{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/waffling-around-for-performance-visual","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","arxiv_id":"2306.07282","date":"2023-06-12","proceeding":"ICCV 2023 1","authors":["Karsten Roth","Jae Myung Kim","A. Sophia Koepke","Oriol Vinyals","Cordelia Schmid","Zeynep Akata"],"abstract":"The visual classification performance of vision-language models such as CLIP has been shown to benefit from additional semantic knowledge from large language models (LLMs) such as GPT-3. In particular, averaging over LLM-generated class descriptors, e.g. \"waffle, which has a round shape\", can notably improve generalization performance. In this work, we critically study this behavior and propose WaffleCLIP, a framework for zero-shot visual classification which simply replaces LLM-generated descriptors with random character and word descriptors. Without querying external models, we achieve comparable performance gains on a large number of visual classification tasks. This allows WaffleCLIP to both serve as a low-cost alternative, as well as a sanity check for any future LLM-based vision-language model extensions. We conduct an extensive experimental study on the impact and shortcomings of additional semantics introduced with LLM-generated descriptors, and showcase how - if available - semantic context is better leveraged by querying LLMs for high-level concepts, which we show can be done to jointly resolve potential class name ambiguities. Code is available here: https://github.com/ExplainableML/WaffleCLIP.","url_abs":"https://arxiv.org/abs/2306.07282v2","url_pdf":"https://arxiv.org/pdf/2306.07282v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"waffling-around-for-performance-visual","repo_url":"https://github.com/explainableml/waffleclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"waffling-around-for-performance-visual","repo_url":"https://github.com/hk1ee/comparative-clip","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.07282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07282"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hk1ee/comparative-clip","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/explainableml/waffleclip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ExplainableML/WaffleCLIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5fde11e2c3b80a04","entry":"aggregate_similarity","repo":"hk1ee/comparative-clip","repo_kind":"listed","path":"src/tools.py","file_url":"https://github.com/hk1ee/comparative-clip/blob/HEAD/src/tools.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fde11e2c3b80a04"}},{"code_sha256_prefix":"7496518009557dce","entry":"denormalize","repo":"ExplainableML/WaffleCLIP","repo_kind":"official","path":"waffle_tools.py","file_url":"https://github.com/ExplainableML/WaffleCLIP/blob/HEAD/waffle_tools.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7496518009557dce"}},{"code_sha256_prefix":"d382e047433f0947","entry":"generate_prompt","repo":"ExplainableML/WaffleCLIP","repo_kind":"official","path":"generate_descriptors.py","file_url":"https://github.com/ExplainableML/WaffleCLIP/blob/HEAD/generate_descriptors.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d382e047433f0947"}},{"code_sha256_prefix":"3de9cd37f5734894","entry":"load_json","repo":"ExplainableML/WaffleCLIP","repo_kind":"official","path":"waffle_tools.py","file_url":"https://github.com/ExplainableML/WaffleCLIP/blob/HEAD/waffle_tools.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3de9cd37f5734894"}},{"code_sha256_prefix":"46062947cf3ab0e6","entry":"stringtolist","repo":"ExplainableML/WaffleCLIP","repo_kind":"official","path":"generate_descriptors.py","file_url":"https://github.com/ExplainableML/WaffleCLIP/blob/HEAD/generate_descriptors.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46062947cf3ab0e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}