Skip to content

Robotics and Computer Vision Lab

AI in Sensing, AI in Perception, AI in Action

  • About
    • History
    • Photo
    • Admission
  • Members
  • Publications
    • Patents
  • X-Review
  • X-Diary
  • Peer Review

Profile

허 재연

About Posts
[PR-L 2023] Jigsaw-ViT: Learning jigsaw puzzles in vision transformer
  • Posted on: 02/26/2024 –
  • Comments: 4 Comments
[NeurIPS 2022] Active Learning Helps Pretrained Models Learn the Intended Task
  • Posted on: 02/19/2024 –
  • Comments: 8 Comments
[ECCV 2016] Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
  • Posted on: 02/05/2024 –
  • Comments: 8 Comments
[ICML 2017] On Calibration of Modern Neural Networks
  • Posted on: 01/21/2024 –
  • Comments: 2 Comments
[CVPR 2018] The Power of Ensembles for Active Learning in Image Classification
  • Posted on: 01/14/2024 –
  • Comments: 4 Comments
2023년을 마무리 하며 – 허재연
  • Posted on: 01/07/2024 –
  • Comments: No Comments
[IEEE Wireless Communication 2018] Active Learning for Wireless IoT Intrusion Detection
  • Posted on: 11/19/2023 –
  • Comments: 2 Comments
[CVPR 2019] Learning Loss for Active Learning
  • Posted on: 11/12/2023 –
  • Comments: 6 Comments
[ICML 2021] Effective Evaluation of Deep Active Learning on Image Classification Tasks
  • Posted on: 11/05/2023 –
  • Comments: 2 Comments
[IEEE transactions 2017] CEAL : Cost-Effective Active Learning for Deep Image Classification
  • Posted on: 10/08/2023 –
  • Comments: 12 Comments
Newer Posts 1 2 … 6 7 8 Older Posts

Conference Deadline

NEW POST

  • [ICML 2026] Causal-JEPA: Learning World Models through Object-Level Latent Masking
  • [ICML 2026] Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
  • [ICLR 2021] AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE
  • [ICRA 2025] Dual-BEV Nav: Dual-layer BEV-based Heuristic Path Planning for Robotic Navigation in Unstructured Outdoor Environments
  • [CVPR2025] ProAPO: Progressively Automatic Prompt Optimization for Visual Classification

New Comment

  1. 홍 주영 on [ICML 2026] Are Object-Centric Representations Better At Compositional Generalization?07/27/2026

    Q1. k-means 실험의 목적? >> DINOv2+k-means와 DINOv2+CA는 DINOSAURv2의 장점이 단순히 token을 줄였기 때문인지 확인하는 비교 실험입니다. 아마 리뷰어가 "그냥 토큰…

  2. 이 예은 on [arXiv 2025] UniFGVC: Universal Training-Free Few-Shot Fine-Grained Visual Classification via Attribute-Aware Multimodal Retrieval07/27/2026

    안녕하세요 주영님! 댓글 감사드립니다. 질문주신 것과 관련된 실험들이 있었는데, 리뷰에는 담지 못한 것 같아 댓글로 설명드리고자 합니다. 잘못된(판별력 있는 description…

  3. 이 예은 on [arXiv 2025] UniFGVC: Universal Training-Free Few-Shot Fine-Grained Visual Classification via Attribute-Aware Multimodal Retrieval07/27/2026

    안녕하세요 주연님 댓글 감사합니다! 저도 학습없이 fine-grained class에 대해 discriminative한 캡션을 잘~뽑아서 classification 성능을 올린다는 점에서 이 논문을 재미있게 읽은…

  4. 이 예은 on [arXiv 2025] UniFGVC: Universal Training-Free Few-Shot Fine-Grained Visual Classification via Attribute-Aware Multimodal Retrieval07/27/2026

    안녕하세요 승현님 댓글 감사합니다! Q1) Category-Discriminative Visual Captioner과정에서, 타겟 이미지와 시각적으로 유사한 t개의 샘플을 선택한다고 하셨는데, 클래스당 K개의 이미지로 구성된다면…

  5. 홍 주영 on ICML 2026 참관기07/27/2026

    특정 대화 하나보다는, 저자들이 후속 연구와 현재 방법의 한계를 솔직하게 설명해주셨던 순간들이 기억에 남습니다. 논문에 적힌 결과보다 저자들이 실제로 중요하게…

  • Sign-in
  • RCV-Calendar
  • RCV-Github
  • Paper R/W
    • Arxiv
    • Deadline
    • Overleaf
  • Coding
    • OnlineJudge
    • Kaggle

포기하지 않는 강한 집념 만이 작은 차이를 만든다.

Design by SejongRCV