Comments (6)
90.6 means [self-supervised pretrain on K400 (no label)] -> [finetune on UCF101]
96.8 means [supervised pretrain on K400 (use label)] -> [finetune on UCF101]
The meaningful random init baseline is 77.0 in our Table 1, meaning [pretrain on nothing] -> [finetune on UCF101].
from coclr.
Hi, thanks for the answer. I checked [1] again, and found out in fully-supervised learning, I3D pretrained on nothing and achieve 88.8% (Table 4) with rgb only. I am wondering what makes such a big gap between 77.0 and 88.8?
[1] Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
from coclr.
- UCF101 top1 88.8% in "Quo Vadis, Action Recognition" Table 4 is two-stream result. Two-stream is known to be better than single stream.
- Video resolution, they use 224x224, we use 128x128. Larger resolution is known to be better than low resolution on classification tasks.
- Also backbone is different, they use I3D (inflated Inception network), we use S3D. But I think 1&2 is the main reason for this baseline accuracy gap.
from coclr.
I see! Appreciate your help! I am wondering is there any ImageNet pretrained-weights provided by S3D? As many paper claimed using it.
from coclr.
S3D is a 3D CNN, usually being used for the video input.
I don't think people train S3D on ImageNet. If there is paper claiming using S3D with ImageNet weights, I guess that means "ImageNet inflated" weights, where they take the I3D network, expand convolution kernels by coping multiple times along the time dimension.
from coclr.
Agree! Thanks very much!:)
from coclr.
Related Issues (20)
- 2-Stream evaluation on UCF101 HOT 1
- Possible to share S3D model trained on UCF101 -RGB only end to end fine tuned (reported accuracy 81.4) HOT 1
- Making Kinetics-400 RGB lmdb dataset. HOT 2
- Command for Linear Probe and Finetuning HOT 1
- How to generate corresponding 'video_source.json'? HOT 1
- AttributeError: 'str' object has no attribute 'decode' HOT 2
- information about requirements and dateset preparations HOT 1
- lmdb_dataset.py txn.get(self.get_video_id[name].encode('ascii'))) HOT 6
- Issue about DistributedDataParallel(DDP) HOT 3
- Reproducing CoCLR RGB Results??? HOT 1
- fusing two-stream predictions HOT 1
- Question about the code in eval/main_classifier.py HOT 2
- question about ten crop
- Can we design a downstream task for action detection? HOT 5
- Two-stream feature
- TypeError: order must be str, not int HOT 2
- main_classifier.py: error: unrecognized arguments: --final_bn
- I can't download the pretrained model HOT 1
- A question about convert_video_to_lmdb.py HOT 2
- Download Link of Checkpoint HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from coclr.