In the era of vision Transformers, the recent success of VanillaNet shows the huge potential of simple and concise convolutional neural networks (ConvNets). Where such models mainly focus on runtime, it is also crucial to simultaneously focus on other aspects, e.g., FLOPs, parameters, etc, to strengthen their utility further. To this end, we introduce a refreshing ConvNet macro design called Columnar Stage Network (CoSNet). CoSNet has a systematically developed simple and concise structure, smaller depth, low parameter count, low FLOPs, and attention- less operations, well suited for resource-constrained deployment. The key novelty of CoSNet is deploying parallel convolutions with fewer kernels fed by input replication, using columnar stacking of these convolutions, and minimizing the use of 1×1 convolution layers. Our comprehensive evaluations show that CoSNet rivals many renowned ConvNets and Transformer designs under resource-constrained scenarios. Pretrained models shall be open-sourced.

Channel pruning approaches for convolutional neural networks (ConvNets) deactivate the channels, statically or dynamically, and require special implementation. In addition, channel squeezing in representative ConvNets is carried out via$1\times 1$convolutions which dominates a large portion of computations and network parameters. Given these chal-lenges, we propose an effective multi-purpose module for dynamic channel sampling, namely Pick-or-Mix (PiX), which does not require special implementation. PiX divides a set of channels into subsets and then picks from them, where the picking decision is dynamically made per each pixel based on the input activations. We plug PiX into prominent ConvNet architectures and verify its multi-purpose utilities. After replacing$1\times 1$channel squeezing layers in ResNet with PiX, the network becomes 25% faster without losing accuracy. We show that PiX allows ConvNets to learn bet-ter data representation than widely adopted approaches to enhance networks' representation power (e.g., SE, CBAM, AFF, SKNet, and DWP). We also show that PiX achieves state-of-the-art performance on network downscaling and dynamic channel pruning applications. Code: https://github.com/ashishkumar822/PiX

In this work, we present a robotic solution to automate the task of wall construction. To that end, we present an end-to-end visual perception framework that can quickly detect and localize bricks in a clutter. Further, we present a light computational method of brick pose estimation that incorporates the above information. The proposed detection network predicts a rotated box compared to YOLO and SSD, thereby maximizing the object’s region in the predicted box regions. In addition, precision (P), recall (R), and mean-average-precision (mAP) scores are reported to evaluate the proposed framework. We observed that for our task, the proposed scheme outperforms the upright bounding box detectors. Further, we deploy the proposed visual perception framework on a robotic system endowed with a UR5 robot manipulator and demonstrate that the system can successfully replicate a simplified version of the wall-building task in an autonomous mode.

In this work, we present a pragmatic approach to enable unmanned aerial vehicle (UAVs) to autonomously perform highly complicated tasks of object pick and place. This paper is largely inspired by challenge-2 of MBZIRC 2020 and is primarily focused on the task of assembling large 3D structures in outdoors and GPS-denied environments. Primary contributions of this system are: (i) a novel computationally efficient deep learning based unified multi-task visual perception system for target localization, part segmentation, and tracking, (ii) a novel deep learning based grasp state estimation, (iii) a retracting electromagnetic gripper design, (iv) a remote computing approach which exploits state-of-the-art MIMO based high speed (5000Mb/s) wireless links to allow the UAVs to execute compute intensive tasks on remote high end compute servers, and (v) system integration in which several system components are weaved together in order to develop an optimized software stack. We use DJI Matrice-600 Pro, a hexrotor UAV and interface it with the custom designed gripper. Our framework is deployed on the specified UAV in order to report the performance analysis of the individual modules. Apart from the manipulation system, we also highlight several hidden challenges associated with the UAVs in this context.

In this paper, we present a semi supervised deep quick learning framework for instance detection and pixelwise semantic segmentation of images in a dense clutter of items. The framework can quickly and incrementally learn novel items in an online manner by real-time data acquisition and generating corresponding ground truths on its own. To learn various combinations of items, it can synthesize cluttered scenes, in real time. The overall approach is based on the tutor-child analogy in which a deep network (tutor) is pretrained for class-agnostic object detection which generates labeled data for another deep network (child). The child utilizes a customized convolutional neural network head for the purpose of quick learning. There are broadly four key components of the proposed framework: semi supervised labeling, occlusion aware clutter synthesis, a customized convolutional neural network head, and instance detection. The initial version of this framework was implemented during our participation in Amazon Robotics Challenge (ARC), 2017. Our system was ranked 3rd rd, 4th and 5 th worldwide in pick, stow-pick and stow task respectively. The proposed framework is an improved version over ARC'17 where novel features such as instance detection and online learning has been added.

One of the main challenges in the vision-based grasping is the selection of feasible grasp regions while interacting with novel objects. Recent approaches exploit the power of convolutional neural network (CNN) to achieve accurate grasping at the cost of high computational power and time. In this paper, we present a novel unsupervised learning based algorithm for the selection of feasible grasp regions. Unsupervised learning infers the pattern in dataset without any external labels. We applied k-means clustering at every sampling stage in image plane to identify the grasp regions, followed by axes assignment method. We define a novel concept of Grasp Decide Index (GDI) to select the best grasp pose in the image plane. We have conducted several experiments in clutter or isolated environment on standard objects of Amazon Robotics Challenge 2017 and Amazon Picking Challenge 2016. We compared the results with prior learning based approaches to validate the robustness and adaptive nature of our algorithm for a variety of novel objects in different domains.