{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights","html":"","width":"100%","height":180,"duration":1216,"description":"\n 🤗 Upvotes: 21 | cs.LG, cs.CV\n\n Authors:\n Jonathan Kahana, Or Nathan, Eliahu Horwitz, Yedid Hoshen\n\n Title:\n Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights\n\n Arxiv:\n http://arxiv.org/abs/2502.09619v1\n\n Abstract:\n With the increasing numbers of publicly available models, there are probably pretrained, online models for most tasks users require. However, current model search methods are rudimentary, essentially a text-based search in the documentation, thus users cannot find the relevant models. This paper presents ProbeLog, a method for retrieving classification models that can recognize a target concept, such as \"Dog\", without access to model metadata or training data. Differently from previous probing methods, ProbeLog computes a descriptor for each output dimension (logit) of each model, by observing its responses on a fixed set of inputs (probes). Our method supports both logit-based retrieval (\"find more logits like this\") and zero-shot, text-based retrieval (\"find all logits corresponding to dogs\"). As probing-based representations require multiple costly feedforward passes through the model, we develop a method, based on collaborative filtering, that reduces the cost of encoding repositories by 3x. We demonstrate that ProbeLog achieves high retrieval accuracy, both in real-world and fine-grained search tasks and is scalable to full-size repositories.\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}