Tweet

@ai_fast_track

More from @ai_fast_track

AI Fast Track (26/30)

@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

AI Fast Track (26/30)

@ai_fast_track

23 Nov

@ai_fast_track

I’m at Day 23 of my 30 posts (on Object Detection) in 30 days challenge

I gathered 12 visual summaries on OD Modeling 🎁

A lot of people find those posts helpful, follow @ai_fast_track to catch the upcoming posts, and give this tweet a quick retweet 🙏

Summary of summaries👇

https://twitter.com/ai_fast_track/status/1453368771285032971

1- Common Object Detector Architecture you should be familiar with:

https://twitter.com/ai_fast_track/status/1453368771285032971

https://twitter.com/ai_fast_track/status/1460297658472574982

2- Four Feature Pyramid Network (FPN) Designs you should know:

https://twitter.com/ai_fast_track/status/1460297658472574982

Read 14 tweets

AI Fast Track (26/30)

@ai_fast_track

20 Nov

FCOS is an an anchor-free object detector.

It was one of first competitors of anchor-based single/two stage object detectors.

Understanding FCOS will help understanding other model inspired by FCOS.

Summary ...👇

📌 FCOS reformulates object detection in a per-pixel prediction fashion

📌 It uses multi-level prediction to improve the recall and resolve the ambiguity resulted from overlapped bounding boxes

📌 It proposes “center-ness” branch, which helps suppress the low-quality detected bounding boxes and improves the overall performance by a large margin

📌 It avoids complex computation such as the intersection-over-union (IoU)

Read 6 tweets

AI Fast Track (26/30)

@ai_fast_track

18 Nov

How to create a robustness evaluation dataset?

"Natural Adversarial Objects" (NAO) dataset is a challenging robustness evaluation dataset for models trained on MSCOCO

📌 Models generally perform well on large scale training sets

📌 They generalize on test sets coming from the same distribution

📌 When using NAO dataset, EfficientDet-D7 mAP reduced by 74.5% compared to MSCOCO

📌 Faster RCNN reduced by 36.3% compared to MSCOCO

📌 They evaluated 7 SOTA models, and showed they consistently fail to perform accurately on NAO, comparing to MSCOCO

📌 The drop is present on both in-distribution and out-of-distribution objects

Read 6 tweets

AI Fast Track (26/30)

@ai_fast_track

17 Nov

❇VFNet: A very interesting model that isn’t under the radar. You should give it a try :)

VariFocalNet: An IoU-aware Dense Object Detector

🧊 Background:
📌 Accurately ranking candidate detections is crucial for dense object detectors to achieve high performance
...

📌 Prior work uses the classification score or a combination of classification and predicted localization scores (centerness) to rank candidates.

📌 Those 2 scores are still not optimal

🧊 Novelty:
📌 VFNet proposes to learn an IoU-Aware Classification Score (IACS)

📌IACS is used as a joint representation of object presence confidence and localization accuracy using IoU

📌 VFNet introduces the VariFocal Loss

📌 The VariFocal Loss down-weights only negative examples for addressing the class imbalance problem during training

Read 7 tweets

AI Fast Track (26/30)

@ai_fast_track

16 Nov

@OpenMMLab

📢 The amazing @OpenMMLab just released a new project:

MMFlow: an open-source optical flow toolbox written in Pytorch

OpenMMLab hosts several impressive open-source projects for both academic research and industrial applications.

OpenMMLab covers a wide range of research topics of computer vision, e.g., classification, detection, segmentation and super-resolution.

📌 MMCV: Foundational library for computer vision.

📌 MIM: MIM Installs OpenMMLab Packages.

📌 MMClassification: Image classification toolbox and benchmark.

📌 MMDetection: Detection toolbox and benchmark.

📌 MMDetection3D: Next-generation platform for general 3D object detection.

📌 MMSegmentation: Semantic segmentation toolbox and benchmark.

Read 6 tweets

Share this page!

AI Fast Track (26/30)

Try unrolling a thread yourself!

More from @ai_fast_track

AI Fast Track (26/30)

AI Fast Track (26/30)

AI Fast Track (26/30)

AI Fast Track (26/30)

AI Fast Track (26/30)

AI Fast Track (26/30)

Did Thread Reader help you today?

Like this author's thread?