Abstract: Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image embeddings with small networks. Network distillation has been successfully applied to improve image classification, but has hardly been explored for metric learning. To do so, we propose two new loss functions that model the
communication of a deep teacher network to a small student network. We evaluate our system in several datasets, including CUB-200-2011, Cars-196, Stanford Online Products and show that embeddings computed using small student networks perform significantly better than those computed using standard networks of similar size. Results on a very compact network (MobileNet-0.25), which can be
used on mobile devices, show that the proposed method can greatly improve Recall@1 results from 27.5% to 44.6%. Furthermore, we investigate various aspects of distillation for embeddings, including hint and attention layers, semisupervised learning and cross quality distillation.

Abstract: Color description is a challenging task because of large variations in RGB values which occur due to scene accidental events, such as shadows, shading, specularities, illuminant color changes, and changes in viewing geometry. Traditionally, this challenge has been addressed by capturing the variations in physics-based models, and deriving invariants for the undesired variations. The drawback of this approach is that sets of distinguishable colors in the original color space are mapped to the same value in the photometric invariant space. This results in a drop of discriminative power of the color description. In this paper we take an information theoretic approach to color description. We cluster color values together based on their discriminative power in a classification problem. The clustering has the explicit objective to minimize the drop of mutual information of the final representation. We show that such a color description automatically learns a certain degree of photometric invariance. We also show that a universal color representation, which is based on other data sets than the one at hand, can obtain competing performance. Experiments show that the proposed descriptor outperforms existing photometric invariants. Furthermore, we show that combined with shape description these color descriptors obtain excellent results on four challenging datasets, namely, PASCAL VOC 2007, Flowers-102, Stanford dogs-120 and Birds-200.

Abstract: This paper is concerned with recognizing realistic human actions in videos based on spatio-temporal interest points (STIPs). Existing STIP-based action recognition approaches operate on intensity representations of the image data. Because of this, these approaches are sensitive to disturbing photometric phenomena such as highlights and shadows. Moreover, valuable information is neglected by discarding chromaticity from the photometric representation. These issues are addressed by Color STIPs. Color STIPs are multi-channel reformulations of existing intensity-based STIP detectors and descriptors, for which we consider a number of chromatic representations derived from the opponent color space. This enhanced modeling of appearance improves the quality of subsequent STIP detection and description. Color STIPs are shown to substantially outperform their intensity-based counterparts on the challenging UCF~sports, UCF11 and UCF50 action recognition benchmarks. Moreover, the results show that color STIPs are currently the single best low-level feature choice for STIP-based approaches to human action recognition.

Abstract: Facial emotion recognition is an inherently complex problem due to individual diversity in facial features and racial and cultural differences. Moreover, facial expressions typically reflect the mixture of people’s emotional statuses, which can be expressed using compound emotions. Compound facial emotion recognition makes the problem even more difficult because the discrimination between dominant and complementary emotions is usually weak. We have created a database that includes 31,250 facial images with different emotions of 115 subjects whose gender distribution is almost uniform to address compound emotion recognition. In addition, we have organized a competition based on the proposed dataset, held at FG workshop 2020. This paper analyzes the winner’s approach—a two-stage recognition method (1st stage, coarse recognition; 2nd stage, fine recognition), which enhances the classification of symmetrical emotion labels.

Abstract: Two key factors affecting the performance of Error Correcting Output Codes (ECOC) in multiclass classification problems are the independence of binary classifiers and the problem-dependent coding design. In this paper, we propose an evolutionary algorithm-based approach to the design of an application-dependent codematrix in the ECOC framework. The central idea of this work is to design a three-dimensional codematrix, where the third dimension is the feature space of the problem domain. In order to do that, we consider the feature space in the design process of the codematrix with the aim of improving the independence and accuracy of binary classifiers. The proposed method takes advantage of some basic concepts of ensemble classification, such as diversity of classifiers, and also benefits from the evolutionary approach for optimizing the three-dimensional codematrix, taking into account the problem domain. We provide a set of experimental results using a set of benchmark datasets from the UCI Machine Learning Repository, as well as two real multiclass Computer Vision problems. Both sets of experiments are conducted using two different base learners: Neural Networks and Decision Trees. The results show that the proposed method increases the classification accuracy in comparison with the state-of-the-art ECOC coding techniques.

Abstract: The sewerage infrastructure is one of the most important and expensive infrastructures in modern society. In order to efficiently manage the sewerage infrastructure, automated sewer inspection has to be utilized. However, while sewer
defect classification has been investigated for decades, little attention has been given to classifying sewer pipe properties such as water level, pipe material, and pipe shape, which are needed to evaluate the level of sewer pipe deterioration.
In this work we classify sewer pipe defects and properties concurrently and present a novel decoder-focused multi-task classification architecture Cross-Task Graph Neural Network (CT-GNN), which refines the disjointed per-task predictions using cross-task information. The CT-GNN architecture extends the traditional disjointed task-heads decoder, by utilizing a cross-task graph and unique class node embeddings. The cross-task graph can either be determined a priori based on the conditional probability between the task classes or determined dynamically using self-attention.
CT-GNN can be added to any backbone and trained end-toend at a small increase in the parameter count. We achieve state-of-the-art performance on all four classification tasks in the Sewer-ML dataset, improving defect classification and
water level classification by 5.3 and 8.0 percentage points, respectively. We also outperform the single task methods as well as other multi-task classification approaches while introducing 50 times fewer parameters than previous modelfocused approaches.

Abstract: This paper presents the combined use of gradient and mutual information for infrared and intensity templates matching. We propose to joint: (i) feature matching in a multiresolution context and (ii) information propagation through scale-space representations. Our method consists in combining mutual information with a shape descriptor based on gradient, and propagate them following a coarse-to-fine strategy. The main contributions of this work are: to offer a theoretical formulation towards a multimodal stereo matching; to show that gradient and mutual information can be reinforced while they are propagated between consecutive levels; and to show that they are valid cost functions in multimodal template matchings. Comparisons are presented showing the improvements and viability of the proposed approach.

Abstract: Before the big data era, scene recognition was often approached with two-step inference using localized intermediate representations (objects, topics, and so on). One of such approaches is the semantic manifold (SM), in which patches and images are modeled as points in a semantic probability simplex. Patch models are learned resorting to weak supervision via image labels, which leads to the problem of scene categories co-occurring in this semantic space. Fortunately, each category has its own co-occurrence patterns that are consistent across the images in that category. Thus, discovering and modeling these patterns are critical to improve the recognition performance in this representation. Since the emergence of large data sets, such as ImageNet and Places, these approaches have been relegated in favor of the much more powerful convolutional neural networks (CNNs), which can automatically learn multi-layered representations from the data. In this paper, we address many limitations of the original SM approach and related works. We propose discriminative patch representations using neural networks and further propose a hybrid architecture in which the semantic manifold is built on top of multiscale CNNs. Both representations can be computed significantly faster than the Gaussian mixture models of the original SM. To combine multiple scales, spatial relations, and multiple features, we formulate rich context models using Markov random fields. To solve the optimization problem, we analyze global and local approaches, where a top-down hierarchical algorithm has the best performance. Experimental results show that exploiting different types of contextual relations jointly consistently improves the recognition accuracy.