본문 바로가기
반응형

분류 전체보기359

Diffusion Models Beat GANs on Image Synthesis (NeurIPS 2021) https://arxiv.org/abs/2105.05233 Diffusion Models Beat GANs on Image Synthesis We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models. We achieve this on unconditional image synthesis by finding a better architecture through a series of ablations. For conditional imag arxiv.org 참고 영상 : https://www.youtube.com/watch?v=gN1FQhQsUTE .. 2023. 5. 17.
Zero-Shot Contrastive Loss for Text-Guided Diffusion Image Style Transfer https://arxiv.org/pdf/2303.08622.pdf Contribution - Zero-shot style transfer model 제안함 - 이를 위한 zero-shot contrastive loss 를 제안함 Overview of Proposed Method DDIM 으로 Forward 하고, Reverse 과정에서 DDPM을 사용. 그리고 Reverse 중간중간에 CLIP loss와 ZeCon loss를 추가해주면서 Style과 Content 에 대한 학습을 이룸. main contribution 중 하나는 추가적은 training 없이, guide 가 가능하다는 것이다. 이 때, CLIP으로 Style 을 guide 하고, ZeCon으로 content를 guide 함 Style G.. 2023. 4. 26.
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization https://arxiv.org/pdf/2006.16241.pdf Abstract 4개의 real-world distribution을 가진 dataset을 공개 : change image style , image blurriness, geographic location, camera operation, etc. 이러한 새로운 데이터셋으로 robustness를 위한 견고성을 개선하기 위한 방법을 테스트. 그 결과 larger model을 사용할수록 artificial data augmentations이 real-world distribution에서 robustness 하다는 것을 발견하였다. 데이터 증강이 효과가 있다는 것에 아이디어를 얻어 1000 배 더 많은 데이터로 pretrained 된 모델을 능가.. 2023. 3. 21.
Improving Object Detection with Selective Self-Supervised Self-Training https://arxiv.org/pdf/2007.09162.pdf The paper proposes a novel learning method called selective self-supervised self-training to improve object detection by leveraging diverse Web images and rectifying the supervision signals in Web images using a selective net, achieving state-of-the-art results on detecting different object classes. Key insights: Image-to-image search is an effective method f.. 2023. 3. 17.
Towards Adversarially Robust Object Detection https://arxiv.org/pdf/1907.10310.pdf Arixv GPT The paper "Towards Adversarially Robust Object Detection" proposes an adversarial training approach to improve the robustness of object detection models against adversarial attacks, and verifies its effectiveness through extensive experiments on PASCAL-VOC and MS-COCO datasets. Key insights and lessons learned: Object detection models are vulnerable.. 2023. 3. 16.
Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming https://arxiv.org/pdf/1907.07484.pdf Arixv GPT Summary The paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" presents a benchmark to evaluate object detection models' performance under various image corruptions and weather conditions, crucial for real-orld applications like autonomous driving. The authors provide three benchmark datasets with a large v.. 2023. 3. 16.
반응형