Abstract: We propose a method that aims to lessen the significant accuracy degradation
that a discriminative classifier can suffer when it is trained in a specific domain (source domain) and applied in a different one (target domain). The principal reason for this degradation is the discrepancies in the distribution of the features that feed the classifier in different domains. Therefore, we propose a domain adaptation method that maps the features from the different domains into a common subspace and learns a discriminative domain-invariant classifier within it. Our algorithm combines bilinear classifiers and multi-task learning for domain adaptation.
The bilinear classifier encodes the feature transformation and classification
parameters by a matrix decomposition. In this way, specific feature transformations for multiple domains and a shared classifier are jointly learned in a multi-task learning framework. Focusing on domain adaptation for visual object detection, we apply this method to the state-of-the-art deformable part-based model for cross domain pedestrian detection. Experimental results show that our method significantly avoids the domain drift and improves the accuracy when compared to several baselines.

Abstract: We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textual content, that can provide discriminative semantic interpretetion, and can thus aid in classifcation tasks. To this end, we develop a framework using off-the-shelf components, and demonstrate the effectiveness of Textual cues in semantic Classfication tasks.

Abstract: We present the results of recent challenges in Automated Computer Vision (AutoCV, renamed here for clarity AutoCV1 and AutoCV2, 2019), which are part of a series of challenge on Automated Deep Learning (AutoDL). These two competitions aim at searching for fully automated solutions for classification tasks in computer vision, with an emphasis on any-time performance. The first competition was limited to image classification while the second one included both images and videos. Our design imposed to the participants to submit their code on a challenge platform for blind testing on five datasets, both for training and testing, without any human intervention whatsoever. Winning solutions adopted deep learning techniques based on already published architectures, such as AutoAugment, MobileNet and ResNet, to reach state-of-the-art performance in the time budget of the challenge (only 20 minutes of GPU time). The novel contributions include strategies to deliver good preliminary results at any time during the learning process, such that a method can be stopped early and still deliver good performance. This feature is key for the adoption of such techniques by data analysts desiring to obtain rapidly preliminary results on large datasets and to speed up the development process. The soundness of our design was verified in several aspects: (1) Little overfitting of the on-line leaderboard providing feedback on 5 development datasets was observed, compared to the final blind testing on the 5 (separate) final test datasets, suggesting that winning solutions might generalize to other computer vision classification tasks; (2) Error bars on the winners’ performance allow us to say with confident that they performed significantly better than the baseline solutions we provided; (3) The ranking of participants according to the any-time metric we designed, namely the Area under the Learning Curve, was different from that of the fixed-time metric, i.e. AUC at the end of the fixed time budget. We released all winning solutions under open-source licenses. At the end of the AutoDL challenge series, all data of the challenge will be made publicly available, thus providing a collection of uniformly formatted datasets, which can serve to conduct further research, particularly on meta-learning.

Abstract: We present the design and beta tests of a new machine learning challenge called AutoCV (for Automated Computer Vision), which is the first event in a series of challenges we are planning on the theme of Automated Deep Learning. We target applications for which Deep Learning methods have had great success in the past few years, with the aim of pushing the state of the art in fully automated methods to design the architecture of neural networks and train them without any human intervention. The tasks are restricted to multi-label image classification problems, from domains including medical, areal, people, object, and handwriting imaging. Thus the type of images will vary a lot in scales, textures, and structure. Raw data are provided (no features extracted), but all datasets are formatted in a uniform tensor manner (although images may have fixed or variable sizes within a dataset). The participants's code will be blind tested on a challenge platform in a controlled manner, with restrictions on training and test time and memory limitations. The challenge is part of the official selection of IJCNN 2019.

Abstract: We present the 2016 ChaLearn Looking at People and Faces of the World Challenge and Workshop, which ran three competitions on the common theme of face analysis from still images. The first one, Looking at People, addressed age estimation, while the second and third competitions, Faces of the World, addressed accessory classification and smile and gender classification, respectively. We present two crowd-sourcing methodologies used to collect manual annotations. A custom-build application was used to collect and label data about the apparent age of people (as opposed to the real age). For the Faces of the World data, the citizen-science Zooniverse platform was used. This paper summarizes the three challenges and the data used, as well as the results achieved by the participants of the competitions. Details of the ChaLearn LAP FotW competitions can be found at http://gesture.chalearn.org.

Abstract: We present in this paper a novel study aiming at identifying the differences in visual search patterns between physicians of diverse levels of expertise during the screening of colonoscopy videos. Physicians were clustered into two groups -experts and novices- according to the number of procedures performed, and fixations were captured by an eye-tracker device during the task of polyp search in different video sequences. These fixations were integrated into heat maps, one for each cluster. The obtained maps were validated over a ground truth consisting of a mask of the polyp, and the comparison between experts and novices was performed by using metrics such as reaction time, dwelling time and energy concentration ratio. Experimental results show a statistically significant difference between experts and novices, and the obtained maps show to be a useful tool for the characterisation of the behaviour of each group.

Abstract: We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance.