Representation Disentanglement

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection
Jun 27, 2026Yang Guo, Zihan Yang, Feifei Kou +3Small Object Detection Representation Disentanglement
Shenzhen Campus of Sun Yat-sen University · Beijing University of Posts and Telecommunications, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China +2
Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders
Jun 19, 2026Wonseok Shin, Songkuk KimText Embeddings Sentence Embeddings
Yonsei University
The Representational Limit of Scalar Interactions: An Interventional Decomposition
Jun 17, 2026Potito Aghilar, Sabino Roccotelli, Stanislao Fidanza +3Feature Interaction Modeling Representation Disentanglement
Polytechnic University of Bari · University of Bari Aldo Moro
Effects of sparsity and superposition on loss in simple autoencoders
Jun 16, 2026Mriganka Basu Roy Chowdhury, Eric McLaughlin WeinerFeature Superposition Activation Sparsity
Department of Statistics, UC Berkeley · Department of Materials Science, UC Berkeley
Value-order Decomposition for Generalist Anomaly Detection
Jun 12, 2026Miaoyun Zhao, Jing Chen, Miaoni Zhao +1Industrial Anomaly Detection Representation Disentanglement
Dalian University of Technology · Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology), Ministry of Education, Dalian, China · Xi’an Chang’an Vanke City Primary School
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
Jun 10, 2026Shun Shao, Zheng Zhao, Anna Korhonen +2Debiased ML Algorithmic Fairness
University of Cambridge · University of Edinburgh · University of Groningen +1
Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
Jun 4, 2026Seyed Arshan Dalili, Mehrdad MahdaviRepresentation Disentanglement Sparse Autoencoders
The Pennsylvania State University
Dual Feature Decoupling for Fine-Grained OOD Detection
Jun 4, 2026Xiaokun Li, Yaping Huang, Qingji GuanRepresentation Disentanglement OOD Detection
School of Computer Science and Technology, Beijing Jiaotong University, No. 3 Shangyuan Village, Haidian District, Beijing, China
Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding
Jun 2, 2026Zhengyi Zhao, Shubo Zhang, Zezhong Wang +6Multimodal Disentangled Representation Learning Representation Disentanglement
The Chinese University of Hong Kong · Huawei · Central China Normal University +3
Representational Capacity: Geometric Limits on Feature Representation in Transformer Language Models
Jun 1, 2026Alexander GuhaFeature Superposition Transformer Expressivity
Arizona State University
Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing
May 31, 2026Sukhun Ko, Jeahun Sung, Soo Ye Kim +1Diffusion Transformer Compositional Image Generation
CMLab, Chung-Ang University · Adobe Research
Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance
May 29, 2026Doğukan Bağcı, Bernt Schiele, Simone Schaub-Meyer +2Disentangled Representation Learning Representation Disentanglement
Max Planck Institute for Informatics, SIC · Department of Computer Science, TU Darmstadt
Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders
May 28, 2026Pierre-Antoine Lequeu, Camille Barboule, Benjamin PiwowarskiTransformer Interpretability Disentangled Representation Learning
Sorbonne Université, CNRS, ISIR, Paris, France · Orange Innovation
Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
May 25, 2026Ruoxi Cheng, Haoxuan Ma, Zhengfei Hai +6Adversarial Representation Learning Vision-Language Models
Fudan University · Tencent · Nanjing University +3
DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
May 25, 2026Renjie Lu, Xulong Zhang, Xiaoyang Qu +2Multimodal Disentangled Representation Learning Unified Multimodal Models
Ping An Technology (Shenzhen) Co., Ltd., Shenzhen, China · University of Science and Technology of China, Hefei, China.
Loki: Representation over Architecture for Diffusion-Based Portrait Animation
May 22, 2026Pouyan Navard, Sernam LimVideo Diffusion Models 3D Morphable Models
The Ohio State University · University of Central Florida
DAMA: Disentangled Body-Anchored Gaussians for Controllable Multi-Layered Avatars
May 20, 2026Daniel Eskandar, Berna Kabadayi, Garvita Tiwari +13D Gaussian Splatting 3D Reconstruction
University of Tübingen, Germany · Tübingen AI Center, Germany · Zuse School ELIZA, Germany +2
Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
May 20, 2026Romeo Valentin, Olivia Beyer Bruvik, Marc R. Schlichting +1Representation Disentanglement Mechanistic Interpretability
Stanford Intelligent Systems Laboratory, Stanford University, Stanford, CA, USA
JointHRRP-Net: A Statistically Constrained Decoupling Network for Joint Target and Jamming Recognition in Composite Jamming
May 19, 2026Yunfei Zhao, Mei Liu, Shuowei Liu +2Representation Disentanglement
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
May 18, 2026Xichen Yan, Zelin Zang, Changxi Chi +8Representation Disentanglement Multi-Scale Feature Fusion
Jinan University · Westlake University · HKISI +1
Probing for Representation Manifolds in Superposition
May 18, 2026Alexander ModellFeature Superposition Neural Representation Geometry
Department of Mathematics Imperial College London, U.K.
Content-Style Identification via Differential Independence
May 18, 2026Subash Timilsina, Hoang-Son Nguyen, Sagar Shrestha +1Representation Identifiability Causal Counterfactual Generation
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USA.
Large language models reorganize representational geometry during in-context learning
May 16, 2026Hua-Dong Xiong, Li Ji-An, Robert C. Wilson +2Neural Representation Geometry Representation Disentanglement
School of Psychological and Brain Sciences, Georgia Tech · Department of Psychology, New York University · School of Psychological and Brain Sciences, Georgia Tech 3 Center of Excellence for Computational Cognition, Georgia Tech +2
HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
May 14, 2026Man Wang, Chenyang Liu, Wenjun Li +5Remote Sensing Image Understanding Image Captioning
College of Computer Science, Inner Mongolia University, Hohhot 010021, China · Research Center for Spatiotemporal Intelligence, Inner Mongolia University, Hohhot 010021, China · Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University, Beijing 100191, China +3
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
May 14, 2026Tommaso Mencattini, Francesco Montagna, Francesco LocatelloRate-Distortion Theory Representation Disentanglement
EPFL · Institute of Science and Technology Austria
4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation
May 12, 2026Ying Zang, Xuanyi Liu, Yidong Han +94D Reconstruction Depth Estimation
4Huzhou University · 2Peking University · 1KOKONI 3D, Moxin Technology +4
Learning Protein Structure-Function Relationships through Knowledge-guided Representation Decomposition
May 12, 2026Mingqing Wang, Zhiwei Nie, Athanasios V. Vasilakos +2Representation Disentanglement 3D Representation Learning
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · School of Electronic and Computer Engineering, Peking University, Shenzhen, China +2
A framework for analyzing concept representations in neural models
May 2, 2026Burin Naowarat, Hao Tang, Sharon GoldwaterRepresentation Disentanglement Neural Network Interpretability
The Centre for Speech Technology Research School of Informatics, University of Edinburgh, United Kingdom
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
Apr 22, 2026Xingyu Zhu, Junfeng Fang, Shuo Wang +4Vision-Language Models VLM Adaptation
MoE Key Lab of BIPC, University of Science and Technology of China · National University of Singapore
PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment
Apr 21, 2026Chaonan Ji, Jinwei Qi, Sheng Xu +2Disentangled Representation Learning Representation Disentanglement
Tongyi Lab

Jun 27, 2026, cs.CVJ/K move · Enter open · S save

Adaptive Spectrum-Aware Feature Disentangled Network for Small Object Detection

Yang Guo, Zihan Yang, Feifei Kou, Yulan Hu+2

Shenzhen Campus of Sun Yat-sen University · Beijing University of Posts and Telecommunications, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China+2

Small Object Detection Representation Disentanglement

Open paper AskPDF arXiv

Small Object Detection (SOD) is a fundamental yet challenging problem in computer vision due to its limited spatial resolution and weak visual cues. Although recent approaches have achieved remarkable advances, the background distractors in different frequency spectra still degrade the performance. In this paper, we propose a novel small object detection framework termed SFDNet, which is capable of detecting small objects via efficient spectrum-aware feature disentanglement. Specifically, we propose an Adaptive Spectrum Disentanglement (ASD) module that decomposes backbone features into multiple complementary spectral components, aiming to construct discriminative object-relevant representations by discarding the background distractors for each component. Afterwards, to strengthen the semantic consistency of the similar objects in the same class, we propose a Class-Wise Prototype Distillation (CPD) procedure, which establishes class prototypes for the object instances and enforces the compact representation by efficient prototype distillation. Extensive experiments on multiple challenging benchmarks show that SFDNet outperforms existing state-of-the-art methods by a large margin. Our code is available at https://github.com/ManOfStory/SFDNet.

Momentum

Related topics

Latest papers 66