In the task of Object Recognition, there exists a dichotomy between the categorization of objects and estimating object pose, where the former necessitates a view-invariant representation, while the latter requires a representation capable of capturing pose information over different categories of objects. With the rise of deep architectures, the prime focus has been on object category recognition. Deep learning methods have achieved wide success in this task. In contrast, object pose regression using these approaches has received relatively much less attention. In this paper we show how deep architectures, specifically Convolutional Neural Networks (CNN), can be adapted to the task of simultaneous categorization and pose estimation of objects. We investigate and analyze the layers of various CNN models and extensively compare between them with the goal of discovering how the layers of distributed representations of CNNs represent object pose information and how this contradicts with object category representations. We extensively experiment on two recent large and challenging multi-view datasets. Our models achieve better than state-of-the-art performance on both datasets.
Despite significant progress in object categorization, in recent years, a number of important challenges remain, mainly, ability to learn from limited labeled data and ability to recognize object classes within large, potentially open, set of labels. Zero-shot learning is one way of addressing these challenges, but it has only been shown to work with limited sized class vocabularies and typically requires separation between supervised and unsupervised classes, allowing former to inform the latter but not vice versa. We propose the notion of semi-supervised vocabulary-informed learning to alleviate the above mentioned challenges and address problems of supervised, zero-shot and open set recognition using a unified framework. Specifically, we propose a maximum margin framework for semantic manifold-based recognition that incorporates distance constraints from (both supervised and unsupervised) vocabulary atoms, ensuring that labeled samples are projected closest to their correct prototypes, in the embedding space, than to others. We show that resulting model shows improvements in supervised, zero-shot, and large open set recognition, with up to 310K class vocabulary on AwA and ImageNet datasets.
Object categorization is a hot issue of an image mining. Contextual information between objects is one of the important semantic knowledge of an image. However, the previous researches for an object categorization have not made full use of the contextual information, especially the spatial relations between objects. In addition, the object categorization methods, which generally use the probabilistic graphical models to implement the incorporation of contextual information with appearance of objects, are almost inevitable to evaluate the intractable partition function for normalization. In this work, we introduced fully-connected fuzzy spatial relations including directional, distance and topological relations between object regions, so the spatial relational information could be fully utilized. Then, the spatial relations were considered as well as co-occurrence and appearance of objects by using energy-based model, where the energy function was defined as the region-object association potential and the configuration potential of objects. Minimizing the energy function of whole image arrangement, we obtained the optimal label set about the image regions and addressed the evaluation of intractable partition function in conditional random fields. Experimental results show the validity and reliability of this proposed method.
Object recognition in images involves identifying objects with partial occlusions, viewpoint changes, varying illumination, cluttered backgrounds. Recent work in object recognition uses machine learning techniques SVM-KNN, Local Ensemble Kernel Learning, Multiple Kernel Learning. In this paper, we want to utilize SVM as week learners in AdaBoost. Experiments are done with classifiers like near- est neighbor, k-nearest neighbor, Support vector machines, Local learning(SVM- KNN) and AdaBoost. Models use Scale-Invariant descriptors and Pyramid his- togram of gradient descriptors. AdaBoost is trained with set of week classifier as SVMs, each with kernel distance function on different descriptors. Results shows AdaBoost with SVM outperform other methods for Object Categorization dataset.
In Computer Vision, problem of identifying or classifying the objects present in an image is called Object Categorization. It is a challenging problem, especially when the images have clutter background, occlusions or different lighting conditions. Many vision features have been proposed which aid object categorization even in such adverse conditions. Past research has shown that, employing multiple features rather than any single features leads to better recognition. Multiple Kernel Learning (MKL) framework has been developed for learning an optimal combination of features for object categorization. Existing MKL methods use linear combination of base kernels which may not be optimal for object categorization. Real-world object categorization may need to consider complex combination of kernels(non-linear) and not only linear combination. Evolving non-linear functions of base kernels using Genetic Programming is proposed in this report. Experiment results show that non-kernel generated using genetic programming gives good accuracy as compared to linear combination of kernels.
Manifold distances are very effective tools for visual object recognition. However, most of the traditional manifold distances between images are based on the pixel-level comparison and thus easily affected by image rotations and translations. In this paper, we propose a new manifold distance to model the dissimilarities between visual objects based on the Complex Wavelet Structural Similarity (CW-SSIM) index. The proposed distance is more robust to rotations and translations of images than the traditional manifold distance and the CW-SSIM index based distance. In addition, the proposed distance is combined with the $k$-medoids clustering method to derive a new clustering method for visual object categorization. Experiments on Coil-20, Coil-100 and Olivetti Face Databases show that the proposed distance measure is better for visual object categorization than both the traditional manifold distances and the CW-SSIM index based distances.
The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem. The evalution tests the influence of the following choices of the architecture: non-linearity (ReLU, ELU, maxout, compatibility with batch normalization), pooling variants (stochastic, max, average, mixed), network width, classifier design (convolutional, fully-connected, SPP), image pre-processing, and of learning parameters: learning rate, batch size, cleanliness of the data, etc. The performance gains of the proposed modifications are first tested individually and then in combination. The sum of individual gains is bigger than the observed improvement when all modifications are introduced, but the "deficit" is small suggesting independence of their benefits. We show that the use of 128x128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets. The results are obtained an order of magnitude faster than with the standard 224 pixel images.
Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations. But despite these huge variations, our visual system is able to invariantly recognize any object in just a fraction of a second. To date, various computational models have been proposed to mimic the hierarchical processing of the ventral visual pathway, with limited success. Here, we show that the association of both biologically inspired network architecture and learning rule significantly improves the models' performance when facing challenging invariant object recognition problems. Our model is an asynchronous feedforward spiking neural network. When the network is presented with natural images, the neurons in the entry layers detect edges, and the most activated ones fire first, while neurons in higher layers are equipped with spike timing-dependent plasticity. These neurons progressively become selective to intermediate complexity visual features appropriate for object categorization. The model is evaluated on 3D-Object and ETH-80 datasets which are two benchmarks for invariant object recognition, and is shown to outperform state-of-the-art models, including DeepConvNet and HMAX. This demonstrates its ability to accurately recognize different instances of multiple object classes even under various appearance conditions (different views, scales, tilts, and backgrounds). Several statistical analysis techniques are used to show that our model extracts class specific and highly informative features.
What if we could effectively read the mind and transfer human visual capabilities to computer vision methods? In this paper, we aim at addressing this question by developing the first visual object classifier driven by human brain signals. In particular, we employ EEG data evoked by visual object stimuli combined with Recurrent Neural Networks (RNN) to learn a discriminative brain activity manifold of visual categories. Afterwards, we train a Convolutional Neural Network (CNN)-based regressor to project images onto the learned manifold, thus effectively allowing machines to employ human brain-based features for automated visual classification. We use a 32-channel EEG to record brain activity of seven subjects while looking at images of 40 ImageNet object classes. The proposed RNN based approach for discriminating object classes using brain signals reaches an average accuracy of about 40%, which outperforms existing methods attempting to learn EEG visual object representations. As for automated object categorization, our human brain-driven approach obtains competitive performance, comparable to those achieved by powerful CNN models, both on ImageNet and CalTech 101, thus demonstrating its classification and generalization capabilities. This gives us a real hope that, indeed, human mind can be read and transferred to machines.
Convolutional Neural Networks (CNNs) trained on large scale RGB databases have become the secret sauce in the majority of recent approaches for object categorization from RGB-D data. Thanks to colorization techniques, these methods exploit the filters learned from 2D images to extract meaningful representations in 2.5D. Still, the perceptual signature of these two kind of images is very different, with the first usually strongly characterized by textures, and the second mostly by silhouettes of objects. Ideally, one would like to have two CNNs, one for RGB and one for depth, each trained on a suitable data collection, able to capture the perceptual properties of each channel for the task at hand. This has not been possible so far, due to the lack of a suitable depth database. This paper addresses this issue, proposing to opt for synthetically generated images rather than collecting by hand a 2.5D large scale database. While being clearly a proxy for real data, synthetic images allow to trade quality for quantity, making it possible to generate a virtually infinite amount of data. We show that the filters learned from such data collection, using the very same architecture typically used on visual data, learns very different filters, resulting in depth features (a) able to better characterize the different facets of depth images, and (b) complementary with respect to those derived from CNNs pre-trained on 2D datasets. Experiments on two publicly available databases show the power of our approach.
The $k$-means clustering algorithm is popular but has the following main drawbacks: 1) the number of clusters, $k$, needs to be provided by the user in advance, 2) it can easily reach local minima with randomly selected initial centers, 3) it is sensitive to outliers, and 4) it can only deal with well separated hyperspherical clusters. In this paper, we propose a Local Density Peaks Searching (LDPS) initialization framework to address these issues. The LDPS framework includes two basic components: one of them is the local density that characterizes the density distribution of a data set, and the other is the local distinctiveness index (LDI) which we introduce to characterize how distinctive a data point is compared with its neighbors. Based on these two components, we search for the local density peaks which are characterized with high local densities and high LDIs to deal with 1) and 2). Moreover, we detect outliers characterized with low local densities but high LDIs, and exclude them out before clustering begins. Finally, we apply the LDPS initialization framework to $k$-medoids, which is a variant of $k$-means and chooses data samples as centers, with diverse similarity measures other than the Euclidean distance to fix the last drawback of $k$-means. Combining the LDPS initialization framework with $k$-means and $k$-medoids, we obtain two novel clustering methods called LDPS-means and LDPS-medoids, respectively. Experiments on synthetic data sets verify the effectiveness of the proposed methods, especially when the ground truth of the cluster number $k$ is large. Further, experiments on several real world data sets, Handwritten Pendigits, Coil-20, Coil-100 and Olivetti Face Database, illustrate that our methods give a superior performance than the analogous approaches on both estimating $k$ and unsupervised object categorization.
Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects. First, we incorporate deep convolutional neural networks into active learning. Through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. Second, we present a cost-effective sample selection strategy to improve the classification performance with less manual annotations. Unlike traditional methods focusing on only the uncertain samples of low prediction confidence, we especially discover the large amount of high confidence samples from the unlabeled set for feature learning. Specifically, these high confidence samples are automatically selected and iteratively assigned pseudo-labels. We thus call our framework "Cost-Effective Active Learning" (CEAL) standing for the two advantages.Extensive experiments demonstrate that the proposed CEAL framework can achieve promising results on two challenging image classification datasets, i.e., face recognition on CACD database [1] and object categorization on Caltech-256 [2].
Many theories have emerged which investigate how in- variance is generated in hierarchical networks through sim- ple schemes such as max and mean pooling. The restriction to max/mean pooling in theoretical and empirical studies has diverted attention away from a more general way of generating invariance to nuisance transformations. We con- jecture that hierarchically building selective invariance (i.e. carefully choosing the range of the transformation to be in- variant to at each layer of a hierarchical network) is im- portant for pattern recognition. We utilize a novel pooling layer called adaptive pooling to find linear pooling weights within networks. These networks with the learnt pooling weights have performances on object categorization tasks that are comparable to max/mean pooling networks. In- terestingly, adaptive pooling can converge to mean pooling (when initialized with random pooling weights), find more general linear pooling schemes or even decide not to pool at all. We illustrate the general notion of selective invari- ance through object categorization experiments on large- scale datasets such as SVHN and ILSVRC 2012.
Deep networks thrive when trained on large scale data collections. This has given ImageNet a central role in the development of deep architectures for visual object classification. However, ImageNet was created during a specific period in time, and as such it is prone to aging, as well as dataset bias issues. Moving beyond fixed training datasets will lead to more robust visual systems, especially when deployed on robots in new environments which must train on the objects they encounter there. To make this possible, it is important to break free from the need for manual annotators. Recent work has begun to investigate how to use the massive amount of images available on the Web in place of manual image annotations. We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy. By combining these two results, we obtain a method for learning powerful deep object models automatically from the Web. We confirm the effectiveness of our approach through object categorization experiments using our Web-derived version of ImageNet on a popular robot vision benchmark database, and on a lifelong object discovery task on a mobile robot.
The human visual system contains a hierarchical sequence of modules that take part in visual perception at different levels of abstraction, i.e., superordinate, basic, and subordinate levels. One important question is to identify the "entry" level at which the visual representation is commenced in the process of object recognition. For a long time, it was believed that the basic level had advantage over two others; a claim that has been challenged recently. Here we used a series of psychophysics experiments, based on a rapid presentation paradigm, as well as two computational models, with bandpass filtered images to study the processing order of the categorization levels. In these experiments, we investigated the type of visual information required for categorizing objects in each level by varying the spatial frequency bands of the input image. The results of our psychophysics experiments and computational models are consistent. They indicate that the different spatial frequency information had different effects on object categorization in each level. In the absence of high frequency information, subordinate and basic level categorization are performed inaccurately, while superordinate level is performed well. This means that, low frequency information is sufficient for superordinate level, but not for the basic and subordinate levels. These finer levels require high frequency information, which appears to take longer to be processed, leading to longer reaction times. Finally, to avoid the ceiling effect, we evaluated the robustness of the results by adding different amounts of noise to the input images and repeating the experiments. As expected, the categorization accuracy decreased and the reaction time increased significantly, but the trends were the same.This shows that our results are not due to a ceiling effect.
A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simulate heredity and determine the architectures of offspring networks. In this study, we take a deeper look at the notion of synaptic cluster-driven evolution of deep neural networks which guides the evolution process towards the formation of a highly sparse set of synaptic clusters in offspring networks. Utilizing a synaptic cluster-driven genetic encoding, the probabilistic encoding of synaptic traits considers not only individual synaptic properties but also inter-synaptic relationships within a deep neural network. This process results in highly sparse offspring networks which are particularly tailored for parallel computational devices such as GPUs and deep neural network accelerator chips. Comprehensive experimental results using four well-known deep neural network architectures (LeNet-5, AlexNet, ResNet-56, and DetectNet) on two different tasks (object categorization and object detection) demonstrate the efficiency of the proposed method. Cluster-driven genetic encoding scheme synthesizes networks that can achieve state-of-the-art performance with significantly smaller number of synapses than that of the original ancestor network. ($\sim$125-fold decrease in synapses for MNIST). Furthermore, the improved cluster efficiency in the generated offspring networks ($\sim$9.71-fold decrease in clusters for MNIST and a $\sim$8.16-fold decrease in clusters for KITTI) is particularly useful for accelerated performance on parallel computing hardware architectures such as those in GPUs and deep neural network accelerator chips.
We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch, within the same image, conditioned on their real-valued relative spatial offset. Unlike auto-encoders, that aim to encode and reconstruct original image patches, our network aims to encode and reconstruct intermediate representations of the spatially offset patches. As such, the network learns a spatially conditioned contextual representation. By testing performance with various patch selection mechanisms we show that focusing on object-centric patches is important, and that using object proposal as a patch selection mechanism leads to the highest improvement in performance. Further, unlike auto-encoders, context encoders [21], or other forms of unsupervised feature learning, we illustrate that contextual supervision (with pre-trained model initialization) can improve on existing pre-trained model performance. We build our spatial context networks on top of standard VGG_19 and CNN_M architectures and, among other things, show that we can achieve improvements (with no additional explicit supervision) over the original ImageNet pre-trained VGG_19 and CNN_M models in object categorization and detection on VOC2007.
This paper addresses image classification through learning a compact and discriminative dictionary efficiently. Given a structured dictionary with each atom (columns in the dictionary matrix) related to some label, we propose cross-label suppression constraint to enlarge the difference among representations for different classes. Meanwhile, we introduce group regularization to enforce representations to preserve label properties of original samples, meaning the representations for the same class are encouraged to be similar. Upon the cross-label suppression, we don't resort to frequently-used $\ell_0$-norm or $\ell_1$-norm for coding, and obtain computational efficiency without losing the discriminative power for categorization. Moreover, two simple classification schemes are also developed to take full advantage of the learnt dictionary. Extensive experiments on six data sets including face recognition, object categorization, scene classification, texture recognition and sport action categorization are conducted, and the results show that the proposed approach can outperform lots of recently presented dictionary algorithms on both recognition accuracy and computational efficiency.
We report on an extensive study of the benefits and limitations of current deep learning approaches to object recognition in robot vision scenarios, introducing a novel dataset used for our investigation. To avoid the biases in currently available datasets, we consider a natural human-robot interaction setting to design a data-acquisition protocol for visual object recognition on the iCub humanoid robot. Analyzing the performance of off-the-shelf models trained off-line on large-scale image retrieval datasets, we show the necessity for knowledge transfer. We evaluate different ways in which this last step can be done, and identify the major bottlenecks affecting robotic scenarios. By studying both object categorization and identification problems, we highlight key differences between object recognition in robotics applications and in image retrieval tasks, for which the considered deep learning approaches have been originally designed. In a nutshell, our results confirm the remarkable improvements yield by deep learning in this setting, while pointing to specific open challenges that need be addressed for seamless deployment in robotics.
Biologically inspired model (BIM) for image recognition is a robust computational architecture, which has attracted widespread attention. BIM can be described as a four-layer structure based on the mechanisms of the visual cortex. Although the performance of BIM for image recognition is robust, it takes the randomly selected ways for the patch selection, which is sightless, and results in heavy computing burden. To address this issue, we propose a novel patch selection method with oriented Gaussian-Hermite moment (PSGHM), and we enhanced the BIM based on the proposed PSGHM, named as PBIM. In contrast to the conventional BIM which adopts the random method to select patches within the feature representation layers processed by multi-scale Gabor filter banks, the proposed PBIM takes the PSGHM way to extract a small number of representation features while offering promising distinctiveness. To show the effectiveness of the proposed PBIM, experimental studies on object categorization are conducted on the CalTech05, TU Darmstadt (TUD), and GRAZ01 databases. Experimental results demonstrate that the performance of PBIM is a significant improvement on that of the conventional BIM.