Skip to yearly menu bar Skip to main content


Oral 5D

Halle A 3

Moderator: Yifei Wang

Thu 9 May 1 a.m. PDT — 1:45 a.m. PDT
Chat is not available.

Thu 9 May 1:00 - 1:15 PDT

Interpreting CLIP's Image Representation via Text-Based Decomposition

Yossi Gandelsman · Alexei Efros · Jacob Steinhardt

We investigate the CLIP image encoder by analyzing how individual model components affect the final representation. We decompose the image representation as a sum across individual image patches, model layers, and attention heads, and use CLIP's text representation to interpret the summands. Interpreting the attention heads, we characterize each head's role by automatically finding text representations that span its output space, which reveals property-specific roles for many heads (e.g. location or shape). Next, interpreting the image patches, we uncover an emergent spatial localization within CLIP. Finally, we use this understanding to remove spurious features from CLIP and to create a strong zero-shot image segmenter. Our results indicate that scalable understanding of transformer models is attainable and can be used to repair and improve models.

Thu 9 May 1:15 - 1:30 PDT

Honorable Mention
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

Shashank Venkataramanan · Mamshad Nayeem Rizve · Joao Carreira · Yuki Asano · Yannis Avrithis

Self-supervised learning has unlocked the potential of scaling up pretraining to billions of images, since annotation is unnecessary. But are we making the best use of data? How more economical can we be? In this work, we attempt to answer this question by making two contributions. First, we investigate first-person videos and introduce a Walking Tours'' dataset. These videos are high-resolution, hours-long, captured in a single uninterrupted take, depicting a large number of objects and actions with natural scene transitions. They are unlabeled and uncurated, thus realistic for self-supervision and comparable with human learning. Second, we introduce a novel self-supervised image pretraining method tailored for learning from continuous videos. Existing methods typically adapt image-based pretraining approaches to incorporate more frames. Instead, we advocate atracking to learn to recognize'' approach. Our method called DoRA, leads to attention maps that DiscOver and tRAck objects over time in an end-to-end manner, using transformer cross-attention. We derive multiple views from the tracks and use them in a classical self-supervised distillation loss. Using our novel approach, a single Walking Tours video remarkably becomes a strong competitor to ImageNet for several image and video downstream tasks.