Datasets › Office-31

Office-31 (Office Dataset)

Introduced in Adapting Visual Category Models to New Domains1 Jan 2010 archive 2025-07-28

The Office dataset contains 31 object categories in three domains: Amazon, DSLR and Webcam. The 31 categories in the dataset consist of objects commonly encountered in office settings, such as keyboards, file cabinets, and laptops. The Amazon domain contains on average 90 images per class and 2817 images in total. As these images were captured from a website of online merchants, they are captured against clean background and at a unified scale. The DSLR domain contains 498 low-noise high resolution images (4288×2848). There are 5 objects per category. Each object was captured from different viewpoints on average 3 times. For Webcam, the 795 images of low resolution (640×480) exhibit significant noise and color as well as white balance artifacts.

Source: Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensors Image Source: https://www.researchgate.net/publication/310953258

Homepage Benchmarks Papers JSON

Benchmarks archive 2025-07-28

All 7 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

		First row (archive order)	Paper	Code
Domain Adaptation	Office-31	FFTAT Average Accuracy 96.0	Feature Fusion Transferability Aware Transformer for...	Shawey94/NoisyNN +1	40	Compare
Universal Domain Adaptation	Office-31	UniAM H-score 95.95	Universal Domain Adaptation via Compressive Attention Matching	—	12	Compare
Partial Domain Adaptation	Office-31	SLM Accuracy (%) 98.38	Select, Label, and Mix: Learning Discriminative...	—	7	Compare
Multi-target Domain Adaptation	Office-31	MCDA Accuracy 89.6	Class Overwhelms: Mutual Conditional Blended-Target...	Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation	5	Compare
Unsupervised Domain Adaptation	Office-31	PMTrans Accuracy 95.3	Patch-Mix Transformer for Unsupervised Domain...	—	5	Compare
Blended-target Domain Adaptation	Office-31	MCDA Average Accuracy 89.6	Class Overwhelms: Mutual Conditional Blended-Target...	Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation	2	Compare
Open-Set Multi-Target Domain Adaptation	Office-31	COSMo H-Score 90.01	COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation	munish30monga/COSMo	1	Compare

Papers archive 2025-07-28

30 shown of 65 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 643. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

			Date	Samples run Syntology
Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation	2	1	10 Nov 2024	not harvested
COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation	1	1	31 Aug 2024	not harvested
EUDA: An Efficient Unsupervised Domain Adaptation via Self-Supervised Vision Transformer	1	1	31 Jul 2024	not harvested
Unsupervised Domain Adaption Harnessing Vision-Language Pre-training	1	1	19 Apr 2024	not harvested
SF(DA)²: Source-free Domain Adaptation Through the Lens of Data Augmentation	1	1	16 Mar 2024	ran 1 of 5 samples (4 unverified; 5 pointer-only for licence)
LEAD: Learning Decomposition for Source-free Universal Domain Adaptation	2	1	6 Mar 2024	ran 9 of 11 samples (2 unverified; 9 pointer-only for licence)
Prompt-based Distribution Alignment for Unsupervised Domain Adaptation	1	1	15 Dec 2023	ran 3 of 4 samples (1 unverified)
MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation	1	1	13 Dec 2023	ran 1 of 1 samples (0 unverified)
Gradual Source Domain Expansion for Unsupervised Domain Adaptation	1	1	16 Nov 2023	not harvested
Universal Domain Adaptation via Compressive Attention Matching	0	1	24 Apr 2023	not harvested
CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation	0	1	19 Apr 2023	not harvested
Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspective	0	2	23 Mar 2023	not harvested
Upcycling Models under Domain and Category Shift	3	1	13 Mar 2023	not harvested
Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation	1	2	3 Feb 2023	ran 0 of 4 samples (4 unverified)
Free Lunch for Domain Adversarial Training: Environment Label Smoothing	1	1	1 Feb 2023	ran 1 of 2 samples (1 unverified; 2 pointer-only for licence)
Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All in One Classifier	1	1	1 Jan 2023	not harvested
Backprop Induced Feature Weighting for Adversarial Domain Adaptation with Iterative Label Distribution Alignment	1	1	1 Jan 2023	not harvested
Unified Optimal Transport Framework for Universal Domain Adaptation	1	1	31 Oct 2022	ran 1 of 3 samples (2 unverified)
Selective Partial Domain Adaptation	2	1	1 Oct 2022	not harvested
Safe Self-Refinement for Transformer-based Domain Adaptation	1	1	16 Apr 2022	ran 9 of 19 samples (10 unverified; 1 pointer-only for licence)
Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation	1	1	8 Apr 2022	ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
Global-Local Regularization Via Distributional Robustness	1	1	1 Mar 2022	not harvested
Geometric Anchor Correspondence Mining With Uncertainty Modeling for Universal Domain Adaptation	0	1	1 Jan 2022	not harvested
UMAD: Universal Model Adaptation under Domain and Category Shift	0	1	16 Dec 2021	not harvested
Contrastive Vicinal Space for Unsupervised Domain Adaptation	1	1	26 Nov 2021	not harvested
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation	2	1	13 Sep 2021	ran 1 of 8 samples (7 unverified)
Source Class Selection with Label Propagation for Partial Domain Adaptation	1	1	1 Sep 2021	not harvested
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation	1	1	18 Jun 2021	not harvested
Domain Consensus Clustering for Universal Domain Adaptation	1	2	5 Jun 2021	not harvested
OVANet: One-vs-All Network for Universal Domain Adaptation	2	1	7 Apr 2021	ran 4 of 12 samples (8 unverified)

The full list of 65 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Domain Adaptation Unsupervised Domain Adaptation Multi-Source Unsupervised Domain Adaptation Partial Domain Adaptation Universal Domain Adaptation Multi-target Domain Adaptation Blended-target Domain Adaptation Open-Set Multi-Target Domain Adaptation Unsupervised Domain Adaptationn

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

Office-31

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections