Deep neural networks have achieved remarkable success in computer vision tasks. Existing neural networks mainly operate in the spatial domain with fixed input sizes. For practical applications, images are usually large and have to be downsampled to the predetermined input size of neural networks. Even though the downsampling operations reduce computation and the required communication bandwidth, it removes both redundant and salient information obliviously, which results in accuracy degradation. Inspired by digital signal processing theories, we analyze the spectral bias from the frequency perspective and propose a learning-based frequency selection method to identify the trivial frequency components which can be removed without accuracy loss. The proposed method of learning in the frequency domain leverages identical structures of the well-known neural networks, such as ResNet-50, MobileNetV2, and Mask R-CNN, while accepting the frequency-domain information as the input. Experiment results show that learning in the frequency domain with static channel selection can achieve higher accuracy than the conventional spatial downsampling approach and meanwhile further reduce the input data size. Specifically for ImageNet classification with the same input size, the proposed method achieves 1.41% and 0.66% top-1 accuracy improvements on ResNet-50 and MobileNetV2, respectively. Even with half input size, the proposed method still improves the top-1 accuracy on ResNet-50 by 1%. In addition, we observe a 0.8% average precision improvement on Mask R-CNN for instance segmentation on the COCO dataset.
We present the preliminary high-level design and features of DynamicPPL.jl, a modular library providing a lightning-fast infrastructure for probabilistic programming. Besides a computational performance that is often close to or better than Stan, DynamicPPL provides an intuitive DSL that allows the rapid development of complex dynamic probabilistic programs. Being entirely written in Julia, a high-level dynamic programming language for numerical computing, DynamicPPL inherits a rich set of features available through the Julia ecosystem. Since DynamicPPL is a modular, stand-alone library, any probabilistic programming system written in Julia, such as Turing.jl, can use DynamicPPL to specify models and trace their model parameters. The main features of DynamicPPL are: 1) a meta-programming based DSL for specifying dynamic models using an intuitive tilde-based notation; 2) a tracing data-structure for tracking RVs in dynamic probabilistic models; 3) a rich contextual dispatch system allowing tailored behaviour during model execution; and 4) a user-friendly syntax for probabilistic queries. Finally, we show in a variety of experiments that DynamicPPL, in combination with Turing.jl, achieves computational performance that is often close to or better than Stan.
We present an end-to-end algorithm for training deep neural networks to grasp novel objects. Our algorithm builds all the essential components of a grasping system using a forward-backward automatic differentiation approach, including the forward kinematics of the gripper, the collision between the gripper and the target object, and the metric of grasp poses. In particular, we show that a generalized Q1 grasp metric is defined and differentiable for inexact grasps generated by a neural network, and the derivatives of our generalized Q1 metric can be computed from a sensitivity analysis of the induced optimization problem. We show that the derivatives of the (self-)collision terms can be efficiently computed from a watertight triangle mesh of low-quality. Put together, our algorithm allows the computation of grasp poses for high-DOF grippers in unsupervised mode with no ground truth data or improves the results in supervised mode using a small dataset. Our new learning algorithm significantly simplifies the data preparation for learning-based grasping systems and leads to higher qualities of learned grasps on common 3D shape datasets, achieving a 22% higher success rate on physical hardware and 0.12 higher value of the Q1 grasp quality metric.
We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variation, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category. In particular, CASS is modeled as the latent space of a deep generative model of canonical 3D shapes with normalized pose and size. We train a variational auto-encoder (VAE) for generating 3D point clouds in the canonical space from an RGBD image. The VAE is trained in a cross-category fashion, exploiting the publicly available large 3D shape repositories. Since the 3D point cloud is generated in normalized pose and size, the encoder of the VAE learns view-factorized RGBD embedding. It maps an RGBD image in arbitrary view into a pose-independent 3D shape representation. Object pose and size are then estimated via contrasting it with a pose-dependent feature of the input RGBD extracted with a separate deep neural networks. We integrate the learning of CASS and pose and size estimation into an end-to-end trainable network, achieving the state-of-the-art pose and size accuracy.
Based on further studying the low-rank subspace clustering (LRSC) and L2-graph subspace clustering algorithms, we propose a F-graph subspace clustering algorithm with a symmetric constraint (FSSC), which constructs a new objective function with a symmetric constraint basing on F-norm, whose the most significant advantage is to obtain a closed-form solution of the coefficient matrix. Then, take the absolute value of each element of the coefficient matrix, and retain the k largest coefficients per column, set the other elements to 0, to get a new coefficient matrix. Finally, FSSC performs spectral clustering over the new coefficient matrix. The experimental results on face clustering and motion segmentation show FSSC algorithm can not only obviously reduce the running time, but also achieve higher accuracy compared with the state-of-the-art representation-based subspace clustering algorithms, which verifies that the FSSC algorithm is efficacious and feasible.
We present a target-driven navigation approach for improving the cross-target and cross-scene generalization for visual navigation. Our approach incorporates an information-theoretic regularization into a deep reinforcement learning (RL) framework. First, we present a supervised generative model to constrain the intermediate process of the RL policy, which is used to generate a future observation from a current observation and a target. Next, we predict a navigation action by analyzing the difference between the generated future and the current. Our approach takes into account the connection between current observations and targets, and the interrelation between actions and visual transformations. This results in a compact and generalizable navigation model. We perform experiments on the AI2-THOR framework and the Active Vision Dataset (AVD) and show at least 7.8% improvement in navigation success rate and 5.7% in SPL, compared to the supervised baseline, in unexplored environments.
Cross-scene model adaption is a crucial feature for camera relocalization applied in real scenarios. It is preferable that a pre-learned model can be quickly deployed in a novel scene with as little training as possible. The existing state-of-the-art approaches, however, can hardly support few-shot scene adaption due to the entangling of image feature extraction and 3D coordinate regression, which requires a large-scale of training data. To address this issue, inspired by how humans relocalize, we approach camera relocalization with a decoupled solution where feature extraction, coordinate regression and pose estimation are performed separately. Our key insight is that robust and discriminative image features used for coordinate regression should be learned by removing the distracting factor of camera views, because coordinates in the world reference frame are obviously independent of local views. In particular, we employ a deep neural network to learn view-factorized pixel-wise features using several training scenes. Given a new scene, we train a view-dependent per-pixel 3D coordinate regressor while keeping the feature extractor fixed. Such a decoupled design allows us to adapt the entire model to novel scene and achieve accurate camera pose estimation with only few-shot training samples and two orders of magnitude less training time than the state-of-the-arts.
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.