Papers › Class-Balanced Distillation for Long-Tailed Visual Recognition
Class-Balanced Distillation for Long-Tailed Visual Recognition
Ahmet Iscen, André Araujo, Boqing Gong, Cordelia Schmid
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. An effective and simple approach to long-tailed visual recognition is to learn feature representations and a classifier separately, with instance and class-balanced sampling, respectively. In this work, we introduce a new framework, by making the key observation that a feature representation learned with instance sampling is far from optimal in a long-tailed setting. Our main contribution is a new training method, referred to as Class-Balanced Distillation (CBD), that leverages knowledge distillation to enhance feature representations. CBD allows the feature representation to evolve in the second training stage, guided by the teacher learned in the first stage. The second stage uses class-balanced sampling, in order to focus on under-represented classes. This framework can naturally accommodate the usage of multiple teachers, unlocking the information from an ensemble of models to enhance recognition capabilities. Our experiments show that the proposed technique consistently outperforms the state of the art on long-tailed recognition benchmarks such as ImageNet-LT, iNaturalist17 and iNaturalist18.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | iNaturalist 2018 | CBD-ENS (ResNet-101) | Top-1 Accuracy | 75.3% | #26 of 60 | Archive leaderboard | report |
| Image Classification | iNaturalist 2018 | CBD-ENS (ResNet-50) | Top-1 Accuracy | 73.6% | #31 of 60 | Archive leaderboard | report |
| Long-tail Learning | ImageNet-LT | CBD-ENS (ResNet-152) | Top-1 Accuracy | 57.7 | #26 of 69 | Archive leaderboard | report |
| Long-tail Learning | ImageNet-LT | CBD-ENS (ResNet-50) | Top-1 Accuracy | 55.6 | #36 of 69 | Archive leaderboard | report |
| Long-tail Learning | iNaturalist 2018 | CBD-ENS (ResNet-101) | Top-1 Accuracy | 75.3% | #13 of 43 | Archive leaderboard | report |
| Long-tail Learning | iNaturalist 2018 | CBD-ENS (ResNet-50) | Top-1 Accuracy | 73.6% | #21 of 43 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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