Tweet

@ai_fast_track

https://twitter.com/ai_fast_track/status/1458493806362378244

https://twitter.com/ai_fast_track/status/1466998473312677894

https://twitter.com/ai_fast_track/status/1466440518787813381

https://twitter.com/ai_fast_track/status/1456648693969559561

https://twitter.com/ai_fast_track/status/1461789169651441664

https://twitter.com/ai_fast_track/status/1461440883291787266

https://twitter.com/ai_fast_track/status/1465773297837215750

https://twitter.com/ai_fast_track/status/1456989190936137728

https://twitter.com/ai_fast_track/status/1455214027139862535

https://twitter.com/ai_fast_track/status/1467532334073323523

@ai_fast_track

More from @ai_fast_track

AI Fast Track (37/45)

@ai_fast_track

5 Dec

@kaggle

Interested in testing several object detection models in one single notebook, in @kaggle Competitions?

Here is a getting started notebook where you could test 5 different models: VFNet, EfficientDet, RetinaNet, Faster-RCNN, and YOLOv5.

🎁 Kaggle NB: kaggle.com/faridone/icevi…

The kaggle notebook is a stripped one. Check out the long version in Colab.

🎁 Colab NB: airctic.com/0.11.0/getting…

That way, you have access to 2 platforms where you get familiar with IceVision

We have a #kaggle dedicated channel in our IceVision forum where kagglers share their knowledge.

• IceVision Forum: discord.gg/JDBeZYK

• IceVision Repo: github.com/airctic/IceVis…

Read 4 tweets

AI Fast Track (37/45)

@ai_fast_track

4 Dec

@fastdotai

💡 Prop Tip to 🚀 fast track your object detection training

All @fastdotai users use this method for free!

It's fine_tune()

We noticed an important increase in the COCO Metric when we train object detection models using this method even with the simple default values

Fine tuning has 2 phases:

🧊 Phase 1: Freeze your model's backbone and neck. Train your model for a couple of epochs (e.g. 1 to 5)

📈 Phase 2: Unfreeze the whole model. Train for higher number of periods (depending on your dataset, and how hard/easy your data is)

Phase 1 is a kind of warm-up for your model head.

Here is an example showing how to call the fine_tune() method.

In this case, we freeze both the backbone and the neck for 1 epoch in phase 1, and train for 20 epochs in phase 2.

Read 5 tweets

AI Fast Track (37/45)

@ai_fast_track

2 Dec

Detecting small object detection is one of the most challenging tasks in object detection.

❓ Want to know an effective way to overcome that❓

Check out the SAHI integration in IceVision🧊
👇

All IceVision models transparently support SAHI (MMDetection, EfficientDet, Torchvision, and YOLOv5). The results are quite impressive!

SAHI is a very cool library that drastically improves detection of small objects.

📌 It is simply used at inference time

📌 It leverages high resolution images.

📌 Your training process remains the same as usual.

🔎 At the high level, this is how SAHI works:

1- It takes a high resolution (e.g.1920 x 1024 px), and divide it in patches (e.g. 128 x 128 px)

Read 7 tweets

AI Fast Track (37/45)

@ai_fast_track

30 Nov

🎉🎊🥳Day 30/30: Labeling data and training object detection models are time consuming and expensive.

Here is a Survey of Self-Supervised and Few-Shot Object Detection (FSOD). Those technique aim at alleviating those issues.

The authors have categorized, reviewed, and compared several few-shot and self-supervised object detection methods

📌 FSOD is about training a model on novel (unseen) object classes with little data. It still requires prior training on many labeled data of base (seen) classes

📌 Self-Supervised Learning (SSL) methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection

📌 Combining few-shot and self-supervised object detection is a promising research direction

Read 8 tweets

AI Fast Track (37/45)

@ai_fast_track

26 Nov

Day 26/30: General Gaussian Heatmap Labeling is Arbitrary-Oriented Object Detection AOOD

📌 It uses an anchor-free object-adaptation label assignment strategy to deﬁne positive candidates based on 2D GH, reﬂecting shape and direction features of arbitrary-oriented objects.

📌 GGHL improves the AOOD performance with low parameter-tuning and time costs.

📌 It is also applicable to most AOOD methods to improve their performance including lightweight models.

📰 Paper: A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection

abs: arxiv.org/abs/2109.12848…
pdf: arxiv.org/pdf/2109.12848…

Read 4 tweets

AI Fast Track (37/45)

@ai_fast_track

24 Nov

Day 24/30: 🥇 EfficientDet is a very popular object detection model for a good reason!

Let’s see why

📌 EfficientDet achieved State-Of-The-Art (SOTA) accuracy while reducing both the size of parameters, and the FLOPS, when it was released. It’s still a very good contender.

📌 Before introducing EfficientDet, models were getting impressively big to achieve SOTA results

❓ The authors asked the following question:
Is it possible to build a scalable detection architecture with both higher accuracy and better efficiency across # resource constraints?

So, they systematically studied neural network architecture design choices for object detection, and proposed several key optimizations to improve efficiency:

1- A weighted bi-directional feature pyramid network (BiFPN), which allows easy and fast multiscale feature fusion

Read 8 tweets

Share this page!

AI Fast Track (37/45)

Try unrolling a thread yourself!

More from @ai_fast_track

AI Fast Track (37/45)

AI Fast Track (37/45)

AI Fast Track (37/45)

AI Fast Track (37/45)

AI Fast Track (37/45)

AI Fast Track (37/45)

Did Thread Reader help you today?

Like this author's thread?