https://github.com/anvoynov/BigGANsAreWatching
공식 코드Object Segmentation Without Labels with Large-Scale Generative Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Saliency Detection is a preprocessing step in computer vision which aims at finding salient objects in an image.
Source: An Unsupervised Game-Theoretic Approach to Saliency Detection
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Object Segmentation Without Labels with Large-Scale Generative Models
Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation
Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network
FixaTons: A collection of Human Fixations Datasets and Metrics for Scanpath Similarity
A positive feedback method based on F-measure value for Salient Object Detection
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecasting
Group Collaborative Learning for Co-Salient Object Detection
FastSal: a Computationally Efficient Network for Visual Saliency Prediction
Generative Transformer for Accurate and Reliable Salient Object Detection
Generative Transformer for Accurate and Reliable Salient Object Detection
Hyperspectral Image Dataset for Benchmarking on Salient Object Detection
SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks
Simultaneous Image-to-Zero and Zero-to-Noise: Diffusion Models with Analytical Image Attenuation
Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception
Few-Cost Salient Object Detection with Adversarial-Paced Learning
Inner and Inter Label Propagation: Salient Object Detection in the Wild
DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Prediction
Panoramic Vision Transformer for Saliency Detection in 360° Videos
Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.