The goal of *generalized* few-shot semantic segmentation (GFSS) is to recognize *novel-class* objects through training with a few annotated examples and the *base-class* model that learned the knowledge about the base classes. Unlike the classic few-shot semantic segmentation, GFSS aims to classify pixels into both base and novel classes, meaning it is a more practical setting. Current GFSS methods rely on several techniques such as using combinations of customized modules, carefully designed loss functions, meta-learning, and transductive learning. However, we found that a simple rule and standard supervised learning substantially improve the GFSS performance. In this paper, we propose a simple yet effective method for GFSS that does not use the techniques mentioned above. Also, we theoretically show that our method perfectly maintains the segmentation performance of the base-class model over most of the base classes. Through numerical experiments, we demonstrated the effectiveness of our method. It improved in novel-class segmentation performance in the $1$-shot scenario by $6.1$% on the PASCAL-$5^i$ dataset, $4.7$% on the PASCAL-$10^i$ dataset, and $1.0$% on the COCO-$20^i$ dataset. Our code is publicly available at https://github.com/IBM/BCM.

Deep neural networks have recently led to promising results for the task of multiple sound source localization. Yet, they require a lot of training data to cover a variety of acoustic conditions and micro-phone array layouts. One can leverage acoustic simulators to inexpensively generate labeled training data. However, models trained on synthetic data tend to perform poorly with real-world recordings due to the domain mismatch. Moreover, learning for different microphone array layouts makes the task more complicated due to the infinite number of possible layouts. We propose to use adversarial learning methods to close the gap between synthetic and real do-mains. Our novel ensemble-discrimination method significantly improves the localization performance without requiring any label from the real data. Furthermore, we propose a novel explicit transformation layer to be embedded in the localization architecture. It enables the model to be trained with data from specific microphone array layouts while generalizing well to unseen layouts during inference.

In this paper, we propose novel deep learning based algorithms for multiple sound source localization. Specifically, we aim to find the 2D Cartesian coordinates of multiple sound sources in an enclosed environment by using multiple microphone arrays. To this end, we use an encoding-decoding architecture and propose two improvements on it to accomplish the task. In addition, we also propose two novel localization representations which increase the accuracy. Lastly, new metrics are developed relying on resolution-based multiple source association which enables us to evaluate and compare different localization approaches. We tested our method on both synthetic and real world data. The results show that our method improves upon the previous baseline approach for this problem.

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not achieve the desired performance in the real world due to a gap between synthetic and real images. We propose a method that transfers learned detection of an object position from a simulation environment to the real world. This method uses only a significantly limited dataset of real images while leveraging a large dataset of synthetic images using variational autoen-coders. Additionally, the proposed method consistently performed well in different lighting conditions, in the presence of other distractor objects, and on different backgrounds. Experimental results showed that it achieved accuracy of 1.5 mm to 3.5 mm on average. Furthermore, we showed how the method can be used in a real-world scenario like a “pick-and-place” robotic task.

The high precision assembly of mechanical parts requires precision that exceeds that of robots. Conventional part-mating methods used in the current manufacturing require numerous parameters to be tediously tuned before deployment. We show how a robot can successfully perform a peg-in-hole task with a tight clearance through training a recurrent neural network with reinforcement learning. In addition to reducing manual effort, the proposed method also shows a better fitting performance with a tighter clearance and robustness against positional and angular errors for the peg-in-hole task. The neural network learns to take the optimal action by observing the sensors of a robot to estimate the system state. The advantages of our proposed method are validated experimentally on a 7-axis articulated robot arm.

A method of micromanipulation using a microcoil array is proposed. Active coils drive permanent magnets on a work platform. The magnets can push mechanical parts to perform 2-dimensional assembly. Three-dimensional operation may be achieved from 2D magnet motion when the permanent magnets are part of a closed loop spatial linkage. Manipulation on a 4 cm/spl times/4 cm coil array was tested. Based on this large scale experiment, we fabricated a microcoil array using IC-based processes. A 4/spl times/4 microcoil array with 8 turns per coil was fabricated. The chip area including bonding pads, is 3.6 mm/spl times/3.6 mm. The minimum current necessary to attract a magnet and its speed were evaluated. A 0.6 mm/spl times/0.6 mm/spl times/0.3 mm magnet moved at 79 mm/s. The top speed for a magnet to follow a square trajectory was evaluated, and it was demonstrated that a 1.1 mg magnet could push a 13.4 mg object out of microcoil array.

Magnetic force is useful for manipulating objects without contact. We propose a method of micromanipulation using this force. The concept is based upon linkage-free end-effectors and different from the concept of serial-link manipulators. Multiple cylindrical permanent magnets work as end-effectors. The permanent magnets on the stage, above an arrangement of solenoids, manipulate objects by pushing. Furthermore, 3D manipulation can be achieved as a link mechanism is used. A prototype of the manipulator has been fabricated. The manipulation field measures 4.5 cm/spl times/4.5 cm and consists of 6/spl times/6 solenoids. The magnets are 6 mm in diameter. The ability of a magnet to follow a control signal and the force for pushing an object have been evaluated. Furthermore, a prototype of the link mechanism has been fabricated. The vertical force for pushing down and pulling up an object have also been evaluated.