LIFT: Learned Invariant Feature Transform

Abstract

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-toend differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

“…Some of these techniques have extracted immediate activations as the descriptor [16,14,9,33], which have shown to be effective for patch-level matching. Other methods have directly learned a similarity measure for comparing patches using a convolutional similarity network [19,51,41,50]. Even though CNN-based descriptors encode a discriminative structure with a deep architecture, they have inherent limitations in handling large intra-class variations [41,10].…”

“…Instead, we compute the similarity of sampled patch pairs through CNNs. With l omitted for simplicity, the self-similarity between a patch pair P i−s and P i−t is formulated through a Siamese network, followed by decision or metric network [51,19] or a simple L 2 distance [41,50] as shown in Fig. 2(a).…”

“…[51] 0.753 0.405 0.335 0.498 MatchN. [19] 0.561 0.380 0.270 0.404 LIFT [50] 0.730 0.318 0.306 0.451 VGG [42] 0 Table 1. Matching accuracy for various feature descriptors with fixed SF optimization on the Taniai benchmark [45].…”

“…Over the past few years, convolutional neural network (CNN) based features have become increasingly popular for correspondence estimation thanks to their localization precision of matched points and their invariance to minor geometric deformations and illumination changes [19,51,41,50]. However, for computing semantic correspondences within this framework, greater invariance is needed to deal with the more substantial appearance differences.…”

Appearance-based Salient Features Extraction in Medical Images Using Sparse Contourlet-based Representation

“…In [13], Dual tree complex wavelet transform is used in a content-based image retrieval application. In [14], the authors used a deep network architecture to build a linear invariant feature transform (LIFT). In [15], Mark Brow et al presented a generalized framework for salience feature detection using histogram.…”