Recently, open-vocabulary image classification by vision language pre-training has
demonstrated incredible achievements, that the model can classify arbitrary categories …

Abstract We design a Kernelized Few-shot Object Detector by leveraging kernelized
matrices computed over multiple proposal regions, which yield expressive non-linear …

In this paper, we tackle the challenging problem of Few-shot Object Detection. Existing
FSOD pipelines (i) use average-pooled representations that result in information loss; and/or …

Visual representation based on covariance matrix has demonstrates its efficacy for image
classification by characterising the pairwise correlation of different channels in convolutional …

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 …

Fine-grained visual classification can be addressed by deep representation learning under
supervision of manually pre-defined targets (eg, one-hot or the Hadamard codes). Such …

Riemannian manifold plays a vital role as a powerful mathematical tool in computer vision,
with important applications in curved shape analysis and classification. Significant progress …

Previous works show global covariance pooling (GCP) has great potential to improve deep
architectures especially on visual recognition tasks, where post-normalization of GCP plays …

Global covariance pooling (GCP) as an effective alternative to global average pooling has
shown good capacity to improve deep convolutional neural networks (CNNs) in a variety of …

Bilinear pooling has achieved excellent performance in fine-grained recognition tasks.
Nevertheless, high-dimensional bilinear features suffer from over-fitting and inefficiency. To …