ControlFlag: A Self-Supervised Idiosyncratic Pattern Detection System for Software Control Structures

IntelLabs/control-flag 6 Nov 2020

Software debugging has been shown to utilize upwards of half of developers' time.

696
2.21 stars / hour

Parameter Prediction for Unseen Deep Architectures

facebookresearch/ppuda 25 Oct 2021

We introduce a large-scale dataset of diverse computational graphs of neural architectures - DeepNets-1M - and use it to explore parameter prediction on CIFAR-10 and ImageNet.

93
2.07 stars / hour

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ifzhang/ByteTrack arXiv 2021

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos.

 Ranked #1 on Multi-Object Tracking on MOT17 (using extra training data)

Multi-Object Tracking

1,231
2.04 stars / hour

Image-Based CLIP-Guided Essence Transfer

hila-chefer/targetclip 24 Oct 2021

We propose to perform such blending in a way that incorporates two latent spaces: that of the generator network and that of the semantic network.

78
1.75 stars / hour

NeRV: Neural Representations for Videos

haochen-rye/nerv 26 Oct 2021

In contrast, with NeRV, we can use any neural network compression method as a proxy for video compression, and achieve comparable performance to traditional frame-based video compression approaches (H. 264, HEVC \etc).

Denoising Neural Network Compression +2

39
1.13 stars / hour

Wav2CLIP: Learning Robust Audio Representations From CLIP

descriptinc/lyrebird-wav2clip 21 Oct 2021

We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP).

Cross-Modal Retrieval Image Generation +2

67
1.01 stars / hour

SCENIC: A JAX Library for Computer Vision Research and Beyond

google-research/scenic 18 Oct 2021

Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond.

186
0.90 stars / hour

Layered Neural Atlases for Consistent Video Editing

ykasten/layered-neural-atlases 23 Sep 2021

We present a method that decomposes, or "unwraps", an input video into a set of layered 2D atlases, each providing a unified representation of the appearance of an object (or background) over the video.

Style Transfer Video Editing +2

49
0.86 stars / hour

MuJoCo: A physics engine for model-based control

deepmind/mujoco IEEE/RSJ IROS 2012

To facilitate optimal control applications and in particular sampling and finite differencing, the dynamics can be evaluated for different states and controls in parallel.

2,549
0.83 stars / hour

Resolution-robust Large Mask Inpainting with Fourier Convolutions

saic-mdal/lama 15 Sep 2021

We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function.

Image Inpainting LAMA

1,067
0.82 stars / hour