On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

• URL: http://arxiv.org/abs/2106.07091v1
• Date: Sun, 13 Jun 2021 20:55:16 GMT
• Title: On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
• Abstract summary: We show that OOCS pathways complement each other in their response to light stimuli, ensuring this way a strong edge-detection capability. We provide empirical evidence showing that networks supplied with the OOCS edge representation gain accuracy and illumination-robustness compared to standard deep models.
• Score: 54.73738206624343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks with two residual components, ubiquitous in the visual processing system of vertebrates: On-center and off-center pathways, with excitatory center and inhibitory surround; OOCS for short. The on-center pathway is excited by the presence of a light stimulus in its center but not in its surround, whereas the off-center one is excited by the absence of a light stimulus in its center but not in its surround. We design OOCS pathways via a difference of Gaussians, with their variance computed analytically from the size of the receptive fields. OOCS pathways complement each other in their response to light stimuli, ensuring this way a strong edge-detection capability, and as a result, an accurate and robust inference under challenging lighting conditions. We provide extensive empirical evidence showing that networks supplied with the OOCS edge representation gain accuracy and illumination-robustness compared to standard deep models.

Related papers

• Optical linewidth narrowing for device-coupled single T centers [0.0]
  Single T centers in silicon have emerged as promising optically active spins for quantum networking applications.<n>One of the major obstacles to advancing the system is their broad optical linewidth due to spectral diffusion.<n>We tackle this issue by utilizing above-band optical excitation delivered via a laser scanning microscope to device-coupled single T centers.
  arXiv  Detail & Related papers  (2026-07-30T16:37:52Z)
• Current Injection Spiking Neural Network for Infrared and Visible Image Fusion [55.20584003351512]
  Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content.<n>We propose CIS-Fuse, a spiking network that performs cross-modal fusion directly at the membrane-potential level.<n>Experiments on four IVIF benchmarks and on downstream detection and segmentation show that CIS-Fuse achieves fusion quality on par with state-of-the-art ANN-based methods.
  arXiv  Detail & Related papers  (2026-07-22T08:10:02Z)
• Debiasing Central Fixation Confounds Reveals a Peripheral "Sweet Spot" for Human-like Scanpaths in Hard-Attention Vision [0.0]
  Task-driven hard-attention models for vision are often evaluated by how well their scanpaths match human gaze.<n>We show that a trivial center-fixation baseline achieves surprisingly strong scanpath scores, approaching many learned policies.<n>We propose GCS, a center-debiased composite metric augmented with movement similarity.
  arXiv  Detail & Related papers  (2026-02-16T15:25:26Z)
• Center Focusing Network for Real-Time LiDAR Panoptic Segmentation [58.1194137706868]
  A novel center focusing network (CFNet) is introduced to achieve accurate and real-time LiDAR panoptic segmentation. CFFE is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers. Our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method.
  arXiv  Detail & Related papers  (2023-11-16T01:52:11Z)
• Exploring Geometry of Blind Spots in Vision Models [56.47644447201878]
  We study the phenomenon of under-sensitivity in vision models such as CNNs and Transformers. We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space. We estimate the extent of these connected higher-dimensional regions over which the model maintains a high degree of confidence.
  arXiv  Detail & Related papers  (2023-10-30T18:00:33Z)
• Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression [41.24757573290883]
  We design a compact neural network representation for the light field compression task. It is composed of two types of complementary kernels: descriptive kernels (descriptors) that store scene description information learned during training, and modulatory kernels (modulators) that control the rendering of different SAIs from the queried perspectives.
  arXiv  Detail & Related papers  (2023-07-12T12:58:03Z)
• Learnable Differencing Center for Nighttime Depth Perception [39.455428679154934]
  We propose a simple yet effective framework called LDCNet. Our key idea is to use Recurrent Inter-Convolution Differencing (RICD) and Illumination-Affinitive Intra-Convolution Differencing (IAICD) to enhance the nighttime color images. On both nighttime depth completion and depth estimation tasks, extensive experiments demonstrate the effectiveness of our LDCNet.
  arXiv  Detail & Related papers  (2023-06-26T09:21:13Z)
• When Spectral Modeling Meets Convolutional Networks: A Method for Discovering Reionization-era Lensed Quasars in Multi-band Imaging Data [0.0]
  We introduce a new spatial geometry veto criterion, implemented via image-based deep learning. We make the first application of this approach in a systematic search for reionization-era lensed quasars. The training datasets are constructed by painting deflected point-source lights over actual galaxy images to generate realistic galaxy-quasar lens models.
  arXiv  Detail & Related papers  (2022-11-26T11:27:13Z)
• Effect of Localization on Photoluminescence and Zero-Field Splitting of Silicon Color Centers [3.324869575908454]
  A number of silicon defect centers emit single photons in the telecommunication $O$-band. The two-carbon G-center, self-interstitial W-center, and spin-$1/2$ T-center are the most intensively studied silicon defect centers. Motivation is provided for how these properties are intimately related to the localization of electronic states in the defect centers.
  arXiv  Detail & Related papers  (2022-06-10T01:02:08Z)
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images [82.1679766706423]
  Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. We propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs. Our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2021-10-27T07:18:32Z)
• SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments [50.761917113239996]
  We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences without dense depth labels. Our self-supervised algorithm is designed for challenging indoor environments with textureless regions, glossy and transparent surface, non-Lambertian surfaces, moving people, longer and diverse depth ranges and scenes captured by complex ego-motions.
  arXiv  Detail & Related papers  (2020-11-10T08:55:07Z)
• A Parallel Down-Up Fusion Network for Salient Object Detection in Optical Remote Sensing Images [82.87122287748791]
  We propose a novel Parallel Down-up Fusion network (PDF-Net) for salient object detection in optical remote sensing images (RSIs) It takes full advantage of the in-path low- and high-level features and cross-path multi-resolution features to distinguish diversely scaled salient objects and suppress the cluttered backgrounds. Experiments on the ORSSD dataset demonstrate that the proposed network is superior to the state-of-the-art approaches both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2020-10-02T05:27:57Z)
• View-consistent 4D Light Field Depth Estimation [37.04038603184669]
  We propose a method to compute depth maps for every sub-aperture image in a light field in a view consistent way. Our method precisely defines depth edges via EPIs, then we diffuse these edges spatially within the central view.
  arXiv  Detail & Related papers  (2020-09-09T01:47:34Z)

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.