Tweet

@ai_fast_track

More from @ai_fast_track

AI Fast Track

@ai_fast_track

2 Nov

YOLO Real-Time (YOLO-ReT) architecture targets edge devices.

It achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO using MobileNetV2×0.75 backbone.

Here is a brief description of the YOLO-ReT 👇

Both model accuracy and execution time (Frame Per Second) are crucial when deploying a model on edge device. YOLO-ReT is based on these 2 ideas:

⏹ Backbone Truncation: Only 60% of the backbone is initialised with pretrained weights. Using all the weights harms model accuracy

⏹ Raw Feature Collection and Redistribution (RFCR):

📌 Fuse {C2, C3, C4} into C5 layer (fused feature map)

📌 Discard last CNN layers

📌 Pass the fused feature map through a 5x5 Mobile Convolution block (MBConv)

Read 6 tweets

AI Fast Track

@ai_fast_track

27 Oct

✨Common Object Detector Architecture you should be familiar with:

📌 Common object detectors are divided into One-Stage Detectors (OSD), and Two-Stage Detectors (TSD)

📌 Both OSD and TSD can be either anchor-based (relying on anchor boxes) or anchor-free

📌 OSD use the whole feature maps to predict bounding boxes/labels: Dense Prediction

📌 TSD have an extra step hence two-stage: extracting proposals (regions of interest)

📌 Proposals are used to extract feature map regions to predict bounding boxes/labels: Sparse Prediction

📌 TSD don't use the whole feature map for prediction

📌 TSD (e.g. Faster R-CNN) used to be more accurate than STD (e.g. SSD, YOLO, etc.)

📌 STD (e.g. EfficientDet, RetinaNet, VFNet, YOLOX, etc.) recently show better results than TSD

📌 STD are faster than TSD

Read 5 tweets

AI Fast Track

@ai_fast_track

25 Oct

🧐7 things you should know about the Focal Loss:

📌 It was introduced in the RetinaNet paper to address the foreground-background class imbalance encountered during training of dense detectors (one-stage detectors)
...

📌 It’s derived from the cross-entropy loss such that it down-weights the loss assigned to well-classiﬁed examples. It's used in the classification head.

📌 It’s used in many one-stage object detection models: EfficientDet, FCOS, VFNet, and many other models

📌 It can also be used in two-stage object detection models: e.g. Sparse R-CNN

📌 It crashes losses associated to easy examples: for a confidence score of 0.9, the focal loss is 100 times smaller than the cross-entropy loss (see figure here above)

Read 5 tweets

AI Fast Track

@ai_fast_track

21 Oct

🥇YOLOX beat YOLOv5. They won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021).

I briefly explain how they created it, here below👇

YOLOX will be soon supported in our IceVision Framework (Repo: github.com/airctic/IceVis…)

Considering YOLOv4 and YOLOv5 might be a little bit over-optimized for the anchor-based pipeline, they choose YOLOv3 as their starting point.

They transformed YOLOv3 into YOLOX by using the following techniques:

🟦 Decoupled head,
🟦 Anchor-free architecture (like FCOS), and

🟦 Advanced label assigning strategy (SimOTA)

They also used some other training strategies such as: adding EMA weights updating, cosine LR schedule, IoU loss, and IoU-aware branch.

pdf: arxiv.org/pdf/2107.08430…
abs: arxiv.org/abs/2107.08430
repo: github.com/Megvii-BaseDet…

Read 4 tweets

AI Fast Track

@ai_fast_track

20 Oct

@NVIDIAAI

Here is a cool approach for effective labeling from @NVIDIAAI

📰Active Learning for Deep Object Detection via Probabilistic Modeling

Object detection labeling is both time consuming and expensive. Active learning to the rescue:
🧵

🟧They use mixture density networks to estimate, in one forward pass of a single model, both localization and classification uncertainties

🟧 They leverage them in the scoring function for active learning.

🟧 Then, those data points with the top-K scores are sent for labeling

🟧 They use SSD pytorch for their implementation

📰Paper: Active Learning for Deep Object Detection via Probabilistic Modeling

PDF: arxiv.org/abs/2103.16130
Abs: arxiv.org/pdf/2103.16130…
Repo: github.com/NVlabs/AL-MDN

Read 4 tweets

AI Fast Track

@ai_fast_track

30 Dec 20

CornerNet Follow-up Paper- CenterNet: Keypoint Triplets for Object Detection
🧵
- CornerNet focus on detecting object edges leads to generating boxes sharing similar edges👇

- 🔥CenterNet Solution🔥: It adds a Center Pooling

- Objects central parts have richer features (map) than corner regions (those rely on Corner Pooling to compensate features lack). CenterNet correctly detects objects by checking the central parts, in addition to their corners.

Performance Comparison: CenterNet ranks among the top SOTA Two-Stage Detectors.

Read 6 tweets

Share this page!

AI Fast Track

Try unrolling a thread yourself!

More from @ai_fast_track

AI Fast Track

AI Fast Track

AI Fast Track

AI Fast Track

AI Fast Track

AI Fast Track

Did Thread Reader help you today?

Like this author's thread?