paper-with-me

Papers

Unsupervised Learning of Structured Representations via Closed-Loop Transcription

2022-10-30 · Shengbang Tong, Xili Dai, Yubei Chen, Mingyang Li, Zengyi Li, Brent Yi, Yann Lecun, Yi Ma

This paper proposes an unsupervised method for learning a unified representation that serves both discriminative and generative purposes. While most existing unsupervised learning approaches focus on a representation for only one of these two goals, we show that a unified representation can enjoy the mutual benefits of having both. Such a representation is attainable by generalizing the recently proposed \textit{closed-loop transcription} framework, known as CTRL, to the unsupervised setting. This entails solving a constrained maximin game over a rate reduction objective that expands features of all samples while compressing features of augmentations of each sample. Through this process, we see discriminative low-dimensional structures emerge in the resulting representations. Under comparable experimental conditions and network complexities, we demonstrate that these structured representations enable classification performance close to state-of-the-art unsupervised discriminative representations, and conditionally generated image quality significantly higher than that of state-of-the-art unsupervised generative models. Source code can be found at https://github.com/Delay-Xili/uCTRL.

📄 PDF Abstract BibTeX arXiv:2210.16782

Code (1)

delay-xili/uctrl 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
AdaGrad AdaGrad is a stochastic optimization method that adapts the learning rate to the parameters. It performs smaller updates for parameters associated with frequently occurring…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Incremental Learning of Structured Memory via Closed-Loop Transcription

2022-02-11 · Shengbang Tong, Xili Dai, Ziyang Wu, Mingyang Li 외

This work proposes a minimal computational model for learning structured memories of multiple object classes in an incremental setting. Our approach is based on establishing a closed-loop transcription between the classe…

Incremental Learning

Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction

2021-11-12 · Xili Dai, Shengbang Tong, Mingyang Li, Ziyang Wu 외

This work proposes a new computational framework for learning a structured generative model for real-world datasets. In particular, we propose to learn a closed-loop transcription between a multi-class multi-dimensional …

Decoder

Closed-Loop Transcription via Convolutional Sparse Coding

2023-02-18 · Xili Dai, Ke Chen, Shengbang Tong, Jingyuan Zhang 외

Autoencoding has achieved great empirical success as a framework for learning generative models for natural images. Autoencoders often use generic deep networks as the encoder or decoder, which are difficult to interpret…

Rolling Shutter Correction

Reinforcement Learning-based Control of Nonlinear Systems using Carleman Approximation: Structured and Unstructured Designs

2023-02-21 · Jishnudeep Kar, He Bai, Aranya Chakrabortty

We develop data-driven reinforcement learning (RL) control designs for input-affine nonlinear systems. We use Carleman linearization to express the state-space representation of the nonlinear dynamical model in the Carle…

Reinforcement Learning (RL)

CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation

2025-07-04 · Elena Bueno-Benito, Mariella Dimiccoli arxiv

Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clustering using pseudo-labels. Unlike othe…

Unsupervised Action Segmentation