Exploring Geometry of Blind Spots in Vision Models

• URL: http://arxiv.org/abs/2310.19889v1
• Date: Mon, 30 Oct 2023 18:00:33 GMT
• Title: Exploring Geometry of Blind Spots in Vision Models
• Authors: Sriram Balasubramanian, Gaurang Sriramanan, Vinu Sankar Sadasivan, Soheil Feizi
• Abstract summary: 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.
• Score: 56.47644447201878
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the remarkable success of deep neural networks in a myriad of settings, several works have demonstrated their overwhelming sensitivity to near-imperceptible perturbations, known as adversarial attacks. On the other hand, prior works have also observed that deep networks can be under-sensitive, wherein large-magnitude perturbations in input space do not induce appreciable changes to network activations. In this work, we study in detail the phenomenon of under-sensitivity in vision models such as CNNs and Transformers, and present techniques to study the geometry and extent of "equi-confidence" level sets of such networks. We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space using orthogonal components of the local gradients. Given a source image, we use this algorithm to identify inputs that lie in the same equi-confidence level set as the source image despite being perceptually similar to arbitrary images from other classes. We further observe that the source image is linearly connected by a high-confidence path to these inputs, uncovering a star-like structure for level sets of deep networks. Furthermore, we attempt to identify and estimate the extent of these connected higher-dimensional regions over which the model maintains a high degree of confidence. The code for this project is publicly available at https://github.com/SriramB-98/blindspots-neurips-sub

Related papers

• Robot Localization and Mapping Final Report -- Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry [2.512491726995032]
  Visual odometry (VO) and SLAM have been using multi-view geometry via local structure from motion for decades. Deep neural networks to extract high level features is ubiquitous in computer vision. The goal of this work is to tackle these limitations of past approaches and to develop a method that can provide better depths and pose estimates.
  arXiv  Detail & Related papers  (2023-09-08T06:24:17Z)
• Deep Convolutional Pooling Transformer for Deepfake Detection [54.10864860009834]
  We propose a deep convolutional Transformer to incorporate decisive image features both locally and globally. Specifically, we apply convolutional pooling and re-attention to enrich the extracted features and enhance efficacy. The proposed solution consistently outperforms several state-of-the-art baselines on both within- and cross-dataset experiments.
  arXiv  Detail & Related papers  (2022-09-12T15:05:41Z)
• Neural Contourlet Network for Monocular 360 Depth Estimation [37.82642960470551]
  We provide a new perspective that constructs an interpretable and sparse representation for a 360 image. We propose a neural contourlet network consisting of a convolutional neural network and a contourlet transform branch. In the encoder stage, we design a spatial-spectral fusion module to effectively fuse two types of cues.
  arXiv  Detail & Related papers  (2022-08-03T02:25:55Z)
• FuNNscope: Visual microscope for interactively exploring the loss landscape of fully connected neural networks [77.34726150561087]
  We show how to explore high-dimensional landscape characteristics of neural networks. We generalize observations on small neural networks to more complex systems. An interactive dashboard opens up a number of possible application networks.
  arXiv  Detail & Related papers  (2022-04-09T16:41:53Z)
• Multi-attentional Deepfake Detection [79.80308897734491]
  Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. We propose a new multi-attentional deepfake detection network. Specifically, it consists of three key components: 1) multiple spatial attention heads to make the network attend to different local parts; 2) textural feature enhancement block to zoom in the subtle artifacts in shallow features; 3) aggregate the low-level textural feature and high-level semantic features guided by the attention maps.
  arXiv  Detail & Related papers  (2021-03-03T13:56:14Z)
• An Empirical Method to Quantify the Peripheral Performance Degradation in Deep Networks [18.808132632482103]
  convolutional neural network (CNN) kernels compound with each convolutional layer. Deeper and deeper networks combined with stride-based down-sampling means that the propagation of this region can end up covering a non-negligable portion of the image. Our dataset is constructed by inserting objects into high resolution backgrounds, thereby allowing us to crop sub-images which place target objects at specific locations relative to the image border. By probing the behaviour of Mask R-CNN across a selection of target locations, we see clear patterns of performance degredation near the image boundary, and in particular in the image corners.
  arXiv  Detail & Related papers  (2020-12-04T18:00:47Z)
• Ventral-Dorsal Neural Networks: Object Detection via Selective Attention [51.79577908317031]
  We propose a new framework called Ventral-Dorsal Networks (VDNets) Inspired by the structure of the human visual system, we propose the integration of a "Ventral Network" and a "Dorsal Network" Our experimental results reveal that the proposed method outperforms state-of-the-art object detection approaches.
  arXiv  Detail & Related papers  (2020-05-15T23:57:36Z)
• Verification of Deep Convolutional Neural Networks Using ImageStars [10.44732293654293]
  Convolutional Neural Networks (CNN) have redefined the state-of-the-art in many real-world applications. CNNs are vulnerable to adversarial attacks, where slight changes to their inputs may lead to sharp changes in their output. We describe a set-based framework that successfully deals with real-world CNNs, such as VGG16 and VGG19, that have high accuracy on ImageNet.
  arXiv  Detail & Related papers  (2020-04-12T00:37:21Z)
• Learning Depth With Very Sparse Supervision [57.911425589947314]
  This paper explores the idea that perception gets coupled to 3D properties of the world via interaction with the environment. We train a specialized global-local network architecture with what would be available to a robot interacting with the environment. Experiments on several datasets show that, when ground truth is available even for just one of the image pixels, the proposed network can learn monocular dense depth estimation up to 22.5% more accurately than state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-03-02T10:44:13Z)

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.