{"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/the-devil-is-in-the-channels-mutual-channel","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","arxiv_id":"2002.04264","date":"2020-02-11","proceeding":null,"authors":["Dongliang Chang","Yifeng Ding","Jiyang Xie","Ayan Kumar Bhunia","Xiaoxu Li","Zhanyu Ma","Ming Wu","Jun Guo","Yi-Zhe Song"],"abstract":"Key for solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms -- a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive on spatial-wise. The end result is therefore a set of feature channels that each reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford-Cars). Ablative studies further demonstrate the superiority of MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Code available at https://github.com/dongliangchang/Mutual-Channel-Loss","url_abs":"https://arxiv.org/abs/2002.04264v3","url_pdf":"https://arxiv.org/pdf/2002.04264v3.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":"the-devil-is-in-the-channels-mutual-channel","repo_url":"https://github.com/dongliangchang/Mutual-Channel-Loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"the-devil-is-in-the-channels-mutual-channel","repo_url":"https://github.com/frgfm/Holocron","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"the-devil-is-in-the-channels-mutual-channel","repo_url":"https://github.com/Kurumi233/Mutual-Channel-Loss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-categorization","task_name":"Image Categorization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/fine-grained-image-classification-on-fgvc","task":"Fine-Grained Image Classification","dataset":"FGVC Aircraft","model":"MC Loss (B-CNN)","rank_in_archive_order":32,"of":57,"metrics":{"Accuracy":"92.9%"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"MC Loss (B-CNN)","rank_in_archive_order":48,"of":83,"metrics":{"Accuracy":"94.4%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2002.04264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.04264"}},"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/frgfm/Holocron","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dongliangchang/Mutual-Channel-Loss","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Kurumi233/Mutual-Channel-Loss","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"samples":2,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"dongliangchang/Mutual-Channel-Loss","repo_kind":"official","path":"CUB-200-2011_ResNet18.py","file_url":"https://github.com/dongliangchang/Mutual-Channel-Loss/blob/HEAD/CUB-200-2011_ResNet18.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":"fac5364e2f53c6db"}},{"code_sha256_prefix":"ac269a0e4b8d946e","entry":"default_loader","repo":"Kurumi233/Mutual-Channel-Loss","repo_kind":"listed","path":"dataload.py","file_url":"https://github.com/Kurumi233/Mutual-Channel-Loss/blob/HEAD/dataload.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac269a0e4b8d946e"}},{"code_sha256_prefix":"80779b7a31a59036","entry":"Mask","repo":"dongliangchang/Mutual-Channel-Loss","repo_kind":"official","path":"CUB-200-2011_ResNet18.py","file_url":"https://github.com/dongliangchang/Mutual-Channel-Loss/blob/HEAD/CUB-200-2011_ResNet18.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80779b7a31a59036"}},{"code_sha256_prefix":"90d61abe3df5849f","entry":"gray_loader","repo":"Kurumi233/Mutual-Channel-Loss","repo_kind":"listed","path":"dataload.py","file_url":"https://github.com/Kurumi233/Mutual-Channel-Loss/blob/HEAD/dataload.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90d61abe3df5849f"}},{"code_sha256_prefix":"7375f22b6e02d48f","entry":"resnet18","repo":"dongliangchang/Mutual-Channel-Loss","repo_kind":"official","path":"CUB-200-2011_ResNet18.py","file_url":"https://github.com/dongliangchang/Mutual-Channel-Loss/blob/HEAD/CUB-200-2011_ResNet18.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7375f22b6e02d48f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}