Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection

By Gong Cheng, Junwei Han, Peicheng Zhou, Dong Xu. IEEE Transactions on Image Processing, 2019

371 citations recorded by the source corpus.

The performance of object detection has recently been significantly improved due to the powerful features learnt through convolutional neural networks (CNNs). Despite the remarkable success, there are still several major challenges in object detection, including object rotation, within-class diversity, and between-class similarity, which generally degenerate object detection performance. To address these issues, we build up the existing state-of-the-art object detection systems and propose a simple but effective method to train rotation-invariant and Fisher discriminative CNN models to further boost object detection performance. This is achieved by optimizing a new objective function that explicitly imposes a rotation-invariant regularizer and a Fisher discrimination regularizer on the CNN features. Specifically, the first regularizer enforces the CNN feature representations of the training samples before and after rotation to be mapped closely to each other in order to achieve rotation-invariance. The second regularizer constrains the CNN features to have small within-class scatter but large between-class separation. We implement our proposed method under four popular object detection frameworks, including region-CNN (R-CNN), Fast R- CNN, Faster R- CNN, and R- FCN. In the experiments, we comprehensively evaluate the proposed method on the PASCAL VOC 2007 and 2012 data sets and a publicly available aerial image data set. Our proposed methods outperform the existing baseline methods and achieve the state-of-the-art results.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/5c5700614c0fc3db3a6f4d96d956027015c61690

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation (2020, background): “…form of L is n -norm, e.g., Mean-Square Error (MSE) loss and Smooth-(cid:96) 1 loss [22], which have been widely adopted in object detection [23], [24], pedestrian detection [25], [26], text detection [27]– [29], 3D detection [30], [31], pose estimation [32], [33], and instance segmentation [18],…”
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness (2019, methodology): “These approaches are based on augmenting the training data either statically [17, 30, 7, 45], ie.”
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey (2019, methodology): “Following this idea, more methods are proposed to learn image features by solving more difficult spatial puzzles [22], [42], [43], [44], [125].”
Object Detection in 20 Years: A Survey (2019, neutral): “Designing rotation invariant loss functions is a recent popular solution, where a constraint on the detection loss is added so that the feature of rotated objects keeps unchanged [169], [170], [171].”
Anchor-Free Oriented Proposal Generator for Object Detection (2021, background): “Many latest works [17]–[26] are based on the two-stage framework.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, background): “Multi-modal and multi-level feature fusion [37] is essential for many computer vision tasks, such as object detection [8,21,26,68], semantic segmentation [29,30, 32,65], co-attention tasks [19,70] and classiﬁcation [38,40,51].”
ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection (2023, background): “As a fundamental vision task, object detection remains a hot topic in both academia and industry, and has made considerable progress in small object detection [1], face and pedestrian detection [2] and oriented object detection [3, 4], thanks to the rapid development of convolutional neural networks”
Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, methodology): “in [6], [9], [10] use rotation-invariant convolutional neural Jian Ding and Liangpei Zhang are with the State Key Laboratory LIESMARS, Wuhan University, Wuhan, Hubei 430079, China.”
Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark (2019, methodology): “, 2017), RIFD‐CNN (with Faster R‐CNN framework) (Cheng et al., 2019), Faster R‐CNN (Ren et al.”