{"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/featsharp-your-vision-model-features-sharper","title":"FeatSharp: Your Vision Model Features, Sharper","arxiv_id":"2502.16025","date":"2025-02-22","proceeding":null,"authors":["Mike Ranzinger","Greg Heinrich","Pavlo Molchanov","Jan Kautz","Bryan Catanzaro","Andrew Tao"],"abstract":"The feature maps of vision encoders are fundamental to myriad modern AI tasks, ranging from core perception algorithms (e.g. semantic segmentation, object detection, depth perception, etc.) to modern multimodal understanding in vision-language models (VLMs). Currently, in computer vision, the frontier of general purpose vision backbones are Vision Transformers (ViT), typically trained using contrastive loss (e.g. CLIP). A key problem with most off-the-shelf ViTs, particularly CLIP, is that these models are inflexibly low resolution. Most run at 224x224px, while the \"high resolution\" versions are around 378-448px, but still inflexible. We introduce a novel method to coherently and cheaply upsample the feature maps of low-res vision encoders while picking up on fine-grained details that would otherwise be lost due to resolution. We demonstrate the effectiveness of this approach on core perception tasks as well as within agglomerative model (RADIO) training as a way of providing richer targets for distillation.","url_abs":"https://arxiv.org/abs/2502.16025v1","url_pdf":"https://arxiv.org/pdf/2502.16025v1.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":"featsharp-your-vision-model-features-sharper","repo_url":"https://github.com/nvlabs/radio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"model","task_name":"model"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.16025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16025"}},"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":"deterministic:regex_extraction","url":"https://github.com/NVlabs/FeatSharp","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/mhamilton723/FeatUp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvlabs/radio","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":9,"ran_fixture":2,"unverified":9},"by_repo_kind":{"listed":{"samples":20,"ran":11,"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":20,"samples":[{"code_sha256_prefix":"dce6ca0bf18b3f2e","entry":"Bottleneck","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dce6ca0bf18b3f2e"}},{"code_sha256_prefix":"7bfc22546fab98f5","entry":"C2f","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7bfc22546fab98f5"}},{"code_sha256_prefix":"23523ebc9c1f4d72","entry":"Conv","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"23523ebc9c1f4d72"}},{"code_sha256_prefix":"45be5b8f40e06bd5","entry":"Conv2d_BN","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"45be5b8f40e06bd5"}},{"code_sha256_prefix":"c22f7b3faad1fe11","entry":"Downsample","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c22f7b3faad1fe11"}},{"code_sha256_prefix":"16c1d81c4dd31d64","entry":"HiResNeck","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"16c1d81c4dd31d64"}},{"code_sha256_prefix":"6b0de0d2218e76ec","entry":"InterpolateLayer","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6b0de0d2218e76ec"}},{"code_sha256_prefix":"8aeb7bbb05b7dbbe","entry":"PatchEmbed","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8aeb7bbb05b7dbbe"}},{"code_sha256_prefix":"183686b6b72cb764","entry":"SwiGLU","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"183686b6b72cb764"}},{"code_sha256_prefix":"7ada4aafa440565e","entry":"pixel_unshuffle","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7ada4aafa440565e"}},{"code_sha256_prefix":"0652c4e6e4af6e9b","entry":"window_partition","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0652c4e6e4af6e9b"}},{"code_sha256_prefix":"ecb9ea6045040ce7","entry":"ConvBlock","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ecb9ea6045040ce7"}},{"code_sha256_prefix":"a2543e1d7f7e9813","entry":"ERADIO","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a2543e1d7f7e9813"}},{"code_sha256_prefix":"10474d9b4e630917","entry":"ERADIOLayer","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"10474d9b4e630917"}},{"code_sha256_prefix":"12d5196fc905b81f","entry":"GRAAttentionBlock","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"12d5196fc905b81f"}},{"code_sha256_prefix":"f4144fb782c06f3e","entry":"Mlp","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f4144fb782c06f3e"}},{"code_sha256_prefix":"76b411f448f3cf17","entry":"MultiResolutionAttention","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"76b411f448f3cf17"}},{"code_sha256_prefix":"adfe8de9799155a4","entry":"PosEmbMLPSwinv2D","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"adfe8de9799155a4"}},{"code_sha256_prefix":"d2498ee9f64b719e","entry":"WindowAttention","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d2498ee9f64b719e"}},{"code_sha256_prefix":"9336e8a3880957bd","entry":"window_reverse","repo":"nvlabs/radio","repo_kind":"listed","path":"radio/eradio_model.py","file_url":"https://github.com/nvlabs/radio/blob/HEAD/radio/eradio_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9336e8a3880957bd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}