Search Results for author:
Found 21 papers, 5 papers with code
Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
(ii) Some datasets that are assumed to be biased toward dynamics are actually biased toward static information.
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information
To show the efficacy of our approach, we analyse two widely studied tasks, action recognition and video object segmentation.
Simpler Does It: Generating Semantic Labels with Objectness Guidance
Extensive experiments demonstrate the high quality of our generated pseudo-labels and effectiveness of the proposed framework in a variety of domains.
SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness
The premise is based on the notion of feature binding, which is defined as the process by which activations spread across space and layers in the network are successfully integrated to arrive at a correct inference decision.
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via global pooling removes all spatial information.
Fibro-CoSANet: Pulmonary Fibrosis Prognosis Prediction using a Convolutional Self Attention Network
Although lung function decline is assessed by the forced vital capacity (FVC), determining the accurate progression of IPF remains a challenge.
Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
; (ii) Does position encoding affect the learning of semantic representations?
Shape or Texture: Understanding Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a `texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Shape or Texture: Disentangling Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a 'texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Boundary Effects in CNNs: Feature or Bug?
Finally, we demonstrate the implications of these findings on a number of real-world tasks to show that position information can act as a feature or a bug.
Bidirectional Attention Network for Monocular Depth Estimation
In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks.
Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness
In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical information throughout the network.
How Much Position Information Do Convolutional Neural Networks Encode?
In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent.
Distributed Iterative Gating Networks for Semantic Segmentation
In this paper, we present a canonical structure for controlling information flow in neural networks with an efficient feedback routing mechanism based on a strategy of Distributed Iterative Gating (DIGNet).
Recurrent Iterative Gating Networks for Semantic Segmentation
The iterative nature of this mechanism allows for gating to spread in both spatial extent and feature space.
Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks
Further to this, we present data, analysis and baseline benchmark results towards addressing the problem of salient object ranking.
Semantics Meet Saliency: Exploring Domain Affinity and Models for Dual-Task Prediction
With that said, there is an apparent relationship between these two problem domains in that the composition of a scene and associated semantic categories is certain to play into what is deemed salient.
Gated Feedback Refinement Network for Coarse-to-Fine Dense Semantic Image Labeling
In order to address this issue, we also propose Gated Feedback Refinement Network (G-FRNet) that addresses this limitation.
Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects
In this paper, we argue that work to date has addressed a problem that is relatively ill-posed.
Gated Feedback Refinement Network for Dense Image Labeling
Effective integration of local and global contextual information is crucial for dense labeling problems.
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions.
