All Videos Channels

Users can generate videos up to 1080p resolution, up to 20 sec long, and in widescreen, vertical or square aspect ratios. You can bring your own assets to extend, remix, and blend, or generate entirely new content from text.

9  Followers

We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn. Fifteen years ago, Quiroga et al.1 discovered that the human brain possesses multimodal neurons. These neurons respond to clusters of abstract concepts centered around a common high-level theme, rather than any specific visual feature. The most famous of these was the “Halle Berry” neuron, a neuron featured in both Scientific American⁠(opens in a new window) and The New York Times⁠(opens in a new window), that responds to photographs, sketches, and the text “Halle Berry” (but not other names). Two months ago, OpenAI announced CLIP⁠, a general-purpose vision system that matches the performance of a ResNet-50,2 but outperforms existing vision systems on some of the most challenging datasets. Each of these challenge datasets, ObjectNet, ImageNet Rendition, and ImageNet Sketch, stress tests the model’s robustness to not recognizing not just simple distortions or changes in lighting or pose, but also to complete abstraction and reconstruction—sketches, cartoons, and even statues of the objects. Now, we’re releasing our discovery of the presence of multimodal neurons in CLIP. One such neuron, for example, is a “Spider-Man” neuron (bearing a remarkable resemblance to the “Halle Berry” neuron) that responds to an image of a spider, an image of the text “spider,” and the comic book character “Spider-Man” either in costume or illustrated. Our discovery of multimodal neurons in CLIP gives us a clue as to what may be a common mechanism of both synthetic and natural vision systems—abstraction. We discover that the highest layers of CLIP organize images as a loose semantic collection of ideas, providing a simple explanation for both the model’s versatility and the representation’s compactness.