Computer Science and Programming

2022-08-04 12:33:06 UFO: segmentation 140+ FPS

Unified Transformer Framework for Co-Segmentation, Co-Saliency & Salient Object Detection. All in one!


𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
Unified framework for co-segmentation
Co-segmentation, co-saliency, saliency
Block for long-range dependencies
Able to reach for 140 FPS in inference
The new SOTA on multiple datasets

Paper:
https://arxiv.org/pdf/2203.04708v2.pdf

Code:
https://github.com/suyukun666/UFO


@computer_science_and_programming Open / Comment

2022-07-25 13:15:48 Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration

learnable parameter to dynamically adjust the semantic correlations and spatial context intensities for effective information propagation.

Github: https://github.com/164140757/scm

Paper: https://arxiv.org/abs/2207.10447v1

Dataset: https://paperswithcode.com/dataset/cub-200-2011

@computer_science_and_programming Open / Comment

2022-07-15 12:33:09 Instance Shadow Detection with A Single-Stage Detector

Deep framework, and an evaluation metric to approach this new task.

Github: https://github.com/stevewongv/InstanceShadowDetection

Instance Shadow Detection: https://github.com/stevewongv/SSIS

Video:



Colab: https://colab.research.google.com/drive/1y9UpS5uA1YuoMyvYVzcKL4ltA_FDu_x0?usp=sharing

Paper: https://arxiv.org/abs/2207.04614v1

Datasets: https://paperswithcode.com/dataset/soba

@computer_science_and_programming Open / Comment

2022-07-06 14:43:50 Prosody Cloning in Zero-Shot Multispeaker Text-to-Speech

IMS Toucan is a toolkit for teaching, training and using state-of-the-art Speech Synthesis models.

Github: https://github.com/DigitalPhonetics/IMS-Toucan
https://github.com/rballester/tntorch

Pre-Generated Audios: https://multilingualtoucan.github.io/

Cloning prosody across speakers: https://toucanprosodycloningdemo.github.io/

Interactive Demo: https://huggingface.co/spaces/Flux9665/IMS-Toucan

Paper: https://arxiv.org/abs/2206.12229v1

@computer_science_and_programming Open / Comment

2022-06-27 10:12:11 CVPR 2022 open access

All accepted papers list:
https://openaccess.thecvf.com/CVPR2022?day=2022-06-21

@computer_science_and_programming Open / Comment

2022-06-17 07:50:43 MIT, Introduction to Deep Learning, 2022 Lecture series

Website:
http://introtodeeplearning.com/

Lecture:




@computer_science_and_programming Open / Comment

2022-06-07 09:35:01 Squeezeformer: An Efficient Transformer for Automatic Speech Recognition

Github: https://github.com/kssteven418/squeezeformer

Paper: https://arxiv.org/abs/2206.00888v1

Dataset: https://paperswithcode.com/dataset/librispeech

@computer_science_and_programming Open / Comment

2022-05-30 14:52:20 AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition

Github: https://github.com/ShoufaChen/AdaptFormer

Paper: https://arxiv.org/abs/2205.13535v1

Dataset: https://paperswithcode.com/dataset/something-something-v2

@computer_science_and_programming Open / Comment

2022-05-20 12:34:06 RefineMask: Towards High-Quality Instance Segmentation
with Fine-Grained Features (CVPR 2021)

Paper:
https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_RefineMask_Towards_High-Quality_Instance_Segmentation_With_Fine-Grained_Features_CVPR_2021_paper.pdf

Source:
https://github.com/zhanggang001/RefineMask

@computer_science_and_programming Open / Comment

2022-05-10 09:30:52 Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)

Github: https://github.com/dvlab-research/focalsconv

Paper: https://arxiv.org/abs/2204.12463

Dataset: https://paperswithcode.com/dataset/nuscenes

@computer_science_and_programming Open / Comment