Densely Connected Convolutional Networks · HackerPapers discussions

Densely Connected Convolutional Networks — mentioned by godelski

Thu, 18 Sep 2025 23:08:48 GMT

You're correct, I also added some info in a sibling comment that might interest you. But you might also be interested in reading the DenseNet paper[0]. While it's convs, the ideas still apply. There's actually a lot of research in this topic though they'll be in more "theory" papers and the ideas are slow to propagate into the mainstream works. [0] https://arxiv.org/abs/1608.06993

Paper and discussion history. A mention is not an endorsement.

Densely Connected Convolutional Networks — mentioned by gwern

Sun, 24 Mar 2024 14:25:31 GMT

Yeah, you can't change the model much with low LRs. That's the point! Same reason you don't get continual-learning if you just keep using low LRs: https://arxiv.org/abs/2403.08763 You need to really shake up the model if you want to learn some genuinely better (ie. different) internal representations that exploits the DenseNet (https://arxiv.org/abs/1608.06993)/LTG-BERT (https://arxiv.org/abs/2311.02265) arch you're using here.

Paper and discussion history. A mention is not an endorsement.

Densely Connected Convolutional Networks — mentioned by tmp65535

Thu, 30 Dec 2021 16:16:33 GMT

Here is the first (?) application of deep learning to improve the pornography experience, an Android app called Melondream published in early 2017: http://driftwheeler.com Surprisingly, almost 5 years after being published, this app still serves thousands of user sessions per day. That rate continues to slowly grow. Except for its user interface, the whole app (client and server) was written in Go (https://pkg.go.dev/golang.org/x/mobile/cmd/gomobile). It uses densenet feature vectors (https://arxiv.org/abs/1608.06993) to allow "touch-to-search" (ha!) with a fractional norm distance metric…

Paper and discussion history. A mention is not an endorsement.

Densely Connected Convolutional Networks — mentioned by nomad225

Wed, 02 Jun 2021 20:46:30 GMT

Densely Connected Convolutional Networks (https://arxiv.org/abs/1608.06993) use the idea you're talking about quite effectively.

Paper and discussion history. A mention is not an endorsement.

Densely Connected Convolutional Networks — mentioned by tanilama

Tue, 14 Nov 2017 07:25:52 GMT

https://arxiv.org/abs/1512.03385 Deep Residual Learning for Image Recognition Citation 4000+. Milestone of image recognition. https://arxiv.org/abs/1502.01852 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. Also known as PreLU, citation 1600+. The initialization scheme is widely adapted by a lot of following works. Those are the most influential ones, all come from Kaiming He. He is now in FAIR, and keeps very good publication record, with works like MASK-RCNN, but that doesn't really count as purely Chinese contribution, so we skipped here. Some…

Paper and discussion history. A mention is not an endorsement.

Densely Connected Convolutional Networks — HN submission

Wed, 26 Jul 2017 02:16:28 GMT

Densely Connected Convolutional Networks: CVPR 2017 Best Paper Award Winner

29 points; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Densely Connected Convolutional Networks — mentioned by iraphael

Sun, 23 Jul 2017 01:07:44 GMT

* Densely Connected Convolutional Networks [0] by Gao Huang, Zhuang Liu, Laurens van der Maaten, & Kilian Q. Weinberger. * Learning from Simulated and Unsupervised Images through Adversarial Training [1] by Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Joshua Susskind, Wenda Wang, & Russell Webb CVPR 2017 Best Paper Honorable Mention Awards * Annotating Object Instances with a Polygon-RNN [2] by Lluís Castrejón, Kaustav Kundu, Raquel Urtasun, & Sanja Fidler * YOLO9000: Better, Faster, Stronger [3] by Joseph Redmon & Ali Farhadi CVPR 2017 Best Student Paper Award * Computational Imaging on…

Paper and discussion history. A mention is not an endorsement.

Densely Connected Convolutional Networks — HN submission

Sat, 22 Jul 2017 20:17:59 GMT

Best paper award CVPR 2017 DenseNets

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Densely Connected Convolutional Networks — HN submission

Fri, 17 Feb 2017 15:22:14 GMT

Densely Connected Convolutional Networks

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Densely Connected Convolutional Networks — mentioned by ogrisel

Tue, 22 Nov 2016 19:05:36 GMT

For deep convnets the vanishing gradient problems can mostly be solved by using residual architectures. See: https://arxiv.org/abs/1603.05027 This is kind of related to solving the vanishing gradient issue in RNNs by using additive recurrent architectures like LSTMs and GRUs. Alternatively it's possible to use concatenative skip connections as in DenseNets: https://arxiv.org/abs/1608.06993 Still using 1000 layers is useless in practice. State of the art image classification models are in the range 30-100 layers with residual connections and varying numbers of channels per layer depending on…

Paper and discussion history. A mention is not an endorsement.