXiv  Detail & Related papers  (2026-03-30T15:58:33Z)
• MirrorLA: Reflecting Feature Map for Vision Linear Attention [49.41670925034762]
  Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance.<n>We propose MirrorLA, a geometric framework that substitutes passive truncation with active reorientation.<n>MirrorLA achieves state-of-the-art performance across standard benchmarks, demonstrating that strictly linear efficiency can be achieved without compromising representational fidelity.
  arXiv  Detail & Related papers  (2026-02-04T09:14:09Z)
• LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning [26.88556500272625]
  We propose a novel 3D variational autoencoder framework built upon unsigned distance fields (UDFs)<n>Our core innovation is a local-to-global architecture that processes the UDF by partitioning it into uniform subvolumes, UBlocks.<n> Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility.
  arXiv  Detail & Related papers  (2025-11-13T07:34:43Z)
• HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping [11.035994094874141]
  HBSplat is a framework that seamlessly integrates robust structural cues, virtual view constraints, and occluded region completion.<n> HBSplat sets a new state-of-the-art, achieving up to 21.13 dB PSNR and 0.189 LPIPS, while maintaining real-time inference.
  arXiv  Detail & Related papers  (2025-09-29T15:03:31Z)
• Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception [71.26728044621458]
  DeCLIP is a novel framework that enhances CLIP by decoupling the self-attention module to obtain content'' and context'' features respectively.<n>It consistently achieves state-of-the-art performance across a broad spectrum of tasks, including 2D detection and segmentation, 3D instance segmentation, video instance segmentation, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2025-08-15T06:43:51Z)
• LIRA: Inferring Segmentation in Large Multi-modal Models with Local Interleaved Region Assistance [56.474856189865946]
  Large multi-modal models (LMMs) struggle with inaccurate segmentation and hallucinated comprehension.<n>We propose LIRA, a framework that capitalizes on the complementary relationship between visual comprehension and segmentation.<n>LIRA achieves state-of-the-art performance in both segmentation and comprehension tasks.
  arXiv  Detail & Related papers  (2025-07-08T07:46:26Z)
• FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception [7.258172311752019]
  Overlapping object perception aims to decouple the randomly overlapping foreground-background features, extracting foreground features while suppressing background features, which holds significant application value in fields such as security screening and medical auxiliary diagnosis.<n>We propose a general Frequency-based Anti-Overlapping Framework (FOAM) to assist the model in extracting more texture and contour information.<n>Specifically, we design the Frequency Spatial Transformer Block (FSTB), which can simultaneously extract features from both the frequency and spatial domains, helping the network capture more texture features from the foreground.
  arXiv  Detail & Related papers  (2025-06-16T13:58:49Z)
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior [64.71091831762214]
  Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture, is intriguing for downstream applications. Recent approaches incorporate semantic or geometric regularization to address this issue, but they suffer significant degradation in underconstrained areas. We propose DP-Recon, which employs diffusion priors in the form of Score Distillation Sampling (SDS) to optimize the neural representation of each individual object under novel views.
  arXiv  Detail & Related papers  (2025-03-19T02:11:31Z)
• Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation [79.66299178949257]
  Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. vision-language foundation models, especially CLIP, have emerged as powerful tools for acquiring open-vocabulary capabilities. H-CLIP achieves new SOTA open-vocabulary semantic segmentation results while only requiring updating approximately 4% of the total parameters of CLIP.
  arXiv  Detail & Related papers  (2024-05-29T07:41:34Z)
• Fourier Boundary Features Network with Wider Catchers for Glass Segmentation [12.465008923418406]
  We propose a new method for constraining the segmentation of reflection surface and penetrating glass. The proposed method yields better segmentation performance compared with the state-of-the-art (SOTA) methods in glass image segmentation.
  arXiv  Detail & Related papers  (2024-05-15T15:52:27Z)
• Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks [82.03459331544737]
  We study the performance of ConvResNeXts, trained with weight decay from the perspective of nonparametric classification. Our analysis allows for infinitely many building blocks in ConvResNeXts, and shows that weight decay implicitly enforces sparsity on these blocks.
  arXiv  Detail & Related papers  (2023-07-04T11:08:03Z)
• A bioinspired three-stage model for camouflaged object detection [8.11866601771984]
  We propose a three-stage model that enables coarse-to-fine segmentation in a single iteration. Our model employs three decoders to sequentially process subsampled features, cropped features, and high-resolution original features. Our network surpasses state-of-the-art CNN-based counterparts without unnecessary complexities.
  arXiv  Detail & Related papers  (2023-05-22T02:01:48Z)
• OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detection [51.153003057515754]
  OPA-3D is a single-stage, end-to-end, Occlusion-Aware Pixel-Wise Aggregation network. It jointly estimates dense scene depth with depth-bounding box residuals and object bounding boxes. It outperforms state-of-the-art methods on the main Car category.
  arXiv  Detail & Related papers  (2022-11-02T14:19:13Z)
• Object-aware Monocular Depth Prediction with Instance Convolutions [72.98771405534937]
  We propose a novel convolutional operator which is explicitly tailored to avoid feature aggregation. Our method is based on estimating per-part depth values by means of superpixels. Our evaluation with respect to the NYUv2 as well as the iBims dataset clearly demonstrates the superiority of Instance Convolutions.
  arXiv  Detail & Related papers  (2021-12-02T18:59:48Z)
• Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition Kernels [24.266548097679973]
  We propose a concept of decomposition kernels for light field super-composition. In particular, we systematically unify the decomposition operations of various sub-spaces into a series of such decomposition kernels. The proposed DKNet is experimentally verified to achieve substantial improvements by 1.35 dB, 0.83 textures, and 1.80 dB PSNR in 2x, 3x and 4x LFSR scales.
  arXiv  Detail & Related papers  (2021-11-07T12:47:12Z)
• S3Net: 3D LiDAR Sparse Semantic Segmentation Network [1.330528227599978]
  S3Net is a novel convolutional neural network for LiDAR point cloud semantic segmentation. It adopts an encoder-decoder backbone that consists of Sparse Intra-channel Attention Module (SIntraAM) and Sparse Inter-channel Attention Module (SInterAM)
  arXiv  Detail & Related papers  (2021-03-15T22:15:24Z)
• Cylindrical Convolutional Networks for Joint Object Detection and Viewpoint Estimation [76.21696417873311]
  We introduce a learnable module, cylindrical convolutional networks (CCNs), that exploit cylindrical representation of a convolutional kernel defined in the 3D space. CCNs extract a view-specific feature through a view-specific convolutional kernel to predict object category scores at each viewpoint. Our experiments demonstrate the effectiveness of the cylindrical convolutional networks on joint object detection and viewpoint estimation.
  arXiv  Detail & Related papers  (2020-03-25T10:24:58Z)

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.