InAugment: Improving Classifiers via Internal Augmentation

8 Apr 2021moabarar/inaugment

Image augmentation techniques apply transformation functions such as rotation, shearing, or color distortion on an input image.

IMAGE AUGMENTATION

2
08 Apr 2021

Semantic Scene Completion via Integrating Instances and Scene in-the-Loop

8 Apr 2021yjcaimeow/SISNet

The key insight is that we decouple the instances from a coarsely completed semantic scene instead of a raw input image to guide the reconstruction of instances and the overall scene.

INDOOR SCENE UNDERSTANDING SCENE UNDERSTANDING

6
08 Apr 2021

BR-NS: an Archive-less Approach to Novelty Search

8 Apr 2021salehiac/BR-NS

In this paper, we discuss an alternative approach to novelty estimation, dubbed Behavior Recognition based Novelty Search (BR-NS), which does not require an archive, makes no assumption on the metrics that can be defined in the behavior space and does not rely on nearest neighbours search.

1
08 Apr 2021

Learning What To Do by Simulating the Past

ICLR 2021 HumanCompatibleAI/deep-rlsp

Since reward functions are hard to specify, recent work has focused on learning policies from human feedback.

0
08 Apr 2021

ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition

8 Apr 2021microsoft/ORBIT-Dataset

To close this gap, we present the ORBIT dataset and benchmark, grounded in a real-world application of teachable object recognizers for people who are blind/low vision.

FEW-SHOT LEARNING OBJECT RECOGNITION

0
08 Apr 2021

Geometry-based Distance Decomposition for Monocular 3D Object Detection

8 Apr 2021MagicRock100/MonoRCNN

The experimental results show that our method achieves the state-of-the-art performance on the monocular 3D Object detection and Birds Eye View tasks on the KITTI dataset, and can generalize to images with different camera intrinsics.

AUTONOMOUS DRIVING MONOCULAR 3D OBJECT DETECTION

3
08 Apr 2021

Modulated Periodic Activations for Generalizable Local Functional Representations

8 Apr 2021lucidrains/siren-pytorch

Our approach produces generalizable functional representations of images, videos and shapes, and achieves higher reconstruction quality than prior works that are optimized for a single signal.

174
08 Apr 2021

Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation

8 Apr 2021fengpeng-yue/ASRTTS

Machine Speech Chain, which integrates both end-to-end (E2E) automatic speech recognition (ASR) and text-to-speech (TTS) into one circle for joint training, has been proven to be effective in data augmentation by leveraging large amounts of unpaired data.

DATA AUGMENTATION DOMAIN ADAPTATION SPEECH RECOGNITION

2
08 Apr 2021

Handwriting Transformers

8 Apr 2021ankanbhunia/Handwriting-Transformers

We propose a novel transformer-based styled handwritten text image generation approach, HWT, that strives to learn both style-content entanglement as well as global and local writing style patterns.

IMAGE GENERATION TEXT GENERATION

6
08 Apr 2021

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

8 Apr 2021speechbrain/speechbrain

The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory.

SPEECH ENHANCEMENT

1,745
08 Apr 2021