24 August 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Power Normalizations ( PN ) are useful non-linear operators which tackle feature imbalances in classification problems. We study PNs in the deep learning setup via a novel PN layer pooling feature maps. Our layer combines the feature vectors and their respective spatial locations in the feature maps produced by the last convolutional layer of CNN into a positive definite matrix with second-order statistics to which PN operators are applied, forming so-called Second-order Pooling ( SOP ). As the main goal of this paper is to study Power Normalizations, we investigate the role and meaning of MaxExp and Gamma, two popular PN functions. To this end, we provide probabilistic interpretations of such element-wise operators and discover surrogates with well-behaved derivatives for end-to-end training. Furthermore, we look at the spectral applicability of MaxExp and Gamma by studying Spectral Power Normalizations ( SPN ). We show that SPN on the autocorrelation/covariance matrix and the Heat Diffusion Process (HDP) on a graph Laplacian matrix are closely related, thus sharing their properties. Such a finding leads us to the culmination of our work, a fast spectral MaxExp which is a variant of HDP for covariances/autocorrelation matrices. We evaluate our ideas on fine-grained recognition, scene recognition, and material classification, as well as in few-shot learning and graph classification.
13 January 2022 in IEEE Transactions on Multimedia
We propose a Multi-level Second-order (MlSo) few-shot learning network for supervised or unsupervised few-shot image classification and few-shot action recognition. We leverage so-called power-normalized second-order base learner streams combined with features that express multiple levels of visual abstraction, and we use self-supervised discriminating mechanisms. As Second-order Pooling (SoP) is popular in image recognition, we employ its basic element-wise variant in our pipeline. The goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning. As SoP can handle convolutional feature maps of varying spatial sizes, we also introduce image inputs at multiple spatial scales into MlSo. To exploit the discriminative information from multi-level and multi-scale features, we develop a Feature Matching (FM) module that reweights their respective branches. We also introduce a self-supervised step, which is a discriminator of the spatial level and the scale of abstraction. Our pipeline is trained in an end-to-end manner. With a simple architecture, we demonstrate respectable results on standard datasets such as Omniglot, mini-ImageNet, tiered-ImageNet, Open MIC, fine-grained datasets such as CUB Birds, Stanford Dogs and Cars, and action recognition datasets such as HMDB51, UCF101, and mini-MIT.
11 August 2020 in IEEE Access
Despite CNN-based deblur models have shown their superiority when solving motion blurs, restoring a photorealistic image from severe motion blur remains an ill-posed problem due to the loss of temporal information and textures. Event cameras such as Dynamic and Active-pixel Vision Sensor (DAVIS) can simultaneously produce gray-scale Active Pixel Sensor (APS) frames and events, which can capture fast motions as events of very high temporal resolution, i. e. , $1~\mu s$ , can provide extra information for blurry APS frames. Due to the natural noise and sparsity of events, we employ a recurrent encoder-decoder architecture to generate dense recurrent event representations, which encode the overall historical information. We concatenate the original blurry image with the event representation as our hybrid input, from which the network learns to restore the sharp output. We conduct extensive experiments on GoPro dataset and a real event blurry dataset captured by DAVIS240C. Our experimental results on both synthetic and real images demonstrate state-of-the-art performance for $1280\times 720 $ images at 30 fps.
14 November 2022 in International Journal of Computer Vision