The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) AI Trends 2024: Computer Vision with Naila Murray - #665
15 snips
Jan 2, 2024 Naila Murray, Director of AI Research at Meta, discusses the cutting-edge landscape of computer vision. They explore advancements like controllable AI generation, multimodal models, and tools such as Segment Anything for intuitive image segmentation. Naila dives into the possibilities of ControlNet and DINOv2, emphasizing their roles in object recognition and complex scenarios. Looking ahead, she shares insights on opportunities in self-supervised learning and generative models, forecasting exciting innovations for 2024 in AI.
AI Snips
Chapters
Transcript
Episode notes
Vision and Language
- Computer vision and language models are increasingly intertwined.
- Language models act as zero-shot predictors for various visual tasks.
Controllable Generation
- Controllable generation in computer vision allows manipulation of generated images.
- This is achieved through various prompts like text, visual cues, depth, or segmentation masks.
Decoding Brain Recordings
- Researchers decoded brain recordings by embedding them into CLIP's semantic space.
- This aligns brain signals with visual and textual content, enabling decoding of observed stimuli.