We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method1is featured with 1) the exponential moving averaging strategy to update the teacher from the student online, 2) using plenty of region proposals and soft pseudo-labels as the student’s training targets, and 3) a light-weighted detection-specific data ensemble for the teacher to generate more reliable pseudo-labels. Compared to the recent state-of-the-art – STAC, which uses hard labels on sparsely selected hard pseudo samples, the teacher in our model exposes richer information to the student with soft-labels on many proposals. Our model achieves COCO-style AP of 53.04% on VOC07 val set, 8.4% better than STAC, when using VOC12 as unlabeled data. On MS-COCO, it outperforms prior work when only a small percentage of data is taken as labeled. It also reaches 53.8% AP on MS-COCO test-dev with 3.1% gain over the fully supervised ResNet-152 Cascaded R-CNN, by tapping into unlabeled data of a similar size to the labeled data.

Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The problem of detecting such novel classes has been addressed in the literature, but most prior works have focused on providing simple binary or regressive decisions, e.g., the output would be "known," "novel," or corresponding confidence intervals. In this paper, we study more informative novelty detection schemes based on a hierarchical classification framework. For an object of a novel class, we aim for finding its closest super class in the hierarchical taxonomy of known classes. To this end, we propose two different approaches termed top-down and flatten methods, and their combination as well. The essential ingredients of our methods are confidence-calibrated classifiers, data relabeling, and the leave-one-out strategy for modeling novel classes under the hierarchical taxonomy. Furthermore, our method can generate a hierarchical embedding that leads to improved generalized zero-shot learning performance in combination with other commonly-used semantic embeddings.

Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way. This paper addresses the problem of learning object structures in an image modeling process without supervision. We propose an autoencoding formulation to discover landmarks as explicit structural representations. The encoding module outputs landmark coordinates, whose validity is ensured by constraints that reflect the necessary properties for landmarks. The decoding module takes the landmarks as a part of the learnable input representations in an end-to-end differentiable framework. Our discovered landmarks are semantically meaningful and more predictive of manually annotated landmarks than those discovered by previous methods. The coordinates of our landmarks are also complementary features to pretrained deep-neural-network representations in recognizing visual attributes. In addition, the proposed method naturally creates an unsupervised, perceptible interface to manipulate object shapes and decode images with controllable structures.

Associating image regions with text queries has been recently explored as a new way to bridge visual and linguistic representations. A few pioneering approaches have been proposed based on recurrent neural language models trained generatively (e.g., generating captions), but achieving somewhat limited localization accuracy. To better address natural-language-based visual entity localization, we propose a discriminative approach. We formulate a discriminative bimodal neural network (DBNet), which can be trained by a classifier with extensive use of negative samples. Our training objective encourages better localization on single images, incorporates text phrases in a broad range, and properly pairs image regions with text phrases into positive and negative examples. Experiments on the Visual Genome dataset demonstrate the proposed DBNet significantly outperforms previous state-of-the-art methods both for localization on single images and for detection on multiple images. We we also establish an evaluation protocol for natural-language visual detection. Code is available at: http://ytzhang.net/projects/dbnet.

Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical explanation and develop a mathematical model of sparse signal recovery that is consistent with CNNs with random weights. We give an exact connection to a particular model of model-based compressive sensing (and its recovery algorithms) and random-weight CNNs. We show empirically that several learned networks are consistent with our mathematical analysis and then demonstrate that with such a simple theoretical framework, we can obtain reasonable reconstruction results on real images. We also discuss gaps between our model assumptions and the CNN trained for classification in practical scenarios.

Unsupervised learning and supervised learning are key research topics in deep learning. However, as high-capacity supervised neural networks trained with a large amount of labels have achieved remarkable success in many computer vision tasks, the availability of large-scale labeled images reduced the significance of unsupervised learning. Inspired by the recent trend toward revisiting the importance of unsupervised learning, we investigate joint supervised and unsupervised learning in a large-scale setting by augmenting existing neural networks with decoding pathways for reconstruction. First, we demonstrate that the intermediate activations of pretrained large-scale classification networks preserve almost all the information of input images except a portion of local spatial details. Then, by end-to-end training of the entire augmented architecture with the reconstructive objective, we show improvement of the network performance for supervised tasks. We evaluate several variants of autoencoders, including the recently proposed “what-where" autoencoder that uses the encoder pooling switches, to study the importance of the architecture design. Taking the 16-layer VGGNet trained under the ImageNet ILSVRC 2012 protocol as a strong baseline for image classification, our methods improve the validation-set accuracy by a noticeable margin.

Object detection systems based on the deep convolutional neural network (CNN) have recently made ground-breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are discriminative for categorization, inaccurate localization is still a major source of error for detection. Building upon high-capacity CNN architectures, we address the localization problem by 1) using a search algorithm based on Bayesian optimization that sequentially proposes candidate regions for an object bounding box, and 2) training the CNN with a structured loss that explicitly penalizes the localization inaccuracy. In experiments, we demonstrate that each of the proposed methods improves the detection performance over the baseline method on PASCAL VOC 2007 and 2012 datasets. Furthermore, two methods are complementary and significantly outperform the previous state-of-the-art when combined.

In addition to identifying the content within a single image, relating images and generating related images are critical tasks for image understanding. Recently, deep convolutional networks have yielded breakthroughs in producing image labels, annotations and captions, but have only just begun to be used for producing high-quality image outputs. In this paper we develop a novel deep network trained end-to-end to perform visual analogy making, which is the task of transforming a query image according to an example pair of related images. Solving this problem requires both accurately recognizing a visual relationship and generating a transformed query image accordingly. Inspired by recent advances in language modeling, we propose to solve visual analogies by learning to map images to a neural embedding in which analogical reasoning is simple, such as by vector subtraction and addition. In experiments, our model effectively models visual analogies on several datasets: 2D shapes, animated video game sprites, and 3D car models.

Gait, as a promising biometric for recognizing human identities, can be nonintrusively captured as a series of acceleration signals using wearable or portable smart devices. It can be used for access control. Most existing methods on accelerometer-based gait recognition require explicit step-cycle detection, suffering from cycle detection failures and intercycle phase misalignment. We propose a novel algorithm that avoids both the above two problems. It makes use of a type of salient points termed signature points (SPs), and has three components: 1) a multiscale SP extraction method, including the localization and SP descriptors; 2) a sparse representation scheme for encoding newly emerged SPs with known ones in terms of their descriptors, where the phase propinquity of the SPs in a cluster is leveraged to ensure the physical meaningfulness of the codes; and 3) a classifier for the sparse-code collections associated with the SPs of a series. Experimental results on our publicly available dataset of 175 subjects showed that our algorithm outperformed existing methods, even if the step cycles were perfectly detected for them. When the accelerometers at five different body locations were used together, it achieved the rank-1 accuracy of 95.8% for identification, and the equal error rate of 2.2% for verification.

Many latent factors of variation interact to generate sensory data; for example pose, morphology and expression in face images. We propose to learn manifold coordinates for the relevant factors of variation and to model their joint interaction. Most existing feature learning algorithms focus on a single task and extract features that are sensitive to the task-relevant factors and invariant to all others. However, models that just extract a single set of invariant features do not exploit the relationships among the latent factors. To address this we propose a higher-order Boltzmann machine that incorporates multiplicative interactions among groups of hidden units that each learn to encode a factor of variation. Furthermore, we propose a manifold-based training strategy that allows effective disentangling, meaning that units in each group encode a distinct type of variation. Our model achieves state-of-the-art emotion recognition and face verification performance on the Toronto Face Database, and we also demonstrate disentangled features learned on the CMU Multi-PIE dataset.

This paper focuses on the task of recovering the neutral 3D face of a person when given his/her 3D face model with facial expression. We propose a learning-based expression removal framework to tackle this task. Our basic idea is to model expression residue from samples, and then use the inferred expression residue from the input expressional face model to recover the neutral one. A two-step non-rigid alignment method is introduced to make all the face models topologically share a common structure. Then we construct two spaces, normal space and expression residue space, for modeling expression. Therefore, the expression removal problem can be formalized as the inference of expression residue from normal spaces. The neutral face model can be generated in a Poisson-based framework by the inferred expression residue. The experimental results on BU-3DFED database demonstrate the effectiveness of our approach.